Wildland fire and fuel characteristics are useful in developing wildfire prediction tools that can be used to allocate wildfire resources and guide land management practices. Wildfire prediction in arid habitats in the southwestern United States is of specific concern because of the negative ecological impacts of fire on desert habitats and the current lack of accurate fire prediction tools for such areas. Wildfires in desert ecosystems threaten endangered wildlife such as the desert tortoise (Gopherus agassizii), damage native plant species through increased seed and plant mortality, and jeopardize unique plant communities through increased likelihood of exotic plant invasions. By measuring fuel loads within various vegetation types of the Mojave Desert and using remote sensing techniques to model those fuel loads, this study examines the ability to model previous fire occurrences and estimate future fire potential using satellite imagery derived Normalized Difference Vegetation Index (NDVI) and Fuel Moisture Content (FMC) along with ignition potential data (lightning strikes and distance to roads), topographical data (elevation and aspect), and climate information (maximum and minimum temperatures). Satellite data were used to create a suite of potential fuel load models that were then evaluated using AIC model selection and narrowed to the two best fit models for describing fuel load estimates derived from on-the-ground fuel load iv surveys. Of those two models, Model 2 had a better R² (0.35) and AIC (-366.5703) than Model 1 (0.29 and -348.2616 respectively). However, Model 1, which incorporated spring NDVI, elevation, maximum temperature, and aspect, was chosen as the most defensible model in terms of the ecological interactions driving fuel production. Model 1 was then used in conjunction with 2005 remote sensing and fire occurrence data to predict fire potential for that year. Fuel load Model 1 along with spring FMC at maximum temperature, lightning strikes, distance to roads, and perennial vegetation type were modeled and a Receiver Operating Characteristic (ROC) curve was used to evaluate the agreement between model predictions and actual fire occurrence. The ROC evaluation rendered an Area Under the Curve value of 0.90 indicating accurate prediction of fire occurrence for 2005. This study provides evidence that remote sensing techniques can be used in combination with field surveys to accurately predict wildfire potential in desert habitats observed in Gold Butte, Nevada. Additionally, this research provides a baseline by which future wildfire potential estimates can be streamlined for the Gold Butte area with the possibility for improved estimate accuracy with continued research to improve on the techniques described herein. Improving the accuracy of wildfire prediction in the area of Gold Butte can help land managers maximize their efficiency and effectiveness in wildland fire suppression as well as expand on the base of knowledge used towards protecting natural plant communities, restoring endangered species habitat, and managing public access and use in natural areas. This research also has potential applications in other arid and semi-arid ecoregions of the American southwest and perhaps other countries as well.