Bo Peng’s research while affiliated with China University of Geosciences and other places

Yu’nan County is located in the Pacific Rim geological disaster-prone area. Frequent landslides are an important cause of population, property, and infrastructure losses, which directly threaten the sustainable development of the regional social economy. Based on field survey data, this paper employs the coefficient of variation method (CV) and an improved TOPSIS model (Kullback-Leibler-Technique for Order Preference by Similarity to an Ideal Solution) to assess the social vulnerability to landslide disasters in 182 administrative villages of Yu’nan County. Also, it conducts a ranking and comprehensive analysis of their social vulnerability levels. Finally, the accuracy of the evaluation results is validated by applying the losses incurred from landslide disasters per unit area within the same year. The results indicate significant spatial variability in social vulnerability across Yu’nan County, with 68 out of 182 administrative villages exhibiting moderate vulnerability levels or higher. This suggests a high risk of widespread damage from potential disasters. Among these, Xincheng village has the highest social vulnerability score, while Chongtai village has the lowest, with a 0.979 difference in their vulnerabilities. By comparing the actual losses incurred per unit area from landslides, it is found that the social vulnerability results predicted by the CV-KL-TOPSIS model are more consistent with the actual survey results. Furthermore, among the ten sub-factors, population density, building value, and road value contribute most significantly to the overall weight with 0.269, 0.152, and 0.105, respectively, suggesting that in mountainous areas where the population is relatively concentrated, high social vulnerability to landslide hazards is a reflection of population characteristics and local economic level. The evaluation framework and evaluation indicators proposed in this paper can systematically and accurately evaluate the social vulnerability of landslide-prone areas, which provide a reference for urban planning and management in landslide-prone areas.

Rainfall is intrinsically linked to the occurrence of landslide catastrophes. Identifying the most suitable rainfall threshold model for an area is crucial for establishing effective daily landslide hazard warnings, which are essential for the precise prevention and management of local landslides. This study introduces a novel approach that utilizes multilayer perceptron (MLP) regression to calculate rainfall thresholds for 453 rainfall-induced landslides. This research represents the first attempt to integrate MLP and ordinary least squares methods for determining the optimal rainfall threshold model tailored to distinct subregions, categorized by topographical and climatic conditions. Additionally, an innovative application of a three-dimensional convolutional neural network (CNN-3D) model is introduced to enhance the accuracy of landslide susceptibility predictions. Finally, a comprehensive methodology is developed to integrate daily rainfall warning levels with landslide susceptibility predictions using a superposition matrix, thus offering daily landslide hazard warning results for the study area. The key findings of this study are as follows. (1) The optimal rainfall threshold models and calculation methods vary across different subregions, underscoring the necessity for tailored approaches. (2) The CNN-3D model substantially improves the accuracy of landslide susceptibility predictions. (3) The daily landslide hazard warnings were validated using anticipated rainfall data from 19 July 2020, thereby demonstrating the reliability of both the landslide hazard warning results and the rainfall threshold model. This study presents a substantial advancement in the precise prediction and management of landslide hazards by employing innovative modeling techniques.

To achieve the regional goal of “double carbon”, it is necessary to map the carbon stock prediction for a wide area accurately and in a timely fashion. This paper introduces a long- and short-term memory network algorithm called the Self-Attention Convolutional Long and Short-Term Memory Network (SA-ConvLSTM). This paper takes the Wuhan urban circle of China as the research object, establishes a carbon stock AI prediction model, constructs a carbon stock change evaluation system, and investigates the correlation between carbon stock change and land use change during urban expansion. The results demonstrate that (1) the overall accuracy of the ConvLSTM and SA-ConvLSTM models improved by 4.68% and 4.70%, respectively, when compared to the traditional metacellular automata prediction methods (OS-CA, Open Space Cellular Automata Model), and for small sample categories such as barren land, shrubs, and grassland, the accuracy of SA-ConvLSTM increased by 17.15%, 43.12%, and 51.37%, respectively; (2) from 1999 to 2018, the carbon stock in the Wuhan urban area showed a decreasing trend, with an overall decrease of 6.49 × 10⁶ MgC. The encroachment of arable land due to rapid urbanization is the main reason for the decrease in carbon stock in the Wuhan urban area. From 2018 to 2023, the predicted value of carbon stock in the Wuhan urban area was expected to increase by 9.17 × 10⁴ MgC, mainly due to the conversion of water bodies into arable land, followed by the return of cropland to forest; (3) the historical spatial error model (SEM) indicates that for each unit decrease in carbon stock change, the Single Land Use Dynamic Degree (SLUDD) of water bodies and impervious surfaces will increase by 119 and 33 units, respectively. For forests, grasslands, and water bodies, the future spatial error model (SEM) indicated that for each unit increase in carbon stock change, the SLUDD would increase by 55, 7, and −305 units, respectively. This study demonstrates that we can use deep neural networks as a new method for predicting land use expansion, revealing the key impacts of land use change on carbon stock change from both historical and future perspectives and providing valuable insights for policymakers.

Landslide susceptibility mapping (LSM) can accurately estimate the location and probability of landslides. An effective approach for precise LSM is crucial for minimizing casualties and damage. The existing LSM methods primarily rely on static indicators, such as geomorphology and hydrology, which are closely associated with geo-environmental conditions. However, landslide hazards are often characterized by significant surface deformation. The Small Baseline Subset-Interferometric Synthetic Aperture Radar (SBAS-InSAR) technology plays a pivotal role in detecting and characterizing surface deformation. This work endeavors to assess the accuracy of SBAS-InSAR coupled with ensemble learning for LSM. Within this research, the study area was Shiyan City, and 12 static evaluation factors were selected as input variables for the ensemble learning models to compute landslide susceptibility. The Random Forest (RF) model demonstrates superior accuracy compared to other ensemble learning models, including eXtreme Gradient Boosting, Logistic Regression, Gradient Boosting Decision Tree, and K-Nearest Neighbor. Furthermore, SBAS-InSAR was utilized to obtain surface deformation rates both in the vertical direction and along the line of sight of the satellite. The former is used as a dynamic characteristic factor, while the latter is combined with the evaluation results of the RF model to create a landslide susceptibility optimization matrix. Comparing the precision of two methods for refining LSM results, it was found that the method integrating static and dynamic factors produced a more rational and accurate landslide susceptibility map.

Rainfall is intrinsically connected to the incidence of landslide catastrophes. Exploring the ideal rainfall threshold model (RTM) for an area in order to determine the rainfall warning level (RWL) for the region for daily landslide hazard warning (LHW) is critical for precise prevention and management of local landslides. In this paper, a method for calculating rainfall thresholds using multilayer perceptron (MLP) regression is proposed for 453 rainfall-induced landslides. First, the study area was divided into subareas based on topography and climate conditions. Then, two methods, MLP and ordinary least squares (OLS), were utilized to explore the optimal RTM for each subregion. Subsequently, 11 factors along with three models were selected to predict landslide susceptibility (LS). Finally, to obtain daily LHW result for the study area, a superposition matrix was employed to overlay the daily RWL with the ideal LS prediction results. The following are the study's findings: (1) The optimal RTMs and calculation methods are different for different subregions. (2) The Three-dimensional convolutional neural network model produces more accurate LS prediction results. (3) The daily LHW was validated using anticipated rainfall data for July 19, 2020, and the validation results proved the correctness of the LHW results and RTM.