Understanding the coupling among drought, water content of the soil, and forest fires is essential in the fire risk study framework

In this context, improved wildfires prediction tools, such as risk, severity, burnt area, are urgently needed and in this work, the use of remotely sensed and in-situ sensed soil moisture (SM) data, as well as land surface temperature (LST) as key variables in the climate-wildfires relationship is explored. Therefore a vital need is to increase the quantity and quality of available information at relevant spatiotemporal scales, which will be accomplished through an integrated space and ground sensing grid for estimating SM, LST, and other climate variables. Space data will consist of commercial data spanning superspectral, thermal IR, hyperspectral, SAR (microwave radar) as well as data provided by NASA use of funding: 1.understand the relationship between soil moisture and land surface temperature on wildfire risk and burnt area through statistical and AI / deep learning methods 2. Determine stakeholder information requirements 3. Develop a real-time simulation window to disseminate ensembled model results to the users. Deliverables: analytical software, report & training to fire agencies