Frequent landslide disasters on the Loess Plateau in northwestern China have had a serious impact on the lives and production of the people in the region due to the fragile ecological environment and severe soil erosion. The effective monitoring and management of landslide hazards is hindered by the wide range of landslide features and scales in remotely sensed imagery, coupled with the shortage of local information and technology. To address this issue, we constructed a loess landslide dataset of 11,010 images and established a landslide detection network model. Coordinate Attention (CA) is integrated into the backbone with the aid of the YOLO model to capture precise location information and remote spatial interaction data from landslide images. Furthermore, the neck includes the Convolutional Block Attention Module (CBAM), which prompts the model to prioritize focusing on legitimate landslide objectives while also filtering out background noise to extract valid feature information. To efficiently extract classification and location details from landslide images, we introduce the lightweight Decoupled Head. This enhances detection accuracy for landslide objectives without excessively increasing model parameters. Furthermore, the utilization of the SIoU loss function improves angle perception for landslide detection algorithms and reduces the deviation between the predicted box and the ground truth box. The improved model achieves landslide object detection at multiple scales with a mAP of 92.28%, an improvement of 4.01% compared to the unimproved model.

Shale gas, a significant recoverable natural gas resource trapped in shale formations, represents a significant energy reservoir. Although China has significant recoverable shale gas reserves, the challenge of controlling drilling costs remains a critical barrier to efficient development. This study presents a novel stacked ensemble learning model that integrates support vector machine (SVM) and long short-term memory (LSTM) networks to improve the accuracy of shale gas drilling cost prediction. The methodology consists of three main phases. First, we constructed a comprehensive, multidimensional spatiotemporal dataset of shale gas drilling costs. Second, we used Gradient Boosting Decision Tree (GBDT) modelling to rank the importance of various factors influencing drilling costs. Finally, we developed a stacked ensemble learning model combining SVM and LSTM architectures to achieve superior cost prediction accuracy. Experimental results demonstrate the effectiveness of the model, with the coefficient of determination (R²) improving from 0.25189/0.33834 (traditional SVM/LSTM models) to 0.55934. Model validation using selected well investment data from the Changning Block shows promising performance, achieving a Mean Absolute Percentage Error (MAPE) of 6.41%, with optimal prediction accuracy in the medium investment range (60–70 million yuan). This innovative approach provides a reliable tool for predicting shale gas drilling costs and offers new methodological perspectives for cost reduction strategies. The results contribute significantly to the sustainable development of shale gas resources and provide valuable insights for industry practitioners and researchers in the fields of energy economics and resource management.

The exploration and development of marine geothermal energy is a field with significant potential, but it is also one that presents considerable challenges and costs. The assessment of marine geothermal reservoir potential is currently based on subjective analysis, and this study proposes an innovative clustering-based method to classify marine geothermal reservoirs systematically. The Yingqiong Basin was analysed to develop a machine learning framework to predict the potential of marine geothermal reservoirs (CPPOGR). The study integrated eight key geothermal features into a unified dataset, employing dimensionality reduction techniques (principal component analysis and sparse autoencoder) and SMOTE to balance the sample size. Machine learning classifiers, including XGBoost, BP Neural Networks, Support Vector Machines, K-Nearest Neighbours, and Random Forests, were utilised for prediction. The experimental results demonstrate that XGBoost is the most suitable classifier, achieving an excellent performance of 0.96 precision, 0.9556 recall, 0.9528 F1 score, and 0.9623 accuracy. These results demonstrate the effectiveness of the proposed CPPOGR in accurately classifying marine geothermal reservoirs based on intrinsic features. This study underscores the potential of integrating cluster analysis with machine learning for efficient reservoir characterisation, thereby offering a novel approach for marine geothermal resource assessment.

The increasing tensions between urban development and ecological environments in China, as evidenced by the country’s rapidly globalising and urbanising society, pose significant challenges to the implementation of sustainable development strategies. In order to evaluate the coupled coordination degree (CCD) between regional development (RD) and ecological carrying capacity (ECC) within the Chengdu-Chongqing Twin Cities Economic Circle, this study proposes a comprehensive CCD evaluation framework. This framework includes indicator analysis, quantitative measurement of coupling coordination, identification of coupling types, and evaluation of coordination impacts. The results indicate that regional development is on a growth trajectory while ecological carrying capacity lags behind. The coupling coordination has shifted from a state of ’basically uncoordinated’ to ’basically coordinated’, exhibiting a decreasing gradient in spatial distribution, with core cities demonstrating leadership. The study thus provides a set of optimised strategies tailored to cities at different stages of development, offering a theoretical foundation and decision-making framework for promoting quality development within the Chengdu-Chongqing Twin Cities Economic Circle.