Bishwaranjan Bhattacharjee


Bishwaranjan Bhattacharjee is a Senior Technical Staff Member (STSM) and Master Inventor at IBM Research, where he leads projects in deep learning and data management. He has published 40 papers in top conferences such as ACL, EMNLP, and AAAI, and has filed over 60 patents. His work has earned multiple awards, including IBM Outstanding Innovation Awards and Technical Achievement Awards, and has been cited in IBM’s Research Division Accomplishments. Recognized at IBM's Corporate Technical Recognition Event, his contributions have been integrated into various DB2 LUW versions and Watson Vision Services. Additionally, he is an IEEE Senior Member and has served on numerous conference program committees.

Aashka Trivedi


Aashka Trivedi is a AI Research Engineer with a focus in knowledge distillation, retrieval augmented generation, model alignment for LLMs, and neural architecture search. A large part of her work makes large language models faster, better and more curated to individual business needs.

Muthukumaran Ramasubramanian


Muthukumaran Ramasubramanian received the M.S. degree incomputer science from the University of Alabama in Huntsville (UAH), where heis currently pursuing the Doctorate degree in computer science. He is also aComputer Science Researcher and leads the Machine Learning Team forNASA–Interagency Implementation and Advanced Concepts Team, UAH. His workfocuses on using deep-NLP techniques to surface novel relationships from largecorpora of text and to deploy deep learning solutions to detecting earthscience phenomena on a global scale. His research interests include machinelearning, big data, computer vision, and scalable cloud services.

Iksha Gurung


Iksha Gurung is a Computer Scientist working with University of Alabama in Huntsville, supporting National Aeronautics and Space Administration Inter-Agency Implementation of Advanced Concepts Team (NASA-IMPACT). He leads the development and machine learning team in NASA-IMPACT.  His projects include applying machine learning to Earth science phenomena studies and scaling the solutions to production.

Lecture content

Large Language Models for Science

The second day of the curriculum on Large-Scale AI for Geosciences focuses on Large Language Models for Science. The objective is to equip participants with the knowledge and skills necessary to understand and develop large language models. These models are crucial for advancing research in geosciences, enabling more efficient processing and interpretation of scientific data. The hands-on training will help participants apply these models in various practical and research contexts within the geoscience field


9:30 - 10:00 (Bishwaranjan Bhattacharjee, Aashka Trivedi)

INDUS overview

10:00 - 11:00 (Iksha Gurung, Muthukumaran Ramasubramanian)

Environment setup, Encoder model finetuning

11:00 - 11:30


11:30 - 13:00 (Muthukumaran Ramasubramanian)

Prompting and Decoder Fine-tuning

13:00 - 14:30 (Iksha Gurung, Muthukumaran Ramasubramanian)

Lunch Break

14:30 - 15:30 (Iksha Gurung, Muthukumaran Ramasubramanian)

Stitching everything together, Deployment

15:30 - 16:00


16:00 - 17:00  (Iksha Gurung, Muthukumaran Ramasubramanian)

Agentic Workflows and Chaining