top of page
1732275459746_edited.jpg
Archisman Bhattacharjee

Science and Human-Centric AI researcher

Welcome to my work in progress! I'm a researcher fascinated by the intersection of science, machine learning, statistics, and philosophy. While this website is still under construction, I'm excited to share my research, projects, ever-growing interest in the arts, and philosophical reflections through this blog.

Dark Rocks

About Me

I am a researcher at the Geophysical Inversion Group, Indian Institute of Science (IISc), where I develop and implement deep learning methods to address inherent limitations in unsupervised and scarce-label scenarios, often encountered in geosciences and other data-scarce fields. One of my key projects is a collaboration with ISRO, the Indian space agency, where I lead efforts to identify subtle elemental signatures in lunar X-ray spectroscopy data recorded by the Chandrayaan-2 mission. At IISc, I am advised by Dr. Pawan Bharadwaj, whose mentorship has been pivotal in shaping my research.

In addition to my academic work, I contribute to Verda.ai, focusing primarily on steganography and audio machine learning while occasionally optimizing computational efficiency in deep learning based workflows. At Verda, we aim to tackle issues like misinformation and ensure the authenticity and provenance of digital content, working towards building a more trustworthy digital ecosystem.

I hold an integrated master's degree in applied geophysics from IIT Dhanbad. My time there exposed me to diverse fields, but it was a rekindled passion for research that ultimately defined my path. My primary focus lies in representation learning—developing deep learning approaches to extract meaningful features from complex data for downstream tasks. I have worked on or am currently engaged in research spanning:

  • Lunar X-ray spectroscopy

  • Speech and audio processing

  • Steganography

  • Seismology

  • Hyperspectral imaging

Beyond academics, I am an avid quizzer and have represented my college at inter-IIT events. Music—particularly progressive rock, metal, and jazz fusion—is a personal passion, and I remain curious about the whys of life and what it means to be human. 

Life may be too short to explore every idea, but connecting with fellow curious minds makes the journey richer.

Latest Blog

Updates

My First Journal Publication!

I am glad to share that the first project I led culminated in a paper at IEEE JSTARS!

You can read about it here: DOI: 10.1109/jstars.2025.3533302

I am presenting at CASML 2024. See you there!

I am presenting a poster "Quantizing Quakes: Exploring Neural Codecs for Earthquake Signal Analysis” at the Conference on Applied AI and Scientific Machine Learning (CASML) 2024 Bangalore. If you’re there, feel free to catch up with me!

New post on Residual Vector Quantization.

I have written a new post on Residual Vector Quantization (RVQ), a concept I frequently use in my work. It's a simple yet powerful concept. Read it here.

© 2025 Archisman Bhattacharjee. All rights reserved,

bottom of page