-
will use finite volumes methods combined with physics-informed neural networks (PINNs) which offer a flexible technique that merges data-driven approaches with the underlying physics principles, enabling
-
learning methods. Develop deep learning architectures (e.g., variational autoencoders, graph neural networks, transformers) for cross-omics data representation and feature extraction. Apply multi-view
-
models that merge machine learning techniques with mechanistic frameworks (like physics-informed neural networks and grey-box modeling) to enable predictive simulations of chemical and biochemical
-
convolutional-neural-network architecture for crop classification. Applied Sciences, 11(9), 4292. Bhattacharya, S. & Pandey, M. (2024). PCFRIMDS: Smart Next-Generation Approach for Precision Crop and Fertilizer
-
real-world applications in green chemistry and industrial synthesis. Key Responsibilities: Develop and implement AI/ML models (e.g., graph neural networks, transformer-based models) for retrosynthetic
-
CBS - Postdoctoral Position, Artificial Intelligence Applied to Metabolomics for Health Applications
metabolomics data from clinical studies. Apply deep learning models (e.g., autoencoders, variational autoencoders, graph neural networks) for biomarker discovery, disease classification, and patient