Machine learning (ML) has shown its effectiveness in handling multi-geoinformation. Yet, the black-box nature of ML algorithms has restricted their widespread adoption in the domain of mineral prospectivity mapping (MPM). In this paper, methods for interpreting ML model predictions are introduced to aid ML-based MPM, with the goal of extracting richer insights from the ML modeling of an exploration geochemical dataset. The partial dependence plot (PDP) and accumulated local effect (ALE) plot, along with the SHAP value analysis, were utilized to demonstrate the application of random forest (RF) modeling within both regression and classification frameworks. Initially, the random forest regression (RFR) model established the relationship between the concentrations of Au and those of elements such as As, Sb, and Hg in the study area, and from this model, the most important geochemical elements and their quantitative relationships with Au were revealed by their contributions in the modeling through PDP and ALE analyses. Secondly, the RF classification modeling established the relationships of mineralization occurrences (i.e., known mineral deposits) with geochemical elements (i.e., Au, As, Sb, Hg, Cu, Pb, Zn, and Ag), as did RFR modeling. The most important geochemical elements for indicating regional Au mineralization and the trajectories of PDP and ALE reached a consensus that As and Sb contributed the most, both in the regression and classification modeling, with regard to Au mineralization. Finally, the SHAP values illustrated the behavior of the training samples (i.e., known mineral deposits) in RF modeling, and the resulting prospectivity map was evaluated using receiver operating characteristics.

Territorial space use efficiency (TSUE) serves as a core quantitative metric for evaluating the sustainability of space use, which constitutes a vital component of regional sustainable development. Nevertheless, existing studies have not established a systematic quantitative system for assessing the status of the sustainability of space use based on TSUE. From the perspective of production–living–ecological spaces, this study constructs a multi-dimensional efficiency evaluation framework for sustainable territorial management. This study adopts geographic data envelopment analysis (GeoDEA), spatial autocorrelation analysis and multi-scale geographically weighted regression (MGWR). It calculates TSUE, applies efficiency levels to characterize the status of the sustainability of space use, and further reveals its spatiotemporal evolution and driving mechanisms. The results indicate that the level of the sustainability of space use generally exhibits a fluctuating evolution, with distinct phase transitions emerging around 2010. Only 20% of cities attain medium-high or higher levels of sustainability in space use, with pronounced spatial disparities across the country. Areas with high-efficiency production and living spaces are mainly clustered in eastern and central China, while high-efficiency ecological spaces are concentrated in western and northeastern China. In addition, driving factors exert markedly heterogeneous effects on the three types of territorial functional spaces. This study provides scientific support for implementing differentiated territorial spatial governance and advancing regional sustainable development.

The Solonker-Xar Moron-Changchun-Yanji Suture Zone is the result of the final closure of the Paleo-Asian Ocean (PAO). However, the closure time of the PAO in Northeast China remains controversial. The Hunchun area is located in the easternmost part of the Solonker-Xar Moron-Changchun-Yanji Suture Zone. Tectonism and magmatism in the Hunchun area can provide important information for understanding the late-stage evolution of the PAO. In this study, our zircon U-Pb ages show that the granodiorites and diorites in the Hunchun were formed at 282.3–251.4 Ma. This geochronological evidence suggests prolonged Permian magmatism in the Hunchun area. Whole-rock geochemistry, zircon trace, and Lu-Hf isotope data show that all the intrusive rocks are mainly calc-alkaline series to arc tholeiite series. Granodiorites are I-type granites formed by the partial melting of juvenile lower crust derived from the mantle. Diorites show similar characteristics to the sanukitic high-Mg diorite and are formed by the partial melting of the depleted mantle metasomatized by subduction sediments and/or slab-derived fluids. These results indicate that the Permian diorites and granodiorites in the Hunchun area formed in an active continental margin setting related to the subduction of the PAO plate. Significantly, sudden changes in the whole-rock Sr/Y and (La/Yb)_N ratios and zircon ε_Hf(t) values are observed in the Late Permian-Early Triassic igneous rocks in the eastern Central Asian Orogenic Belt (CAOB). This indicates that the final closure of the PAO in Northeast China likely occurred in the Late Permian-Early Triassic.

Aiming at the problems of complex RPC geometric modeling in multi-view stereo matching (MVS) of satellite remote-sensing images, significant feature noise caused by cross-view occlusion and inconsistent lighting, and blurred edge details of height maps, this paper proposes a satellite MVS height estimation network based on a Mamba-enhanced feature pyramid and deformable RPC sampling, MambaDPSMVS. In the feature extraction stage, the cross-view Mamba module and the single-view self-Mamba enhancement module are designed to realize explicit feature interaction between and within views through direction prediction, direction routing, geometric gating fusion and state-space sequence modeling, and suppress view noise from the source. A deformable sampler for an RPC geometry, RPC-DPSampler, is proposed to achieve accurate alignment of source-view features with the reference view through 3D deformable coarse alignment, block sampling, 2D sub-pixel fine-tuning and view-level attention-weighted aggregation. Then, the cascaded cost is constructed, and the loop encoder–decoder regularization is used to complete the height estimation from coarse to fine. Experiments on the WHU-TLC and US3D datasets show that the MAE/RMSE of the proposed method reaches 1.688 m/2.867 m and 1.744 m/3.847 m, respectively, and the PAG_<1m reaches 61.81% and 62.18%, respectively, which values are better than those of baseline methods such as Sat (Red-Net) and Sat (CasMVS-Net). The ablation experiment further validated the complementarity of Mamba enhancement features and the RPC-DPSampler module in feature expression and geometric alignment.