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.

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.

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.

In large-scale UAV photogrammetry, redundant and weakly correlated image relationships can substantially increase computational costs and reduce matching reliability during SfM reconstruction. To address this issue, this study proposes SC-DFS, a spatial constraint-based image relationship optimization method for efficient UAV image organization and reconstruction. The contribution lies in integrating POS-derived spatial constraints with image relationship graph optimization, where spatial overlap information, image similarity, and F-RANSAC-guided geometric verification are combined to construct weighted image relationships. Subsequently, a depth-first search strategy is employed to extract the connected component containing the largest number of images and optimize the image set for subsequent SfM reconstruction. Experimental results on a large-scale UAV dataset demonstrate that SC-DFS reduces the number of retained images from 2556 to 2274 with visually consistent overall 3D structure. The optimized dataset reduces the sum of the three reported processing-stage times by 2 h and 17 min. The proposed method effectively reduces redundant image relationships, improves image matching efficiency, and provides an efficient solution for large-scale UAV SfM reconstruction in the evaluated acquisition.

To tackle the drawbacks inherent in the Chinese Pangolin Optimization (CPO) algorithm, such as uneven population initialization distribution and a tendency to fall into local optimal solutions, this paper proposes an ACDCPO algorithm that integrates boundary-adaptive contraction initialization, Cauchy inverse cumulative distribution mutation, and dynamic opposition-based learning strategies, which effectively enhances the uniformity of population distribution, improves the ability to jump out of local optimum, and strengthens the adaptive coordination between exploration and exploitation. To validate its performance, the proposed ACDCPO is compared with nine representative algorithms using the CEC2017 and CEC2022 test functions. The results verify that ACDCPO achieves remarkably higher convergence precision and stability than the comparative algorithms. In four typical engineering optimization tasks, ACDCPO shows strong constraint handling ability and engineering adaptability. In addition, based on near-infrared spectrum data, the ACDCPO algorithm optimized the BP network model for the moisture content prediction of Dendrobium huoshanense, and the coefficient of determination (R²) reached 91.211%, which verified the effectiveness of the method in practical applications.

Global climate change and rapid urbanisation exert coupled disturbances on plateau urban agglomerations, where rugged terrain and land-use conversion exacerbate ecological fragmentation and function loss. Most existing research relies on linear analytical frameworks and cannot capture nonlinear ecological shifts, multi-factor coupling feedbacks or stability-transition thresholds for plateau regions; multi-scenario quantitative ecological assessments also remain limited. Taking the Central Yunnan Urban Agglomeration as a case, this study aimed to identify nonlinear ecosystem-service responses and statistically derived ecological breakpoints. Three Shared Socioeconomic Pathway (SSP) scenarios (SSP119, SSP245, SSP585) were integrated into a modelling chain: the Patch-generating Land-Use Simulation (PLUS) model projected 2030 land-use patterns (hindcast: 92.8% overall accuracy (OA), Kappa = 0.8887); the Integrated Valuation of Ecosystem Services and Trade-offs (InVEST) model quantified four key ecosystem services to compute the Multiple-Ecosystem-Services Landscape Index (MESLI); and eXtreme Gradient Boosting-SHapley Additive exPlanations (XGBoost-SHAP) decoded nonlinear drivers and abrupt thresholds. Built-up land increased from 1.15% (2000) to 2.39% (2020), with 2030 projected values of 2.97%, 3.15% and 3.35% under the three scenarios. MESLI reached maxima in mountain forests and minima in intensively developed intermontane basins. Land-use variables contributed >40% to mean-absolute SHAP importance, followed by precipitation and slope. Precipitation breakpoints differed across scenarios (1008 mm, 929 mm, 1065 mm), and an aridity-index threshold of 1.27 was detected for SSP245. Joint-response surfaces show favourable moisture–terrain conditions amplify forest-related multi-ecosystem-service benefits, which are substantially offset by urban encroachment. Statistical results further indicate hydrothermal thresholds are scenario-dependent instead of static, with divergent land-use-climate coupling strength between mountain and basin landscapes in plateau urban agglomerations.