Climate change is causing permafrost in the Qinghai–Tibet Plateau to degrade, triggering thermokarst hazards and impacting the environment. Despite their ecological importance, the distribution and risks of thermokarst lakes are not well understood due to complex influencing factors. In this study, we introduced a new interpretable ensemble learning method designed to improve the global and local interpretation of susceptibility assessments for thermokarst lakes. Our primary aim was to offer scientific support for precisely evaluating areas prone to thermokarst lake formation. In the thermokarst lake susceptibility assessment, we identified ten conditioning factors related to the formation and distribution of thermokarst lakes. In this highly accurate stacking model, the primary learning units were the random forest (RF), extremely randomized trees (EXTs), extreme gradient boosting (XGBoost), and categorical boosting (CatBoost) algorithms. Meanwhile, gradient boosted decision trees (GBDTs) were employed as the secondary learning unit. Based on the stacking model, we assessed thermokarst lake susceptibility and validated accuracy through six evaluation indices. We examined the interpretability of the stacking model using three interpretation methods: accumulated local effects (ALE), local interpretable model-agnostic explanations (LIME), and Shapley additive explanations (SHAP). The results showed that the ensemble learning stacking model demonstrated superior performance and the highest prediction accuracy. Approximately 91.20% of the total thermokarst hazard points fell within the high and very high susceptible areas, encompassing 20.08% of the permafrost expanse in the QTP. The conclusive findings revealed that slope, elevation, the topographic wetness index (TWI), and precipitation were the primary factors influencing the assessment of thermokarst lake susceptibility. This comprehensive analysis extends to the broader impacts of thermokarst hazards, with the identified high and very high susceptibility zones affecting significant stretches of railway and highway infrastructure, substantial soil organic carbon reserves, and vast alpine grasslands. This interpretable ensemble learning model, which exhibits high accuracy, offers substantial practical significance for project route selection, construction, and operation in the QTP.

To address current issues in natural language spatiotemporal queries, including insufficient question semantic understanding, incomplete semantic information extraction, and inaccurate intent recognition, this paper proposes NL2Cypher, a DeBERTa (Decoding-enhanced BERT with disentangled attention)-based natural language spatiotemporal question semantic conversion model. The model first performs semantic encoding on natural language spatiotemporal questions, extracts pre-trained features based on the DeBERTa model, inputs feature vector sequences into BiGRU (Bidirectional Gated Recurrent Unit) to learn text features, and finally obtains globally optimal label sequences through a CRF (Conditional Random Field) layer. Then, based on the encoding results, it performs classification and semantic parsing of spatiotemporal questions to achieve question intent recognition and conversion to Cypher query language. The experimental results show that the proposed DeBERTa-based conversion model NL2Cypher can accurately achieve semantic information extraction and intent understanding in both simple and compound queries when using Chinese corpus, reaching an F1 score of 92.69%, with significant accuracy improvement compared to other models. The conversion accuracy from spatiotemporal questions to query language reaches 88% on the training set and 92% on the test set. The proposed model can quickly and accurately query spatiotemporal data using natural language questions. The research results provide new tools and perspectives for subsequent knowledge graph construction and intelligent question answering, effectively promoting the development of geographic information towards intelligent services.

With the development of computer technology, landslide recognition based on machine learning methods has been widely applied in geological disaster management and research. However, in landslide identification, the problems of an insufficient number of samples and an imbalance of samples are often ignored; that is, landslide samples are much smaller than non-landslide samples. In order to solve this problem, taking the main urban area of Lanzhou City as an example, this paper proposes to construct a semi-supervised generated countermeasure network (SSGAN) model, which aims to achieve high performance with a limited number of labeled samples for precise landslide identification, and to help prevent and reduce the harm caused by disasters. In order to express the environmental characteristics of landslide development and the optical texture features of landslide occurrence, the study constructs three sets of samples to represent landslide features, including a landslide influencing factor sample set, a Sentinel-2A optical remote sensing sample set, a joint influencing factor and Sentinel-2A sample set. The three kinds of sample sets are transferred to SSGAN for training to form a comparative study. The results show that the joint sample set has excellent feature results in discriminator and generator. Through the experimental comparison, the model proposed in this paper is compared with the model without semi-supervised generated confrontation training. The experimental results show that the proposed method is better than the unsupervised adversarial learning model in terms of accuracy, F1 score, Kappa coefficient, and MIoU. A total of 160 landslides have been identified in the study area, with a total area of 10.328 km², with an accuracy rate of 83%. Therefore, the generated results are accurate and reliable, and show that SSGAN can better distinguish landslides from non-landslides in an image, under the condition of obtaining a large number of unmarked environmental features; enhance the effect of landslide classification in complex geographical environment; and then put forward effective suggestions for the prevention and control of landslides and geological disasters in the main urban area of Lanzhou.

As the proper noun for geographical entities, place names provide an intuitive way to identify and access specific geographic locations, playing a key role in semantic expression and spatial retrieval. However, existing research has insufficiently explored the spatio-temporal derivation relationships of place names, failing to fully utilize these relationships to enhance the connectivity between place names and improve spatial retrieval capabilities. Therefore, this paper conducts research on the spatio-temporal derivation relationships of place names, defines them in a standardized manner, clarifies the boundary conditions and identification methods, and then constructs a spatio-temporal derivation network of place names for expression and uses this network to carry out reasoning research on spatial adjacency relationships. Experiments and results showed that using the theory and methods of this paper to identify the spatio-temporal derivation relationships of Canadian place names achieves an accuracy rate of 98.5% and a recall rate of 93.4%, and the reasoning results can effectively improve the accuracy of query results. The research enriches the theoretical framework of spatio-temporal derivation relationships of place names, solves the current problems of unclear definition and inability to automatically identify spatio-temporal derivation relationships, and provides new perspectives and tools for the application practice in the field of geographical information science.

In the contemporary field of geographic information, place name services serve as a core application support in geographic information science, widely applied in public services, cultural tourism, emergency management, and other scenarios. Place name service composition is a critical link in the integration of spatiotemporal knowledge and intelligent services for place names, determining the ability to rapidly solve complex place name problems. Traditional case-based reasoning methods are primarily rule-driven, making it difficult to deeply integrate semantic and graph structural features, and they also lack precision in measuring the similarity of multi-type place name service cases. To address this, this paper integrates knowledge graphs and case-based reasoning to propose a place name service composition method that balances semantic and graph structural similarity, aiming to enhance the response efficiency and recognition accuracy of complex natural language queries. The method consists of two steps: the first is constructing a knowledge graph case base. Semantic feature extraction is performed on the standard geographic question-answering standard dataset GeoQuery corpus to build a place name service knowledge graph case base that integrates semantic associations and spatial attributes. The second step is constructing a similarity model. The method combines four similarity measures—DeBERTa, TF-IDF, SimHash, and maximum common subgraph—and employs the Analytic Hierarchy Process for weighting to develop a novel similarity evaluation model for case-based reasoning. Experiments demonstrate that this method achieves a 21% improvement in F1-score compared to traditional rule-based methods. Furthermore, the developed prototype system for the intelligent recommendation of place name service composition achieves a recommendation accuracy of 92.64%. This research holds significant practical implications and application value for advancing the geographic information field toward intelligent and precision-based development.