PhD researcher in landscape-scale agroecosystem modelling, specializing in geospatial data science, machine learning, and agricultural systems modelling. I develop machine learning, deep learning, and hybrid process-based modelling workflows for crop modelling, yield forecasting, crop mapping, and climate change impact assessment, leveraging large-scale Earth observation, climate, and soil datasets. My research interests include open science, scientific software development, and advancing agricultural science and technology to address real-world challenges, particularly in underserved regions and vulnerable agricultural systems.
Research conducted at the Leibniz Centre for Agricultural Landscape Research (ZALF), Germany.
Research focus: Landscape-scale agroecosystem modelling, spatial and temporal landscape dynamics, crop productivity, and resilience.
Research question: How can spatial and temporal landscape information be represented and integrated into agroecosystem models to improve the understanding and prediction of crop productivity and resilience across scales?
Supervisor: Prof. Dr. Frank Ewert
Discontinued (dropout)
CGPA: 9.04/10.00
CGPA: 9.33/10.00
Percentage: 95.80%. Subjects: Bengali, English, Geography, Computer Application, Philosophy, Mathematics.
Percentage: 90.43%. Subjects: Bengali, English, Mathematics, Physical Science, Life Science, History, Geography.
Coordination and Support Action with ZALF, Germany, as a consortium partner.
Biodiversity, Climate, Agriculture and Food within Planetary Boundaries.
An interpretable deep learning framework for probabilistic crop yield forecasting.
Artificial Intelligence in Agriculture (IF: 16.1; Q1)
Smart Agricultural Technology (IF: 7.1; Q1)
Agricultural and Forest Meteorology (IF: 6.6; Q1)
Gondwana Research (IF: 8.9; Q1)
Smart Agricultural Technology (IF: 7.1; Q1)
Journal of Hydrology (IF: 7.3; Q1)
Science of Remote Sensing (IF: 7.1; Q1)
Scientific Reports (IF: 4.9; Q1)
Discover Sustainability (IF: 5.2; Q1)
Scientific Reports (IF: 4.9; Q1)
Geomatics, Natural Hazards and Risk (IF: 4.9; Q1)
Environmental Sciences Europe (IF: 7.1; Q1)
Graduate Aptitude Test in Engineering (GATE) 2024.
Ranked among the top 0.01 percentile of 777,000 candidates with a test score of 479/500.