Machine Learning-Assisted Low-Dimensional Electrocatalysts Design for Hydrogen Evolution Reaction

Nano-Micro Letters, Год журнала: 2023, Номер 15(1)

Опубликована: Окт. 13, 2023

Abstract Efficient electrocatalysts are crucial for hydrogen generation from electrolyzing water. Nevertheless, the conventional "trial and error" method producing advanced is not only cost-ineffective but also time-consuming labor-intensive. Fortunately, advancement of machine learning brings new opportunities discovery design. By analyzing experimental theoretical data, can effectively predict their evolution reaction (HER) performance. This review summarizes recent developments in low-dimensional electrocatalysts, including zero-dimension nanoparticles nanoclusters, one-dimensional nanotubes nanowires, two-dimensional nanosheets, as well other electrocatalysts. In particular, effects descriptors algorithms on screening investigating HER performance highlighted. Finally, future directions perspectives electrocatalysis discussed, emphasizing potential to accelerate electrocatalyst discovery, optimize performance, provide insights into electrocatalytic mechanisms. Overall, this work offers an in-depth understanding current state its research.

Язык: Английский

---

Machine learning-guided property prediction of energetic materials: Recent advances, challenges, and perspectives

Energetic Materials Frontiers, Год журнала: 2022, Номер 3(3), С. 177 - 186

Опубликована: Авг. 18, 2022

Predicting chemical properties is one of the most important applications machine learning. In recent years, prediction energetic materials using learning has been receiving more attention. This review summarized advances in predicting compounds' (e.g., density, detonation velocity, enthalpy formation, sensitivity, heat explosion, and decomposition temperature) Moreover, it presented general steps for applying to practical from aspects data, molecular representation, algorithms, accuracy. Additionally, raised some controversies specific its possible development directions. Machine expected become a new power driving soon.

Язык: Английский

---

Estimation and Prediction of the Polymers’ Physical Characteristics Using the Machine Learning Models

Polymers, Год журнала: 2023, Номер 16(1), С. 115 - 115

Опубликована: Дек. 29, 2023

This article investigates the utility of machine learning (ML) methods for predicting and analyzing diverse physical characteristics polymers. Leveraging a rich dataset polymers' characteristics, study encompasses an extensive range polymer properties, spanning compressive tensile strength to thermal electrical behaviors. Using various regression like Ensemble, Tree-based, Regularization, Distance-based, research undergoes thorough evaluation using most common quality metrics. As result series experimental studies on selection effective model parameters, those that provide high-quality solution stated problem were found. The best results achieved by Random Forest with highest R2 scores 0.71, 0.73, 0.88 glass transition, decomposition, melting temperatures, respectively. outcomes are intricately compared, providing valuable insights into efficiency distinct ML approaches in properties. Unknown values each characteristic predicted, method validation was performed training predicted values, comparing specified variance characteristic. not only advances our comprehension physics but also contributes informed optimization materials science applications.

Язык: Английский

---

Quantitative Prediction of Inorganic Nanomaterial Cellular Toxicity via Machine Learning

Small, Год журнала: 2023, Номер 19(19)

Опубликована: Фев. 11, 2023

Organic chemistry has seen colossal progress due to machine learning (ML). However, the translation of artificial intelligence (AI) into materials science is challenging, where biological behavior prediction becomes even more complicated. Nanotoxicity a critical parameter that describes their interaction with living organisms screened in every bio-related research. To prevent excessive experiments, such properties have be pre-evaluated. Several existing ML models partially fulfill gap by predicting whether nanomaterial toxic or not. Yet, this binary categorization neglects concentration dependencies crucial for experimental scientists. Here, an ML-based approach proposed quantitative inorganic cytotoxicity achieving precision expressed 10-fold cross-validation (CV) Q2 = 0.86 root mean squared error (RMSE) 12.2% obtained correlation-based feature selection and grid search-based model hyperparameters optimization. provide further flexibility, atom property-based descriptors are introduced allowing extrapolate on unseen samples. Feature importance calculated find interpretable optimal decision-making. These findings allow scientists perform primary silico candidate screening minimize number excessive, labor-intensive experiments enabling rapid development nanomaterials medicinal purposes.

Язык: Английский

---

Representing Polymers as Periodic Graphs with Learned Descriptors for Accurate Polymer Property Predictions

Journal of Chemical Information and Modeling, Год журнала: 2022, Номер 62(22), С. 5435 - 5445

Опубликована: Окт. 31, 2022

Accurately predicting new polymers' properties with machine learning models apriori to synthesis has potential significantly accelerate discovery and development. However, accurately efficiently capturing complex, periodic structures in remains a grand challenge for the polymer cheminformatics community. Specifically, there yet be an ideal solution problems of how capture periodicity polymers, as well optimally develop descriptors without requiring human-based feature design. In this work, we tackle these by utilizing graph representation that accounts coupling it message-passing neural network leverages power deep automatically learn chemically relevant descriptors. Remarkably, approach achieves state-of-the-art performance on 8 out 10 distinct property prediction tasks. These results highlight advancement predictive capability is possible through are specifically optimized unique chemical structure polymers.

Язык: Английский

---

A Strategic Approach to Machine Learning for Material Science: How to Tackle Real-World Challenges and Avoid Pitfalls

Chemistry of Materials, Год журнала: 2022, Номер 34(17), С. 7650 - 7665

Опубликована: Сен. 1, 2022

The exponential growth and success of machine learning (ML) has resulted in its application all scientific domains including material science. Advancement experimental techniques led to an increase the volume science data encouraging scientists investigate data-driven solutions problems. While resources available get started with ML are ever increasing, there is little literature on traversing through space decisions that need be made implement a robust trustworthy solution. A lack such leads researchers wading articles papers trying determine best approach for their problem sometimes also falling prey pitfalls real-world scenario. This paper aims act as guide who want strategically solution use domain knowledge systematic evaluation major aspects pipeline. We focus four pipeline: (1) formulation, (2) curation, (3) feature representation model selection, (4) generalizability performance. In each case, we discuss decisions, provide examples from literature, illustrate how different choices can affect outcome case study predicting compressive strength uniaxially pressed molecular solid, 2,4,6-triamino-1,3,5-trinitrobenzene (TATB) samples. Using similar critical thinking along rigorous diagnostics, assured reliability predictions models.

Язык: Английский

---

Building Chemical Property Models for Energetic Materials from Small Datasets Using a Transfer Learning Approach

Journal of Chemical Information and Modeling, Год журнала: 2022, Номер 62(22), С. 5397 - 5410

Опубликована: Окт. 14, 2022

For many experimentally measured chemical properties that cannot be directly computed from first-principles, the existing physics-based models do not extrapolate well to out-of-sample molecules, and experimental datasets themselves are too small for traditional machine learning (ML) approaches. To overcome these limitations, we apply a transfer approach, whereby simultaneously train multi-target regression model on number of molecules with values large related properties. We demonstrate this methodology predicting impact sensitivity energetic crystals, finding both characteristics dataset architecture important prediction accuracy dataset. Our directed-message passing neural network (D-MPNN) ML using outperforms direct-ML diverse test set, new methods described here widely applicable modeling other structure–property relationships.

Язык: Английский

---

High-throughput design of energetic molecules

Journal of Materials Chemistry A, Год журнала: 2023, Номер 11(45), С. 25031 - 25044

Опубликована: Янв. 1, 2023

High-throughput design of energetic molecules implemented by molecular docking, AI-aided design, an automated computation workflow, a structure−property database, deep learning QSPRs and easy-to-use platform.

Язык: Английский

---

Predicting the enthalpy of formation of energetic molecules via conventional machine learning and GNN

Physical Chemistry Chemical Physics, Год журнала: 2024, Номер 26(8), С. 7029 - 7041

Опубликована: Янв. 1, 2024

Different ML models are used to map the enthalpy of formation from molecular structure, and impact different feature representation methods on results is explored. Among them, GNN achieve impressive results.

Язык: Английский

---

Advancements in methodologies and techniques for the synthesis of energetic materials: A review

Energetic Materials Frontiers, Год журнала: 2024, Номер unknown

Опубликована: Июнь 1, 2024

Recent years have witnessed significant advancements in methodologies and techniques for the synthesis of energetic materials, which are expected to shape future manufacturing applications. Techniques including continuous flow chemistry, electrochemical synthesis, microwave-assisted biosynthesis been extensively employed pharmaceutical fine chemical industries and, gratifyingly, found broader This review comprehensively introduces recent utilization these emerging techniques, aiming provide a catalyst development novel green methods synthesizing materials.

Язык: Английский

---