CV

Project Scientist II

Indian Institute of Tropical Meteorology

• Experience in development of lightning parameterization in BFS using Fortran and shell scripting in Arka HPC
• Experience in development and operationalization of parameter extraction tools for BFS model output (in ≳100 TB) using shell scripting in Arka HPC
• Experience in BFS model output analysis and visualisation using python and GrADS scripting
• Experience in implementation of mesoscale convective system tracking (organization_indices and PyFLEXTRKR) using BFS, GFST1534 and ERA5 dataset
• Completed basic course on Code of Conduct for Government Employees by Institute of Secretariat Training and Management along with 6 others certificate course on Karmayogi platform
• Work have been presented at the Eighth WMO International Workshop on Monsoons (IWM-8), 2025 and INTROMET-2025

Research Fellow

Indian Institute of Tropical Meteorology

• Experience in the development of lightning parameterization for IITM GFS T1534 with the help of Fortran and shell scripting in Pratyush HPC.
• Developed a unique NWP AI-hybrid lightning prediction system with IMD WRF operational output as model input.
• Participated in the Short-Range Prediction System daily operational forecast by generating meteorological forecast products using daily forecast output from GFS T1534 and GEFS T1534.
• Experience in successful installation and execution of GFS T1534 and ARW WRF v3.9.1.1.
• Have conducted extensive data preprocessing of operational forecasting datasets for global and regional models, as well as raw observational data, using Python, CDO, NCO and shell scripting on the UNIX operating system.
• Computed complex statistical analyses and interpreted data using Python, CDO and GrADS.
• Collected data and observed trends while analysing global and regional numerical model output.
• Compiled data in reports and other documents using Markdown, LaTeX, Microsoft Office, Google Workspace, Jupyter and Notion.
• Collaborated with other researchers to write and distribute the impactful results of the forecast skill of the lightning prediction system generated by the global numerical model.
• Followed best practices and scientific protocol to reach defensible conclusions based on solid evidence.
• Upheld all university and regulatory requirements for documentation of findings.

PhD

Indian Institute of Tropical Meteorology; Savitribai Phule Pune University

Atmospheric Sciences

Master of Science

University of Calcutta

Atmospheric Sciences

• Final Grade 80.1%
• Dissertation Probing for connectivity between lightning activity and depth of convection during pre-monsoon season over Kolkata

Bachelor of Science

Asutosh College, University of Calcutta

Physics (Honours)

• Final Grade 65.75%

AGU23 Student Travel Grant

American Geophysical Union

Student Travel Grant to participate in the American Geophysical Union 2023 Annual Meeting (AGU23), held 11-15 December 2023 in San Francisco, California, USA

Best Student Award

Development of Skilled Manpower in Earth System Sciences (DESK), IITM, Pune.

For ranking first in the two-semester Ph.D. course, 2018–2019

DST INSPIRE Fellowship, 2018

Department of Science and Technology (DST), Ministry of Science and Technology, Government of India.

A unique Scheme “Innovation in Science Pursuit for Inspired Research (INSPIRE)” with several components. INSPIRE Fellowship provides fellowship in Basic and Applied Sciences.

GATE 2018

All India Rank 492

CSIR-UGC Lectureship, 2017

All India Rank 492

DST INSPIRE Scholarship, 2012

Department of Science and Technology (DST), Ministry of Science and Technology, Government of India.

For being top 1% rank holder in state higher secondary exams, 2012 in Science subjects.

Performance of a novel NWP–AI hybrid lightning early warning system over Indian Subcontinent

Journal of Earth System Science

NWP models have difficulty in converting complex microphysical and dynamical processes in lightning. In contrast, data-driven AI models fail to capture the latent features associated with lightning activity. A novel NWP–AI hybrid lightning early warning system using a two-autoencoder-based classification model ($C_{2AE}$), which uses IMD WRF 9 km forecast as input, is discussed. The current version of $C_{2AE}$ uses mean square error as a loss function and, after finetuning, can forecast lightning activity with an error of 3% when tested over the training region. Further analysis of different thunderstorm-prone regions for March–April–May 2020 reveals that $C_{2AE}$ can capture the spatial and temporal distribution of lightning independent of the training region.

Lightning Forecasting and Utilization of AI/ML in Early Warnings

Springer Nature Link

In recent years, the application of Artificial Intelligence (AI) in different sectors of society has become one of the most common technologies. As AI becomes a useful tool, incorporating AI in weather forecasts has also started rising. Lightning is one of India’s leading causes of casualty associated with natural disasters. An early warning system for lightning forecast is of utmost importance. However, the atmospheric processes associated with lightning are yet to be fully understood, making it challenging to simulate in a numerical weather prediction (NWP) model for operational purposes. Considering all these factors, in this chapter, we have discussed an AI-based deep learning approach for lightning prediction. This new AI-based lightning prediction system uses the Indian Meteorology Department (IMD) Weather Research and Forecasting (WRF) model at 9 km resolution as input which presently do not have any lightning product. The Indian Institute of Tropical Meteorology (IITM) Lightning Location Network (LLN) observation data is used as target vector to train the model. Due to the high imbalance of rare and severe events (RSEs) like lightning, we have used a novel approach of two-auto encoder-based classification ($C_{2AE}$) to train a deep-learning algorithm to correctly encode meteorological features associated with lightning and non-lightning incidents and, when the trained model is tested on a new dataset, it is able to correctly identify lightning events with statistical significance.

Evaluation of ECMWF Lightning Flash Forecast over Indian Subcontinent during MAM 2020

Atmosphere

During the pre-monsoon season (March–April–May), the eastern and northeastern parts of India, Himalayan foothills, and southern parts of India experience extensive lightning activity. Mean moisture, surface and upper-level winds, the sheared atmosphere in the lower level, and high positive values of vertically integrated moisture flux convergence (VIMFC) create favorable conditions for deep convective systems to occur, generating lightning. From mid-2018, the European Centre for Medium-Range Weather Forecasts (ECMWF) Integrated Forecasting System (IFS) operationally introduced lightning flash density on a global scale. This study evaluates the ECMWF lightning forecasts over India during the pre-monsoon season of 2020 using the Indian Institute of Tropical Meteorology (IITM) Lightning Location Network (LLN) observation data. Qualitative and quantitative analysis of the ECMWF lightning forecast has shown that the lightning forecast with a 72-h lead time can capture the spatial and temporal variation of lightning with a 90% skill score.