Retrieval Model for Surface Dead Fuel Moisture Data Based on Microwave Soil Moisture Content

Wildfires are natural disasters that pose substantial threats to the environment. The accurate prediction of wildfire risk levels and timely implementation of effective mitigation measures are critical for wildfire prevention and ecological security maintenance. Fuel moisture content is an important factor affecting the spread and intensity of wildfires; however, there is currently a lack of large-scale data on surface dead fuel moisture content (DFMC). Therefore, in this study, we aimed to develop a more accurate method for retrieving DFMC by integrating multi-source satellite remote sensing data with machine learning algorithms. Evaluation of six retrieval models (extreme gradient boosting [XGB], linear regression [LR], generalized additive model [GAM], random forest [RF], convolutional neural network [CNN], and long short-term memory [LSTM]) confirmed the adaptability of XGB to four forest types, achieving an average R² value of 0.78. In addition, we used SHAP analysis to assess the importance of the model's influencing factors and identified the significance of soil moisture content (SMC) and evapotranspiration. Furthermore, comparative analysis of four input parameter combinations confirmed the pivotal role of SMC, with the integrated use of ERA5-Land reanalysis data and SMC data achieving optimal model performance while balancing large-scale applicability with accuracy. Additionally, a daily DFMC dataset for the Greater Khingan Mountains was constructed by integrating SMAP soil moisture data, ERA5 meteorological data, and the XGB model. In this study, we innovatively combined microwave remote sensing data with machine learning to provide a robust methodological framework for DFMC data retrieval via microwave remote sensing. Our results establish a foundation for enhancing the precision of forest fire risk early warning systems.