Detailed urban land use information is the prerequisite and foundation for implementing urban land policies and urban land development, and is of great importance for solving urban problems, assisting scientific and rational urban planning. The existing results of urban land use mapping have shortcomings in terms of accuracy or recognition scale, and it is difficult to meet the needs of fine urban management and smart city construction. This study aims to explore approaches that mapping urban land use based on multi-source data, to meet the needs of obtaining detailed land use information and, taking Lanzhou as an example, based on the previous study, we proposed a process of urban land use classification based on multi-source data. A combination road network dataset of Gaode and OpenStreetMap (OSM) was synthetically applied to divide urban parcels, while multi-source features using Sentinel-2A images, Sentinel-1A polarization data, night light data, point of interest (POI) data and other data. Simultaneously, a set of comparative experiments were designed to evaluate the contribution and impact of different features. The results showed that: (1) the combination utilization of Gaode and OSM road network could improve the classification results effectively. Specifically, the overall accuracy and kappa coefficient are 83.75% and 0.77 separately for level I and the accuracy of each type reaches more than 70% for level II; (2) the synthetic application of multi-source features is conducive to the improvement of urban land use classification; (3) Internet data, such as point of interest (POI) information and multi-time population information, contribute the most to urban land use mapping. Compared with single-moment population information, the multi-time population distribution makes more contributions to urban land use. The framework developed herein and the results derived therefrom may assist other cities in the detailed mapping and refined management of urban land use.

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.

Groundwater serves as a crucial resource, with its quality significantly impacted by both natural and human-induced factors. In the highly industrialized and urbanized Yangtze River Delta region, the sources of pollutants in shallow groundwater are more complex, making the identification of groundwater pollution sources a challenging task. In this study, 117 wells in Wujiang District of Suzhou City were sampled, and 16 groundwater quality parameters were analyzed. The fuzzy synthetic evaluation method was used to assess the current status of groundwater pollution in the study area; the principal component analysis (PCA) was employed to discern the anthropogenic and natural variables that influence the quality of shallow groundwater; and the absolute principal component scores–multiple linear regression (APCS-MLR) model was applied to quantify the contributions of various origins toward the selected groundwater quality parameters. The results indicate that the main exceeding indicators of groundwater in Wujiang District are I ($28\%$), $N{H}_4\text{-}N$ ($18\%$), and Mn ($14\%$); overall, the groundwater quality is relatively good in the region, with localized heavy pollution: class IV and class V water are mainly concentrated in the southwest of Lili Town, the north of Songling Town, and the south of Qidu Town. Through PCA, five factors contributing to the hydrochemical characteristics of groundwater in Wujiang District were identified: water–rock interaction, surface water–groundwater interaction, sewage discharge from the textile industry, urban domestic sewage discharge, and agricultural non-point source pollution. Additionally, the APCS-MLR model determined that the contributions of the three main pollution sources to groundwater contamination are in the following order: sewage discharge from the textile industry ($10.63\%$) > urban domestic sewage discharge ($8.69\%$) > agricultural non-point source pollution ($6.26\%$).

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.