Identifying Descriptors for Promoted Rhodium-Based Catalysts for Higher Alcohol Synthesis via Machine Learning

Data-Driven Insights into Porphyrin Geometry: Interpretable AI for Non-Planarity and Aromaticity Analyses

Porphyrins are involved in numerous and very different chemical and biological processes, due to the sensitivity of their application-relevant properties to subtle structural changes. Applying modern machine learning methodology is very appealing for discovering structure-activity relationships that can be used for design of tailor-made porphyrins for specific purposes. For achieving this goal, a high-quality set consisting of 425 metal porphyrins was established via curation of 7590 porphyrin structures from the Cambridge crystallographic database. Using data-driven techniques for analyzing nonplanarity and "structural aromaticity" allowed for validation of common knowledge in the field as well as discovery of new relations. Aromaticity was found to be influenced differently by distinct nonplanar distortions. Nonplanarity is more sensitive to macrocycle substitutions than to metal or axial ligand effects, while ruffled distortions are dominated by axial ligand size and metal properties. These findings offer new insights into structure-property relationships in porphyrins, providing a data-driven foundation for targeted synthesis to tune aromaticity and nonplanarity. Despite data set limitations, this work demonstrates the value of machine learning in uncovering complex chemical trends.

Understanding the role of supported Rh atoms and clusters during hydroformylation and CO hydrogenation reactions with in situ/operando XAS and DRIFT spectroscopy

Supported Rh single-atoms and clusters on CeO2, MgO, and ZrO2 were investigated as catalysts for hydroformylation of ethylene to propionaldehyde and CO hydrogenation to methanol/ethanol with in situ/operando diffuse reflectance infrared Fourier transform spectroscopy (DRIFTS) and X-ray absorption spectroscopy (XAS). Under hydroformylation reaction conditions, operando spectroscopic investigations unravel the presence of both single atoms and clusters and detected at first propanal and then methanol. We find that the formation of methanol is associated with CO hydrogenation over Rh clusters which was further confirmed under CO hydrogenation conditions at elevated pressure. The activity of catalysts synthesized via a precipitation (PP) method over various supports towards the hydroformylation reaction follows the order: Rh/ZrO2 > Rh/CeO2 > Rh/MgO. Comparing Rh/CeO2 catalysts synthesized via different methods, catalysts prepared by flame spray pyrolysis (FSP) showed catalytic activity for the hydroformylation reaction at lower temperatures (413 K), whereas catalysts prepared by wet impregnation (WI) showed the highest stability. These results not only provide fundamental insights into the atomistic level of industrially relevant reactions but also pave the way for a rational design of new catalysts in the future.

Active learning streamlines development of high performance catalysts for higher alcohol synthesis

Developing efficient catalysts for syngas-based higher alcohol synthesis (HAS) remains a formidable research challenge. The chain growth and CO insertion requirements demand multicomponent materials, whose complex reaction dynamics and extensive chemical space defy catalyst design norms. We present an alternative strategy by integrating active learning into experimental workflows, exemplified via the FeCoCuZr catalyst family. Our data-aided framework streamlines navigation of the extensive composition and reaction condition space in 86 experiments, offering >90% reduction in environmental footprint and costs over traditional programs. It identifies the Fe65Co19Cu5Zr11 catalyst with optimized reaction conditions to attain higher alcohol productivities of 1.1 gHA h-1 gcat-1 under stable operation for 150 h on stream, a 5-fold improvement over typically reported yields. Characterization reveals catalytic properties linked to superior activities despite moderate higher alcohol selectivities. To better reflect catalyst demands, we devise multi-objective optimization to maximize higher alcohol productivity while minimizing undesired CO2 and CH4 selectivities. An intrinsic trade-off between these metrics is uncovered, identifying Pareto-optimal catalysts not readily discernible by human experts. Finally, based on feature-importance analysis, we formulate data-informed guidelines to develop performance-specific FeCoCuZr systems. This approach goes beyond existing HAS catalyst design strategies, is adaptable to broader catalytic transformations, and fosters laboratory sustainability.

Machine-Learning-Assisted Descriptors Identification for Indoor Formaldehyde Oxidation Catalysts

The development of highly efficient catalysts for formaldehyde (HCHO) oxidation is of significant interest for the improvement of indoor air quality. Up to 400 works relating to the catalytic oxidation of HCHO have been published to date; however, their analysis for collective inference through conventional literature search is still a challenging task. A machine learning (ML) framework was presented to predict catalyst performance from experimental descriptors based on an HCHO oxidation catalysts database. MnOx, CeO2, Co3O4, TiO2, FeOx, ZrO2, Al2O3, SiO2, and carbon-based catalysts with different promoters were compiled from the literature. Notably, 20 descriptors including reaction catalyst composition, reaction conditions, and catalyst physical properties were collected for data mining (2263 data points). Furthermore, the eXtreme Gradient Boosting algorithm was employed, which successfully predicted the conversion efficiency of HCHO with an R-square value of 0.81. Shapley additive analysis suggested Pt/MnO2 and Ag/Ce-Co3O4 exhibited excellent catalytic performance of HCHO oxidation based on the analysis of the entire database. Validated by experimental tests and theoretical simulations, the key descriptor identified by ML, i.e., the first promoter, was further described as metal-support interactions. This study highlights ML as a useful tool for database establishment and the catalyst rational design strategy based on the importance of analysis between experimental descriptors and the performance of complex catalytic systems.

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.

Data-Driven Tunnel Oxide Passivated Contact Solar Cell Performance Analysis Using Machine Learning

Tunnel oxide passivated contacts (TOPCon) have gained interest as a way to increase the energy conversion efficiency of silicon solar cells, and the International Technology Roadmap of Photovoltaics forecasts TOPCon to become an important technology despite a few remaining challenges. To review the recent development of TOPCon cells, this work has compiled a dataset of all device data found in current literature, which sums up to 405 devices from 131 papers. This may seem like a surprisingly small number of cells given the recent interest in the TOPCon architecture, but it illustrates a problem of data dissemination in the field. Notwithstanding the limited number of cells, there is a great diversity in cell manufacturing procedures, and this work observes a gradual increase in performance indicating that the field has not yet converged on a set of best practices. By analyzing the data using statistical methods and machine learning (ML) algorithms, this work is able to reinforces some commonly held hypotheses related to the performance differences between different device architectures. This work also identifies a few more unintuitive feature combinations that would be of interest for further experimentally studies. This work also aims to inspire improvements in data management and dissemination within the TOPCon community.

Machine-Learning-Driven High-Throughput Screening of Transition-Metal Atom Intercalated g-C3N4/MX2 (M = Mo, W; X = S, Se, Te) Heterostructures for the Hydrogen Evolution Reaction

Rising global energy demand, accompanied by environmental concerns linked to conventional fossil fuels, necessitates a shift toward cleaner and sustainable alternatives. This study focuses on the machine-learning (ML)-driven high-throughput screening of transition-metal (TM) atom intercalated g-C3N4/MX2 (M = Mo, W; X = S, Se, Te) heterostructures to unravel the rich landscape of possibilities for enhancing the hydrogen evolution reaction (HER) activity. The stability of the heterostructures and the intercalation within the substrates are verified through adhesion and binding energies, showcasing the significant impact of chalcogenide selection on the interaction properties. Based on hydrogen adsorption Gibbs free energy (ΔGH) computed via density functional theory (DFT) calculations, several ML models were evaluated, particularly random forest regression (RFR) emerges as a robust tool in predicting HER activity with a low mean absolute error (MAE) of 0.118 eV, thereby paving the way for accelerated catalyst screening. The Shapley Additive exPlanation (SHAP) analysis elucidates pivotal descriptors that influence the HER activity, including hydrogen adsorption on the C site (HC), MX layer (HMX), S site (HS), and intercalation of TM atoms at the N site (IN). Overall, our integrated approach utilizing DFT and ML effectively identifies hydrogen adsorption on the N site (site-3) of g-C3N4 as a pivotal active site, showcasing exceptional HER activity in heterostructures intercalated with Sc and Ti, underscoring their potential for advancing catalytic performance.

Unravelling CO2 Reduction Reaction Intermediates on High Entropy Alloy Catalysts: An Interpretable Machine Learning Approach to Establish Scaling Relations

Establishment of a scaling relation among the reaction intermediates is highly important but very much challenging on complex surfaces, such as surfaces of high entropy alloys (HEAs). Herein, we designed an interpretable machine learning (ML) approach to establish a scaling relation among CO2 reduction reaction (CO2 RR) intermediates adsorbed at the same adsorption site. Local Interpretable Model-Agnostic Explanations (LIME), Accumulated Local Effects (ALE), and Permutation Feature Importance (PFI) are used for the global and local interpretation of the utilized black box models. These methods were successfully applied through an iterative way and validated on CuCoNiZnMg and CuCoNiZnSnbased HEAs data. Finally, we successfully predicted adsorption energies of *H2 CO (MAE: 0.24 eV) and *H3 CO (MAE: 0.23 eV) by using the *HCO training data. Similarly, adsorption energy of *O (MAE: 0.32 eV) is also predicted from *H training data. We believe that our proposed method can shift the paradigm of state-of-the-art ML in catalysis towards better interpretability.

Accelerated discovery of multi-elemental reverse water-gas shift catalysts using extrapolative machine learning approach

Designing novel catalysts is key to solving many energy and environmental challenges. Despite the promise that data science approaches, including machine learning (ML), can accelerate the development of catalysts, truly novel catalysts have rarely been discovered through ML approaches because of one of its most common limitations and criticisms-the assumed inability to extrapolate and identify extraordinary materials. Herein, we demonstrate an extrapolative ML approach to develop new multi-elemental reverse water-gas shift catalysts. Using 45 catalysts as the initial data points and performing 44 cycles of the closed loop discovery system (ML prediction + experiment), we experimentally tested a total of 300 catalysts and identified more than 100 catalysts with superior activity compared to those of the previously reported high-performance catalysts. The composition of the optimal catalyst discovered was Pt(3)/Rb(1)-Ba(1)-Mo(0.6)-Nb(0.2)/TiO2. Notably, niobium (Nb) was not included in the original dataset, and the catalyst composition identified was not predictable even by human experts.

The promotional role of Mn in CO2 hydrogenation over Rh-based catalysts from a surface organometallic chemistry approach

Rh-based catalysts modified by transition metals have been intensively studied for CO₂ hydrogenation due to their high activity. However, understanding the role of promoters at the molecular level remains challenging due to the ill-defined structure of heterogeneous catalysts. Here, we constructed well-defined RhMn@SiO₂ and Rh@SiO₂ model catalysts via surface organometallic chemistry combined with thermolytic molecular precursor (SOMC/TMP) approach to rationalize the promotional effect of Mn in CO₂ hydrogenation. We show that the addition of Mn shifts the products from almost pure CH₄ to a mixture of methane and oxygenates (CO, CH₃OH, and CH₃CH₂OH) upon going from Rh@SiO₂ to RhMn@SiO₂. In situ X-ray absorption spectroscopy (XAS) confirms that the Mn^II is atomically dispersed in the vicinity of metallic Rh nanoparticles and enables to induce the oxidation of Rh to form the Mn-O-Rh interface under reaction conditions. The formed interface is proposed to be key to maintaining Rh⁺ sites, which is related to suppressing the methanation reaction and stabilizing the formate species as evidenced by in situ DRIFTS to promote the formation of CO and alcohols.

Unveiling the migration of Cr and Cd to biochar from pyrolysis of manure and sludge using machine learning

Heavy metal (HM) in biochar derived from pyrolysis of sludge or manure is the main issue for its large-scale application in soils for carbon sequestration. However, there is a paucity of efficient approaches to predict and comprehend the HM migration during pyrolysis for preparing low HM-contained biochar. Herein, the data on the feedstock information (FI), additive, total concentration of feedstock (FTC) of HM Cr and Cd, and pyrolysis condition, were extracted from the literature, to predict total concentration (TC) and retention rate (RR) of Cr and Cd in sludge/manure biochar using ML for mapping their migration during pyrolysis. Two datasets for Cr and Cd were compiled with 388 and 292 data points from 48 and 37 peer-review papers. The results indicated that the TC and RR of Cr and Cd could be predicted by the Random Forest model with test R² of 0.74-0.98. Their TC and RR in biochar were dominated by the FTC and FI, respectively; while pyrolysis temperature was the most important to Cd RR. Moreover, potassium-based inorganic additives decreased the TC and RR of Cr while increased those of Cd. The predictive models and insights provided by this work could aid the understanding of HM migration during manure and sludge pyrolysis and guide the preparation of low HM-contained biochar.

What do we talk about, when we talk about single-crystal termination-dependent selectivity of Cu electrocatalysts for CO2 reduction? A data-driven retrospective

We mine from the literature experimental data on the CO₂ electrochemical reduction selectivity of Cu single crystal surfaces. We then probe the accuracy of a machine learning model trained to predict faradaic efficiencies for 11 CO₂ reduction reaction products, as a function of the applied voltage at which the reaction takes place, and the relative amounts of non equivalent surface sites, distinguished according to their nominal coordination. A satisfactory model accuracy is found only when discriminating data according to their provenance. On one hand, this result points at a qualitative agreement across reported experimental CO₂ reduction reactions trends for single-crystal surfaces with well-defined terminations. On the other, this finding hints at the presence of differences in nominally identical catalysts and/or CO₂ reduction reaction measurements, which result in quantitative disagreement between experiments.