Grant: Discovery Grants Program - Individual
University of Toronto
$50,000.00
A Self Driving Laboratory Powered by a Trustable and Interpretable AI Framework for the Discovery of Novel Compositionally Complex Alloys
EF 2024-25
Résumé
This program seeks to combine Artificial Intelligence (AI) and High-Throughput Experimentation to realize a 100x increase in the discovery of novel complex metal alloy coatings that are resistant to corrosion, have high conductivity, and are exceptionally hard. The work leverages existing and future federal investments in Self-Driving Labs, meaning AI-directed scientific robots capable of performing research with minimal human intervention. The CFI funded Sputtertron, a unique experimental platform capable of automatically performing on-line synthesis and characterization of materials, will be used to explore composition, processing, and property relationships in complex alloys. Through this platform we will be able to (1) Design and dynamically test an interpretable AI that can be trained in minutes (or seconds) and used to provide predictions of new potential materials (2) generate an open database of synthesis-processing-conductivity-corrosion resistance-elastic property relationships for 10,000 previously unexplored alloys and (3) Develop an inference framework that uses physical models and our less structured understanding of the physical world (tacit knowledge) to extract relevant information from large materials datasets. The materials data and AI codes generated will be made openly available to be accessed and built upon by all Canadians. We will also conduct a yearly online AI model competition where the top three teams will work together to plan 1 month of experiments on the Sputtertron with the goal of discovering new transformative materials or demonstrating dynamic AI benchmarking.
The data, code, and materials generated through this effort will have far ranging impacts for Canadian society. Ultrahard and corrosion resistant alloys are of vital importance for things like enhanced oil recovery and drilling in mining. The database of 10,000 experimentally validated alloys and their associated stability ranges in different solutions will revolutionize the way alloys are selected for applications including in chemical plants, electrical connections, and infrastructure. Each scientific code we develop will be scoped by convening members of the broader community including industry, academia, and government labs to specifically identify key stumbling blocks and constraints to scientific progress. The undergraduate and graduate students trained by this program will be bilingual in materials science and AI with an understanding of how to link the two together and generate new materials, new understanding, and accelerate society towards the Canada 2030 decarbonization goals.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
RGPIN-2023-04843
Name nom
Hattrick-Simpers, Jason
Department département
Department of Materials Science and Engineering
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
50000
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
1208
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Materials sciences
Area of application fr
Sciences des matériaux
Research subject code
2001
Research subject group en
Materials science and technology
Research subject group fr
Science et technologie des matériaux
Research subject en
Materials structure, properties and testing
Research subject fr
Structure, propriétés et essais des matériaux
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
A Self Driving Laboratory Powered by a Trustable and Interpretable AI Framework for the Discovery of Novel Compositionally Complex Alloys
Keywords
corrosion resistant coatings; green energy technologies; carbon capture utilization and storage; high-throughput experimentation; artificial intelligence; autonomous systems; self-driving labs; high entropy alloys; scientific-ai
Application summary
This program seeks to combine Artificial Intelligence (AI) and High-Throughput Experimentation to realize a 100x increase in the discovery of novel complex metal alloy coatings that are resistant to corrosion, have high conductivity, and are exceptionally hard. The work leverages existing and future federal investments in Self-Driving Labs, meaning AI-directed scientific robots capable of performing research with minimal human intervention. The CFI funded Sputtertron, a unique experimental platform capable of automatically performing on-line synthesis and characterization of materials, will be used to explore composition, processing, and property relationships in complex alloys. Through this platform we will be able to (1) Design and dynamically test an interpretable AI that can be trained in minutes (or seconds) and used to provide predictions of new potential materials (2) generate an open database of synthesis-processing-conductivity-corrosion resistance-elastic property relationships for 10,000 previously unexplored alloys and (3) Develop an inference framework that uses physical models and our less structured understanding of the physical world (tacit knowledge) to extract relevant information from large materials datasets. The materials data and AI codes generated will be made openly available to be accessed and built upon by all Canadians. We will also conduct a yearly online AI model competition where the top three teams will work together to plan 1 month of experiments on the Sputtertron with the goal of discovering new transformative materials or demonstrating dynamic AI benchmarking.
The data, code, and materials generated through this effort will have far ranging impacts for Canadian society. Ultrahard and corrosion resistant alloys are of vital importance for things like enhanced oil recovery and drilling in mining. The database of 10,000 experimentally validated alloys and their associated stability ranges in different solutions will revolutionize the way alloys are selected for applications including in chemical plants, electrical connections, and infrastructure. Each scientific code we develop will be scoped by convening members of the broader community including industry, academia, and government labs to specifically identify key stumbling blocks and constraints to scientific progress. The undergraduate and graduate students trained by this program will be bilingual in materials science and AI with an understanding of how to link the two together and generate new materials, new understanding, and accelerate society towards the Canada 2030 decarbonization goals.