Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) is a new remote-sensing technique, and it can be used to estimate near-surface soil moisture from Signal-to-Noise Ratio (SNR) data. Considering the effects of vegetation changes on GNSS-IR in some environments, a non-linear inversion method for soil moisture is proposed. Firstly, the SNR data and satellite elevation angles are solved using Translation, Editing, and Quality Checking. The direct and reflected signals are separated using a low-order polynomial; then, a sinusoidal fitting model of the reflection signal is established; it is used to obtain the amplitude and phase of the SNR interferogram. Finally, an estimation model of vegetation water content and prediction model of the vegetation phase changes are established to modify the original phase and weaken the influence on the vegetation changes. Based on the corrected phase, a Genetic Algorithm Back Propagation Neural Network (BPNN) model is established for soil moisture inversion. According to the GPS monitoring data from the Plate Boundary Observatory H2O network, the experiment indicates that (1) The BPNN is introduced to inverse the soil moisture content, and the non-linear fitting ability of the model is well developed, and the fitting process is stable; (2) the modified phase effectively reduced the effects of vegetation changes on the soil moisture inversion. The correlation coefficient (r) between the inversion results and soil moisture value greatly improved, and the root mean square error and mean absolute error are less than 0.060 and 0.050, respectively. Therefore, the soil moisture problem can be treated as a non-linear event, and the algorithm is feasible and effective.

The frequent occurrence and spread of wildfires pose a serious threat to the ecological environment and urban development. Therefore, assessing regional wildfire susceptibility is crucial for the early prevention of wildfires and formulation of disaster management decisions. However, current research on wildfire susceptibility primarily focuses on improving the accuracy of models, while lacking in-depth study of the causes and mechanisms of wildfires, as well as the impact and losses they cause to the ecological environment and urban development. This situation not only increases the uncertainty of model predictions but also greatly reduces the specificity and practical significance of the models. We propose a comprehensive evaluation framework to analyze the spatial distribution of wildfire susceptibility and the effects of influencing factors, while assessing the risks of wildfire damage to the local ecological environment and urban development. In this study, we used wildfire information from the period 2013–2022 and data from 17 susceptibility factors in the city of Guilin as the basis, and utilized eight machine learning algorithms, namely logistic regression (LR), artificial neural network (ANN), K-nearest neighbor (KNN), support vector regression (SVR), random forest (RF), gradient boosting decision tree (GBDT), light gradient boosting machine (LGBM), and eXtreme gradient boosting (XGBoost), to assess wildfire susceptibility. By evaluating multiple indicators, we obtained the optimal model and used the Shapley Additive Explanations (SHAP) method to explain the effects of the factors and the decision-making mechanism of the model. In addition, we collected and calculated corresponding indicators, with the Remote Sensing Ecological Index (RSEI) representing ecological vulnerability and the Night-Time Lights Index (NTLI) representing urban development vulnerability. The coupling results of the two represent the comprehensive vulnerability of the ecology and city. Finally, by integrating wildfire susceptibility and vulnerability information, we assessed the risk of wildfire disasters in Guilin to reveal the overall distribution characteristics of wildfire disaster risk in Guilin. The results show that the AUC values of the eight models range from 0.809 to 0.927, with accuracy values ranging from 0.735 to 0.863 and RMSE values ranging from 0.327 to 0.423. Taking into account all the performance indicators, the XGBoost model provides the best results, with AUC, accuracy, and RMSE values of 0.927, 0.863, and 0.327, respectively. This indicates that the XGBoost model has the best predictive performance. The high-susceptibility areas are located in the central, northeast, south, and southwest regions of the study area. The factors of temperature, soil type, land use, distance to roads, and slope have the most significant impact on wildfire susceptibility. Based on the results of the ecological vulnerability and urban development vulnerability assessments, potential wildfire risk areas can be identified and assessed comprehensively and reasonably. The research results of this article not only can improve the specificity and practical significance of wildfire prediction models but also provide important reference for the prevention and response of wildfires.

Obtaining high-precision, long-term sequences of vegetation water content (VWC) is of great significance for assessing surface vegetation growth, soil moisture, and fire risk. In recent years, the global navigation satellite system-interferometric reflection (GNSS-IR) has become a new type of remote sensing technology with low cost, all-weather capability, and a high temporal resolution. It has been widely used in the fields of snow depth, sea level, soil moisture content, and vegetation water content. The normalized microwave reflectance index (NMRI) based on GNSS-IR technology has been proven to be effective in monitoring changes in VWC. This paper considers the advantages and disadvantages of remote sensing technology and GNSS-IR technology in estimating VWC. A point-surface fusion method of GNSS-IR and MODIS data based on the GA–BP neural network is proposed to improve the accuracy of VWC estimation. The vegetation index products (NDVI, GPP, LAI) and the NMRI that unified the temporal and spatial resolution were used as the input and output data of the training model, and the GA–BP neural network was used for training and modeling. Finally, a spatially continuous NMRI product was generated. Taking a particular area of the United States as a research object, experiments show that (1) a neural network can realize the effective fusion of GNSS-IR and MODIS products. By comparing the GA–BP neural network, BP neural network, and multiple linear regression (MLR), the three models fusion effect. The results show that the GA–BP neural network has the best modeling effect, and the r and RMSE between the model estimation result and the reference value are 0.778 and 0.0332, respectively; this network is followed by the BP neural network, in which the r and RMSE are 0.746 and 0.0465, respectively. MLR has the poorest effect, with r and RMSE values of 0.500 and 0.0516, respectively. (2) The spatiotemporal variation in the 16 days/500 m resolution NMRI product obtained by GA–BP neural network fusion is consistent with that in the experimental area. Through the testing of GNSS stations that did not participate in the modeling, the r between the estimated value of the NMRI and the reference value is greater than 0.87, and the RMSE is less than 0.049. Therefore, the method proposed in this paper is optional and effective. The spatially continuous NMRI products obtained by fusion can reflect the changes in VWC in the experimental area more intuitively.

Precipitable water vapor (PWV) plays a vital role in climate research, especially for Antarctica in which meteorological observations are insufficient due to the adverse climate and topography therein. Reanalysis data sets provide a great opportunity for Antarctic water vapor research. This study investigates the climatological PWV means, variability and trends over Antarctica from four reanalyses, including the fifth generation of European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis (ERA5), the Second Modern-Era Retrospective analysis for Research and Applications (MERRA-2), Japanese 55-year Reanalysis (JRA-55) and National Centers for Environmental Prediction/Department of Energy (NCEP/DOE), in the period of 2001–2018 based on radiosonde and GNSS observations. PWV data from the ERA5, MERRA-2, JRA-55 and NCEP/DOE have been evaluated by radiosonde and GNSS observations, showing that ERA5 and MERRA-2 perform better than JRA-55 and NCEP/DOE with mean root mean square (RMS) errors below 1.2 mm. The climatological PWV mean distribution over Antarctica roughly shows a decreasing trend from west to east, with the highest content in summer and the lowest content in winter. The PWV variability is generally small over Antarctica, showing a seasonal dependence that is larger in the cold season and smaller in the warm season. PWV trends for all reanalyses at most Antarctic regions are insignificant and most reanalyses present overall drying trends from 2001 to 2018, except for ERA5 exhibiting a moistening trend. PWV trends also show seasonal and regional dependence. All reanalyses are generally consistent with radiosonde and GNSS observations in reproducing the PWV means (mean differences within 1.1 mm), variability (mean differences within 3%) and trends (mean differences within 6.4% decade⁻¹) over Antarctica, except for NCEP/DOE showing spurious variability and trends in East Antarctica. Results can help us further understand these four reanalysis PWV products and promote climate research in Antarctica.