Research Interests

Keywords: Weather Forecasting, Remote Sensing, Bayesian & Frequentist ML, UQ, XAI

My research lies at the intersection of artificial intelligence and environmental science, with a strong focus on developing accurate and interpretable forecasting models for weather and climate systems. I employ deep learning, Bayesian machine learning, and explainable AI to understand and predict environmental changes across time and space. My work leverages remote sensing data—including satellite and UAV imagery—to support land use monitoring, climate impact assessment, and risk estimation. Through these efforts, I aim to contribute to sustainable environmental planning and resilience-building in the face of climate variability and change. Some specific focus areas include:

  • Data-driven rainfall prediction and seasonal climate forecasting using deep learning and Bayesian methods
  • Environmental change detection and climate impact quantification using spatial-temporal data
  • Uncertainty quantification (UQ) and explainable AI (XAI) for interpretable and trustworthy environmental models

Research Experience

  • Postdoctoral Research Associate (1st August 2023 - ongoing)

    Computing and Data Sciences, Boston University, Massachusetts, USA

  • Research Associate (8th June 2022 - 7th June 2023)

    CYENS Centre of Excellence (SuPerWorld MRG), Nicosia, Cyprus

  • Assistant Project Engineer (3th April 2014 - 4th July 2015)

    Indian Institute of Technology Guwahati, Assam, India

  • Research Intern (15th December 2020 - 31th May 2022)

    CYENS Centre of Excellence (SuPerWorld MRG), Nicosia, Cyprus

Ongoing Projects

Seasonal Rainbelt Forecast

Currently working on seasonal rainbelt forecasting using a data-driven approach that incorporates partial differential equations (PDE) as a regularizer to improve model accuracy and physical consistency.

Rainfall Forecasting

A deep learning model predicts rainfall over Ghana with accuracy comparable to or better than ECMWF’s 18-hour forecasts. Combining this model with traditional numerical weather prediction further improves performance.

Selected Publications

Book Chapter

  • Kalita, I., Chakraborty, S., & Choudhury, N. (2022). AI-Based Smart Agriculture Monitoring Using Ground-Based and Remotely Sensed Images. In The New Advanced Society: Artificial Intelligence and Industrial Internet of Things Paradigm (pp. 191-221).

Journals

  • Kalita, I., Kamilaris, A., Havinga, P., & Reva, I. (2024). Assessing the Health Impact of Disinfection Byproducts in Drinking Water. ACS ES&T Water.
  • Kalita, I., Chakraborty, S., Reddy, T.G.G., & Roy, M. (2024). A deep learning-based technique for firm classification and domain adaptation in land cover classification using time-series aerial images. Earth Science Informatics, 17(1), 655-678.
  • Kalita, I., Singh, G.P., & Roy, M. (2023). Crop classification using aerial images by analyzing an ensemble of DCNNs under multi-filter & multi-scale framework. Multimedia Tools and Applications, 82(12), 18409-18433.
  • Kalita, I., & Roy, M. (2022). Class-Wise Subspace Alignment-Based Unsupervised Adaptive Land Cover Classification in Scene-Level Using Deep Siamese Network. IEEE Transactions on Neural Networks and Learning Systems.

Conferences

  • Kalita, I., Mugganawar, N., & Roy, M. (2022, July). Unsupervised cross-sensor domain adaptation using adversarial network for land cover classification. In IGARSS 2022 - IEEE International Geoscience and Remote Sensing Symposium (pp. 5724-5727). IEEE.
  • Kalita, I., & Roy, M. (2022, July). Inception time DCNN for land cover classification by analyzing multi-temporal remotely sensed images. In IGARSS 2022 - IEEE International Geoscience and Remote Sensing Symposium (pp. 5736-5739). IEEE.
  • Kalita, I., & Roy, M. (2022, July). Deep learning method for agriculture monitoring under adaptive environment using UAV-based aerial images. In 2022 IEEE Region 10 Symposium (TENSYMP) (pp. 1-6). IEEE.
  • Kalita, I., Karatsiolis, S., & Kamilaris, A. (2021). Land use change detection using deep siamese neural networks and weakly supervised learning. In Computer Analysis of Images and Patterns: 19th International Conference, CAIP 2021 (pp. 24-35). Springer International Publishing.

For all publications, please visit my Google Scholar page.

Interested in collaboration? Please email me at indrajit@bu.edu with details about your background and research interests.

Interested for colaboration? Please don't hesitate to email me at indrajit@bu.edu, providing details about your background and research interests.

Want to know more about my projects? Kindly email me at indrajit@bu.edu, using the title of the project or research paper as the subject.