The promise of artificial intelligence in chemical engineering: Is it here, finally?

Venkatasubramanian, Venkat

doi:10.1002/aic.16489

Cited by 472 publications

(298 citation statements)

References 95 publications

Supporting

Mentioning

298

Contrasting

Order By: Relevance

“…in the interpretation of spectroscopic data [27] and for general pattern detection [28]. Mitchell recently reviewed a wide range of ML techniques that have been applied to different problems in cheminformatics and drug discovery covering the last 30 years [29], and Venkatasubramanian reviewed machine learning applications in chemical engineering [30]. Early applications of ANNs as replacement for conventional interatomic potentials have been reported already in the 1990s.…”

Section: Progress In Machine Learning Methods For Materials Simulationsmentioning

confidence: 99%

Machine learning for the modeling of interfaces in energy storage and conversion materials

Artrith

2019

J. Phys. Energy

View full text Add to dashboard Cite

The properties and atomic-scale dynamics of interfaces play an important role for the performance of energy storage and conversion devices such as batteries and fuel cells. In this topical review, we consider recent progress in machine-learning (ML) approaches for the computational modeling of materials interfaces. ML models are computationally much more efficient than first principles methods and thus allow to model larger systems and extended timescales, a necessary prerequisites for the accurate description of many interface properties. Here we review the recent major developments of ML-based interatomic potentials for atomistic modeling and ML approaches for the direct prediction of materials properties. This is followed by a discussion of ML applications to solid-gas, solid-liquid, and solid-solid interfaces as well as to nanostructured and amorphous phases that commonly form in interface regions. We then highlight how ML has been used to obtain important insights into the structure and stability of interfaces, interfacial reactions, and mass transport at interfaces. Finally, we offer a perspective on the current state of ML potential development and identify future directions and opportunities for this exciting research field.

show abstract

Section: Progress In Machine Learning Methods For Materials Simulationsmentioning

confidence: 99%

Machine learning for the modeling of interfaces in energy storage and conversion materials

Artrith

2019

J. Phys. Energy

View full text Add to dashboard Cite

show abstract

“…A summary of commonly used ML tools and algorithms for materials design and discovery applications is provided by Liu et al [354] Meanwhile, unsupervised learning looks for similarities among entities in input data to cluster them into various groups of similar features, or identifies trends and patterns in the data. [355] To name a few tools, principal component analysis (PCA) [356] and t-distributed stochastic neighbor embedding (t-SNE) [357] have reportedly been employed for separation of catalysts based on product types [345] and active site motif analysis. [347] Once models are developed the performance is evaluated by application to unseen data.…”

Section: Mechanics Of Machine Learningmentioning

confidence: 99%

A Disquisition on the Active Sites of Heterogeneous Catalysts for Electrochemical Reduction of CO₂ to Value‐Added Chemicals and Fuel

Daiyan

Saputera

Masood

et al. 2020

Advanced Energy Materials

135

104

View full text Add to dashboard Cite

Renewable‐electricity‐powered electrocatalytic CO2 reduction reactions (CO2RR) have been identified as an emerging technology to address the issue of rising CO2 emissions in the atmosphere. While the CO2RR has been demonstrated to be technically feasible, further improvements in catalyst performance through active sites engineering are a prerequisite to accelerate its commercial feasibility for utilization in large CO2‐emitting industrial sources. Over the years, the improved understanding of the interaction of CO2 with the active sites has allowed superior catalyst design and subsequent attainment of prominent CO2RR activity in literature. This review tracks the evolution of the understanding of CO2RR active sites on different electrocatalysts such as metals, metal‐oxides, single atoms, metal‐carbon, and subsequently metal‐free carbon‐based catalysts. Despite the tremendous research efforts in the field, many scientific questions on the role of various active sites in governing CO2RR activity, selectivity, stability, and pathways are still unanswered. These gaps in knowledge are highlighted and a discussion is set forth on the merits of utilizing advanced in‐situ and operando characterization techniques and machine learning (ML). Using this technique, the underlying mechanisms can be discerned, and as a result new strategies for designing active sites may be uncovered. Finally, this review advocates an interdisciplinary approach to discover and design CO2RR active sites (rather than focusing merely on catalyst activity) in a bid to stimulate practical research for industrial application.

show abstract

“…In recent years, deep learning has a wide array of applications in the PSE domain, such as process monitoring [193,194], refinery scheduling [195], and soft sensor [196]. For extensive surveys on deep learning in the PSE area, we refer the reader to the review papers on this subject [14,197]. In real applications, uncertainty data exhibit very complex and highly nonlinear characteristic.…”

Section: Leveraging Deep Learning Techniques For Hedging Against Uncementioning

confidence: 99%

Optimization under uncertainty in the era of big data and deep learning: When machine learning meets mathematical programming

Ning

You

2019

Computers & Chemical Engineering

261

View full text Add to dashboard Cite

This paper reviews recent advances in the field of optimization under uncertainty via a modern data lens, highlights key research challenges and promise of data-driven optimization that organically integrates machine learning and mathematical programming for decision-making under uncertainty, and identifies potential research opportunities. A brief review of classical mathematical programming techniques for hedging against uncertainty is first presented, along with their wide spectrum of applications in Process Systems Engineering. A comprehensive review and classification of the relevant publications on data-driven distributionally robust optimization, data-driven chance constrained program, data-driven robust optimization, and data-driven scenario-based optimization is then presented. This paper also identifies fertile avenues for future research that focuses on a closed-loop data-driven optimization framework, which allows the feedback from mathematical programming to machine learning, as well as scenario-based optimization leveraging the power of deep learning techniques. Perspectives on online learningbased data-driven multistage optimization with a learning-while-optimizing scheme is presented.

show abstract

The promise of artificial intelligence in chemical engineering: Is it here, finally?

Cited by 472 publications

References 95 publications

Machine learning for the modeling of interfaces in energy storage and conversion materials

Machine learning for the modeling of interfaces in energy storage and conversion materials

A Disquisition on the Active Sites of Heterogeneous Catalysts for Electrochemical Reduction of CO₂ to Value‐Added Chemicals and Fuel

Optimization under uncertainty in the era of big data and deep learning: When machine learning meets mathematical programming

Contact Info

Product

Resources

About

The promise of artificial intelligence in chemical engineering: Is it here, finally?

Cited by 472 publications

References 95 publications

Machine learning for the modeling of interfaces in energy storage and conversion materials

Machine learning for the modeling of interfaces in energy storage and conversion materials

A Disquisition on the Active Sites of Heterogeneous Catalysts for Electrochemical Reduction of CO2 to Value‐Added Chemicals and Fuel

Optimization under uncertainty in the era of big data and deep learning: When machine learning meets mathematical programming

Contact Info

Product

Resources

About

A Disquisition on the Active Sites of Heterogeneous Catalysts for Electrochemical Reduction of CO₂ to Value‐Added Chemicals and Fuel