About Me
I am fifth-year PhD candidate in the department of Computer Science at Virginia Tech. I work in the Science-Guided Machine Learning Lab, and I am advised by Dr. Anuj Karpatne.
I received my Bachelor's in Electronics and Tele-communication engineering from Jadavpur University.
My broader research interests are in deep learning and artificial intelligence. My current research is geared towards the development of next-generation AI solutions for
scientific applications with the ultimate goal of accelerating scientific discovery. Specifically, I infuse underlying scientific laws with deep learning
models to improve their overall generalizability and interpretability. I enjoy working on interdisciplinary projects and have experience working on a diverse range
problems from climate and sustainability, solving partial differential equations (PDEs) to cell biology.
New
New My paper titled "Multi-task Learning for Source Attribution and Field Reconstruction for Methane Monitoring." accepted in Digital Twins for Accelerated Discovery of Climate and Sustainability workshop (ADoCS) at IEEE Big Data 2022. Check out the
preprint.
New Workshop paper titled "Source Identification and Field Reconstruction of Advection-Diffusion Process from Sparse Sensor Measurements." accepted in Machine Learning for Physical Sciences (ML4PS) workshop at NeurIPS 2022.
[paper] [poster]
New Super excited to present my work on "Rethinking the Importance of Sampling in Physics-informed Neural Networks." in 3rd Symposium of Knowledge-guided AI (KGML) at AAAI 2022.
[paper]
New New preprint available "Mitigating Propagation Failures in PINNs using Evolutionary Sampling."
[preprint]
New New preprint available "Deep Learning Enabled Label-free Cell Force Computation in Deformable Fibrous Environments."
[preprint]
New Thirlled for my invited talk at Allan Turing Institute, London, UK titled "Uncertainty quantification with Physics-informed Machine Learning".
New Started internship at IBM T.J. Watson Research Center under the mentorship of Levente Klein and Kyongmin Yeo.
New Super thrilled to share that my two invited book chapters in "Knowledge-guided Machine Learning: Accelerating Discovery using Scientific Knowledge and Data" book is now available online.
[book]
New Excited to give a guest lecture on "Advanced Topics in Deep Learning" at CS 5525 (Data Analytics) course at Viginia Tech.
New Our paper "Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)" is accepted at Neural Information Processing Systems (NeurIPS) 2021.
[paper]
New Workshop paper titled "PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics." accepted in 2nd Symposium of Science-guided AI (SGAI) at AAAI 2021.
[paper]
New Started internship at AWS Lambda as Applied Research Scientist intern under the mentorship of John Konstantinides.
New Our paper "PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics" is accepted at SIG KDD 2021.
[paper]
New Workshop paper titled "Physics-Informed Discriminator (PID) for Conditional Generative Adversarial Nets." accepted in Machine Learning for Physical Sciences (ML4PS) workshop at NeurIPS 2020.
[paper]
New Our paper "Physics-Guided Architecture (PGA) of Neural Networks for Quantifying Uncertainty in Lake Temperature Modeling" is accepted at SDM 2020.
[paper]
New Workshop paper accepted at Fragile-Earth Workshop at KDD 2019.