Geological disaster could pose a great threat to human development and ecosystem health. An ecological risk assessment of geological disasters is critical for ecosystem management and prevention of risks. Herein, based on the “probability-loss” theory, a framework integrating the hazard, vulnerability, and potential damage for assessing the ecological risk of geological disasters was proposed and applied to Fujian Province. In the process, a random forest (RF) model was implemented for hazard assessment by integrating multiple factors, and landscape indices were adopted to analyze vulnerability. Meanwhile, ecosystem services and spatial population data were used to characterize the potential damage. Furthermore, the factors and mechanisms that impact the hazard and influence risk were analyzed. The results demonstrate that (1) the regions exhibiting high and very high levels of geological hazard cover an area of 10.72% and 4.59%, respectively, and are predominantly concentrated in the northeast and inland regions, often distributed along river valleys. Normalized difference vegetation index (NDVI), precipitation, elevation, and slope are the most important factors for the hazard. (2) The high ecological risk of the study area shows local clustering and global dispersion. Additionally, human activities have a significant influence on ecological risk. (3) The assessment results based on the RF model have high reliability with a better performance compared with the information quantity model, especially when identifying high-level hazard areas. Our study will improve research on the ecological risk posed by geological disasters and provide effective information for ecological planning and disaster mitigation.

As the global population increases and cities expand, increasing social needs and ecosystem degradation generally coexist, especially in China’s urban agglomerations. Identifying ecological security patterns (ESPs) for urban agglomerations serves as an effective way to sustain regional ecological security and promote harmonious ecological conservation and economic development. Focusing on the Fujian Delta Urban Agglomeration (FDUA) as an example, this study aims to present a framework for linking the supply and demand of ecosystem services (ESs) to identify ESPs in 2020. First, the ecological sources are delimited by coupling the supply and demand of four critical ESs (carbon storage, water provision, grain production, and outdoor recreation). Afterward, the resistance coefficient is modified using nighttime light intensity data and the ecological risk index, the second of which combines the effects of the soil erosion sensitivity index, the geological disaster risk index, and the land desertification risk index. Then, ecological corridors are determined by employing the minimum cumulative resistance method. With the integration of ecological sources and corridors, the ESPs of the FDUA can be identified. The results show a distinct supply–demand mismatch for ESs, with supply exhibiting an upward gradient from coastal cities to inland mountain cities and demand showing the opposite trend. The ESPs consist of 8359 km² of ecological sources that are predominantly forests, 171 ecological corridors with a total length of 789.04 km, 34 pinch points, 26 barriers, and 48 break points. This paper presents a realizable approach for constructing ESPs for urban agglomerations, which will help decision makers optimize ecological sources and ecological protection policies.

The large-scale variation issue in high-resolution aerial images significantly lowers the accuracy of segmenting small objects. For a deep-learning-based semantic segmentation model, the main reason is that the deeper layers generate high-level semantics over considerably large receptive fields, thus improving the accuracy for large objects but ignoring small objects. Although the low-level features extracted by shallow layers contain small-object information, large-object information has predominant effects. When the model, using low-level features, is trained, the large objects push the small objects aside. This observation motivates us to propose a novel reverse difference mechanism (RDM). The RDM eliminates the predominant effects of large objects and highlights small objects from low-level features. Based on the RDM, a novel semantic segmentation method called the reverse difference network (RDNet) is designed. In the RDNet, a detailed stream is proposed to produce small-object semantics by enhancing the output of RDM. A contextual stream for generating high-level semantics is designed by fully accumulating contextual information to ensure the accuracy of the segmentation of large objects. Both high-level and small-object semantics are concatenated when the RDNet performs predictions. Thus, both small- and large-object information is depicted well. Two semantic segmentation benchmarks containing vital small objects are used to fully evaluate the performance of the RDNet. Compared with existing methods that exhibit good performance in segmenting small objects, the RDNet has lower computational complexity and achieves 3.9–18.9% higher accuracy in segmenting small objects.

Landslide susceptibility assessment constitutes a pivotal method of preventing and reducing losses caused by geological disasters. However, traditional models are often influenced by subjective grading factors, which can result in unscientific and inaccurate assessment outcomes. In this study, we thoroughly analyze various landslide causative factors, including geological, topographical, hydrological, and environmental components. A quantitative continuous model was employed, with methods such as frequency ratio (FR), cosine amplitude (CA), information value (IV), and certainty factor (CF) being applied in order to assess the landslide susceptibility of the Wanzhou coastline in the Three Gorges Reservoir area. The results were then compared with methods such as Bias-Standardised Information Value (BSIV), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosted Decision Tree (GBDT). This process led to the following key conclusions: (1) Most landslide susceptibility zones are predominantly banded and clustered on both sides of the Dewuidu River, particularly along the left bank of the Yangtze River from Dewuidu Town to Wanzhou City, as well as in the main urban area of Wanzhou. Clusters of the Yangtze River mainstem and surrounding towns characterize these areas. (2) The enhanced statistical analysis model shows a notable increase in sensitivity to landslides, achieving an Area Under the Curve (AUC) of 0.8878 for the IV model—an improvement of 0.0639 over the traditional BSIV model. This enhancement aligns closely with machine learning capabilities, and the spatial results obtained are more continuous. (3) By substituting manual grading with a quantitative continuous model, we achieve a balance between interpretability and computational efficiency. These findings lay a scientific foundation for the prevention and management of geological disasters in Wanzhou and provide valuable insights for comparable regions undertaking landslide susceptibility assessments.

Accurate landslide susceptibility assessment (LSA) is essential for regional disaster prevention and mitigation planning. Although machine learning and deep learning models have been widely adopted for LSA, their transferability across regions is often compromised by distributional discrepancies between source and target datasets. To address this challenge, we adapted the conditional domain adversarial network (CDAN) framework for cross-regional landslide susceptibility assessment to mitigate domain shift and improve cross-regional robustness. Two cross-regional transfer experiments were conducted to compare CDAN with conventional machine learning, direct-transfer deep learning, and representative domain adaptation methods. The results showed that CDAN achieved the highest mean Accuracy and F1 score among the benchmark models in both target domains, with Accuracy values of 0.77 and 0.80 and F1 scores of 0.78 and 0.80, respectively. The corresponding values of the area under the receiver operating characteristic curve (AUC) were 0.837 and 0.836, respectively. Neighborhood-based spatial information also improved the direct-transfer performance of conventional machine learning models compared with single-pixel representations. These results indicate that the CDAN-based framework can reduce the reliance on labeled target-domain samples and support county-level cross-regional landslide susceptibility assessment under domain shift.

Accurate discrimination between rice and artificial grassland remains challenging in regional agricultural monitoring because both herbaceous types share similar spectral signatures during vegetative growth, and existing land-cover products do not treat artificial grassland as a separate class. Using Jurong City, Jiangsu Province, as the study area, we propose a framework that optimizes red-edge vegetation index selection within crop-specific phenological windows to separate rice from grassland. Using Unmanned Aerial Vehicle (UAV) multispectral imagery and Sentinel-2 satellite data, we quantified spectral separability across eight phenological stages using Fisher ratios. We identified two optimal discrimination windows: early tillering (mid-June) and heading–flowering (early September). Within the heading–flowering window, a dual-index classification rule combining Normalized Difference Red-Edge Index (NDRE) and Green Normalized Difference Vegetation Index (GNDVI) was transferred from UAV to Sentinel-2 and used to produce a 10 m rice–grassland map for the entire city. Spatial agreement with two publicly available rice datasets reached 75.2% and 79.5% for rice pixels, reflecting differences in spatial resolution, reference year, and class definition rather than classification error. Independent field validation using 200 samples yielded an overall accuracy of 92.50% (F1-score = 0.93), confirming the effectiveness of the VI–window optimization strategy. The framework offers an interpretable, physiology-driven alternative for crop-type mapping that relies solely on widely available multispectral bands.