Date of Award

2026-08-01

Degree Name

Master of Science

Department

Engineering

Advisor(s)

Natalia N. Villanueva-Rosales

Abstract

Urban water management in semi-arid regions requires an improved understanding of how vegetation and climatic conditions influence landscape water demand. Existing approaches often lack an integrated, spatially consistent framework to quantify this relationship at fine scales. This study proposes a patch-level framework to estimate relative landscape water demand by integrating vegetation coverage, vegetation condition, and atmospheric demand. Vegetation coverage is derived from high-resolution imagery obtained from the National Agriculture Imagery Program (NAIP) using a U-Net segmentation model with a MobileNetV2 backbone. A patch-based representation is used to ensure spatial consistency across the study area. Seasonal vegetation dynamics are captured using multi-temporal Sentinel-2 Normalized Difference Vegetation Index (NDVI) time series, and atmospheric demand is represented by reference evapotranspiration (ETo) derived from gridMET and ground weather station data. These components are combined in an index to estimate weekly relative landscape water demand at the patch level. Experimental results demonstrate that the vegetation segmentation component achieved strong performance, with the best configuration using RGBN imagery and a combined Binary Cross Entropy (BCE)-Dice loss obtaining an Intersection over Union (IoU) of 0.8881 and an F1-score of 0.9407. The resulting framework generates spatially explicit estimates of relative water demand while maintaining interpretability and scalability for urban-scale applications. By integrating vegetation structure, seasonal dynamics, and atmospheric conditions, the proposed approach provides a data-driven and transferable framework to support residents and other stakeholders in urban water management, vegetation monitoring, and sustainable water-use planning in semi-arid urban areas such as El Paso.

Language

en

Provenance

Received from ProQuest

File Size

81 p.

File Format

application/pdf

Rights Holder

Jesus Daniel Pereyra Manriquez

Download

Share

COinS