Land cover classification (LCC) of heterogeneous mining areas is important for understanding the influence of mining activities on regional geo-environments. Hyperspectral remote sensing images (HSI) provide spectral information and influence LCC. Convolutional neural networks (CNNs) improve the performance of hyperspectral image classification with their powerful feature learning ability. However, if pixel-wise spectra are used as inputs to CNNs, they are ineffective in solving spatial relationships. To address the issue of insufficient spatial information in CNNs, capsule networks adopt a vector to represent position transformation information. Herein, we combine a clustering-based band selection method and residual and capsule networks to create a deep model named ResCapsNet. We tested the robustness of ResCapsNet using Gaofen-5 Imagery. The images covered two heterogeneous study areas in Wuhan City and Xinjiang Province, with spatially weakly dependent and spatially basically independent datasets, respectively. Compared with other methods, the model achieved the best performances, with averaged overall accuracies of 98.45 and 82.80% for Wuhan study area, and 92.82 and 70.88% for Xinjiang study area. Four transfer learning methods were investigated for cross-training and prediction of those two areas and achieved good results. In summary, the proposed model can effectively improve the classification accuracy of HSI in heterogeneous environments.

Desertification is one of the most critical environmental and socioeconomic issues in the world today. Located in the transitional region between the desert and the Loess Plateau, the Mu Us Sandy Land is one of the nine most environmentally sensitive areas in the world. Remote sensing provides an effective technical method for desertification monitoring. In order to analyze the spatiotemporal distribution of desertification in the Mu Us Sandy Land from 1991 to 2021, the “MSAVI-Albedo” model was employed to extract desertification data in 1991, 2002, 2009 and 2021. The clustering characteristics of desertification were analyzed based on Moran’s I statistic. Subsequently, the driving forces in desertification changes were investigated using a geographical detector to analyze the influence of soil, meteorology, and topography on desertification. Additionally, the impact of meteorological and human factors on desertification change in the Mu Us Sandy Land was assessed. From 1991 to 2021, the degree of desertification of the Mu Us Sandy Land showed an overall decreasing trend, and the percentage of land classified as undergoing extremely severe, severe, moderate and mild desertification was improved by 86.11%, 81.82%, 52.5% and 37.42%, respectively. The proportion of land classified as undergoing extremely severe desertification decreased from 29.22% to 5.62%, and the proportion of land undergoing no desertification increased from 4.16% to 18.33%. At the same time, the desertification center shifted westward, and the desertification distribution showed a clustering trend. It is known that different factors affect the formation and distribution of desertification in the Mu Us Sandy Land in the following order: soil, meteorology, and topography. Over the past 30 years, the mean annual temperature and annual precipitation increased at rates of 0.01871 °C/a and 1.0374 mm/a, respectively, while the mean annual wind speed decreased at a rate of 0.00945 m/s·a. These changes provided more favorable natural conditions for vegetation growth and sand fixation. Human factors, such as economic development, agriculture and animal husbandry practices, and the policy of returning farmland to forest (grassland) also had a significant impact on the desertification process, leading to a year-by-year improvement in the ecological environment of the Mu Us Sandy Land.

Under the combined effects of climate change, overexploitation, and intense grazing, temperate steppe in northern China is experiencing increasing deterioration, which is typified by a shift from structural degradation to functional disruption. Accurately tracking steppe degradation using remote sensing technology has emerged as a crucial scientific concern. Prior research failed to integrate ecosystem structure and function and lacked reference baselines, relying only on individual indicators to quantify degradation. To resolve these gaps, this study established a novel degradation evaluation index system integrating ecosystem structure and function, incorporating vegetation community distribution and proportions of degradation-indicator species to define reference states and quantify degradation severity. Analyzed spatiotemporal evolution and drivers across the temperate typical steppe (2013–2022). Key findings reveal (1) non-degraded and slightly degraded areas dominated (75.57% mean coverage), showing an overall fluctuating improvement trend; (2) minimal transitions between degradation levels, with stable conditions prevailing (59.52% unchanged area), indicating progressive degradation reversal; and (3) natural factors predominated as degradation drivers. The integrated structural–functional framework enables more sensitive detection of early degradation signals, thereby informing more effective steppe restoration management.

The North China Craton (NCC) experienced extensive destruction and modification of its subcontinental lithospheric mantle during the Mesozoic, a period marked by intensive tectonism, magmatism, and mineralization. Among the key manifestations of this event are the Shizhuzi magmatic complex (SMC) and related Mo-Cu-Au deposits in the Liaodong Peninsula. This study presents new zircon U-Pb ages and Hf isotope data, along with whole-rock major and trace element geochemical data. Meanwhile, by incorporating published datasets, the magmatism and mineralization of the SMC are discussed. Two-stage magmatic activity is identified in the SMC as follows: (1) Stage I (130–126 Ma) associated with mineralization, and (2) Stage II (121–117 Ma), both corresponding to the peak destruction of the NCC. The mineralized granitoids exhibit I-type affinities and formed in an extension setting. Quartz diorites within this suite were derived from the partial melting of an enriched mantle source, and the high-temperature thermal underplating associated with this process subsequently triggered partial melting of the basaltic lower crust, leading to the generation of granodiorites and monzonitic granites. These rocks experienced limited fractional crystallization (dominated by plagioclase + biotite) and are linked to Mo-Cu-Au mineralization. In contrast, the non-mineralized granitoids are high-K calc-alkaline, peraluminous A-type granites, which developed in an extremely extensional tectonic setting. They were derived from partial melting of ancient lower crust and display characteristics of highly fractionated granites, having undergone extensive crystallization differentiation involving plagioclase + K-feldspar during magmatic evolution. The mineralized and non-mineralized granitoids exhibit distinct differences in lithology, major/trace element characteristics, Hf isotopes, and degree of fractional crystallization. Our proposed two-stage magmatic model—coupled with a mineralization phase—provides significant insights into both magmatic processes and metallogenesis in the Liaodong Peninsula. It further offers key perspectives into the Early Cretaceous decratonization of the NCC in terms of its tectonic–magmatic–mineralization evolution.

Ecosystem vulnerability assessment is paramount for local environmental stability and lasting economic progress. This study selects Hubei Province as the research area, applying multi-source spatiotemporal datasets spanning the period 2000–2023. A pressure–state–response (PSR) framework, incorporating 14 distinct indicators, was developed. The selection criteria for these indicators adhered to principles of scientific rigor, all-encompassing scope, statistical representativeness, and practical applicability. The chosen indicators effectively encompass natural, anthropogenic, and socio-economic drivers, aligning with the specific ecological attributes and key vulnerability factors pertinent to Hubei Province. The analytic network process (ANP) method and entropy weighting (EW) method were integrated to ascertain comprehensive weights, thereby computing the ecological vulnerability index (EVI). In the meantime, we analyzed temporal and spatial EVI shifts. Spatial autocorrelation analysis, the geodetic detector, the Theil–Sen median, the Mann–Kendall trend test, and the Grey–Markov model were employed to elucidate spatial distribution, driving factors, and future trends. Results indicate that Hubei Province exhibited mild ecological vulnerability from 2000 to 2023, but with a notable deteriorating trend: extreme vulnerability areas expanded from 0.34% to 0.94%, while moderate and severe vulnerability zones also increased. Eastern regions demonstrate elevated vulnerability, but they were lower in the west, correlating with human activity intensity. The global Moran’s I index ranged from 0.8579 to 0.8725, signifying a significant positive spatial correlation of ecological vulnerability, with the highly vulnerable areas concentrated in regions with intense human activities, while the less vulnerable areas are located in ecologically intact areas. Habitat quality index and carbon sinks emerged as key drivers, possibly stemming from the forest–wetland composite ecosystem’s high dependence on water conservation, biodiversity maintenance, and carbon storage functions. Future projections based on Grey–Markov models indicate that ecological fragility in Hubei Province will exhibit an upward trend, with ecological conservation pressures continuing to intensify. This research offers a preliminary reference basis of grounds for ecological zoning, as well as sustainable regional development in Hubei Province, while also providing a theoretical and practical framework for constructing an ecological security pattern within the Yangtze River Economic Belt (YREB) and facilitating ecological governance in analogous river basins globally, thereby contributing to regional sustainable development goals.

Rare earth elements (REEs) play an important role in emerging renewable energy technology, the production of advanced materials, energy conservation, and high-end manufacturing industries, making them an irreplaceable strategic resource. The diagnostic spectral absorption features of REEs in the visible and near-infrared spectrum can be effectively used for identifying the occurrences of REEs on the Earth’s surface. This study systematically compared three airborne hyperspectral sensors—HyMap, CASI-1500h, and AisaFENIX 1K—for detecting REEs in the Bayan Obo area of Inner Mongolia, China. The CASI-1500h imagery performed most effectively in identifying the locations of REEs among the three sensors evaluated here. Additionally, this study proposed a hyperspectral workflow for REE identification, which enabled the detection of REE-bearing minerals regardless of the host rock types—including carbonatites and associated dikes, fenite-syenites, and metamorphic feldspar-quartz sandstone. Laboratory-based spectroscopy and mineral chemistry analyses indicated that the absorption features of the REE-bearing mineral monazite within the 400–1000 nm range can be ascribed to Nd³⁺. This study demonstrates the potential of airborne hyperspectral technology for efficient and large-scale exploration of REE deposits.