With the influence of climate change and human activities, the frequency and scale of forest fires have been increasing continuously, posing a significant threat to the environment and human safety. Therefore, rapid and accurate forest fire detection has become essential for effective control of forest fires. This study proposes a Forest Fire Detection and Segmentation Model (FFDSM) based on unmanned aerial vehicle (UAV) infrared images to address the problems of forest fire occlusion and the poor adaptability of traditional forest fire detection methods. The FFDSM integrates the YOLO (You Only Look Once) v5s-seg, Efficient Channel Attention (ECA), and Spatial Pyramid Pooling Fast Cross-Stage Partial Channel (SPPFCSPC) to improve the detection accuracy of forest fires of different sizes. The FFDSM enhances the detection and extraction capabilities of forest fire features, enabling the accurate segmentation of forest fires of different sizes and shapes. Furthermore, we conducted ablation and controlled experiments on different attention mechanisms, spatial pyramid pooling (SPP) modules, and fire sizes to verify the effectiveness of the added modules and the adaptability of the FFDSM model. The results of the ablation experiment show that, compared to the original YOLOv5s-seg model, the models fused with the ECA and SPPFCSPC achieve an improved accuracy, with FFDSM showing the greatest improvement. FFDSM achieves a 2.1% increase in precision, a 2.7% increase in recall, a 2.3% increase in mAP@0.5, and a 4.2% increase in mAP@0.5:0.95. The results of the controlled experiments on different attention mechanisms and SPP modules demonstrate that the ECA+SPPFCSPC model (FFDSM) performs the best, with a precision, recall, mAP@0.5, and mAP@0.5:0.95 reaching 0.959, 0.870, 0.907, and 0.711, respectively. The results of the controlled experiment on different fire sizes show that FFDSM outperforms YOLOv5s-seg for all three fire sizes, and it performs the best for small fires, with a precision, recall, mAP@0.5, and mAP@0.5:0.95 reaching 0.989, 0.938, 0.964, and 0.769, respectively, indicating its good adaptability for early forest fire detection. The results indicate that the forest fire detection model based on UAV infrared images (FFDSM) proposed in this study exhibits a high detection accuracy. It is proficient in identifying obscured fires in optical images and demonstrates good adaptability in various fire scenarios. The model effectively enables real-time detection and provides early warning of forest fires, providing valuable support for forest fire prevention and scientific decision making.

Healthy soil is the key foundation of the world’s agriculture and an essential resource to ensure the world’s food security. Soil erosion is one of the serious forms of soil degradation and a major threat to sustainable terrestrial ecosystems. In this study, we utilized a continuous Landsat satellite image dataset to map soil erosion changes (1990–2020) based on the RUSLE model across the Pearl River Basin. The study results indicated that: (1) The multi-year area-specific soil erosion average in the Pearl River Basin is approximately 538.95 t/(km²·a) with an annual soil loss of approximately 353 million tons; (2) The overall soil erosion displayed a decreasing trend over the past 30 years with an annual decreasing rate of −13.44(±1.53) t/(km²·a); (3) Soil erosion, dominated by low- and moderate-level erosion, primarily occurred in the tributary basin of Xijiang River, especially in the areas with slopes > 15°, low vegetation coverage, or poorly managed forests; (4) the NDVI and land cover were the dominant factors regulating soil erosion dynamics versus the insignificant role of precipitation played in the erosion procedure. The study results are valuable for soil erosion management and water conservation in the Pearl River Basin.

In recent decades, global climate change has made natural hazards increasingly prevalent. Droughts, as a common natural hazard, have been a hot study topic for years. Most studies conducted drought monitoring in arid and semi-arid regions. In humid and sub-humid regions, due to climate change, seasonal droughts and seasonal water shortages were often observed too, but have not been well studied. This study, using a MODIS satellite-based aridity index (SbAI), investigated spatiotemporal changes in drought conditions in the subtropical Pearl River Basin. The study results indicated that the inter-annual SbAI exhibited a significant decreasing trend, illustrating a wetter trend observed in the basin in the past two decades. The decreasing trend in the SbAI was statistically significant in the dry season, but not in the monsoon season. The drought conditions displayed an insignificant expansion in the monsoon season, but exhibited statistically significant shrinking in the dry season. The Pearl River Basin has become wetter over past two decades, probably due to the results of natural impacts and human activities. The areas with increased drought conditions are more likely impacted by human activities such as water withdrawal for irrigation and industrial uses, and fast urbanization and increased impervious surfaces and resultant reduction in water storage capacity. This study provided a valuable reference for drought assessment across the Pearl River Basin.

Precipitation is a key component of the hydrological cycle and one of the important indicators of climate change. Due to climate change, extreme precipitation events have globally and regionally increased in frequency and intensity, leading to a higher probability of natural disasters. This study, using the long-term APHRODITE dataset, employed six precipitation indices to analyze the spatiotemporal changes in extreme precipitation in the Pearl River Basin during 1951–2015. The Mann–Kendall (M–K) test was used to verify the significance of the observed trends. The results indicate that: (1) the interannual PRCPTOT showed a trend with an average positive increase of 0.019 mm/yr, which was followed by an increase in SDII, R95P, and RX1day, and a decrease in R95D and CWD; seasonal PRCPTOT also displayed an increase in summer and winter and a decrease in spring and autumn, corresponding to increases in R95P and SDII in all seasons. (2) The annual precipitation increases from the west to east of the basin, similar to the gradient distribution of SDII, R95P and RX1day, with the high R95D happening in the middle and lower reaches of the Xijiang River, but the CWD increased from the north to south of the basin. The seasonal spatial distributions of PRCPTOT, SDII, and R95P are relatively similar except in autumn, showing an increase from the west to east of the basin in spring and winter and a gradual increase from the north to south of the basin in summer, indicating that the Beijiang and Dongjiang tributary basins are more vulnerable to floods. (3) The MK test results exhibited that the Yunnan–Guizhou Plateau region in the upper reaches of the Xijiang River Basin became drier, and there was an increase in extreme precipitation in the Beijiang and Dongjiang river basins. The study results facilitate valuable flood mitigation, natural hazard control and water resources management in the Pearl River Basin.

An efficient monitoring of forest fire risk and its dynamic changes is an important way to prevent and reduce forest fire hazards. This study integrated the ignition effect of fire sources and the impact of landform into the calculation of forest fire risk using digital-terrain-slope factor, and developed an optimized forest fire risk model (fire-potential-index slope, FPIS). Combined with Landsat 8 satellite images, the study retrieved and analyzed the variations of forest fire risk in Zhaoqing City, Guangdong province, for four consecutive periods in the dry season, 2019. It was found that the high forest fire risk area was mainly distributed in the valley plains of Huaiji district, Fengkai district and Guangning district, the depressions of the Sihui district, and mountain-edge areas of Dinghu district and Gaoyao district, and accounted for 8.9% on 20 October but expanded to 19.89% on 7 December 2019. However, the further trend analysis indicated that the forest fire risk with significant increasing trend only accounted for 6.42% in Zhaoqing. Compared to the single high forest fire risk results, the changing trend results effectively narrowed the key areas for forest fire prevention (2.48%–12.47%) given the actual forest fires in the city. For the four forest fire events (Lingshan mountain, Hukeng industrial area, Xiangang county and Huangniuling ridge forest fires), it was found that the forest fire risk with significant increasing trend in these regions accounted for 26.63%, 35.84%, 54.6% and 73.47%, respectively, which further proved that the forest fire risk changing trend had a better indicated significance for real forest fire events than the high forest fire risk results itself (1.89%–71.69%). This study suggested that the forest fire risk increasing trend could be well used to reduce the probability of misjudgment and improve the accuracy of the early-warning areas when predicting forest fires.