Machine Learning in Chemical Engineering: A Perspective

Artur M. Schweidtmann; Erik Esche; Asja Fischer; Marius Kloft; Jens Uwe Repke; Sebastian Sager; Alexander Mitsos

doi:10.1002/cite.202100083

Machine Learning in Chemical Engineering: A Perspective

Artur M. Schweidtmann^*, Erik Esche, Asja Fischer, Marius Kloft, Jens Uwe Repke, Sebastian Sager, Alexander Mitsos

^*Corresponding author for this work

ChemE/Product and Process Engineering

Research output: Contribution to journal › Review article › peer-review

53 Citations (Scopus)

488 Downloads (Pure)

Abstract

The transformation of the chemical industry to renewable energy and feedstock supply requires new paradigms for the design of flexible plants, (bio-)catalysts, and functional materials. Recent breakthroughs in machine learning (ML) provide unique opportunities, but only joint interdisciplinary research between the ML and chemical engineering (CE) communities will unfold the full potential. We identify six challenges that will open new methods for CE and formulate new types of problems for ML: (1) optimal decision making, (2) introducing and enforcing physics in ML, (3) information and knowledge representation, (4) heterogeneity of data, (5) safety and trust in ML applications, and (6) creativity. Under the umbrella of these challenges, we discuss perspectives for future interdisciplinary research that will enable the transformation of CE.

Original language	English
Pages (from-to)	2029-2039
Journal	Chemie-Ingenieur-Technik
Volume	93
Issue number	12
DOIs	https://doi.org/10.1002/cite.202100083
Publication status	Published - 2021

Keywords

Deep learning
Hybrid modeling
Machine learning
Optimization
Reinforcement learning

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1002/cite.202100083

cite.202100083Final published version, 3.08 MBLicence: CC BY

Cite this

@article{f72ce719822247819ca623808bd6897e,

title = "Machine Learning in Chemical Engineering: A Perspective",

abstract = "The transformation of the chemical industry to renewable energy and feedstock supply requires new paradigms for the design of flexible plants, (bio-)catalysts, and functional materials. Recent breakthroughs in machine learning (ML) provide unique opportunities, but only joint interdisciplinary research between the ML and chemical engineering (CE) communities will unfold the full potential. We identify six challenges that will open new methods for CE and formulate new types of problems for ML: (1) optimal decision making, (2) introducing and enforcing physics in ML, (3) information and knowledge representation, (4) heterogeneity of data, (5) safety and trust in ML applications, and (6) creativity. Under the umbrella of these challenges, we discuss perspectives for future interdisciplinary research that will enable the transformation of CE.",

keywords = "Deep learning, Hybrid modeling, Machine learning, Optimization, Reinforcement learning",

author = "Schweidtmann, {Artur M.} and Erik Esche and Asja Fischer and Marius Kloft and Repke, {Jens Uwe} and Sebastian Sager and Alexander Mitsos",

year = "2021",

doi = "10.1002/cite.202100083",

language = "English",

volume = "93",

pages = "2029--2039",

journal = "Chemie-Ingenieur-Technik",

issn = "0009-286X",

publisher = "Wiley",

number = "12",

}

TY - JOUR

T1 - Machine Learning in Chemical Engineering

T2 - A Perspective

AU - Schweidtmann, Artur M.

AU - Esche, Erik

AU - Fischer, Asja

AU - Kloft, Marius

AU - Repke, Jens Uwe

AU - Sager, Sebastian

AU - Mitsos, Alexander

PY - 2021

Y1 - 2021

N2 - The transformation of the chemical industry to renewable energy and feedstock supply requires new paradigms for the design of flexible plants, (bio-)catalysts, and functional materials. Recent breakthroughs in machine learning (ML) provide unique opportunities, but only joint interdisciplinary research between the ML and chemical engineering (CE) communities will unfold the full potential. We identify six challenges that will open new methods for CE and formulate new types of problems for ML: (1) optimal decision making, (2) introducing and enforcing physics in ML, (3) information and knowledge representation, (4) heterogeneity of data, (5) safety and trust in ML applications, and (6) creativity. Under the umbrella of these challenges, we discuss perspectives for future interdisciplinary research that will enable the transformation of CE.

AB - The transformation of the chemical industry to renewable energy and feedstock supply requires new paradigms for the design of flexible plants, (bio-)catalysts, and functional materials. Recent breakthroughs in machine learning (ML) provide unique opportunities, but only joint interdisciplinary research between the ML and chemical engineering (CE) communities will unfold the full potential. We identify six challenges that will open new methods for CE and formulate new types of problems for ML: (1) optimal decision making, (2) introducing and enforcing physics in ML, (3) information and knowledge representation, (4) heterogeneity of data, (5) safety and trust in ML applications, and (6) creativity. Under the umbrella of these challenges, we discuss perspectives for future interdisciplinary research that will enable the transformation of CE.

KW - Deep learning

KW - Hybrid modeling

KW - Machine learning

KW - Optimization

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85117518109&partnerID=8YFLogxK

U2 - 10.1002/cite.202100083

DO - 10.1002/cite.202100083

M3 - Review article

AN - SCOPUS:85117518109

SN - 0009-286X

VL - 93

SP - 2029

EP - 2039

JO - Chemie-Ingenieur-Technik

JF - Chemie-Ingenieur-Technik

IS - 12

ER -

Machine Learning in Chemical Engineering: A Perspective

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this