GROUNDWATER WITHDRAWAL ESTIMATION USING INTEGRATED REMOTE SENSING PRODUCTS AND MACHINE LEARNING

<p>"The rising demands for water, food, and energy primarily driven by the increasing global population constitute a pressing issue worldwide. Therefore, the water-food-energy nexus plays a substantial role in developing globally applicable sustainable solutions. Recent technological advancements, including the earth observation programs using spaceborne remote sensing platforms, have enabled us to monitor various critical components affecting the globe. Groundwater, which comprises the world's 30% freshwater, is one such key component of the global water resources and supplies nearly half of the global drinking water.</p> <p>Despite groundwater overdraft in many parts of the world, including the United States (US), there are limited efforts to monitor groundwater withdrawals at scales suitable for addressing water security issues. This research uses different passive and active satellite sensor data to predict annual groundwater withdrawals at various spatial resolutions ranging from 1 km to 5 km. This dissertation aims to develop an integrated approach combining various remote sensing, modeled, and gridded hydrometeorological data sets with a machine learning model which automatically learns the inter-relationships among these variables and groundwater withdrawals. It is tested in three regions (with substantially varying climate, aquifer characteristics, irrigation demands, and in-situ data sets) of the Conterminous US— Kansas, Arizona, and the Mississippi Alluvial Plain. The validation results show good agreement with the in-situ groundwater pumping data available over these regions with the coefficient of determination (R²) varying from 0.5 to 0.8"--Abstract, p. iii</p>

Name thesis:degree_name

Ph. D. in Geological Engineering

Grantor

Missouri University of Science and Technology

Author dc:creator

• MAJUMDAR, SAYANTAN

• estimation and forecasting
• geospatial
• groundwater hydrology
• machine learning
• remote sensing
• time series analysis
• Engineering
• Geological Engineering

Repository record dc:identifier

https://scholarsmine.mst.edu/doctoral_dissertations/3230

OAI identifier oai:identifier

oai:scholarsmine.mst.edu:doctoral_dissertations-4235