The Karst region is a critical ecological barrier and functional zone in China. Understanding the spatiotemporal evolution of its ecosystem services and its relationship with human activities and climate change is of importance for achieving regional ecological protection and high-quality development. In this study, we used the InVEST model and CASA model to evaluate the spatiotemporal evolution pattern of ecosystem services in the study area from 2000 to 2020. The XGBoost–SHAP model was used to reveal the key indicators and thresholds of changes in major ecosystem services in the study area due to climate change and human activities. The results showed significant land use changes in the study area from 2000 to 2020, particularly the conversion of cropland to construction land, which was more intense in economically developed areas. The areas of forest and grassland increased initially but later decreased due to the impact of human activities and natural factors. Habitat quality (HQ) showed an overall declining trend, while soil retention (SR) and water yield (WY) services exhibited significant interannual variations due to climate change. The changes in rainfall had a particularly notable impact on these services; in years with excessive rainfall, soil erosion intensified, leading to a decline in SR services, whereas in years with moderate rainfall, SR and WY services improved. Carbon fixation (CF) services were enhanced with the expansion of forest areas. The XGBoost–SHAP model further revealed that the effects of rainfall and sunshine duration on ecosystem services were nonlinear, while population density and the proportion of construction land had a significant negative impact on habitat quality and soil retention. The expansion of construction land had the most significant negative impact on habitat quality, whereas the increase in forest land significantly improved carbon fixation and the soil retention capacity. By revealing the mechanisms of the impact of climate change and human activities on ecosystem services, we aimed to provide support for the promotion of ecological conservation and sustainable development strategies in the study area, as well as to provide an important reference for areas with geographic similarities to the study area.

Exploring the spatio-temporal differentiation characteristics and coupling coordination relationship of the composite ecosystem of urban agglomerations is of great significance for promoting the synergistic sustainable development and integration construction of urban agglomerations. This paper is based on LUCC (Land Use and Land Cover Change) data, a DEM (Digital Elevation Model), and temperature, precipitation, and other multi-source data, using the central Yunnan urban agglomeration as an example and constructing a multi-dimensional evaluation index system highlighting development quality and efficiency. The entropy weight method was first used to determine the comprehensive weights to evaluate the regional economic and social development level. Then, the InVEST (Integrated Valuation of Ecosystem Services and Trade-offs) model was used to quantitatively calculate and analyze the spatial and temporal evolution characteristics of the four key ecosystem services, evaluating the spatio-temporal evolution characteristics of the natural subsystem. The coupling coordination model was used to quantitatively analyze the evolution of the coupling coordination of the composite ecosystems in the central Yunnan urban agglomeration during the period of 2010–2020, and to reveal its development law. The results show the following: ➀ During the study period, the socio-economic subsystems in the central Yunnan urban agglomeration demonstrated an outward radiative growth from Kunming City, marked by underdeveloped sub-centers and prevalent low-level areas. ② Trends in ecosystem services varied, with water and soil conservation showing fluctuating increases, carbon sequestration remaining stable, and habitat quality declining. The critically important integrated ecosystem services zone of the natural subsystem is mainly located in the northeastern region and southwestern edge of the study area. ③ In 2020, the coupling coordination degree of the composite ecosystem was 0.9492. This showed that economic, social, and ecological subsystems are highly coupled, with consistent overall development trends and strong interactions. ④ The increase in the degree of harmonization amounted to 7.82%, with lagging subsystems varying in the degree of harmonization in subregions. This study can provide a scientific foundation for the development of policies for the Central Yunnan urban agglomeration, promoting regional sustainable development and optimizing the spatial pattern of the national territory.

With the popularity of spatiotemporal big data applications, more and more sensitive data are generated by users, and the sharing and secure storage of spatiotemporal big data are faced with many challenges. In response to these challenges, the present paper puts forward a new technology called CSSoB (Classified Secure Storage Technology over Blockchain) that leverages blockchain technology to enable classified secure storage of spatiotemporal big data. This paper introduces a twofold approach to tackle challenges associated with spatiotemporal big data. First, the paper proposes a strategy to fragment and distribute space–time big data while enabling both encryption and nonencryption operations based on different data types. The sharing of sensitive data is enabled via smart contract technology. Second, CSSoB’s single-node storage performance was assessed under local and local area network (LAN) conditions, and results indicate that the read performance of CSSoB surpasses its write performance. In addition, read and write performance were observed to increase significantly as the file size increased. Finally, the transactions per second (TPS) of CSSoB and the Hadoop Distributed File System (HDFS) were compared under varying thread numbers. In particular, when the thread number was set to 100, CSSoB demonstrated a TPS improvement of 7.8% in comparison with HDFS. Given the remarkable performance of CSSoB, its adoption can not only enhance storage performance, but also improve storage security to a great extent. Moreover, the fragmentation processing technology employed in this study enables secure storage and rapid data querying while greatly improving spatiotemporal data processing capabilities.

The issue of abandoned cropland poses a significant threat to national food security and the sustainable use of land resources, highlighting the urgent need for an efficient and interpretable remote sensing identification framework. This study integrates three authoritative land cover datasets—the European Space Agency WorldCover (ESA), the Environmental Systems Research Institute Land Cover (ESRI), and the China Resource and Environment Data Cloud Platform (CRLC). Multi-source remote sensing features were extracted using the Google Earth Engine platform, and high-quality training samples were constructed by randomly selecting sample points based on these features in ArcGIS. A recursive feature cross-validation method is employed to eliminate redundant variables, thereby optimizing the feature structure without compromising classification accuracy. In terms of model construction, a multi-objective optimization strategy combining the Non-dominated Sorting Genetic Algorithm II (NSGA-II) and eXtreme Gradient Boosting (XGBoost) is proposed. By incorporating a pruning mechanism, computational efficiency is significantly improved—accelerating the identification speed by up to 75%—while maintaining model accuracy (OA: 0.9817; Kappa: 0.9633; F1-score: 0.9817; recall: 0.9866). For result interpretation, the SHapley Additive exPlanations (SHAP) method is used to evaluate global feature importance, revealing that variables such as SAVG, B3_p25, Road, DEM, and Population contribute most significantly to the identification of abandoned cropland. Meanwhile, the Local Interpretable Model-Agnostic Explanations (LIME) method is applied to conduct local interpretability analysis on typical samples. The results show that, while some samples share consistent dominant features with the global results, others exhibit stronger local influences from features such as slope and SAVG. The combination of SHAP and LIME for global–local interpretability provides insight into the heterogeneous drivers of cropland abandonment and enhances the transparency of the classification model. This study presents a practical, scalable framework for the rapid identification and management of abandoned cropland, balancing precision, interpretability, and efficiency.

Accurate identification of cultivated land in plateau and mountainous regions remains challenging due to complex terrain and the fragmented, small-scale distribution of farmland. This study develops a high-precision cropland identification model tailored to such environments, aiming to advance precision agriculture and support the scientific planning and refined management of agricultural resources. Taking Xundian County, Yunnan Province, as a case study, multispectral, synthetic aperture radar (SAR), topographic, texture, and time-series features were integrated to construct a comprehensive multi-source feature space. A baseline land use map was generated by fusing datasets from the European Space Agency (ESA), the Environmental Systems Research Institute (ESRI), and the China Resource and Environment Data Cloud (CRLC). Using 4000 randomly selected sample points, five machine learning algorithms—Support Vector Machine (SVM), Random Forest (RF), Tabular Multiple Prediction (TABM), XGBoost, and the NSGA-II optimized XGBoost (NSGA-II-XGBoost)—were compared for cropland identification. Results show that the NSGA-II-XGBoost model consistently achieved superior performance in classification accuracy, stability, and adaptability, reaching an overall accuracy of 95.75%, a Kappa coefficient of 0.91, a recall of 0.96, and an F1-score of 0.96. These findings demonstrate the strong capability of the NSGA-II-XGBoost model for cropland mapping under complex topographic conditions, providing a robust technical framework and methodological reference for farmland protection and natural resource classification in other mountainous regions.

Spatiotemporal big data are a kind of data that marks time information and geographic location and has been widely applied in various fields. However, there are always security issues with spatiotemporal big data, especially in data collection and authentication. Traditional authentication protocols are less efficient in the face of ultra-large-scale IoT (Internet of Things, IoT) device verification, and the threat of single-point failure is relatively large. Given these complications, a group authentication scheme is proposed in this paper with blockchain spatiotemporal big data. The decentralization of the blockchain is utilized to solve the single point of failure, and the single-point authentication is combined with the group authentication, the authentication efficiency is improved through the group authentication, and the illegal nodes are accurately identified using the single-point authentication. The simulation results demonstrate that using the MHT (Merkel Hash Tree, MHT) algorithm for group authentication can effectively improve the authentication efficiency of the entire system when the number of users exceeds 200. The time overhead is only 4 ms when the number of users is 16,000. It can have a large throughput (400–500 tps) and a low latency (1–2 s) at the same time when the block size is 1500 KB. This study not only verifies the legitimacy of each device and protects the security of spatiotemporal big data, but also significantly reinforces the authentication efficiency compared with similar schemes.