About
I am Midhun Murukesh, a PhD graduate and former Prime Minister's Research Fellow (PMRF) from the Climate and Glacier Modelling Lab (Thesis Guide: Dr. Pankaj Kumar, Associate Professor), Department of Earth and Environmental Sciences, Indian Institute of Science Education and Research (IISER) Bhopal.
My research focuses on precipitation downscaling, hydro-climate extremes, and physically interpretable deep learning models— bridging artificial intelligence and climate science to improve regional climate projections over India and beyond. Having completed my PhD, I am looking forward to the next chapter of my research career, exploring opportunities to advance climate science through innovative AI-driven approaches.
Research Highlights
Bridging Artificial Intelligence and Climate Science
Regional Climate Impacts
Regional impacts of climate change over India, with a focus on how large-scale change signals translate to local hydro-climate risk.
Precipitation Extremes
Analyzing precipitation extremes under a changing climate using observational, reanalysis, satellite, and CMIP6 datasets.
Explainable AI
Physics-informed machine learning and attribution methods (e.g., Integrated Gradients) to interpret what downscaling models learn.
Super-Resolution Networks
Image super-resolution neural networks (CNNs, GANs) for spatial downscaling and reconstruction of gridded rainfall data.
Transfer & Zero-Shot Learning
Transfer learning, data augmentation, and zero-shot precipitation downscaling across global climate regimes.
Next-Gen Climate Tools
Developing next-generation tools and reproducible Python/Bash workflows for large-scale climate data analysis.
Publications
Journal Articles
- Murukesh, M., & Kumar, P. (2026). Zero-shot transferability of deep learning models for precipitation super-resolution across diverse climate regimes. Earth and Space Science, 13, e2026EA005059. Paper → Data →
- Kumari, A., Kumar, P. & Murukesh, M. (2026). Unravelling Changes in Precipitation Extremes over India using CMIP6 Simulations under the High-Emission SSP5-8.5 Scenario. Pure and Applied Geophysics, 183, 5455–5483. Paper →
- Murukesh, M., & Kumar, P. (2026). Robust Deep Learning-based Downscaling of Mean and Extreme Precipitation over the Indian Subcontinent. Environmental Research: Climate, 5(2), 025029. Paper → Data →
- Golla, S., Murukesh, M., & Kumar, P. (2024). Comparative Assessment of Image Super-Resolution Techniques for Spatial Downscaling of Gridded Rainfall Data. SN Computer Science, 5(3), 312. Paper → Data →
- Murukesh, M., Golla, S., & Kumar, P. (2024). Downscaling and Reconstruction of High-resolution Gridded Rainfall Data over India using Deep Learning-based Generative Adversarial Network. Modeling Earth Systems and Environment, 10(2), 2221–2237. Paper → Data →
- Kumar, P., Javed, A., Kolli, R. K., Sachan, D., Dinesh, A. S., Murukesh, M., et al. (2023). National Colloquium for Advances in Weather and Climate Prediction and Climate Change Projection over South Asia: Applications in Water and Agriculture Sectors. Bulletin of the American Meteorological Society, 104(9), E1564–E1569. Paper →
Manuscripts Under Review
- Murukesh, M., Kumar, P., & P. B. Sujit (2026). Skill-Equivalent Deep Learning Models Learn Physically Distinct Attribution Patterns in Precipitation Downscaling (under review).
- Murukesh, M., & Kumar, P. (2026). Physically Interpretable Deep Learning Models for Precipitation Downscaling: Insights from Explainable AI over India (under review).
Conference Abstracts
- Murukesh, M., & Kumar, P. (2025). Comparative analysis of deep learning architectures trained for downscaling gridded precipitation across India. EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025 (oral presentation; in-person). Abstract →
- Murukesh, M., Kumar, P., & Gupta, R. P. (2024). Are deep learning methods viable for precipitation downscaling over the highly complex terrain of the Western Himalayas? Asia Oceania Geosciences Society 21st Annual Meeting (AOGS 2024), June 23–28, 2024, Pyeongchang, Gangwon-do, South Korea (oral presentation; in-person).
- Murukesh, M., & Kumar, P. (2024). Downscaling and reconstruction of high-resolution precipitation fields using a deep residual neural network: An assessment over Indian subcontinent. European Geophysical Union General Assembly 2024 (EGU 2024), April 14–19, 2024, Vienna, Austria and online (poster presentation; in-person). Abstract →
- Kumar, P., & Murukesh, M. (2024). Deep learning-based super-resolution generative adversarial network for gridded precipitation downscaling across India. European Geophysical Union General Assembly 2024 (EGU 2024), April 14–19, 2024, Vienna, Austria, and online (poster presentation). Abstract →
- Murukesh, M. (2023). Statistical Downscaling of Gridded Precipitation across India using Super-resolution Generative Adversarial Network (SRGAN). 39th M.P. Young Scientist Congress (MPYSC 2024), February 21–23, 2023, Gwalior, India (oral presentation; in-person). Abstract →
- Murukesh, M. & Kumar, P. (2023). A comprehensive intercomparison of novel deep learning techniques for super-resolution bias-correction of gridded precipitation. American Geophysical Union Annual Meeting 2023 (AGU 2023), December 11–15, 2023, San Francisco, CA and online (poster presentation; virtual).
- Murukesh, M. & Kumar, P. (2023). Investigating the impact of custom loss functions to train a deep neural network for downscaling gridded precipitation data. International Conference of Regional Climate–CORDEX 2023 (ICRC-CORDEX 2023), September 25–29, 2023, IITM Pune (oral presentation; in-person). Session →
- Murukesh, M. & Kumar, P. (2023). Evaluating the transferability of a deep learning technique to downscale gridded precipitation data. International Climate Research Conclave (ICRC 2023), May 26–27, 2023, IIT Bombay (poster presentation; in-person).
- Murukesh, M., Golla, S., & Kumar, P. (2023). Downscaling gridded rainfall across India using deep learning-based generative adversarial networks. 103rd Annual Meeting of American Meteorological Society, January 8–12, 2023, Denver, Colorado, USA (oral presentation; virtual). Abstract →
- Murukesh, M., Golla, S., & Kumar, P. (2022). Spatial downscaling of IMD gridded rainfall using generative adversarial networks. TROPMET-2022, November 29–December 2, 2022, IISER Bhopal (oral presentation). Abstract →
Fellowships & Awards
- 2025 Roland Schlich Early Career Scientist's Travel Support (ECSTS), European Geosciences Union (April 2025)
- 2021 Prime Minister's Research Fellows (PMRF) Scheme, Government of India (May 2021 Cycle)
- 2019 DST-INSPIRE Fellowship, Department of Science and Technology (DST), Government of India
- 2019 University Gold Medal and MSc First Rank from Central University of Rajasthan
- 2018 Summer Research Fellowship Program (SRFP), Indian Academy of Sciences (IASc), Bangalore
- 2014 DST-INSPIRE Scholarship for Higher Education, Department of Science and Technology (DST), Government of India
- 2014 Prathibha Scholarship, Kerala State Council for Science, Technology and Environment (KSCSTE), Government of Kerala
Contact
Interested in collaboration on regional modelling, climate downscaling, explainable AI, or climate extremes? Let's connect.