Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

McMaster University

$36,000.00

In-Silico Material Design in the Era of Machine Learning

EF 2024-25

Résumé
In today's rapidly evolving scientific landscape, my research program addresses two crucial challenges in computational chemistry (comp. chem) and machine learning (ML). Firstly, it seeks to develop data-efficient algorithms for material simulations, especially acknowledging the constraints posed by data scarcity limiting the development of ML models. Secondly, it aims to integrate ML models into comp. chem simulations, promising to enhance our understanding of molecular systems and accelerate material discovery. The proposed research program, which addresses these crucial challenges in computational chemistry and machine learning, is inherently linked to my long-term objectives. This alignment is substantiated by prior work in differentiable quantum simulations, Bayesian ML algorithms for inverse design, and material design. Three short-term projects exemplify the research goals: P.1: Meta-learning for comp. chem. - Focuses on enhancing parameter estimation of existing computational chemistry methodologies using ML models, particularly graph neural networks. The goal is to predict individual optimal parameters. P.2: Fine-tuning existing models - Addresses data-hungry ML approaches by fine-tuning pre-trained models for diverse tasks. The goal is to identify the optimal transfer learning protocol between existing ML models to bridge experimental and simulation data gaps, improving computational accuracy. P.3: Neural basis set - Proposes introducing neural networks as a quantum chemistry basis set candidate, leveraging their ability to approximate a wide range of functions. While a high-risk endeavour, it has the potential to reshape quantum chemistry by addressing limitations encountered in traditional Gaussian-type orbitals models. These research directions aim to advance material simulations and quantum chemistry, offering high-reward opportunities to overcome data limitations and improve existing methodologies in various domains. My research program reflects a multidisciplinary approach with the potential to make significant contributions to materials science and drug discovery fields.
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-2024-06594
Name nom
Vargas-Hernandez, Rodrigo Alejandro
Department département
Chemistry & Chemical Biology
Organization id
27
Institution établissement
McMaster University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
36000
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
1504
Committee name en
Chemistry
Committee name fr
Chimie
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
3400
Research subject group en
Physical chemistry
Research subject group fr
Chimie physique
Research subject en
Physical chemistry
Research subject fr
Chimie physique
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
In-Silico Material Design in the Era of Machine Learning
Keywords
computational chemistry; machine learning; density functional theory; theoretical chemistry; differentiable programming; material science
Application summary
In today's rapidly evolving scientific landscape, my research program addresses two crucial challenges in computational chemistry (comp. chem) and machine learning (ML). Firstly, it seeks to develop data-efficient algorithms for material simulations, especially acknowledging the constraints posed by data scarcity limiting the development of ML models. Secondly, it aims to integrate ML models into comp. chem simulations, promising to enhance our understanding of molecular systems and accelerate material discovery. The proposed research program, which addresses these crucial challenges in computational chemistry and machine learning, is inherently linked to my long-term objectives. This alignment is substantiated by prior work in differentiable quantum simulations, Bayesian ML algorithms for inverse design, and material design. Three short-term projects exemplify the research goals: P.1: Meta-learning for comp. chem. - Focuses on enhancing parameter estimation of existing computational chemistry methodologies using ML models, particularly graph neural networks. The goal is to predict individual optimal parameters. P.2: Fine-tuning existing models - Addresses data-hungry ML approaches by fine-tuning pre-trained models for diverse tasks. The goal is to identify the optimal transfer learning protocol between existing ML models to bridge experimental and simulation data gaps, improving computational accuracy. P.3: Neural basis set - Proposes introducing neural networks as a quantum chemistry basis set candidate, leveraging their ability to approximate a wide range of functions. While a high-risk endeavour, it has the potential to reshape quantum chemistry by addressing limitations encountered in traditional Gaussian-type orbitals models. These research directions aim to advance material simulations and quantum chemistry, offering high-reward opportunities to overcome data limitations and improve existing methodologies in various domains. My research program reflects a multidisciplinary approach with the potential to make significant contributions to materials science and drug discovery fields.