Machine learning for molecular thermodynamics

Ding, Jiaqi; Xu, Nan; Nguyen, Manh Tien; Qiao, Qi; Shi, Yao; He, Yi; Shao, Qing

doi:10.1016/j.cjche.2020.10.044

Cited by 25 publications

(17 citation statements)

References 141 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discoveries of models can be the regression models from measured or simulated data, structure−function relationships, or even conceptual mechanistic models. A typical workflow example of ML-enabled model discovery (see Figure 3b (7) model used for prediction, regression, classification, control, and optimization, to name a few. 7 Although it is necessary to invest some computational cost in the process of model discovery, the ML method can give fast prediction and classification of the properties of the crucial target with relatively low computational expense once the model is constructed.…”

Section: Introduction and Fundamentals Of Machine Learningmentioning

confidence: 99%

“…A typical workflow example of ML-enabled model discovery (see Figure 3b (7) model used for prediction, regression, classification, control, and optimization, to name a few. 7 Although it is necessary to invest some computational cost in the process of model discovery, the ML method can give fast prediction and classification of the properties of the crucial target with relatively low computational expense once the model is constructed. Usually, three independent data sets, which can be built by randomly splitting the original data set, should be prepared for separate training, validation, and testing of ML models.…”

Section: Introduction and Fundamentals Of Machine Learningmentioning

confidence: 99%

“…In recent years, due to the feasibility and flexibility of tools for ML implementation and workflow management, the explosion of new sources of data, and the rapid advancement of algorithms and powerful supercomputer resources, ML is experiencing an immensely fascinating resurgence in numerous scientific and engineering disciplines, such as chemical engineering, , chemistry, , catalysis science, − material science, , and fluid mechanics. ,, This rapidly developing trend is also accompanied by recent advances of ML, especially DL, which greatly contribute to this new era. In this new era of AI-enabled paradigm, discovery and innovation no longer solely rely on human effort and domain expertise but are also significantly supplemented by analytics and mining of knowledge hidden in the data, and the visualization of information. , …”

Section: Introduction and Fundamentals Of Machine Learningmentioning

confidence: 99%

“…Discoveries of models can be the regression models from measured or simulated data, structure–function relationships, or even conceptual mechanistic models. A typical workflow example of ML-enabled model discovery (see Figure b) may include (1) implementation of (high-throughput) experiments/simulations or collection of data from the literature or open database; (2) construction of database; (3) selection of descriptors; (4) determination of algorithm; (5) model training and validation, including feature selection and reduction; (6) model testing; (7) model used for prediction, regression, classification, control, and optimization, to name a few …”

Section: Introduction and Fundamentals Of Machine Learningmentioning

confidence: 99%

See 3 more Smart Citations

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Zhu

Chen

Ouyang

et al. 2022

Ind. Eng. Chem. Res.

118

View full text Add to dashboard Cite

Artificial intelligence (AI), machine learning (ML), and data science are leading to a promising transformative paradigm. ML, especially deep learning and physics-informed ML, is a valuable toolkit that complements incomplete domain-specific knowledge in conventional experimental and computational methods. ML can provide flexible techniques to facilitate the conceptual development of new robust predictive models for multiphase flows and reactors by finding hidden pattern/information/mechanism in a data set. Due to such emergence, we thereby comprehensively survey, explore, analyze, and discuss key advancements of recent ML applications to hydrodynamics, heat and mass transfer, and reactions in single-phase and multiphase flow systems from different aspects: (1) development of multiphase closure models of drag force, turbulence stresses and heat/mass transfer to improve the accuracy and efficiency of typical CFD simulations; (2) image reconstruction, regime identification, key parameter predictions, and optimization of multiphase flow and transport fields; (3) reaction kinetics modeling (e.g., predictions of reaction networks, kinetic parameters, and species production) and reaction condition optimization. These sections also discuss and analyze the key advantages and weakness of ML for solving the problems in the domain of multiphase flows and reactors. Finally, we summarize the under-solving challenges and opportunities in order to identify future directions that would be useful for the research community. Future development and study of multiphase flows and reactors are envisaged to be accelerated by ML and data science.

show abstract

Section: Introduction and Fundamentals Of Machine Learningmentioning

confidence: 99%

Section: Introduction and Fundamentals Of Machine Learningmentioning

confidence: 99%

Section: Introduction and Fundamentals Of Machine Learningmentioning

confidence: 99%

Section: Introduction and Fundamentals Of Machine Learningmentioning

confidence: 99%

See 2 more Smart Citations

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Zhu

Chen

Ouyang

et al. 2022

Ind. Eng. Chem. Res.

118

View full text Add to dashboard Cite

show abstract

“…With the development of science and technology, artificial intelligence has gradually emerged. The part of machine learning is gradually applied to material design due to its small error, high efficiency, a large amount of processing information, and so on. − In the field of perovskite materials, Vishnoi et al predicted the possible existence of more than 300 hitherto unknown double perovskite iodides with organic and inorganic cations in the A site . Gladkikh et al used machine learning methods to predict the band gap of ABX 3 perovskite from element characteristics .…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Accelerates the Discovery of Light-Absorbing Materials for Double Perovskite Solar Cells

et al. 2021

View full text Add to dashboard Cite

Double perovskite materials have excellent electronic and optical properties, which are the star material in the photovoltaic field. However, the large number of family members has brought difficulties to traditional material screening methods. The emergence of machine learning provides new ideas for this problem, and how to apply machine learning to search new functional materials has become a hot research topic. This paper combines machine learning and density functional theory (DFT) calculations to develop a goal-driven method to search for functional materials, aiming to select one that has suitable photoelectric properties and thermal stability from tens of thousands of double perovskite materials. Through a series of processes such as training excellent machine learning models, multicondition combination screening, and DFT calculations, 10 excellent double perovskite materials were finally selected from 16,400 candidate materials to guide subsequent experimental synthesis. Combining the high efficiency of machine learning and the accuracy of DFT calculations compensates for their respective shortcomings and improves the efficiency of finding new materials. In addition, this method also has a certain general applicability and can be extended to the screening of other materials.

show abstract

Protein and Peptide‐Based Nanotechnology for Enhancing Stability, Bioactivity, and Delivery of Anthocyanins

Zhang

Yao

Zhao

et al. 2023

Adv Healthcare Materials

View full text Add to dashboard Cite

Anthocyanin, a unique natural polyphenol, is abundant in plants and widely utilized in biomedicine, cosmetics, and the food industry due to its excellent antioxidant, anticancer, antiaging, antimicrobial, and anti‐inflammatory properties. However, the degradation of anthocyanin in an extreme environment, such as alkali pH, high temperatures, and metal ions, limits its physiochemical stabilities and bioavailabilities. Encapsulation and combining anthocyanin with biomaterials could efficiently stabilize anthocyanin for protection. Promisingly, natural or artificially designed proteins and peptides with favorable stabilities, excellent biocapacity, and wide sources are potential candidates to stabilize anthocyanin. This review focuses on recent progress, strategies, and perspectives on protein and peptide for anthocyanin functionalization and delivery, i.e., formulation technologies, physicochemical stability enhancement, cellular uptake, bioavailabilities, and biological activities development. Interestingly, due to the simplicity and diversity of peptide structure, the interaction mechanisms between peptide and anthocyanin could be illustrated. This work sheds light on the mechanism of protein/peptide–anthocyanin nanoparticle construction and expands on potential applications of anthocyanin in nutrition and biomedicine.

show abstract

Machine learning for molecular thermodynamics

Cited by 25 publications

References 141 publications

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Review of Machine Learning for Hydrodynamics, Transport, and Reactions in Multiphase Flows and Reactors

Machine Learning Accelerates the Discovery of Light-Absorbing Materials for Double Perovskite Solar Cells

Protein and Peptide‐Based Nanotechnology for Enhancing Stability, Bioactivity, and Delivery of Anthocyanins

Contact Info

Product

Resources

About