A landslide is a kind of geological disaster with high frequency, great destructiveness, and wide distribution today. The occurrence of landslide disasters bring huge losses of life and property. In disaster relief operations, timely and reliable intervention measures are very important to prevent the recurrence of landslides or secondary disasters. However, traditional landslide identification methods are mainly based on visual interpretation and on-site investigation, which are time-consuming and inefficient. They cannot meet the time requirements in disaster relief operations. Therefore, to solve this problem, developing an automatic identification method for landslides is very important. This paper proposes such a method. We combined deep learning with landslide extraction from remote sensing images, used a semantic segmentation model to complete the automatic identification process of landslides and used the evaluation indicators in the semantic segmentation task (mean IoU [mIoU], recall, and precision) to measure the performance of the model. We selected three classic semantic segmentation models (U-Net, DeepLabv3+, PSPNet), tried to use different backbone networks for them and finally arrived at the most suitable model for landslide recognition. According to the experimental results, the best recognition accuracy of PSPNet is with the classification network ResNet50 as the backbone network. The mIoU is 91.18%, which represents high accuracy; Through this experiment, we demonstrated the feasibility and effectiveness of deep learning methods in landslide identification.

Rock mineral recognition is a costly and time-consuming task when using traditional methods, during which physical and chemical properties are tested at micro- and macro-scale in the laboratory. As a solution, a comprehensive recognition model of 12 kinds of rock minerals can be utilized, based upon the deep learning and transfer learning algorithms. In the process, the texture features of images are extracted and a color model for rock mineral identification can also be established by the K-means algorithm. Finally, a comprehensive identification model is made by combining the deep learning model and color model. The test results of the comprehensive model reveal that color and texture are important features in rock mineral identification, and that deep learning methods can effectively improve identification accuracy. To prove that the comprehensive model could extract effective features of mineral images, we also established a support vector machine (SVM) model and a random forest (RF) model based on Histogram of Oriented Gradient (HOG) features. The comparison indicates that the comprehensive model has the best performance of all.

In this paper, Feature Engineering (FE) was applied to Landslide Susceptibility Mapping (LSM), while the most suitable conditioning feature dataset and analysis method were tested and analyzed. Tianshui city was taken as the study area, three types of geohazard (collapse, landslide, and unstable slopes) were used, while a total of twenty-three conditioning features were generated; two dimensionless methods (normalization and standardization) were tested afterward. Four Random-Forest-based (RF-based) feature selection methods using different indicators (Gini Impurity, GI; Out of Bag Accuracy, OOBA) were proposed and tested separately. The LSMs of four models were carried out under the guidance results of FE, namely Classification and Regression Tree (CART), Random Forest (RF), Logistic Regression (LR), and Support Vector Machine for Classification (SVC). For feature enhancement, standardization had significant advantages over normalization. All RF-based methods were proven effective, lifting the AUC by 0.01~0.02. The RF model achieved the highest LSM accuracies, respectively, 0.949 (landslide), 0.957, and 0.949 (unstable slopes), improved by 0.008 (landslide), 0.005 (collapse), and 0.013 (unstable slopes). This proved that the FE helped to improve LSM and can help to decide the dominant conditioning factors for regional geohazards.

With the advent of the Internet of Underwater Things, smart things are deployed in the ocean space and establish underwater wireless sensor networks for the monitoring of vast and dynamic underwater environments. When events are found to have possibly occurred, accurate event coverage should be detected, and potential event sources should be determined for the enactment of prompt and proper responses. To address this challenge, a technique that detects event coverage and determines event sources is developed in this article. Specifically, the occurrence of possible events corresponds to a set of neighboring sensor nodes whose sensory data may deviate from a normal sensing range in a collective fashion. An appropriate sensor node is selected as the relay node for gathering and routing sensory data to sink node(s). When sensory data are collected at sink node(s), the event coverage is detected and represented as a weighted graph, where the vertices in this graph correspond to sensor nodes and the weight specified upon the edges reflects the extent of sensory data deviating from a normal sensing range. Event sources are determined, which correspond to the barycenters in this graph. The results of the experiments show that our technique is more energy efficient, especially when the network topology is relatively steady.

The serious geological hazards occurred frequently in the last few years. They have inflicted heavy casualties and property losses. Hence, it is necessary to design a geological information service system to analyze and evaluate geological hazards. With the development of computer and Internet service model, it is now possible to obtain rich data and process the data with some advanced computing techniques under network environment. Then, some technologies, including cyber-physical system, Internet of Things, and cloud computing, have been used in geological information management. Furthermore, the concept of cyber-physical-social-thinking as a broader vision of the Internet of Things was presented through the fusion of those advanced computing technologies. Motivated by it, in this article, a novel modeling and computing method for geological information service system is developed in consideration of the complex data processing requirement of geological service under dynamic environment. Specifically, some key techniques of modeling the information service system and computing geological data via cyber-physical system and Internet of Things are analyzed. Moreover, to show the efficiency of proposed method, two application cases are provided during the cyber-physical-social-thinking modeling and computing for geological information service system.

Traditional methods for assessing urban waterlogging hazards lack real-time efficiency. This study develops a rapid hazard assessment method for urban waterlogging events using social media data and large language models, with the urban waterlogging event in Guilin in 2024 as a case study. We constructed a keyword database for urban waterlogging, combined with web crawling techniques to collect related data from social media platforms. This study applied the BERT-BILSTM-CRF model, the GPT-3.5-turbo model, and the ERNIE-3.5-128K model to extract waterlogging locations, comparing them with the official waterlogging location data to validate and select the optimal model. The model was then used for urban waterlogging hazard assessment at the township scale. The results indicate that the establishment of a keyword database facilitates access to more social media data. The GPT-3.5-turbo model demonstrates superior performance in waterlogging location identification, with a coverage of 93% compared with the actual waterlogging locations, and an F1 score of 0.8066. During the Guilin 6.19 waterlogging, areas with high hazard intensities mainly concentrated in the city center; meanwhile, the hazard intensities of some townships in the suburbs intensified from 17 June to 21 June. This study validates the effectiveness and timeliness of using social media data and large language models for rapid hazard assessment of urban waterlogging events through practical cases, which can provide reliable support for future urban disaster prevention and reduction efforts.