Design of Experimental Conditions with Machine Learning for Collaborative Organic Synthesis Reactions Using Transition-Metal Catalysts

A robust methodology for PEC performance analysis of photoanodes using machine learning and analytical data

Machine learning (ML) is increasingly applied across various fields, including chemistry, for molecular design and optimizing reaction parameters. Yet, applying ML to experimental data is challenging due to the limited number of synthesized samples, which restricts its broader application in device development. In energy harvesting, photoanodes are crucial for solar-driven water splitting, generating hydrogen and oxygen. We explored electrodes like hematite and bismuth vanadate for photocatalytic uses, noting varied photoelectrochemical performances despite similar preparations. To understand this variability, we applied a data-driven ML approach, predicting photocurrent values and identifying key performance influencers even with limited experimental data in the research development of inorganic devices. We have utilized multiple machine learning algorithms to predict the target value in the calculation process, where the contributions of the dominant descriptors were unknown. We introduced a novel methodology, incorporating clustering to manage multicollinearity from correlated analytical data and Shapley analysis for clear interpretation of contributions to performance prediction. This method was validated on hematite and bismuth vanadate, showing superior predictability and factor identification, and then extended to tungsten oxide and bismuth vanadate heterojunction photoanodes. Despite their complexity, our approach achieved determination coefficients (R2) with a prediction accuracy over 0.85, successfully pinpointing performance-determining factors, demonstrating the robustness of the new scheme in advancing photodevice research.

Subtraction Descriptors in Machine Learning for Optimizing the Cocatalyst Effect of Cobalt Phosphate on Hematite Photoanodes

In the quest for sustainable energy solutions, the optimization of the photoelectrochemical (PEC) performance of hematite photoanodes through cocatalysts represents a promising avenue. This study introduces a novel machine learning approach, leveraging subtraction descriptors, to isolate and quantify the specific effects of cobalt phosphate (Co-Pi) as a cocatalyst on hematite's PEC performance. By integrating data from various analytical techniques, including photoelectrochemical impedance spectroscopy and ultraviolet-visible spectroscopy, with advanced machine learning models, we successfully predicted the PEC performance enhancement attributed to Co-Pi. The Gaussian process regression (GPR) model emerged as the most effective, revealing the critical influence of the interfacial resistance, bulk resistance, and interfacial capacitance on the PEC performance. These findings underscore the potential of cocatalysts in improving charge separation and extending charge carrier lifetimes, thereby boosting the efficiency of photocatalytic reactions. This study not only advances our understanding of the cocatalyst effect in photocatalytic systems but also demonstrates the power of machine learning in modifying complex materials and guiding the development of optimized photocatalytic materials. The implications of this research extend beyond hematite photoanodes, offering a generalizable framework for enhancing the photoelectrochemical properties of a wide range of material modifications such as cocatalyst deposition, doping, and passivation.

MonteCat: A Basin-Hopping-Inspired Catalyst Descriptor Search Algorithm for Machine Learning Models

Proposing relevant catalyst descriptors that can relate the information on a catalyst's composition to its actual performance is an ongoing area in catalyst informatics, as it is a necessary step to improve our understanding on the target reactions. Herein, a small descriptor-engineered data set containing 3289 descriptor variables and the performance of 200 catalysts for the oxidative coupling of methane (OCM) is analyzed, and a descriptor search algorithm based on the workflow of the Basin-hopping optimization methodology is proposed to select the descriptors that better fit a predictive model. The algorithm, which can be considered wrapper in nature, consists of the successive generation of random-based modifications to the descriptor subset used in a regression model and adopting them depending on their effect on the model's score. The results are presented after being tested on linear and Support Vector Regression models with average cross-validation r2 scores of 0.8268 and 0.6875, respectively.

Identification of the Contributing Factors to the Photoelectric Conversion Efficiency for Hematite Photoanodes by Using Machine Learning

Hematite has gained significant attention in the field of photocatalysis as one of the most promising materials for the photoanode of photoelectrochemical (PEC) water splitting due to visible light absorption and the abundance of availability. However, its performance improvement process suffers from a serious bottleneck due to "sample variation" and "inactivity". However, the physical origin of them has not yet been elucidated. To address these issues, we have developed a machine learning (ML) strategy using a combination of various analytical data of hematite photoanodes to discern "active/inactive" and identify the dominant factors. For the demonstration purpose of the ML strategy, we picked up one of the dominant factors, the interfacial resistivity between hematite and FTO, which has not generally been explored as a first candidate in the improvement of photocatalytic materials. The operational parameters for the sample preparation were optimized to modify the selected physical property. Along with the improvement of the selected resistivity, we found that the other dominant descriptors related to the properties of bulk hematite and the surface facet were also modified and help improve the PEC performance.

Catalyst Design and Feature Engineering to Improve Selectivity and Reactivity in Two Simultaneous Cross-Coupling Reactions

Highly active catalysts are required in numerous industrial fields; therefore, to minimize costs and development time, catalyst design using machine learning has attracted significant attention. This study focused on a reaction system where two types of cross-coupling reactions, namely, Buchwald-Hartwig type cross-coupling (BHCC) and Suzuki-Miyaura type cross-coupling (SMCC) reactions, occur simultaneously. Constructing a machine-learning model that considers all experimental conditions is essential to accurately predict the product yield for both the BHCC and the SMCC reactions. The objective of this study was to establish explanatory variables x that considered all experimental conditions within the reaction system involving simultaneous cross-couplings and to design catalysts that achieve the target yield and the development of novel reactions. To accomplish this, Bayesian optimization was combined with established variables x to design new catalysts and enhance reaction selectivity. Moreover, the catalyst design in this study successfully pioneered new reactions involving Cu, Rh, and Pt catalysts in a reaction system that did not previously react with transition metals other than Ni or Pd.

Molecular Machine Learning for Chemical Catalysis: Prospects and Challenges

ConspectusIn the domain of reaction development, one aims to obtain higher efficacies as measured in terms of yield and/or selectivities. During the empirical cycles, an admixture of outcomes from low to high yields/selectivities is expected. While it is not easy to identify all of the factors that might impact the reaction efficiency, complex and nonlinear dependence on the nature of reactants, catalysts, solvents, etc. is quite likely. Developmental stages of newer reactions would typically offer a few hundreds of samples with variations in participating molecules and/or reaction conditions. These "observations" and their "output" can be harnessed as valuable labeled data for developing molecular machine learning (ML) models. Once a robust ML model is built for a specific reaction under development, it can predict the reaction outcome for any new choice of substrates/catalyst in a few seconds/minutes and thus can expedite the identification of promising candidates for experimental validation. Recent years have witnessed impressive applications of ML in the molecular world, most of them aimed at predicting important chemical or biological properties. We believe that an integration of effective ML workflows can be made richly beneficial to reaction discovery.As with any new technology, direct adaptation of ML as used in well-developed domains, such as natural language processing (NLP) and image recognition, is unlikely to succeed in reaction discovery. Some of the challenges stem from ineffective featurization of the molecular space, unavailability of quality data and its distribution, in making the right choice of ML model and its technically robust deployment. It shall be noted that there is no universal ML model suitable for an inherently high-dimensional problem such as chemical reactions. Given these backgrounds, rendering ML tools conducive for reactions is an exciting as well as challenging endeavor at the same time. With the increased availability of efficient ML algorithms, we focused on tapping their potential for small-data reaction discovery (a few hundreds to thousands of samples).In this Account, we describe both feature engineering and feature learning approaches for molecular ML as applied to diverse reactions of high contemporary interest. Among these, catalytic asymmetric hydrogenation of imines/alkenes, β-C(sp³)-H bond functionalization, and relay Heck reaction employed a feature engineering approach using the quantum-chemically derived physical organic descriptors as the molecular features─all designed to predict the enantioselectivity. The selection of molecular features to customize it for a reaction of interest is described, along with emphasizing the chemical insights that could be gathered through the use of such features. Feature learning methods for predicting the yield of Buchwald-Hartwig cross-coupling, deoxyfluorination of alcohols, and enantioselectivity of N,S-acetal formation are found to offer excellent predictions. We propose a transfer learning protocol, wherein an ML model such as a language model is trained on a large number of molecules (10⁵-10⁶) and fine-tuned on a focused library of target task reactions, as an effective alternative for small-data reaction discovery (10²-10³ reactions). The exploitation of deep neural network latent space as a method for generative tasks to identify useful substrates for a reaction is demonstrated as a promising strategy.

Design of Molecules with Low Hole and Electron Reorganization Energy Using DFT Calculations and Bayesian Optimization

Materials exhibiting higher mobility than conventional organic semiconducting materials, such as fullerenes and fused thiophenes, are in high demand for applications in printed electronics. To discover new molecules that might show improved charge mobility, the adaptive design of experiments (DoE) to design molecules with low reorganization energy was performed by combining density functional theory (DFT) methods and machine learning techniques. DFT-calculated values of 165 molecules were used as an initial training dataset for a Gaussian process regression (GPR) model, and five rounds of molecular designs applying the GPR model and validation via DFT calculations were executed. As a result, new molecules whose reorganization energy is smaller than the lowest value in the initial training dataset were successfully discovered.

Prediction of the photoelectrochemical performance of hematite electrodes using analytical data

Combination of analytical data could predict and specify the critical factors for the photoelectrode performance.