Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

Unlocking the potential: machine learning applications in electrocatalyst design for electrochemical hydrogen energy transformation

Machine learning (ML) is rapidly emerging as a pivotal tool in the hydrogen energy industry for the creation and optimization of electrocatalysts, which enhance key electrochemical reactions like the hydrogen evolution reaction (HER), the oxygen evolution reaction (OER), the hydrogen oxidation reaction (HOR), and the oxygen reduction reaction (ORR). This comprehensive review demonstrates how cutting-edge ML techniques are being leveraged in electrocatalyst design to overcome the time-consuming limitations of traditional approaches. ML methods, using experimental data from high-throughput experiments and computational data from simulations such as density functional theory (DFT), readily identify complex correlations between electrocatalyst performance and key material descriptors. Leveraging its unparalleled speed and accuracy, ML has facilitated the discovery of novel candidates and the improvement of known products through its pattern recognition capabilities. This review aims to provide a tailored breakdown of ML applications in a format that is readily accessible to materials scientists. Hence, we comprehensively organize ML-driven research by commonly studied material types for different electrochemical reactions to illustrate how ML adeptly navigates the complex landscape of descriptors for these scenarios. We further highlight ML's critical role in the future discovery and development of electrocatalysts for hydrogen energy transformation. Potential challenges and gaps to fill within this focused domain are also discussed. As a practical guide, we hope this work will bridge the gap between communities and encourage novel paradigms in electrocatalysis research, aiming for more effective and sustainable energy solutions.

Machine Learning-Aided Design of Highly Conductive Anion Exchange Membranes for Fuel Cells and Water Electrolyzers

Alkaline anion exchange membrane (AEM)-based fuel cells (AEMFCs) and water electrolyzers (AEMWEs) are vital for enabling the efficient and large-scale utilization of hydrogen energy. However, the performance of such energy devices is impeded by the relatively low conductivity of AEMs. The conventional trial-and-error approach to designing membrane structures has proven to be both inefficient and costly. To address this challenge, a fully connected neural network (FCNN) model is developed based on acid-catalyzed AEMs to analyze the relationship between structure and conductivity among 180,000 AEM variations. Under machine learning guidance, anilinium cation-type membranes are designed and synthesized. Molecular dynamics simulations and Mulliken charge population analysis validated that the presence of a large anilinium cation domain is a result of the inductive effect of N+ and benzene rings. The interconnected anilinium cation domains facilitated the formation of a continuous ion transport channel within the AEMs. Additionally, the incorporation of the benzyl electron-withdrawing group heightened the inductive effect, leading to high conductivity AEM variant as screened by the machine learning model. Furthermore, based on the highly active and low-cost monomers given by machine learning, the large-scale synthesis of anilinium-based AEMs confirms the potential for commercial applications.

Integration Construction of Hybrid Electrocatalysts for Oxygen Reduction

There is notable progress in the development of efficient oxygen reduction electrocatalysts, which are crucial components of fuel cells. However, these superior activities are limited by imbalanced mass transport and cannot be fully reflected in actual fuel cell applications. Herein, the design concepts and development tracks of platinum (Pt)-nanocarbon hybrid catalysts, aiming to enhance the performance of both cathodic electrocatalysts and fuel cells, are presented. This review commences with an introduction to Pt/C catalysts, highlighting the diverse architectures developed to date, with particular emphasis on heteroatom modification and microstructure construction of functionalized nanocarbons based on integrated design concepts. This discussion encompasses the structural evolution, property enhancement, and catalytic mechanisms of Pt/C-based catalysts, including rational preparation recipes, superior activity, strong stability, robust metal-support interactions, adsorption regulation, synergistic pathways, confinement strategies, ionomer optimization, mass transport permission, multidimensional construction, and reactor upgrading. Furthermore, this review explores the low-barrier or barrier-free mass exchange interfaces and channels achieved through the impressive multidimensional construction of Pt-nanocarbon integrated catalysts, with the goal of optimizing fuel cell efficiency. In conclusion, this review outlines the challenges associated with Pt-nanocarbon integrated catalysts and provides perspectives on the future development trends of fuel cells and beyond.

Selective oxygen reduction reaction: mechanism understanding, catalyst design and practical application

The oxygen reduction reaction (ORR) is a key component for many clean energy technologies and other industrial processes. However, the low selectivity and the sluggish reaction kinetics of ORR catalysts have hampered the energy conversion efficiency and real application of these new technologies mentioned before. Recently, tremendous efforts have been made in mechanism understanding, electrocatalyst development and system design. Here, a comprehensive and critical review is provided to present the recent advances in the field of the electrocatalytic ORR. The two-electron and four-electron transfer catalytic mechanisms and key evaluation parameters of the ORR are discussed first. Then, the up-to-date synthetic strategies and in situ characterization techniques for ORR electrocatalysts are systematically summarized. Lastly, a brief overview of various renewable energy conversion devices and systems involving the ORR, including fuel cells, metal-air batteries, production of hydrogen peroxide and other chemical synthesis processes, along with some challenges and opportunities, is presented.

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.

Iterative Approach of Experiment-Machine Learning for Efficient Optimization of Environmental Catalysts: An Example of NOx Selective Reduction Catalysts

An iterative approach between machine learning (ML) and laboratory experiments was developed to accelerate the design and synthesis of environmental catalysts (ECs) using selective catalytic reduction (SCR) of nitrogen oxides (NOx) as an example. The main steps in the approach include training a ML model using the relevant data collected from the literature, screening candidate catalysts from the trained model, experimentally synthesizing and characterizing the candidates, updating the ML model by incorporating the new experimental results, and screening promising catalysts again with the updated model. This process is iterated with a goal to obtain an optimized catalyst. Using the iterative approach in this study, a novel SCR NOx catalyst with low cost, high activity, and a wide range of application temperatures was found and successfully synthesized after four iterations. The approach is general enough that it can be readily extended for screening and optimizing the design of other environmental catalysts and has strong implications for the discovery of other environmental materials.

Contracted Fe-N5-C11 Sites in Single-Atom Catalysts Boosting Catalytic Performance for Oxygen Reduction Reaction

Promoting the catalyst performance for oxygen reduction reaction (ORR) in energy conversion devices through controlled manipulation of the structure of catalytic active sites has been a major challenge. In this work, we prepared Fe-N-C single-atom catalysts (SACs) with Fe-N₅ active sites and found that the catalytic activity of the catalyst with shrinkable Fe-N₅-C₁₁ sites for ORR was significantly improved compared with the catalyst bearing normal Fe-N₅-C₁₂ sites. The catalyst C@PVI-(TPC)Fe-800, prepared by pyrolyzing an axial-imidazole-coordinated iron corrole precursor, exhibited positive shifted half-wave potential (E_1/2 = 0.89 V vs RHE) and higher peak power density (P_max = 129 mW/cm²) than the iron porphyrin-derived counterpart C@PVI-(TPP)Fe-800 (E_1/2 = 0.81 V, P_max = 110 mW/cm²) in 0.1 M KOH electrolyte and Zn-air batteries, respectively. X-ray absorption spectroscopy (XAS) analysis of C@PVI-(TPC)Fe-800 revealed a contracted Fe-N₅-C₁₁ structure with iron in a higher oxidation state than the porphyrin-derived Fe-N₅-C₁₂ counterpart. Density functional theory (DFT) calculations demonstrated that C@PVI-(TPC)Fe-800 possesses a higher HOMO energy level than C@PVI-(TPP)Fe-800, which can increase its electron-donating ability and thus help achieve enhanced O₂ adsorption as well as O-O bond activation. This work provides a new approach to tune the active site structure of SACs with unique contracted Fe-N₅-C₁₁ sites that remarkably promote the catalyst performance, suggesting significant implications for catalyst design in energy conversion devices.

Analysis of the oxygen evolution activity of layered double hydroxides (LDHs) using machine learning guidance

Layered double hydroxides (LDHs) are excellent catalysts for the oxygen evolution reaction (OER) because of their tunable properties, including chemical composition and structural morphology. An interplay between these adjustable properties and other (including external) factors might not always benefit the OER catalytic activity of LDHs. Therefore, we applied machine learning algorithms to simulate the double-layer capacitance to understand how to design/tune LDHs with targeted catalytic properties. The key factors of solving this task were identified using the Shapley Additive explanation and cerium was identified as an effective element to modify the double-layer capacitance. We also compared different modelling methods to identify the most promising one and the results revealed that binary representation is better than directly applying atom numbers as inputs for chemical compositions. Overpotentials of LDH-based materials as predicted targets were also carefully examined and evaluated, and it turns out that overpotentials can be predicted when measurement conditions about overpotentials are added as features. Finally, to confirm our findings, we reviewed additional experimental literature data and used them to test our machine algorithms to predict LDH properties. This analysis confirmed the very credible and robust generalization ability of our final model capable of achieving accurate results even with a relatively small dataset.

Generalized Encapsulations of ZIF-Based Fe-N-C Catalysts with Controllable Nitrogen-Doped Carbon for Significantly-Improved Stability Toward Oxygen Reduction Reaction

The vigorous development of efficient platinum group metal-free catalysts is considerably important to facilitate the universal application of proton exchange membrane fuel cells. Although nitrogen-coordinated atomic iron intercalated in carbon matrix (Fe-N-C) catalysts exhibit promising catalytic activity, the performance in fuel cells, especially the short lifetime, remains an obstacle. Herein, a highly-active Fe-N-C catalyst with a power density of >1 w cm^-2 and prolonged discharge stability with a current density of 357 mA cm^-2 after 40 h of constant voltage discharge at 0.7 V in H₂ -O₂ fuel cells using a controllable and efficient N-C coating strategy is developed. It is clarified that a thicker N-C coating may be more favorable to enhance the stability of Fe-N-C catalysts at the expense of their catalytic activity. The stability enhancement mechanism of the N-C coating strategy is proven to be the synergistic effect of reduced carbon corrosion and iron loss. It is believed that these findings can contribute to the development of Fe-N-C catalysts with high activity and long lifetimes.

Advances in Low Pt Loading Membrane Electrode Assembly for Proton Exchange Membrane Fuel Cells

Hydrogen has the potential to be one of the solutions that can address environmental pollution and greenhouse emissions from traditional fossil fuels. However, high costs hinder its large-scale commercialization, particularly for enabling devices such as proton exchange membrane fuel cells (PEMFCs). The precious metal Pt is indispensable in boosting the oxygen reduction reaction (ORR) in cathode electrocatalysts from the most crucial component, i.e., the membrane electrode assembly (MEA). MEAs account for a considerable amount of the entire cost of PEMFCs. To address these bottlenecks, researchers either increase Pt utilization efficiency or produce MEAs with enhanced performance but less Pt. Only a few reviews that explain the approaches are available. This review summarizes advances in designing nanocatalysts and optimizing the catalyst layer structure to achieve low-Pt loading MEAs. Different strategies and their corresponding effectiveness, e.g., performance in half-cells or MEA, are summarized and compared. Finally, future directions are discussed and proposed, aiming at affordable, highly active, and durable PEMFCs.

Data-driven capacity estimation of commercial lithium-ion batteries from voltage relaxation

Accurate capacity estimation is crucial for the reliable and safe operation of lithium-ion batteries. In particular, exploiting the relaxation voltage curve features could enable battery capacity estimation without additional cycling information. Here, we report the study of three datasets comprising 130 commercial lithium-ion cells cycled under various conditions to evaluate the capacity estimation approach. One dataset is collected for model building from batteries with LiNi_0.86Co_0.11Al_0.03O₂-based positive electrodes. The other two datasets, used for validation, are obtained from batteries with LiNi_0.83Co_0.11Mn_0.07O₂-based positive electrodes and batteries with the blend of Li(NiCoMn)O₂ - Li(NiCoAl)O₂ positive electrodes. Base models that use machine learning methods are employed to estimate the battery capacity using features derived from the relaxation voltage profiles. The best model achieves a root-mean-square error of 1.1% for the dataset used for the model building. A transfer learning model is then developed by adding a featured linear transformation to the base model. This extended model achieves a root-mean-square error of less than 1.7% on the datasets used for the model validation, indicating the successful applicability of the capacity estimation approach utilizing cell voltage relaxation.

Accurate capacity estimation is crucial for lithium-ion batteries' reliable and safe operation. Here, the authors propose an approach exploiting features from the relaxation voltage curve for battery capacity estimation without requiring other previous cycling information.

Accelerated Hydrogen "Spill-Over" Enhances Anode Performance of Tensile Strained Pd-Based Fuel Cell Electrocatalysts

Development of efficient electrocatalysts usually relies on half-cell electrochemical tests for rapid material screening, which however are not always consistent with the associated full cell evaluation. This study designs a tensile-strained Pd anode and reveals that with a lower apparent activity toward the hydrogen oxidation reaction as compared to the unstrained one, it exhibits a surprisingly high activity in proton exchange membrane fuel cells (PEMFCs). With an ultralow Pd loading of 4.5 µg cm^-2 , the tensile-strained Pd achieves a maximum power density of 1048 mW cm^-2 , indicating a 30-fold improvement in power efficiency than that of commercial Pd/C, nearly four times of that of the unstrained one. This discrepancy can be ascribed to the hydrogen-rich surface in the H₂ atmosphere of PEMFCs owing to the accelerated hydrogen "spill-over" in the tensile-strained Pd with a standout hydrogen storage property.

Effectively Increasing Pt Utilization Efficiency of the Membrane Electrode Assembly in Proton Exchange Membrane Fuel Cells through Multiparameter Optimization Guided by Machine Learning

Although proton exchange membrane fuel cells have received attention, the high costs associated with Pt-based catalysts in membrane electrode assemblies (MEAs) remain a huge obstacle for large-scale applications. To solve this urgent problem, the utilization efficiency of Pt in MEAs must be increased. Facing numerous interacting parameters in an attempt to keep experimental costs as low as possible, we innovatively introduce machine learning (ML) to achieve this goal. Nine different ML algorithms are trained on the experimental dataset from our laboratory to precisely predict the performance and Pt utilization (maximum R² = 0.973/0.968). To determine the best synthesis conditions, black-box interpretation methods are applied to provide reliable insights from both qualitative and quantitative perspectives. The optimized choices of ionomer/catalyst ratio, water content, organic solvent, catalyst loading, stirring method, solid content, and ultrasonic spraying flow rate are properly made with few experimental attempts under ML results' guidance. Promising Pt utilization of 0.147 gPt kW^-1 and a power density of 1.02 W cm^-2 are achieved at 0.6 V in a single cell (H₂/air) at an ultralow total loading of 0.15 mg Pt cm^-2. Therefore, this work contributes to the economy of hydrogen energy by paving the way for MEA optimization with complex parameters by ML.

Exploration of the Polarization Curve for Proton-Exchange Membrane Fuel Cells

The polarization curve is the most important profile to evaluate the performance of proton-exchange membrane fuel cells (PEMFCs). To explore the important thermodynamic parameters and their correlation with the composition, fabrication, and operational settings, a comprehensive data set consisting of 446 polarization curves from 191 perfluorosulfonate and 255 sulfonated hydrocarbon-based PEMs is collected. Then, a Markov chain Monte Carlo simulation within the Bayesian frame provides higher than 93% confidence to extract six important thermodynamic parameters including open-circuit potential, the transfer coefficient, the current loss, the reference exchange current density, the internal resistance, and the limiting current density. An extreme gradient boosting algorithm affords a mean determinative coefficient of 0.89 to predict the whole polarization curve and a confidence of 94% to predict the peak power density (PPD). Both approaches to explore the polarization curve for PEMFCs show good robustness in the blind test. Overall, the PPD is positively correlated with the ion-exchange capacity of the polymer, operational temperature, and humidity and is negatively affected by internal resistance, membrane thickness, and the loading of the catalyst. The flow rate of fuels can effectively enhance them, while the increase of catalyst loading or fuel concentration shows deleterious impacts.

DeepReac+: deep active learning for quantitative modeling of organic chemical reactions

Various computational methods have been developed for quantitative modeling of organic chemical reactions; however, the lack of universality as well as the requirement of large amounts of experimental data limit their broad applications. Here, we present DeepReac+, an efficient and universal computational framework for prediction of chemical reaction outcomes and identification of optimal reaction conditions based on deep active learning. Under this framework, DeepReac is designed as a graph-neural-network-based model, which directly takes 2D molecular structures as inputs and automatically adapts to different prediction tasks. In addition, carefully-designed active learning strategies are incorporated to substantially reduce the number of necessary experiments for model training. We demonstrate the universality and high efficiency of DeepReac+ by achieving the state-of-the-art results with a minimum of labeled data on three diverse chemical reaction datasets in several scenarios. Collectively, DeepReac+ has great potential and utility in the development of AI-aided chemical synthesis. DeepReac+ is freely accessible at https://github.com/bm2-lab/DeepReac.

Oxygen Reduction Electrocatalysts toward Practical Fuel Cells: Progress and Perspectives

Fuel cells are an incredibly powerful renewable energy technology, but their broad applications remains lagging because of the high cost and poor reliability of cathodic electrocatalysts for the oxygen reduction reaction (ORR). This review focuses on the recent progress of ORR electrocatalysts in fuel cells. More importantly, it highlights the fundamental problems associated with the insufficient activity translation from rotating disk electrode to membrane electrode assembly in the fuel cells. Finally, for the atomic-level in-depth information on ORR catalysts in fuel cells, potential perspectives are suggested, including large-scale preparation, unified assessment criteria, advanced interpretation techniques, advanced simulation and artificial intelligence. This review aims to provide valuable insights into the fundamental science and technical engineering for efficient ORR electrocatalysts in fuel cells.

Advanced Platinum-Based Oxygen Reduction Electrocatalysts for Fuel Cells

ConspectusFuel cells are among the cutting-edge energy technologies. Their commercial development is still hindered by noble platinum (Pt) catalysts for the oxygen reduction reaction (ORR) at the cathode, which not only determine the energy conversion efficiency and service life but also are closely related to the cost and broad application of fuel cells. Given the bright and enormous future of fuel cells, ORR catalysts should possess highly efficient performance yet meet the acceptable Pt costs for large-scale application. Extensive efforts are concentrated on the optimization of Pt-based nanostructures and upgradation of functional carriers to achieve the low-cost and high-activity Pt-based catalysts. By improving the Pt utilization and accessible surface, reducing Pt consumption and catalyst costs, accelerating mass exchange and electron transfer, alleviating the corrosion and agglomeration of carriers and Pt, accompanying with the assistance of robust yet effective functional supports, the service level and life of Pt-based electrocatalysts would be significantly improved and fuel cells could get into commercial market covering broader applications.In this Account, we focus on the recent development of Pt-based catalysts to figure out the problems associated with ORR catalysts in fuel cells. Recent development of Pt-based catalysts is discussed in different stages: (1) multiscale development of Pt-based nanostructures; (2) multielement regulation over Pt-based alloy composition; (3) upgradation of carbon and noncarbon support architectures; (4) development of integrated Pt-based catalysts for fuel cells. Finally, we propose some future issues (such as reaction mechanism, dynamic evolutions, and structure-activity relationship) for Pt-based catalysts, which mainly involve the preparation strategy of Pt-integrated catalysts (combination of Pt nanostructures with nanocarbons), performance evaluation (standard measurement protocols, laboratory-level rotating disk electrode (RDE) measurements, application-level membrane electrode assembly (MEA) service test), advanced interpretation techniques (spectroscopy, electron microscopy, and in situ monitoring), and cutting-edge simulation/calculations and artificial intelligence (simulation, calculations, machine learning, big data screening). This Account calls for the comprehensive development of multiscale, multicomponent, and high-entropy Pt-based alloy nanostructures, and novel and stable carriers, which provide more available options for rational design of low-cost and high-performance Pt-integrated ORR catalysts. More importantly, it will give an in-depth understanding of the reaction mechanism, dynamic development, and structure-performance relationship for Pt-based catalysts in fuel cells and related energy technologies.

Defect Electrocatalysts and Alkaline Electrolyte Membranes in Solid-State Zinc-Air Batteries: Recent Advances, Challenges, and Future Perspectives

Rechargeable zinc-air batteries (ZABs) have attracted much attention due to their promising capability for offering high energy density while maintaining a long operational lifetime. One of the biggest challenges in developing all-solid-state ZABs is to design suitable bifunctional air-electrodes, which can efficiently catalyze the key oxygen reduction reaction (ORR)/oxygen evolution reaction (OER) electrochemical processes. The other one is to develop robust electrolyte membranes with high ionic conductivity and superb water retention capability. In this review, an in-depth discussion of the challenges, mechanisms, and design strategies for the defect electrocatalyst and the electrolyte membrane in all-solid-state ZABs will be offered. In particular, the crucial defect engineering strategies to tune the ORR/OER catalysts are summarized, including direct controllable strategies: 1) atomically dispersed metal sites control, 2) vacancy defects control, and 3) lattice-strain control, and the indirect strategies: 4) crystallographic structure control and 5) metal-carbon support interaction control. Moreover, the most recent progress in designing electrolyte membranes, including polyvinyl alcohol-based membranes and gel polymer electrolyte membranes, is presented. Finally, the perspectives are proposed for rational design and fabrication of the desired air electrode and electrolyte membrane to improve the performance and prolong the lifetime of all-solid-state ZABs.