This study assesses forest fire severity and land surface temperature (LST) in Gujarat, India, using Google Earth Engine (GEE). The research integrates environmental variables such as slope orientation, elevation, NDVI, drainage density, precipitation, and temperature to evaluate wildfire susceptibility. A random forest regression model is used to predict LST based on these parameters. The study compares locations in Gujarat before and after forest fires using high-resolution satellite data to analyze the extent and type of changes caused by fires. The results include maps showing the geographical distribution of normalized burn ratio (NBR), difference NBR (dNBR), and LST forecasts, providing insights into spatial patterns and trends. The findings indicate that automated temporal analysis using GEE can effectively monitor fire threats across various land cover types. Forest fires have severe impacts, including biodiversity loss, ecosystem damage, and threats to human settlements. The study highlights the importance of accurate fire susceptibility mapping for effective wildfire management and mitigation. The results contribute to a better understanding of fire dynamics in the region, identifying areas with high fire risk and informing strategies for reducing future fire risks. The study also emphasizes the need for further research to explore the underlying causes of forest fires and improve the accuracy of fire severity assessments. The findings provide valuable insights for decision-makers in developing evidence-based policies to protect ecosystems, biodiversity, and communities from the increasing threat of climate change. The study demonstrates the potential of GEE and machine learning techniques in assessing fire susceptibility and managing wildfire risks.This study assesses forest fire severity and land surface temperature (LST) in Gujarat, India, using Google Earth Engine (GEE). The research integrates environmental variables such as slope orientation, elevation, NDVI, drainage density, precipitation, and temperature to evaluate wildfire susceptibility. A random forest regression model is used to predict LST based on these parameters. The study compares locations in Gujarat before and after forest fires using high-resolution satellite data to analyze the extent and type of changes caused by fires. The results include maps showing the geographical distribution of normalized burn ratio (NBR), difference NBR (dNBR), and LST forecasts, providing insights into spatial patterns and trends. The findings indicate that automated temporal analysis using GEE can effectively monitor fire threats across various land cover types. Forest fires have severe impacts, including biodiversity loss, ecosystem damage, and threats to human settlements. The study highlights the importance of accurate fire susceptibility mapping for effective wildfire management and mitigation. The results contribute to a better understanding of fire dynamics in the region, identifying areas with high fire risk and informing strategies for reducing future fire risks. The study also emphasizes the need for further research to explore the underlying causes of forest fires and improve the accuracy of fire severity assessments. The findings provide valuable insights for decision-makers in developing evidence-based policies to protect ecosystems, biodiversity, and communities from the increasing threat of climate change. The study demonstrates the potential of GEE and machine learning techniques in assessing fire susceptibility and managing wildfire risks.