查看更多>>摘要：Heterogeneous catalysis remains at the core of various bulk chemical manufacturing and energy conver-sion processes,and its revolution necessitates the hunt for new materials with ideal catalytic activities and economic feasibility.Computational high-throughput screening presents a viable solution to this challenge,as machine learning(ML)has demonstrated its great potential in accelerating such processes by providing satisfactory estimations of surface reactivity with relatively low-cost information.This review focuses on recent progress in applying ML in adsorption energy prediction,which predominantly quantifies the catalytic potential of a solid catalyst.ML models that leverage inputs from different cate-gories and exhibit various levels of complexity are classified and discussed.At the end of the review,an outlook on the current challenges and future opportunities of ML-assisted catalyst screening is supplied.We believe that this review summarizes major achievements in accelerating catalyst discovery through ML and can inspire researchers to further devise novel strategies to accelerate materials design and,ulti-mately,reshape the chemical industry and energy landscape.
查看更多>>摘要：The issue of opacity within data-driven artificial intelligence(AI)algorithms has become an impediment to these algorithms'extensive utilization,especially within sensitive domains concerning health,safety,and high profitability,such as chemical engineering(CE).In order to promote reliable AI utilization in CE,this review discusses the concept of transparency within AI utilizations,which is defined based on both explainable AI(XAI)concepts and key features from within the CE field.This review also highlights the requirements of reliable AI from the aspects of causality(i.e.,the correlations between the predictions and inputs of an AI),explainability(i.e.,the operational rationales of the workflows),and informativeness(i.e.,the mechanistic insights of the investigating systems).Related techniques are evaluated together with state-of-the-art applications to highlight the significance of establishing reliable AI applications in CE.Furthermore,a comprehensive transparency analysis case study is provided as an example to enhance understanding.Overall,this work provides a thorough discussion of this subject matter in a way that-for the first time-is particularly geared toward chemical engineers in order to raise awareness of responsible AI utilization.With this vital missing link,AI is anticipated to serve as a novel and powerful tool that can tremendously aid chemical engineers in solving bottleneck challenges in CE.
查看更多>>摘要：Information on the physicochemical properties of chemical species is an important prerequisite when performing tasks such as process design and product design.However,the lack of extensive data and high experimental costs hinder the development of prediction techniques for these properties.Moreover,accuracy and predictive capabilities still limit the scope and applicability of most property estimation methods.This paper proposes a new Gaussian process-based modeling framework that aims to manage a discrete and high-dimensional input space related to molecular structure representation with the group-contribution approach.A warping function is used to map discrete input into a continuous domain in order to adjust the correlation between different compounds.Prior selection techniques,including prior elicitation and prior predictive checking,are also applied during the building procedure to provide the model with more information from previous research findings.The framework is assessed using data-sets of varying sizes for 20 pure component properties.For 18 out of the 20 pure component properties,the new models are found to give improved accuracy and predictive power in comparison with other published models,with and without machine learning.
查看更多>>摘要：Non-ionic deep eutectic solvents(DESs)are non-ionic designer solvents with various applications in catalysis,extraction,carbon capture,and pharmaceuticals.However,discovering new DES candidates is challenging due to a lack of efficient tools that accurately predict DES formation.The search for DES relies heavily on intuition or trial-and-error processes,leading to low success rates or missed opportuni-ties.Recognizing that hydrogen bonds(HBs)play a central role in DES formation,we aim to identify HB features that distinguish DES from non-DES systems and use them to develop machine learning(ML)models to discover new DES systems.We first analyze the HB properties of 38 known DES and 111 known non-DES systems using their molecular dynamics(MD)simulation trajectories.The analysis reveals that DES systems have two unique features compared to non-DES systems:The DESs have ① more imbalance between the numbers of the two intra-component HBs and ② more and stronger inter-component HBs.Based on these results,we develop 30 ML models using ten algorithms and three types of HB-based descriptors.The model performance is first benchmarked using the average and minimal receiver oper-ating characteristic(ROC)-area under the curve(AUC)values.We also analyze the importance of individ-ual features in the models,and the results are consistent with the simulation-based statistical analysis.Finally,we validate the models using the experimental data of 34 systems.The extra trees forest model outperforms the other models in the validation,with an ROC-AUC of 0.88.Our work illustrates the impor-tance of HBs in DES formation and shows the potential of ML in discovering new DESs.
万方数据
维普