SamMajumder / EnviroInfer-Sundarbans

Utilizing Interpretable Machine Learning to Analyze and Assess the Environmental Factors Affecting Vegetation Health in the Sundarbans Mangrove Forest.

Verdant Veil: Interpretable ML Assessment of Environmental Impacts on Sundarbans Vegetation

Project Overview

This project leverages interpretable machine learning techniques to analyze and assess the impacts of various environmental factors on the vegetation within the Sundarbans, a unique mangrove area in the delta region of the Padma, Meghna, and Brahmaputra river basins. The Sundarbans is a UNESCO World Heritage Site and a vital area for biodiversity. Understanding how environmental factors affect its vegetation can provide crucial insights for conservation efforts.

Dataset

MODIS/006/MOD13A2:

Kamel Didan - University of Arizona, Alfredo Huete - University of Technology Sydney and MODAPS SIPS - NASA. (2015). MOD13A2 MODIS/Terra Vegetation Indices 16-Day L3 Global 1km SIN Grid. NASA LP DAAC. http://doi.org/10.5067/MODIS/MOD13A2.006​1​.

ECMWF/ERA5/DAILY:

Copernicus Climate Change Service (C3S) (2017): ERA5: Fifth generation of ECMWF atmospheric reanalyses of the global climate. Copernicus Climate Change Service Climate Data Store (CDS), (date of access), https://cds.climate.copernicus.eu/cdsapp#!/home.

HYCOM/sea_surface_elevation:

J. A. Cummings and O. M. Smedstad. 2013: Variational Data Assimilation for the Global Ocean. Data Assimilation for Atmospheric, Oceanic and Hydrologic Applications vol II, chapter 13, 303-343.

HYCOM/sea_temp_salinity:

J. A. Cummings and O. M. Smedstad. 2013: Variational Data Assimilation for the Global Ocean. Data Assimilation for Atmospheric, Oceanic and Hydrologic Applications vol II, chapter 13, 303-343.

Machine Learning Approach

Results