Grant: Discovery Grants Program - Individual
University of Toronto
$43,000.00
Machine Learning for the Understanding and Design of Nanoporous Materials
FY 2023-24
Summary
Innovation in materials design and discovery is at the heart of accelerating technology development to address our global sustainability challenges. The long-term goal of my research program is to develop novel computational and machine learning methods to solve methodological challenges on the way to autonomous, multiscale materials design for energy and environmental applications, including carbon capture, energy storage, and catalysis. Over the next five years, my group will focus on the field of nanoporous materials, particularly, metal-organic frameworks (MOFs). While MOFs feature promising characteristics for several sustainability applications, their design and discovery require a holistic perspective over the full multiscale design process, which involves exploring immense materials spaces, their properties, engineering chemical processes, as well as a techno-economic and life cycle assessment. While exploring all available options using conventional scientific approaches seems intractable, the era of big data and artificial intelligence brings many opportunities to advance chemical sciences and engineering on many fronts. Therefore, we develop innovative methods using computation and machine learning to establish quantitative, multiscale models to understand materials and link them to their synthesis and performance. To realize our long-term research vision, we will work on the following three pillars in short-term: - Integrate machine learning in molecular simulation to improve the quality of computational data - Invent machine learning methods for experimental data to enable predicting properties that are currently inaccessible from simulation, including synthesis and lifetime - Design physics-motivated machine learning algorithms to establish efficient inverse design strategies This research will lead to innovation in nanoporous materials design, which can have significant technological, environmental, and social impacts. In addition, this program can potentially place Canadian industries and companies, active in areas including carbon capture and catalysis, at the forefront of innovation in technological advancements in sustainability. The scientific merit of the developed methods goes beyond the proposed projects and will enable viewing conventional and emerging chemical engineering problems from new angles. My students and postdocs will work in inclusive, multidisciplinary teams and gain advanced skills in areas related to atomistic modeling, machine learning, and artificial intelligence applied in chemistry and chemical engineering, which are in high demand in both industrial and academic environments. As a team, we celebrate diversity and value creativity and curiosity. As the principal investigator, I endeavor to promote an inclusive environment, where my trainees will flourish, and with the transferable and technical skills they acquire, they will become future leaders in various fields of science and engineering.
Program
Discovery Grants Program - Individual
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2023-04232
Name nom
Moosavi, Seyed Mohamad
Department département
Chemical Engineering and Applied Chemistry
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2023
Award amount
43000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1511
Committee name en
Materials and Chemical Engineering
Committee name fr
Génie chimique et des matériaux
Area of application code
305
Area of application group en
Energy resources
Area of application group fr
Ressources d'énergie
Area of application en
Energy storage and conversion
Area of application fr
Stockage et transformation de l'énergie
Research subject code
2017
Research subject group en
Materials science and technology
Research subject group fr
Theoretical studies
Research subject en
Science et technologie des matériaux
Research subject fr
Études théoriques
Application title
Machine Learning for the Understanding and Design of Nanoporous Materials
Keyword
Artificial Intelligence; Carbon Capture; Energy Materials; Gas Separation; Machine Learning; Materials Design and Discovery; Metal-Organic Frameworks; Molecular Simulation; Nanoporous materials
Application summary
Innovation in materials design and discovery is at the heart of accelerating technology development to address our global sustainability challenges. The long-term goal of my research program is to develop novel computational and machine learning methods to solve methodological challenges on the way to autonomous, multiscale materials design for energy and environmental applications, including carbon capture, energy storage, and catalysis. Over the next five years, my group will focus on the field of nanoporous materials, particularly, metal-organic frameworks (MOFs). While MOFs feature promising characteristics for several sustainability applications, their design and discovery require a holistic perspective over the full multiscale design process, which involves exploring immense materials spaces, their properties, engineering chemical processes, as well as a techno-economic and life cycle assessment. While exploring all available options using conventional scientific approaches seems intractable, the era of big data and artificial intelligence brings many opportunities to advance chemical sciences and engineering on many fronts. Therefore, we develop innovative methods using computation and machine learning to establish quantitative, multiscale models to understand materials and link them to their synthesis and performance. To realize our long-term research vision, we will work on the following three pillars in short-term: - Integrate machine learning in molecular simulation to improve the quality of computational data - Invent machine learning methods for experimental data to enable predicting properties that are currently inaccessible from simulation, including synthesis and lifetime - Design physics-motivated machine learning algorithms to establish efficient inverse design strategies This research will lead to innovation in nanoporous materials design, which can have significant technological, environmental, and social impacts. In addition, this program can potentially place Canadian industries and companies, active in areas including carbon capture and catalysis, at the forefront of innovation in technological advancements in sustainability. The scientific merit of the developed methods goes beyond the proposed projects and will enable viewing conventional and emerging chemical engineering problems from new angles. My students and postdocs will work in inclusive, multidisciplinary teams and gain advanced skills in areas related to atomistic modeling, machine learning, and artificial intelligence applied in chemistry and chemical engineering, which are in high demand in both industrial and academic environments. As a team, we celebrate diversity and value creativity and curiosity. As the principal investigator, I endeavor to promote an inclusive environment, where my trainees will flourish, and with the transferable and technical skills they acquire, they will become future leaders in various fields of science and engineering.