Physical Sciences and Mathematics Commons^™

Post-Wildfire Effects On A Headwater Stream In The San Bernardino National Forest, Kelley Giron

Electronic Theses, Projects, and Dissertations

Southern California has experienced prolonged drought conditions that have supported frequent wildfires that adversely impact ecosystems, natural resources, and human development. A primary consequence of these events is the impact on water quality and quantity. Of equal concern is evaluating how diverse land use configurations within a watershed can alter the physio-chemical properties of headwater reaches where drought and wildfire conditions are prevalent. To better understand the extent to which wildfires impact water quality and quantity across a headwater watershed, this study investigates wildfire impacts from the 2021 South Fire to Lytle Creek, a headwater stream of the Santa Ana …

Analysis And Assessment Of Land Use / Land Cover Impact On Human And Natural Ecosystems In The Salton Sea Watershed, 2013 - 2021, Diego Ramirez

Electronic Theses, Projects, and Dissertations

This study represents an interdisciplinary analysis of the changing landscape of the Salton Sea Watershed from 2013 to 2021, focusing on land use land cover (LULC) category changes, climatic variations, and socioeconomic factors. The findings of this research show a shift in land cover categories, portrayed by the changes of natural landscapes and vegetative areas into rapidly increasing urbanized expansion and increased impervious surfaces. These changes pose concerns about increased temperature in the region, a decrease in overall water availability and groundwater infiltration, and an increase in pollution. The study explores 10 sub-watersheds within the Salton Sea Watershed basin, focusing …

Geospatial Wildfire Risk Prediction Using Deep Learning, Abner Alberto Benavides

Electronic Theses, Projects, and Dissertations

This report introduces a thorough analysis of wildfire prediction using satellite imagery by applying deep learning techniques. To find wildfire-prone geographical data, we use U-Net, a convolutional neural network known for its effectiveness in biomedical image segmentation. The input to the model is the Sentinel-2 multispectral images to supply a complete view of the terrain features.

We evaluated the wildfire risk prediction model’s performance using several metrics. The model showed high accuracy, with a weighted average F1 score of 0.91 and an AUC-ROC score of 0.972. These results suggest that the model is exceptionally good at predicting the location of …