Applied Machine Learning for Prediction of CO2 Adsorption on Biomass Waste-Derived Porous Carbons

Chloride corrosion destabilizes chelation of fresh and aged MSWI fly ash: Mechanism and long-term behavior

Chloride ion (Cl-) contributes to the chelated incineration fly ash (CIFA) destabilization, yet there is limited research available on the effect of exogenous Cl- corrosion. This study conducted 60-day column leaching experiments on fresh and aged CIFA (CIFA-F and CIFA-A), utilizing NaCl solutions at concentrations of 0 wt%, 1 wt%, and 3 wt%. It investigated the leaching behaviors of typical heavy metals (HMs) including lead, chromium, and nickel, associated with the leaching features like contents of calcium and dissolved organic matter (DOM), electrical conductivity, and pH. These leaching features were influenced by Cl- level through buffering and salting-out effects, indirectly affecting HM leaching. HM leaching followed a multi-step mechanism: Initially, HM leaching was primarily controlled by outer-sphere ion exchange and diffusion. As the process transitioned, the presence of Cl- hindered the incorporation of OH-, affecting the formation of secondary minerals like Ca2Al(OH)6(H2O)2Cl. This decreased the net charge and specific surface area, reducing CIFA adsorption capacities towards HMs and DOM. Eventually, large quantities of DOM reacted with HM forming non-adsorptive complexes or colloids. Compared to CIFA-F, the more porous structure in CIFA-A that resulted from carbonation may enhanced Cl- interaction with the internal composition, escalating HM long-term leaching risks. To predict future HM leaching behavior, five machine learning models based on the experimental results were constructed, moving beyond traditional decay models. The multi-output long short-term memory model showed best performance (R²> 0.85, MAE < 5.00 %), confirming its superiority. This study offers microscopic insights into the mechanisms of Cl- corrosion causing CIFA destabilization and advances predictive approaches for HM leaching behaviors.

Machine learning-guided rare earth recovery from NdFeB magnet waste: Model development, parameter influence analysis and experimental validation

The rapid expansion of the electric vehicle industry has resulted in substantial production of NdFeB magnet wastes from discarded electromotors. These magnets, weighing up to 2 kg in each electromotor, contain 25-35 wt% of strategic rare earth elements (REEs) such as Nd, Pr, and Dy, and their efficient recycling is crucial for sustainable development and environmental protection. Traditional methods for REEs recovery from NdFeB waste, involving oxidizing calcination and acid leaching, require extensive optimization due to waste variability and technological complexities, leading to high costs and environmental risks. Meanwhile, the influence rules of multi-parameters on REEs leaching are complex to comprehensively revealed by the traditional methods. To address these bottlenecks, this study employs machine learning for intelligent REEs recovery from NdFeB waste, bypassing numerous optimization experiments and reveal the complex influencing mechanisms of multi-parameters on REEs leaching. Based on a dataset of 9650 records, the developed model incorporates 24 input features related to waste properties and technological parameters, with 5 outputs corresponding to Nd, Pr, Dy, Co, and Fe leaching efficiencies. Four algorithms were used to develop 20 models to compare their performance. The XGBoost algorithm exhibited the highest prediction accuracy, with R2 values of 0.80-0.99 in the training, test, validation, and 5-fold cross-validation sets. Furthermore, the intricate influencing mechanisms of waste properties, calcination, and acid-leaching parameters on REEs leaching rates was comprehensively elucidated. Finally, a graphical user interface was developed to guide efficient REEs leaching from NdFeB waste and some experiments were conducted to verify its reliability. This study can skip numerous optimization experiments and improve the optimization efficiency, which achieves efficient and intelligent REEs recycling.

Ensemble-Learning-Guided Optimization Design for Metal-Organic Framework Adsorbents toward CO Adsorption

Metal-organic frameworks (MOFs) hold great potential for carbon monoxide (CO) adsorption owing to their large pore volume, diverse periodic network structures, and designability. Machine learning is anticipated to provide optimization parameters for designing high-efficiency MOFs adsorbents, avoiding time-consuming experiments. Here, we proposed an ensemble-learning strategy accounting for multidimensional analysis of features to rationally design pore geometries, structural properties, and synthesis conditions of MOFs toward high performance for CO adsorption. The extreme gradient boosting model exhibited the best predictive performance (R2 > 0.95) under limited data set size. Porous characteristic was identified as a dominant factor in pristine MOFs. Prediction results illustrated that MOFs featuring one-dimensional, two-dimensional, microporous, and isolated pores were optimal for CO adsorption, with 0.4-0.6 cm3/g total pore volume. This enhanced adsorption capacity can be attributed to the shortened molecular diffusion pathways. The relative significance of structural parameters followed: space groups > geometry > topology. The optimal structural configuration involved space group of R3m, binuclear paddle wheel geometry, and scorpionate-like topology. Regarding transition metal-modified MOFs, incorporated Cu(I) demonstrated the strongest binding affinity toward CO, while Fe(II) and Ni(II) could serve as effective binding sites. This work offers a theoretical guidance for designing efficient adsorbents toward CO adsorption.

A Dataset for Investigations of Amine-Impregnated Solid Adsorbent for Direct Air Capture

Amine-impregnated solid adsorbents are widely explored for point source capture and direct air capture (DAC) to address climate change. Existing literature serves as a valuable source for the investigation of amine-functionalized solid adsorbents. This study selected 52 articles from bibliographic platforms using GPT-assisted data source screening. A total of 1,336 data points were manually collected. Each data point is characterized by 28 features including the CO2 capture performance of various adsorbents from diluted to concentrated sources, resulting in 29,857 records. The methodology addresses inconsistencies in units and terminologies in the published articles and demonstrates database reliability, regularity and integrity through statistical analysis. The diverse types of amines and mesoporous solids in the database offer innovation potential for future research. In addition, two machine learning models were trained to promote dataset reuse by scientists from lab-based research and cheminformatics. This study provides opportunities to explore the use of machine learning on small databases and encourages data sharing and uniform reporting among DAC communities.

A sustainable industrial waste control with AI for predicting CO2 for climate change monitoring

As the challenge of climate change continues to grow, we need creative solutions to predict better and track industrial waste carbon emissions, focusing on sustainable waste management practices. The present study proposes a state-of-the-art Metaverse framework that puts artificial intelligence into action in predicting carbon emissions using energy use patterns and industrial social factors. At the heart of this framework lies a hybrid deep learning model combining convolutional neural networks and Long-term, short-term memory to model complicated spatial and temporal dependencies inherent in data. Further, gradient-boosting machines have been added to improve predictive performance by modeling the nonlinear relationship and interaction between features. The Metaverse environment enables a dynamic and interactive platform for real-time climate monitoring, allowing users to visualize and analyze the impacts of different energy and socio-economic scenarios on carbon emissions. Instead of traditional models, the Metaverse provides an immersive experience with deep knowledge of complex spatial relationships. This interactive capacity allows users to engage with the data more in an adaptable way. The proposed hybrid model achieves 99.5 % predictive accuracy, R2 = 0.995 for carbon emissions, and 99.2 % R2=0.992 for energy consumption compared to traditional methods. Such high accuracy underlines how effective deep learning techniques are combined with ensemble methods in capturing multifaceted climate data. Therefore, the outcome that brings out this AI-driven Metaverse is a potent tool for policymakers and researchers to make informed decisions to mitigate the impact of climate change. This framework consolidates diverse data sources in an immersing virtual environment, making it a very advanced tool in the climate science landscape by providing a comprehensive solution for predicting and monitoring carbon emissions.

Adsorptive removal of gaseous contaminants using biomass-based adsorbents

Biomass-based adsorbents have emerged as attractive materials for the adsorptive removal of gaseous pollutants due to their abundance in nature, low cost, and environmental friendliness. The modification of the adsorbent surfaces has been regarded as an intriguing technique for improving and enhancing their adsorption capacity for efficient removal of pollutants. The present study investigates the most recent developments and applications of biomass-derived adsorbents for removing various gaseous contaminants from air and gas streams. The use of biomass materials such as agricultural waste and wood residue to synthesize adsorbents provides a long-term solution to environmental pollution. This is due to the fact that biomass-derived adsorbents can be designed to have a large surface area, porosity, and surface functionality, thereby increasing their adsorption capacity and selectivity for target pollutants using a variety of chemical processes such as carbonization, activation, and modification. This study presents a comprehensive report on the use of biomass-based adsorbents for the removal of various gaseous pollutants such as carbon dioxide (CO2), volatile organic compounds (VOCs), nitrogen oxides (NO x ), sulfur dioxide (SO2), hydrogen sulphide (H2S) and multi-gas components. The surface chemistry of biomass adsorbents, in addition to their porous nature, is discussed. Multi-gas adsorption properties and the regeneration of biomass adsorbent are also discussed. The challenges and future prospects for developing biomass-based adsorbents for gaseous pollutant removal are also discussed, emphasizing the importance of a thorough understanding of adsorption mechanisms, scalability of manufacturing processes, and integration with existing air purification technologies. The findings of this study present biomass-derived adsorbents as a promising alternative for mitigating the challenges associated with the danger of gaseous pollutants, contributing to sustainable environmental management and public health protection.

Lignocellulose-Derived Energy Materials and Chemicals: A Review on Synthesis Pathways and Machine Learning Applications

Lignocellulose biomass, Earth's most abundant renewable resource, is crucial for sustainable production of high-value chemicals and bioengineered materials, especially for energy storage. Efficient pretreatment is vital to boost lignocellulose conversion to bioenergy and biomaterials, cut costs, and broaden its energy-sector applications. Machine learning (ML) has become a key tool in this field, optimizing pretreatment processes, improving decision-making, and driving innovation in lignocellulose valorization for energy storage. This review explores main pretreatment strategies - physical, chemical, physicochemical, biological, and integrated methods - evaluating their pros and cons for energy storage. It also stresses ML's role in refining these processes, supported by case studies showing its effectiveness. The review examines challenges and opportunities of integrating ML into lignocellulose pretreatment for energy storage, underlining pretreatment's importance in unlocking lignocellulose's full potential. By blending process knowledge with advanced computational techniques, this work aims to spur progress toward a sustainable, circular bioeconomy, particularly in energy storage solutions.

Exploring the response of bacterial community functions to microplastic features in lake ecosystems through interpretable machine learning

Microplastics (MPs) are ubiquitous and have various characteristics. However, their impacts on bacterial community functions in lakes remain elusive. In this study, we identified 33 different MPs features including their abundance, shape, color, size, and polymer type, from Taihu Lake, China. These features were used to construct 48 machine learning models, utilizing four types of machine learning regression algorithms, to investigate how different MP features influence human health, carbon/nitrogen cycling, and energy source-related functions of bacterial communities. The XGBoost models provided the best performance with an average R2 of 0.85 in explaining the abundance of functions. Yellow-, fragment-, and polyethylene terephthalate (PET) MPs were the most important features by Shapley values. Yellow- and PET-MPs mainly had primarily negative impacts on human pathogens pneumonia and chemoheterotrophy, respectively. Fragment-MPs had a primarily positive impact, which shifted from positive to negative at a proportion of 0.5 for methanol oxidation. Moreover, MPs may affect community structure by filtering for functional traits. These findings are important for understanding the effects of MP pollution on bacterial community function and its role in the global carbon and nitrogen cycling and human health and help us to determine the potential impacts of MP pollution on ecosystems.

Efficient Production of Reactive Oxidants by Atmospheric Bacterial-Derived Organic Matter in the Aqueous Phase

Hydroxyl radicals (•OH), singlet oxygen (1O2*), and organic triplet excited states (3C*) play key roles as oxidants ("reactive intermediates (RIs)") in forming and oxidizing aqueous organic aerosols. Bioaerosols are ubiquitous in the atmosphere, but little is known about their photochemical behavior and contributions to atmospheric photochemistry. We investigated the photochemical behavior of aqueous-phase cellular organic matter (COM) and extracellular polymeric substances (EPS) from cultured bacteria isolated from atmospheric PM2.5, focusing on their photochemical production of 3C*, 1O2*, and •OH. The molecular size and aromaticity of chromophores and fluorophores in COM and EPS increased with molecular weight (MW). Apparent quantum yields (ΦRI) of up to 10% and 5% were measured for 1O2* and 3C*, respectively, which are in the upper range of previously reported values. This indicated that COM and EPS contain photosensitizers that are highly efficient at producing 1O2* and 3C*. ΦRI and concentrations ([RI]ss) decreased with MW due to higher-MW molecules engaging in charge-transfer interactions that disrupt photochemical processes and oxidant production. Machine learning models were used to understand and predict oxidant production based on measurable optical and chemical properties of COM and EPS. This study provides new insights into the roles that bioaerosols can play in atmospheric aqueous photochemistry.

Intelligent leaching of Zn and Mn from spent disposable batteries to avoid traditional optimizing experiments

Spent disposable Zn-Mn and Zn-C batteries are important resources for recycling. Acid leaching is the crucial step in the hydrometallurgy process for recycling Zn and Mn from these spent Zn-based batteries. However, to obtain the optimal leaching efficiency, the uncontrollable components in waste feed and various leaching parameters cause numerous replicated optimal experiments, increasing the recovery cost and environmental risks. To solve the issues, we employed machine learning (ML) techniques to construct models to predict Zn and Mn leaching from spent disposable batteries without optimizing experiments. Among four ML algorithms tested, the extreme gradient boosting demonstrated superior predictive performance, achieving an R2 of 0.85-0.98 across the training, test, and verification datasets. An analysis of feature importance indicated that the particle size, waste composition, acid concentration, temperature, and time affected the metal leaching most. This study also revealed the interaction effects of the waste properties and leaching process on the metal leaching. Furthermore, we created a user-friendly graphical user interface (GUI) that enables quick acquisition of metal leaching results, requiring only the measurement of waste particle size and component. Finally, experimental verification confirmed the practicability of the GUI. This study achieves intelligent metal leaching from spent batteries and overcomes the high recovery cost and environmental risks associated with traditional experimental optimizing methods.

Machine learning-based prediction of compost maturity and identification of key parameters during manure composting

Evaluating compost maturity, e.g. via manual seed germination index (GI) measurement, is both time-consuming and costly during composting. This study employed six machine learning methods, including random forest (RF), extra tree (ET), eXtreme gradient boosting, gradient boosting decision tree, back propagation neural network, and multilayer perceptron, to develop models for predicting GI during manure composting. RF and ET exhibited robust predictive performance for GI, achieving high coefficient of determination (R2) of 0.937 and 0.904, respectively, along with root mean squared error of 7.261 and 8.930. SHapley additive exPlanations identified the duration time of composting, total nitrogen, and electrical conductivity as the key features influencing GI. Validation with actual GI data further confirmed the effectiveness of RF and ET models in predicting GI. This study could facilitate optimizing manure composting strategies, enable efficient parameter regulation, reduce labor costs, assist in anomaly detection, and promote intelligent management in real-world composting practices.

Design optimization of bimetal-modified biochar for enhanced phosphate removal performance in livestock wastewater using machine learning

Mg-modified biochar shows high adsorption performance under weakly acidic and neutral water conditions. However, its phosphate removal efficiency markedly decreases in naturally alkaline wastewater, such as that released in livestock farming (anaerobic wastewater with a high phosphate concentration). This research employed six machine learning models to predict and optimize the phosphate removal performance of bimetal-modified biochar (i.e., Mg-Ca/Al/Fe/La) to develop material design strategies suitable for achieving high removal efficiency in alkaline wastewater. Random forest, gradient boosting regressor, and extreme gradient boosting models achieved high prediction accuracy (R2 > 0.98). Model predictions and experimental validations indicated that Mg-Ca-modified biochar still maintained high adsorption capacity under acidic conditions and could effectively realize phosphate adsorption under alkaline conditions, with a removal rate of 99.33 %. Overall, this research focuses on material performance optimization using machine learning, offering insights and methods for developing biochar materials for practical water-treatment applications.

Machine Learning in Computational Design and Optimization of Disordered Nanoporous Materials

This review analyzes the current practices in the data-driven characterization, design and optimization of disordered nanoporous materials with pore sizes ranging from angstroms (active carbon and polymer membranes for gas separation) to tens of nm (aerogels). While the machine learning (ML)-based prediction and screening of crystalline, ordered porous materials are conducted frequently, materials with disordered porosity receive much less attention, although ML is expected to excel in the field, which is rich with ill-posed problems, non-linear correlations and a large volume of experimental results. For micro- and mesoporous solids (active carbons, mesoporous silica, aerogels, etc.), the obstacles are mostly related to the navigation of the available data with transferrable and easily interpreted features. The majority of published efforts are based on the experimental data obtained in the same work, and the datasets are often very small. Even with limited data, machine learning helps discover non-evident correlations and serves in material design and production optimization. The development of comprehensive databases for micro- and mesoporous materials with low-level structural and sorption characteristics, as well as automated synthesis/characterization protocols, is seen as the direction of efforts for the immediate future. This paper is written in a language readable by a chemist unfamiliar with the data science specifics.

Predicting the efficiency of arsenic immobilization in soils by biochar using machine learning

Arsenic (As) pollution in soils is a pervasive environmental issue. Biochar immobilization offers a promising solution for addressing soil As contamination. The efficiency of biochar in immobilizing As in soils primarily hinges on the characteristics of both the soil and the biochar. However, the influence of a specific property on As immobilization varies among different studies, and the development and application of arsenic passivation materials based on biochar often rely on empirical knowledge. To enhance immobilization efficiency and reduce labor and time costs, a machine learning (ML) model was employed to predict As immobilization efficiency before biochar application. In this study, we collected a dataset comprising 182 data points on As immobilization efficiency from 17 publications to construct three ML models. The results demonstrated that the random forest (RF) model outperformed gradient boost regression tree and support vector regression models in predictive performance. Relative importance analysis and partial dependence plots based on the RF model were conducted to identify the most crucial factors influencing As immobilization. These findings highlighted the significant roles of biochar application time and biochar pH in As immobilization efficiency in soils. Furthermore, the study revealed that Fe-modified biochar exhibited a substantial improvement in As immobilization. These insights can facilitate targeted biochar property design and optimization of biochar application conditions to enhance As immobilization efficiency.

Applying machine learning and genetic algorithms accelerated for optimizing ethanol production

Corn straws can produce bioethanol via simultaneous saccharification and co-fermentation (SSCF). However, identifying optimal combinations of operating parameters from numerous possibilities through a cost-effective strategy to improve SSCF efficiency and yield remains challenging. The eXtreme Gradient Boost (XGB) and deep neural network (DNN) models were constructed to accurately predict ethanol yield from only five input variables, achieving >83 % accuracy. Subsequently, the XGB and the DNN models were merged with the genetic algorithm (GA) as the new optimization strategies. Experimental validation showed that the new strategy optimize the efficiency and yield of the SSCF ethanol production system quickly and accurately. Moreover, the potential optimization mechanism was investigated through the comprehensive interpretability analysis for XGB and the microbial ecology analysis. Enzyme Solution Volume (61.7 %) dominated, followed by time (12.9 %), substrate concentration (10.4 %), temperature (7.7 %), and inoculum volume (7.3 %). This efficient and accurate algorithm design strategy can significantly reduce the time required to optimize biochemical systems.

Upcycling biowaste into advanced carbon materials via low-temperature plasma hybrid system: applications, mechanisms, strategies and future prospects

This review focuses on the recent advances in the sustainable conversion of biowaste to valuable carbonaceous materials. This study summarizes the significant progress in biowaste-derived carbon materials (BCMs) via a plasma hybrid system. This includes systematic studies like AI-based multi-coupling systems, promising synthesis strategies from an economic point of view, and their potential applications towards energy, environment, and biomedicine. Plasma modified BCM has a new transition lattice phase and exhibits high resilience, while fabrication and formation mechanisms of BCMs are reviewed in plasma hybrid system. A unique 2D structure can be designed and formulated from the biowaste with fascinating physicochemical properties like high surface area, unique defect sites, and excellent conductivity. The structure of BCMs offers various activated sites for element doping and it shows satisfactory adsorption capability, and dynamic performance in the field of electrochemistry. In recent years, many studies have been reported on the biowaste conversion into valuable materials for various applications. Synthesis methods are an indispensable factor that directly affects the structure and properties of BCMs. Therefore, it is imperative to review the facile synthesis methods and the mechanisms behind the formation of BCMs derived from the low-temperature plasma hybrid system, which is the necessity to obtain BCMs having desirable structure and properties by choosing a suitable synthesis process. Advanced carbon-neutral materials could be widely synthesized as catalysts for application in environmental remediation, energy conversion and storage, and biotechnology.

Predicting the performance of lithium adsorption and recovery from unconventional water sources with machine learning

Selective lithium (Li) recovery from unconventional water sources (UWS) (e.g., shale gas waters, geothermal brines, and rejected seawater desalination brines) using inorganic lithium-ion sieve (LIS) materials can address Li supply shortages and distribution issues. However, the development of high-performance LIS materials and the optimization of recovery-related operating parameters are hampered by the variety of production methods, intricate procedures, and experimental expenses. Machine learning (ML) techniques offer potential solutions for enhancing LIS material development. We collected literature data on Li adsorption, categorizing 16 parameters into adsorbent parameters, operating parameters, and solution components. Three tree-based algorithms-Random Forest (RF), Gradient Boosting Decision Trees (GBDT), and Extreme Gradient Boosting (XGBoost)-were used to evaluate the impact of these parameters on lithium adsorption. The grouped random splitting method limited data leakage and mitigated overfitting. XGBoost demonstrated the best performance, with an R² of 0.98 and a root-mean-squared error (RMSE) of 1.72. The SHAP values highlighted that operating parameters were the most influential, followed by adsorbent parameters and coexisting ion concentrations. Therefore, focusing on optimizing operating parameters or making targeted improvements on LIS based on operating conditions will enhance LIS performances in UWS. These insights are crucial for optimizing Li adsorption processes and designing effective inorganic LIS materials.

Machine learning modeling of thermally assisted biodrying process for municipal sludge

Preparation of activated carbons is an important way to utilize municipal sludge (MS) resources, while drying is a pretreatment method for making activated carbons from MS. In this study, machine learning techniques were used to develop moisture ratio (MR) and composting temperature (CT) prediction models for the thermally assisted biodrying process of MS. First, six machine learning (ML) models were used to construct the MR and CT prediction models, respectively. Then the hyperparameters of the ML models were optimized using the Bayesian optimization algorithm, and the prediction performances of these models after optimization were compared. Finally, the effect of each input feature on the model was also evaluated using SHapley Additive exPlanations (SHAP) analysis and Partial Dependence Plots (PDPs) analysis. The results showed that Gaussian process regression (GPR) was the best model for predicting MR and CT, with R2 of 0.9967 and 0.9958, respectively, and root mean square errors (RMSE) of 0.0059 and 0.354 ℃. In addition, graphical user interface software was developed to facilitate the use of the GPR model for predicting MR and CT by researchers and engineers. This study contributes to the rapid prediction, improvement, and optimization of MR and CT during thermally assisted biodrying of MS, and also provides valuable guidance for the dynamic regulation of the drying process.

Predicting ammonia emissions and global warming potential in composting by machine learning

The amounts of gases emitted from composting are key to evaluating global warming potential (GWP). However, few methods can accurately predict the quantities of relevant gas emissions. In this study, three developed machine-learning models were used to predict NH3 emissions and GWP. The extreme gradient boosting model provided the best predictions (R2 > 90 %) compared to random forest, making it a suitable method for calculating NH3 emissions and GWP. The k-nearest neighbor classification model was utilized to determined compost maturity achieving 92 % accuracy. Shapley Additive ExPlanation analysis was applied to identify key factors influencing gas emissions and maturity. Aeration rate, carbon-to-nitrogen ratio and moisture content showed high importance in decreasing order for predicting NH3 emissions, while NO3- was the most significant factor for predicting GWP. Practical applications of predictive models suggested that prediction of GWP was 792614 Mg CO2e year-1 close to annual calculation of 789000 Mg CO2e year-1 in California.

Application of machine learning approaches to predict ammonium nitrogen transport in different soil types and evaluate the contribution of control factors

The loss of nitrogen in soil damages the environment. Clarifying the mechanism of ammonium nitrogen (NH4+-N) transport in soil and increasing the fixation of NH4+-N after N application are effective methods for improving N use efficiency. However, the main factors are not easily identified because of the complicated transport and retardation factors in different soils. This study employed machine learning (ML) to identify the main influencing factors that contribute to the retardation factor (Rf) of NH4+-N in soil. First, NH4+-N transport in the soil was investigated using column experiments and a transport model. The Rf (1.29 - 17.42) was calculated and used as a proxy for the efficacy of NH4+-N transport. Second, the physicochemical parameters of the soil were determined and screened using lasso and ridge regressions as inputs for the ML model. Third, six machine learning models were evaluated: Adaptive Boosting, Extreme Gradient Boosting (XGB), Random Forest, Gradient Boosting Regression, Multilayer Perceptron, and Support Vector Regression. The optimal ML model of the XGB model with a low mean absolute error (0.81), mean squared error (0.50), and high test r2 (0.97) was obtained by random sampling and five-fold cross-validation. Finally, SHapely Additive exPlanations, entropy-based feature importance, and permutation characteristic importance were used for global interpretation. The cation exchange capacity (CEC), total organic carbon (TOC), and Kaolin had the greatest effects on NH4+-N transport in the soil. The accumulated local effect offered a fundamental insight: When CEC > 6 cmol+ kg-1, and TOC > 40 g kg-1, the maximum resistance to NH4+-N transport within the soil was observed. This study provides a novel approach for predicting the impact of the soil environment on NH4+-N transport and guiding the establishment of an early-warning system of nutrient loss.

Machine learning-driven prediction of phosphorus adsorption capacity of biochar: Insights for adsorbent design and process optimization

Phosphorus (P) pollution in aquatic environments poses significant environmental challenges, necessitating the development of effective remediation strategies, and biochar has emerged as a promising adsorbent for P removal at the cost of extensive research resources worldwide. In this study, a machine learning approach was proposed to simulate and predict the performance of biochar in removing P from water. A dataset consisting of 190 types of biochar was compiled from literature, encompassing various variables including biochar characteristics, water quality parameters, and operating conditions. Subsequently, the random forest and CatBoost algorithms were fine-tuned to establish a predictive model for P adsorption capacity. The results demonstrated that the optimized CatBoost model exhibited high prediction accuracy with an R2 value of 0.9573, and biochar dosage, initial P concentration in water, and C content in biochar were identified as the predominant factors. Furthermore, partial dependence analysis was employed to examine the impact of individual variables and interactions between two features, providing valuable insights for adsorbent design and operating condition optimization. This work presented a comprehensive framework for applying a machine learning approach to address environmental issues and provided a valuable tool for advancing the design and implementation of biochar-based water treatment systems.

Machine learning and experimentally exploring the controversial role of nitrogen in CO2 uptake by waste-derived nitrogen-containing porous carbons

Waste-derived nitrogen-containing porous carbons were widely accepted as promising carbon capture materials. However, roles of nitrogen in CO2 uptake were highly controversial, posing a challenge in designing high CO2 uptake porous carbons. Herein, nitrogen-containing species was firstly introduced into machine learning (ML) models to uncover the complex relationship of nitrogen, micropore and CO2 uptake by combining ML models, DFT computations and experiments. The results revealed that micropore volume (Vmicro) was the most important property influencing CO2 uptake, but was not the only determinant factor. Nitrogen-containing species (pyrrolic/pyridonic-N (N5) and pyridinic-N (N6)) rather than total nitrogen content, also played an essential role. On the one hand, they can enhanced CO2 adsorption by Lewis acid-base and hydrogen bonding. On the other hand, they promoted development of micropores by participating in activation reactions. The model further indicated that excessive N5 (>1.5 wt%) or N6 (>1.7 wt%) led to restriction on developments of micropores, which was attributed to enlargement of pore size, collapses or blockage of micropores. The double edged-sword effect of N5 and N6 on changes of microporous structures was responsible for the long-standing controversy over nitrogen. The result was further verified by synthesizing eight porous carbons with different textural and chemical properties. This study provided not only a new perspective for resolving the controversy of nitrogen in CO2 uptake, but also a graphical user interface prediction software meaningful for designing porous carbons.

Fabrication of Highly Efficient ZIF-8@PEI Monoliths for CO2 Capture Using Phosphorylated Cellulose Nanofiber as a Binder

This study involves the synthesis and comparison of zeolitic imidazolate frameworks (ZIFs), specifically ZIF-8 and ZIF-67 pristine with a commercial zeolite, emphasizing their CO2 affinity and sorption capability. To overcome challenges persisting in the handling and integration of these materials into industrial adsorption processes, particularly when limited to microcrystalline fine powders, we present herein an innovative manufacturing method to produce standalone monolithic supports. This process involves pseudoplastic paste formulations utilizing polyethylenimine (PEI) as a coagulant and locally fabricated phosphorylated cellulose nanofiber (PCNF) as a binding agent. Rheological investigation was conducted to anticipate the required shaping and design by means of paste flowability, consistency, and stiffness. XRD and FTIR results confirm the preservation of crystalline structure and the occurrence of amine functionalization associated with the presence of PEI, respectively. The proposed method significantly enhances the CO2 adsorption performance of the produced ZIF-8 monolith in comparison with that reached when using the pristine material, achieving a capacity of 1.25-2 mmol·g-1 at 30 °C under dry conditions in a pressure range of 1-13 bar, respectively. In other words, this work clearly highlights an effective applicability of the ZIF-8 monolith as an innovative sorbent for further designing CO2 capture industrial setups.

Prediction of adsorption performance of ZIF-67 for malachite green based on artificial neural network using L-BFGS algorithm

Given the necessity and urgency in removing organic pollutants such as malachite green (MG) from the environment, it is vital to screen high-capacity adsorbents using artificial neural network (ANN) methods quickly and accurately. In this study, a series of ZIF-67 were synthesized, which adsorption properties for organic pollutants, especially MG, were systematically evaluated and determined as 241.720 mg g-1 (25 ℃, 2 h). The adsorption process was more consistent with pseudo-second-order kinetics and Langmuir adsorption isotherm, which correlation coefficients were 0.995 and 0.997, respectively. The chemisorption mechanism was considered to be π-π stacking interaction between imidazole and aromatic ring. Then, a Python-based neural network model using the Limited-memory BFGS algorithm was constructed by collecting the crucial structural parameters of ZIF-67 and the experimental data of batch adsorption. The model, optimized extensively, outperformed similar Matlab-based ANN with a coefficient of determination of 0.9882 and mean square error of 0.0009 in predicting ZIF-67 adsorption of MG. Furthermore, the model demonstrated a good generalization ability in the predictive training of other organic pollutants. In brief, ANN was successfully separated from the Matlab platform, providing a robust framework for high-precision prediction of organic pollutants and guiding the synthesis of adsorbents.

Machine learning-driven prediction of phosphorus removal performance of metal-modified biochar and optimization of preparation processes considering water quality management objectives

Developing an optimized and targeted design approach for metal-modified biochar based on water quality conditions and management is achievable through machine learning. This study leveraged machine learning to analyze experimental data on phosphate adsorption by metal-modified biochar from literature published in Web of Science. Using six machine learning models, the phosphate adsorption capacity of biochar and residual phosphate concentration were predicted. After hyperparameter optimization, the gradient boosting model exhibited superior training performance (R2 > 0.96). Metal load quantity, solid-liquid ratio, and pH were key factors influencing adsorption performance. Optimal preparation parameters indicated that Mg-modified biochar achieved the highest adsorption capacity (387-396 mg/g), while La-modified biochar displayed the lowest residual phosphate concentration (0 mg/L). The results of verification experiments based on optimized process parameters closely aligned with model predictions. This study introduces a new machine learning-based approach for tailoring biochar preparation processes considering different water quality management objectives.

Deep learning prediction and experimental investigation of specific capacitance of nitrogen-doped porous biochar

N-doped porous biochar is a promising carbon material for supercapacitor electrodes due to its developed pore structure and high chemical activity which greatly affect the capacitive performance. Predicting the capacitance and exploring the most influential factors are of great significance because it can not only avoid the trial-and-error experiments but also provide guidance for the synthesis of biochar with the aim of capacitance enhancement. In this study, a CNN model with ReLU activation function was established using DenseNet architecture for specific capacitance prediction. The importance and impacts of the physiochemical properties of N-doped porous biochar to the capacitance were revealed. With the guidance of the model, N-doped porous biochar samples with high capacitance were synthesized, the data of which were further used for model validation. This study provides not only a deep learning model which can be used in practice for capacitance prediction but also directions for the synthesis of N-doped porous biochar with high capacitive performance.

Machine learning modeling of fluorescence spectral data for prediction of trace organic contaminant removal during UV/H2O2 treatment of wastewater

Dynamic feedback of the removal performance of trace organic contaminants (TrOCs) is essential towards economical advanced oxidation processes (AOPs), whereas the corresponding quick-response feedback methods have long been desired. Herein, machine learning (ML) multi-target regression random forest (MORF) models were developed based on the fluorescence spectra to predict the removal of TrOCs during UV/H2O2 treatment of municipal secondary effluent as a typical AOP. The predictive performance of the developed MORF model (R2 = 0.83-0.95) exhibited higher accuracy over the traditional linear regression models with R2 increased by ∼0.15. Furthermore, through feature importance analysis, the spectral regions of high importance were identified for different groups of TrOCs, thus enabling faster data acquisition due to remarkably reduced size of required fluorescence spectral scanning region. Specifically, the fluorescence regions Ex(235-275 nm)/Em(325-400 nm) and Ex(240-360 nm)/Em(325-450 nm) were found highly correlated with the removal of the TrOCs susceptible to both photodegradation and •OH degradation and those primarily subject to •OH degradation, respectively. In addition, the spectral regions of high importance were also individually identified for the investigated TrOCs during the AOP. Through providing an efficient ML-based feedback method to monitor TrOC removal during AOP, this study sheds light on the development of dynamic feedback-based strategies for precise and economical advanced treatment of wastewater.

Machine-learning-driven discovery of metal-organic framework adsorbents for hexavalent chromium removal from aqueous environments

HYPOTHESIS

Metal-organic frameworks (MOFs) have been widely studied for Cr(VI) adsorption in water. Theoretically, numerous MOFs can be synthesised by assembling diverse metals and ligands. However, the traditional manual experimentation for screening high-performance MOFs is resource-intensive and inefficient.

EXPERIMENTS

A screening strategy for MOFs based on machine learning was proposed for the adsorption and removal of Cr(VI) from water. By collecting the characteristics of MOFs and the experimental parameters of Cr(VI) adsorption from the literature, a dataset was constructed to predict the adsorption performance. Among the six regression models, the model trained by the extreme gradient boosted tree algorithm had the best performance and was used to simulate the adsorption and screen potential high-performance adsorbents.

FINDINGS

Structure-property analysis indicated that prepared MOF adsorbents with properties of 0.37 < largest cavity diameter < 0.71 nm, 0.18 < pore volume < 0.57 cm3/g, 412 < specific surface area < 1588 m2/g, 0.43 < void fraction < 0.62 will achieve enhanced adsorption of Cr(VI) in water. High-performance adsorbents were successfully screened using a combination of machine-learning prediction and analysis. Experiments were conducted to verify the exceptional adsorption capacity of UiO-66 and MOF-801. This method effectively identified adsorbents and accelerated the development of new MOF adsorbents for contaminant removal, providing a novel approach for the discovery of superior adsorbents.

Machine learning framework for predicting cytotoxicity and identifying toxicity drivers of disinfection byproducts

Drinking water disinfection can result in the formation disinfection byproducts (DBPs, > 700 have been identified to date), many of them are reportedly cytotoxic, genotoxic, or developmentally toxic. Analyzing the toxicity levels of these contaminants experimentally is challenging, however, a predictive model could rapidly and effectively assess their toxicity. In this study, machine learning models were developed to predict DBP cytotoxicity based on their chemical information and exposure experiments. The Random Forest model achieved the best performance (coefficient of determination of 0.62 and root mean square error of 0.63) among all the algorithms screened. Also, the results of a probabilistic model demonstrated reliable model predictions. According to the model interpretation, halogen atoms are the most prominent features for DBP cytotoxicity compared to other chemical substructures. The presence of iodine and bromine is associated with increased cytotoxicity levels, while the presence of chlorine is linked to a reduction in cytotoxicity levels. Other factors including chemical substructures (CC, N, CN, and 6-member ring), cell line, and exposure duration can significantly affect the cytotoxicity of DBPs. The similarity calculation indicated that the model has a large applicability domain and can provide reliable predictions for DBPs with unknown cytotoxicity. Finally, this study showed the effectiveness of data augmentation in the scenario of data scarcity.

Data-driven interpretable analysis for polysaccharide yield prediction

Cornstalks show promise as a raw material for polysaccharide production through xylanase. Rapid and accurate prediction of polysaccharide yield can facilitate process optimization, eliminating the need for extensive experimentation in actual production to refine reaction conditions, thereby saving time and costs. However, the intricate interplay of enzymatic factors poses challenges in predicting and optimizing polysaccharide yield accurately. Here, we introduce an innovative data-driven approach leveraging multiple artificial intelligence techniques to enhance polysaccharide production. We propose a machine learning framework to identify highly accurate polysaccharide yield prediction modeling methods and uncover optimal enzymatic parameter combinations. Notably, Random Forest (RF) and eXtreme Gradient Boost (XGB) demonstrate robust performance, achieving prediction accuracies of 93.0% and 95.6%, respectively, while an independently developed deep neural network (DNN) model achieves 91.1% accuracy. A feature importance analysis of XGB reveals the enzyme solution volume's dominant role (43.7%), followed by time (20.7%), substrate concentration (15%), temperature (15%), and pH (5.6%). Further interpretability analysis unveils complex parameter interactions and potential optimization strategies. This data-driven approach, incorporating machine learning, deep learning, and interpretable analysis, offers a viable pathway for polysaccharide yield prediction and the potential recovery of various agricultural residues.

Predicting maturity and identifying key factors in organic waste composting using machine learning models

The measurement of germination index (GI) in composting is a time-consuming and laborious process. This study employed four machine learning (ML) models, namely Random Forest (RF), Artificial Neural Network (ANN), Support Vector Regression (SVR), and Decision Tree (DT), to predict GI based on key composting parameters. The prediction results showed that the coefficient of determination (R2) for RF (>0.9) and ANN (>0.9) was higher than SVR (<0.6) and DT (<0.8), suggesting that RF and ANN displayed superior predictive performance for GI. The SHapley additive exPlanations value result indicated that composting time, temperature, and pH were the important features contributing to GI. Composting time was found to have the most significant impact on GI. Overall, RF and ANN were suggested as effective tools for predicting GI in composting. This study offers the reliable approach of accurately predicting GI in composting processes, thereby enabling intelligent composting practices.

Machine learning application for predicting key properties of activated carbon produced from lignocellulosic biomass waste with chemical activation

The successful application of gradient boosting regression (GBR) in machine learning to forecast surface area, pore volume, and yield in biomass-derived activated carbon (AC) production underscores its potential for enhancing manufacturing processes. The GBR model, collecting 17 independent variables for two-step activation (2-SA) and 14 for one-step activation (1-SA), demonstrates effectiveness across three datasets-1-SA, 2-SA, and a combined dataset. Notably, in 1-SA, the GBR model yields R2 values of 0.76, 0.90, and 0.83 for TPV, yield, and SSA respectively, and records R2 of 0.90 and 0.91 for yield in 2-SA and combined datasets. The model highlights the significance of the soaking procedure alongside activation temperature in shaping AC properties with 1-SA or 2-SA, illustrating machine learning's potential in optimizing AC production processes.

Improving prediction of N2O emissions during composting using model-agnostic meta-learning

Nitrous oxide (N2O) represents a significant environmental challenge as a harmful, long-lived greenhouse gas that contributes to the depletion of stratospheric ozone and exacerbates global anthropogenic greenhouse warming. Composting is considered a promising and economically feasible strategy for the treatment of organic waste. However, recent research indicates that composting is a source of N2O, contributing to atmospheric pollution and greenhouse effect. Consequently, there is a need for the development of effective, cost-efficient methodologies to quantify N2O emissions accurately. In this study, we employed the model-agnostic meta-learning (MAML) method to improve the performance of N2O emissions prediction during manure composting. The highest R2 and lowest root mean squared error (RMSE) values achieved were 0.939 and 18.42 mg d-1, respectively. Five machine learning methods including the backpropagation neural network, extreme learning machine, integrated machine learning method based on ELM and random forest, gradient boosting decision tree, and extreme gradient boosting were adopted for comparison to further demonstrate the effectiveness of the MAML prediction model. Feature analysis showed that moisture content of structure material and ammonium concentration during composting process were the two most significant features affecting N2O emissions. This study serves as proof of the application of MAML during N2O emissions prediction, further giving new insights into the effects of manure material properties and composting process data on N2O emissions. This approach helps determining the strategies for mitigating N2O emissions.

Active Learning-Based Guided Synthesis of Engineered Biochar for CO2 Capture

Biomass waste-derived engineered biochar for CO2 capture presents a viable route for climate change mitigation and sustainable waste management. However, optimally synthesizing them for enhanced performance is time- and labor-intensive. To address these issues, we devise an active learning strategy to guide and expedite their synthesis with improved CO2 adsorption capacities. Our framework learns from experimental data and recommends optimal synthesis parameters, aiming to maximize the narrow micropore volume of engineered biochar, which exhibits a linear correlation with its CO2 adsorption capacity. We experimentally validate the active learning predictions, and these data are iteratively leveraged for subsequent model training and revalidation, thereby establishing a closed loop. Over three active learning cycles, we synthesized 16 property-specific engineered biochar samples such that the CO2 uptake nearly doubled by the final round. We demonstrate a data-driven workflow to accelerate the development of high-performance engineered biochar with enhanced CO2 uptake and broader applications as a functional material.

Use of machine learning to identify key factors regulating volatilization of semi-volatile organic chemicals from soil to air

Volatilization from soil to air is a key process driving the distribution and fate of semi-volatile organic contaminants. However, quantifying this process and the key environmental governing factors remains difficult. To address this issue, the volatilization fluxes of polybrominated diphenyl ethers (PBDEs) and organophosphate esters (OPEs) from soil were determined in 16 batch experiments orthogonally with six variables (chemical property, soil concentration, air velocity, ambient temperature, soil porosity, and soil moisture) and analyzed with machine learning methods. The results showed that gradient-boosting regression tree models satisfactorily predicted the volatilization fluxes of PBDEs (r2 = 0.82 ± 0.07) and OPEs (r2 = 0.62 ± 0.13). Permutation importance analysis showed that partitioning potential of chemicals between soil and air was the most important factor regulating the volatilization of the target compounds from soil. Temperature and soil porosity played a secondary role in controlling the migration of PBDEs and OPEs, respectively, due to higher volatilization enthalpies of PBDEs than those of OPEs and dominant adsorption of OPEs on mineral surface. The effect of soil moisture was negative and positive for the volatilization fluxes of PBDEs and OPEs, respectively. These results suggested different responses in the soil-air diffusive transport of PBDEs and OPEs to high temperature and rainstorm induced by climate change.

Carbon capture, utilization and sequestration systems design and operation optimization: Assessment and perspectives of artificial intelligence opportunities

Carbon capture, utilization, and sequestration (CCUS) is a promising solution to decarbonize the energy and industrial sectors to mitigate climate change. An integrated assessment of technological options is required for the effective deployment of CCUS large-scale infrastructure between CO2 production and utilization/sequestration nodes. However, developing cost-effective strategies from engineering and operation perspectives to implement CCUS is challenging. This is due to the diversity of upstream emitting processes located in different geographical areas, available downstream utilization technologies, storage sites capacity/location, and current/future energy/emissions/economic conditions. This paper identifies the need to achieve a robust hybrid assessment tool for CCUS modeling, simulation, and optimization based mainly on artificial intelligence (AI) combined with mechanistic methods. Thus, a critical literature review is conducted to assess CCUS technologies and their related process modeling/simulation/optimization techniques, while evaluating the needs for improvements or new developments to reduce overall CCUS systems design and operation costs. These techniques include first principles- based and data-driven ones, i.e. AI and related machine learning (ML) methods. Besides, the paper gives an overview on the role of life cycle assessment (LCA) to evaluate CCUS systems where the combined LCA-AI approach is assessed. Other advanced methods based on the AI/ML capabilities/algorithms can be developed to optimize the whole CCUS value chain. Interpretable ML combined with explainable AI can accelerate optimum materials selection by giving strong rules which accelerates the design of capture/utilization plants afterwards. Besides, deep reinforcement learning (DRL) coupled with process simulations will accelerate process design/operation optimization through considering simultaneous optimization of equipment sizing and operating conditions. Moreover, generative deep learning (GDL) is a key solution to optimum capture/utilization materials design/discovery. The developed AI methods can be generalizable where the extracted knowledge can be transferred to future works to help cutting the costs of CCUS value chain.

Quantitative identification of the co-exposure effects of e-waste pollutants on human oxidative stress by explainable machine learning

Global electronic waste (e-waste) generation continues to grow. The various pollutants released during precarious e-waste disposal activities can contribute to human oxidative stress. This study encompassed 129 individuals residing near e-waste dismantling sites in China, with elevated urinary concentrations of e-waste-related pollutants including heavy metals, polycyclic aromatic hydrocarbons (PAHs), organophosphorus flame retardants (OPFRs), bisphenols (BPs), and phthalate esters (PAEs). Utilizing an explainable machine learning framework, the study quantified the co-exposure effects of these pollutants, finding that approximately 23% and 18% of the variance in oxidative DNA damage and lipid peroxidation, respectively, was attributable to these substances. Heavy metals emerged as the most critical factor in inducing oxidative stress, followed by PAHs and PAEs for oxidative DNA damage, and BPs, OPFRs, and PAEs for lipid peroxidation. The interactions between different pollutant classes were found to be weak, attributable to their disparate biological pathways. In contrast, the interactions among congeneric pollutants were strong, stemming from their shared pathways and resultant synergistic or additive effects on oxidative stress. An intelligent analysis system for e-waste pollutants was also developed, which enables more efficient processing of large-scale and dynamic datasets in evolving environments. This study offered an enticing peek into the intricacies of co-exposure effect of e-waste pollutants.

Feature engineering for improved machine-learning-aided studying heavy metal adsorption on biochar

Due to the broad interest in using biochar from biomass pyrolysis for the adsorption of heavy metals (HMs) in wastewater, machine learning (ML) has recently been adopted by many researchers to predict the adsorption capacity (η) of HMs on biochar. However, previous studies focused mainly on developing different ML algorithms to increase predictive performance, and no study shed light on engineering features to enhance predictive performance and improve model interpretability and generalizability. Here, based on a dataset widely used in previous ML studies, features of biochar were engineered-elemental compositions of biochar were calculated on mole basis-to improve predictive performance, achieving test R2 of 0.997 for the gradient boosting regression (GBR) model. The elemental ratio feature (H-O-2N)/C, representing the H site links to C (non-active site to HMs), was proposed for the first time to help interpret the GBR model. The (H-O-2N)/C and pH of biochar played essential roles in replacing cation exchange capacity (CEC) for predicting η. Moreover, expanding the coverages of variables by adding cases from references improved the generalizability of the model, and further validation using cases without CEC and specific surface area (R2 0.78) and adsorption experimental results (R2 0.72) proved the ML model desirable. Future studies in this area may take into account algorithm innovation, better description of variables, and higher coverage of variables to further increase the model's generalizability.

A machine learning and experimental-based model for prediction of soil sorption capacity toward phenanthrene

Sorption by soil is the fundamental basis for environment fate of hydrophobic organic contaminants (HOCs), which varies significantly depending on diverse properties of soils. Therefore, a generalized approach to predict HOC sorption by soils is required. In this study, 488 data points were extracted from references and adopted to develop models for estimating the sorption capacities of phenanthrene in soils using six different machine learning (ML) approaches. The extreme gradient boosting (XGBT) model demonstrated the most favorable performance, achieving a coefficient of determination of 0.91 and root-mean-square errors of 0.24 for the testing dataset. The XGBT model's performance was further demonstrated by comparing with experimental data from batch sorption tests conducted on 20 soil samples collected from 17 provinces of China. The differences between the predicted values and the experimental values were statistically equal to zero (p = 0.14). Leveraging the XBGT model together with soil properties from the Harmonized World Soil Database, the distribution of sorption capacities in Chinese soils was successfully depicted on a national scale. This research is expected to contribute to a deeper understanding of the migration of persistent organic pollutants in terrestrial system. Furthermore, the established model holds implications for more precise and scientific soil environmental management.

Using machine learning to explore oxyanion adsorption ability of goethite with different specific surface area

In this study, we developed prediction models for the adsorption of divalent and trivalent oxyanions on goethite based on machine learning algorithms. After verifying the reliability of the models, the importance of goethite specific surface area (SSA) and the average oxyanion adsorption capacities of goethite with different SSAs were calculated by shapley additive explanations (SHAP) importance analysis and partial dependence (PD) analysis. Despite there were differences in the feature importance of divalent and trivalent oxyanions, the contribution of goethite's SSA to the adsorption amount ranked the fourth based on SHAP importance, indicating SSA played the important role in oxyanion adsorption. Meanwhile, the PD values of SSA and the optimized complexation constants from surface complexation modeling (SCM) both indicated a non-monotonic relationship between the goethite with different SSA and its oxyanions binding capacity. When the total site concentration and crystal face composition were used as the machine learning model input features, the SHAP importance values of crystal faces and the PD decomposition results indicated that the (001) face showed the crucial influence on oxyanions adsorption amount. These findings demonstrated the important role of crystal face composition in goethite's adsorption ability, and provided a theoretical explanation for the variations of oxyanions adsorption amount on different SSA goethite.

Machine learning applications for biochar studies: A mini-review

Biochar is a promising carbon sink whose application can assist in reducing carbon emissions. Development of this technology currently relies on experimental trials, which are time-consuming and labor-intensive. Machine learning (ML) technology presents a potential solution for streamlining this process. This review summarizes the current research on ML's applications in biochar production, characterization, and applications. It briefly explains commonly used machine learning algorithms and discusses prospects and challenges. A hybrid model that combines ML with mechanism-based analysis could be a future trend, addressing the ML's black-box nature. While biochar studies have adopted ML technology, current works mostly use lab-scale data for model training. Further work is needed to develop ML models based on pilot or industrial-scale data to realize the use of ML techniques for the field application of biochar.

Machine learning prediction and interpretation of the impact of microplastics on soil properties

The annual microplastic (MP) release into soils is 4-23 times higher than that into oceans, significantly impacting soil quality. However, the mechanisms underlying how MPs impact soil properties remain largely unknown. Soil-MP interactions are complex because of soil heterogeneity and varying MP properties. This lack of understanding was exacerbated by the diverse experimental conditions and soil types used in this study. Predicting changes in soil properties in the presence of MPs is challenging, laborious, and time-consuming. To address these issues, machine learning was applied to fit datasets from peer-reviewed publications to predict and interpret how MPs influence soil properties, including pH, dissolved organic carbon (DOC), total P, NO3--N, NH4+-N, and acid phosphatase enzyme activity (acid P). Among the developed models, the gradient boost regression (GBR) model showed the highest R2 (0.86-0.99) compared to the decision tree and random forest models. The GBR model interpretation showed that MP properties contributed more than 50% to altering the acid P and NO3--N concentrations in soils, whereas they had a negligible impact on total P and 10-20% impact on soil pH, DOC, and NH4+-N. Specifically, the size of MPs was the dominant factor influencing acid P (89.3%), pH (71.6%), and DOC (44.5%) in soils. NO3--N was mainly affected by the MP type (52.0%). The NH4+-N was mainly affected by the MP dose (46.8%). The quantitative insights into the impact of MPs on soil properties of this study could aid in understanding the roles of MPs in soil systems.

Intelligent leaching rare earth elements from waste fluorescent lamps

Rare earth elements (REEs), one of the global key strategic resources, are widely applied in electronic information and national defense, etc. The sharply increasing demand for REEs leads to their overexploitation and environmental pollution. Recycling REEs from their second resources such as waste fluorescent lamps (WFLs) is a win-win strategy for REEs resource utilization and environmental production. Pyrometallurgy pretreatment combined with acid leaching is proven as an efficient approach to recycling REEs from WFLs. Unfortunately, due to the uncontrollable components of wastes, many trials were required to obtain the optimal parameters, leading to a high cost of recovery and new environmental risks. This study applied machine learning (ML) to build models for assisting the leaching of six REEs (Tb, Y, Eu, La, and Gd) from WFLs, only needing the measurement of particle size and composition of the waste feed. The feature importance analysis of 40 input features demonstrated that the particle size, Mg, Al, Fe, Sr, Ca, Ba, and Sb content in the waste feed, the pyrometallurgical and leaching parameters have important effects on REEs leaching. Furthermore, their influence rules on different REEs leaching were revealed. Finally, some verification experiments were also conducted to demonstrate the reliability and practicality of the model. This study can quickly get the optimal parameters and leaching efficiency for REEs without extensive optimization experiments, which significantly reduces the recovery cost and environmental risks. Our work carves a path for the intelligent recycling of strategic REEs from waste.

End-to-end machine-learning for high-gravity ammonia stripping: Bridging the gap between scientific research and user-friendly applications

The removal and recovery of ammonia from wastewater are critical processes for achieving global environmental sustainability and promoting circular economic development. High-gravity technology is an advanced solution to achieve ammonia stripping from wastewater. This study used machine-learning (ML) techniques to provide more comprehensive insights on various influencing factors, including the operating parameters, wastewater characteristics, and design parameters of rotating packed beds. Bayesian auto-optimization combined with a boosting algorithm effectively overcame the challenges of modeling complex datasets with small sample sizes, multidimensional data, missing values, and skewed distributions. Accurate ML based predictive models for the ammonia removal efficiency (η) and mass transfer coefficient (KLa) were developed, the performance on the training set was R2 = 0.98 and R2 = 0.89, and on the testing set was R2 = 0.98 and R2 = 0.82. The developed model revealed that the stripping stage and gas-liquid ratio were the most influential features for predicting η, whereas the liquid flow and high-gravity factor were the most important features for predicting KLa. The well-trained model was then deployed in an online software application that could provide both predictive and auto-update functions for operators and managers, ensuring that practitioners could use the model. The end-to-end machine-learning approach used in this study-that is, covering data collection, model development, and application-could improve the availability of research results, providing valuable references for the further advancement of technology in the field of environmental.

Machine learning based prediction and experimental validation of arsenite and arsenate sorption on biochars

Arsenic (As) contamination in water is a significant environmental concern with profound implications for human health. Accurate prediction of the adsorption capacity of arsenite [As(III)] and arsenate [As(V)] on biochar is vital for the reclamation and recycling of polluted water resources. However, comprehending the intricate mechanisms that govern arsenic accumulation on biochar remains a formidable challenge. Data from the literature on As adsorption to biochar was compiled and fed into machine learning (ML) based modelling algorithms, including AdaBoost, LGBoost, and XGBoost, in order to build models to predict the adsorption efficiency of As(III) and As(V) to biochar, based on the compositional and structural properties. The XGBoost model showed superior accuracy and performance for prediction of As adsorption efficiency (for As(III): coefficient of determination (R2) = 0.93 and root mean square error (RMSE) = 1.29; for As(V), R2 = 0.99, RMSE = 0.62). The initial concentrations of As(III) and As(V) as well as the dosage of the adsorbent were the most significant factors influencing adsorption, explaining 48 % and 66 % of the variability for As(III) and As(V), respectively. The structural properties and composition of the biochar explained 12 % and 40 %, respectively, of the variability of As(III) adsorption, and 13 % and 21 % of that of As(V). The XGBoost models were validated using experimental data. R2 values were 0.9 and 0.84, and RMSE values 6.5 and 8.90 for As(III) and As(V), respectively. The ML approach can be a valuable tool for improving the treatment of inorganic As in aqueous environments as it can help estimate the optimal adsorption conditions of As in biochar-amended water, and serve as an early warning for As-contaminated water.

A new perspective on predicting the reaction rate constants of hydrated electrons for organic contaminants: Exploring molecular structure characterization methods and ambient conditions

Hydrated electrons (eaq-) exhibit rapid degradation of diverse persistent organic contaminants (OCs) and hold great promise as a formidable reducing agent in water treatment. However, the diverse structures of compounds exert different influences on the second-order rate constant of hydrated electron reactions (keaq-), while the same OCs demonstrate notable discrepancies in keaq- values across different pH levels. This study aims to develop machine learning (ML) models that can effectively simulate the intricate reaction kinetics between eaq- and OCs. Furthermore, the introduction of the pH variable enables a comprehensive investigation into the impact of ambient conditions on this process, thereby improving the practicality of the model. A dataset encompassing 701 keaq- values derived from 351 peer-reviewed publications was compiled. To comprehensively investigate compound properties, this study introduced molecular descriptor (MD), molecular fingerprint (MF), and the integration of both (MD + MF) as model variables. Furthermore, 60 sets of predictive models were established utilizing two variable screening methodologies (MLR and RF) and ten prominent algorithms. Through statistical parameter analysis, it was determined that descriptors combined with MD and MF, the RF screening method, and the symbolism algorithm exhibited the best predictive efficacy. Importantly, the combination of descriptor models exhibited significantly superior performance compared to individual MF and MD models. Notably, the optimal model, denoted as RF - (MF + MD) - LGB, exhibited highly satisfactory predictive results (R2tra = 0.967, Q2tra = 0.840, R2ext = 0.761). The mechanistic explanation study based on Shapley Additive Explanations (SHAP) values further elucidated the crucial influences of polarity, pH, molecular weight, electronegativity, carbon-carbon double bonds, and molecular topology on the degradation of OCs by eaq-. The proposed modeling approach, particularly the integration of MF and MD, alongside the introduction of pH, may furnish innovative ideas for advanced reduction or oxidation processes (ARPs/AOPs) and machine learning applications in other domains.

Natural Products Derived Porous Carbons for CO2 Capture

As it is now established that global warming and climate change are a reality, international investments are pouring in and rightfully so for climate change mitigation. Carbon capture and separation (CCS) is therefore gaining paramount importance as it is considered one of the powerful solutions for global warming. Sorption on porous materials is a promising alternative to traditional carbon dioxide (CO2 ) capture technologies. Owing to their sustainable availability, economic viability, and important recyclability, natural products-derived porous carbons have emerged as favorable and competitive materials for CO2 sorption. Furthermore, the fabrication of high-quality value-added functional porous carbon-based materials using renewable precursors and waste materials is an environmentally friendly approach. This review provides crucial insights and analyses to enhance the understanding of the application of porous carbons in CO2 capture. Various methods for the synthesis of porous carbon, their structural characterization, and parameters that influence their sorption properties are discussed. The review also delves into the utilization of molecular dynamics (MD), Monte Carlo (MC), density functional theory (DFT), and machine learning techniques for simulating adsorption and validating experimental results. Lastly, the review provides future outlook and research directions for progressing the use of natural products-derived porous carbons for CO2 capture.

Machine Learning Models for Inverse Design of the Electrochemical Oxidation Process for Water Purification

In this study, a machine learning (ML) framework is developed toward target-oriented inverse design of the electrochemical oxidation (EO) process for water purification. The XGBoost model exhibited the best performances for prediction of reaction rate (k) based on training the data set relevant to pollutant characteristics and reaction conditions, indicated by Rext2 of 0.84 and RMSEext of 0.79. Based on 315 data points collected from the literature, the current density, pollutant concentration, and gap energy (Egap) were identified to be the most impactful parameters available for the inverse design of the EO process. In particular, adding reaction conditions as model input features allowed provision of more available information and an increase in the sample size of the data set to improve the model accuracy. The feature importance analysis was performed for revealing the data pattern and feature interpretation by using Shapley additive explanations (SHAP). The ML-based inverse design for the EO process was generalized to a random case for tailoring the optimum conditions with phenol and 2,4-dichlorophenol (2,4-DCP) serving as model pollutants. The resulting predicted k values were close to the experimental k values by experimental verification, accounting for the relative error lower than 5%. This study provides a paradigm shift from conventional trial-and-error mode to data-driven mode for advancing research and development of the EO process by a time-saving, labor-effective, and environmentally friendly target-oriented strategy, which makes electrochemical water purification more efficient, more economic, and more sustainable in the context of global carbon peaking and carbon neutrality.

Prediction of Photochemical Properties of Dissolved Organic Matter Using Machine Learning

Apparent quantum yields (Φ) of photochemically produced reactive intermediates (PPRIs) formed by dissolved organic matter (DOM) are vital to element cycles and contaminant fates in surface water. Simultaneous determination of ΦPPRI values from numerous water samples through existing experimental methods is time consuming and ineffective. Herein, machine learning models were developed with a systematic data set including 1329 data points to predict the values of three ΦPPRIs (Φ3DOM*, Φ1O2, and Φ·OH) based on DOM spectral parameters, experimental conditions, and calculation parameters. The best predictive performances for Φ3DOM*, Φ1O2, and Φ·OH were achieved using the CatBoost model, which outperformed the traditional linear regression models. The significances of the wavelength range and spectral parameters on the three ΦPPRI predictions were revealed, suggesting that DOM with lower molecular weight, lower aromatic content, and a more autochthonous portion possessed higher ΦPPRIs. Chain models were constructed by adding the predicted Φ3DOM* as a new feature into the Φ1O2 and Φ·OH models, which consequently improved the predictive performance of Φ1O2 but worsened the Φ·OH prediction likely due to the complex formation pathways of ·OH. Overall, this study offered robust ΦPPRI prediction across interlaboratory differences and provided new insights into the relationship between PPRIs formation and DOM properties.

Emerging Directions for Carbon Capture Technologies: A Synergy of High-Throughput Theoretical Calculations and Machine Learning

As the world grapples with the challenges of energy transition and industrial decarbonization, the development of carbon capture technologies presents a promising solution. The Scalable Modeling, Artificial Intelligence (AI), and Rapid Theoretical calculations, referred as SMART here, is an interdisciplinary approach that combines high-throughput calculation and data-driven modeling with expertise from chemical, materials, environmental, computer and data science and engineering, leading to the development of advanced capabilities in simulating and optimizing carbon capture processes. This perspective discusses the state-of-the-art material discovery research enabled by high-throughput calculation and data-driven modeling. Further, we propose a framework for material discovery, and illustrate the synergies among deep learning models, pretrained models, and comprehensive data sets, emerging as a robust framework for data-driven design and development in carbon capture. In essence, the adoption of the SMART approach promises a revolutionary impact on efforts in energy transition and industrial decarbonization.