Prediction of arsenic adsorption onto metal organic frameworks and adsorption mechanisms interpretation by machine learning

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.

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.

Dual cross-linked magnetic gelatin/carboxymethyl cellulose cryogels for enhanced Congo red adsorption: Experimental studies and machine learning modelling

To achieve highly efficient and environmentally degradable adsorbents for Congo red (CR) removal, we synthesized a dual-network nanocomposite cryogel composed of gelatin/carboxymethyl cellulose, loaded with Fe3O4 nanoparticles. Gelatin and sodium carboxymethylcellulose were cross-linked using transglutaminase and calcium chloride, respectively. The cross-linking process enhanced the thermal stability of the composite cryogels. The CR adsorption process exhibited a better fit to the pseudo-second-order model and Langmuir model, with maximum adsorption capacity of 698.19 mg/g at pH of 7, temperature of 318 K, and initial CR concentration of 500 mg/L. Thermodynamic results indicated that the CR adsorption process was both spontaneous and endothermic. The performance of machine learning model showed that the Extreme Gradient Boosting model had the highest test determination coefficient (R2 = 0.9862) and the lowest root mean square error (RMSE = 10.3901 mg/g) among the 6 models. Feature importance analysis using SHapley Additive exPlanations (SHAP) revealed that the initial concentration had the greatest influence on the model's prediction of adsorption capacity. Density functional theory calculations indicated that there were active sites on the CR molecule that can undergo electrostatic interactions with the adsorbent. Thus, the synthesized cryogels demonstrate promising potential as adsorbents for dye removal from wastewater.

Development of the design and synthesis of metal-organic frameworks (MOFs) - from large scale attempts, functional oriented modifications, to artificial intelligence (AI) predictions

Owing to the exceptional porous properties of metal-organic frameworks (MOFs), there has recently been a surge of interest, evidenced by a plethora of research into their design, synthesis, properties, and applications. This expanding research landscape has driven significant advancements in the precise regulation of MOF design and synthesis. Initially dominated by large-scale synthesis approaches, this field has evolved towards more targeted functional modifications. Recently, the integration of computational science, particularly through artificial intelligence predictions, has ushered in a new era of innovation, enabling more precise and efficient MOF design and synthesis methodologies. The objective of this review is to provide readers with an extensive overview of the development process of MOF design and synthesis, and to present visions for future developments.

Metal-Organic Frameworks for Dual Photo-Oxidation and Capture of Arsenic from Water

Despite rapid technological progress, heavy metal water pollution, and particularly arsenic contamination, remains a significant global challenge. In addition, the stabilization of trivalent arsenic as neutral arsenite (AsIII) species hinders its removal by conventional sorbents. While adsorption of anionic arsenate (AsV) species is in principle more feasible, there are only few adsorbents capable of adsorbing both forms of arsenic. In this work, we explore the potential of two well-known families of Metal-Organic Frameworks (MOFs), UiO-66 and MIL-125, to simultaneously adsorb and photo-oxidize arsenic species from water. Our results demonstrate that the formation of AsV ions upon light irradiation promotes the subsequent adsorption of AsIII species. Thus, we propose the combined utilization of photocatalysis and adsorption with Metal-Organic Framework photocatalysts for water remediation purposes.

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.

Performance and mechanism of diclofenac adsorption onto 3D poly(m-phenylenediamine)-grafted melamine foam via batch experiment and theoretical studies

Seeking highly efficient adsorbents for pharmaceuticals and personal care products (PPCPs) removal has been a worldwide continuing endeavor. In this study, a new 3D composite material was synthesized by covalently anchoring Poly(m-Phenylenediamine) onto 3D polyvinyl alcohol modified foam framework (PmPD-MF-PVA). PmPD-MF-PVA was characterized and evaluated for its efficacy in removing diclofenac (DCF), a commonly detected PPCPs in both wastewater and surface water. Results showed that the adsorption capacity of PmPD-MF-PVA toward DCF was 1.5 times higher than that of PmPD-MF. The addition of PVA increased deposition area of PmPD, and promoted PmPD loading on the foam surface. Batch adsorption experiments exhibited that the adsorption of DCF was fitted well with Langmuir isotherm and pseudo-second-order kinetic models. The maximum adsorption capacity of PmPD-MF-PVA was 115 mg/g. Meanwhile, PmPD-MF-PVA exhibited better separation ability than the hard-to-separate PmPD. Characterization analysis and density functional theory (DFT) calculation elucidated the main mechanisms of DCF adsorption on PmPD-MF-PVA. Hydrogen bonding and π-π interactions were main drivers for DCF adsorption, followed by electrostatic attraction and hydrophobic forces. This study provides an effective strategy to overcome the drawbacks of PmPD, such as recycling difficulty and agglomeration problems, offering valuable insights for the design of polymers-based adsorbents.

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.