- Developed high-performance Land Use Land Cover (LULC) classification models using Random Forest and Gradient Boosting algorithms for the Tropical Humid forests in South America.- Performed extensive data annotation and preprocessing to create robust training and validation datasets.- Conducted rigorous model evaluation, tuning hyperparameters and implementing strategies to optimize accuracy and performance.

- Worked as part of a team to develop an "AI-based framework and data-driven methodology for post-PCR High-Resolution Melting Analysis" to interpret molecular assays for diagnostic purposes in collaboration with clinicians and molecular biologists.- Contributed to the design and implementation of the AI framework using Python and other relevant tools.- Conducted data pre-processing, cleaning, and visualization tasks using pandas, NumPy, Plotly, and SciPy for signal processing.- Collaborated with the team to analyze and interpret results, presented findings to project stakeholders.- Worked as part of a team to develop an automated application called EXTRACTOR for data acquisition and released an open-source Python library called PyHRM for processing DNA melting signals with feature extraction and automatic thresholding using TensorFlow.- Wrote technical documentation for the application and the library, and thesis for the Major project.- The project has been proposed to "ICMR - Investigator Initiated Projects" as a collaboration of the Department of Computer Applications and Department of Biotechnology.