Over the years, many geological exploration reports and considerable geological data have been accumulated during the prospecting and exploration of the Jiapigou gold metallogenic belt (JGMB). It is very important to fully utilize these geological and mineralogical big data to guide future gold exploration. This work collects the original textual data of different gold deposits in JGMB and constructs a knowledge graph (KG) for deposits based on deep learning (DL) and natural language processing (NLP). Based on the metallogenic geological characteristics of deposits, a visual construction method of a KG for deposits and a calculation of the similarity between deposits are proposed. In this paper, 20 geological entities and 24 relationship categories are considered. By condensing the key KG information, the metallogenic geological conditions and factors controlling the ore in 14 typical deposits in the JGMB are systematically analyzed, and the metallogenic regularity is summarized. By calculating the deposits’ cosine similarities based on the KG, the mineralization types of deposits can be divided into two categories according to the industrial types of ore bodies. The results also show that the KG is a cutting-edge technology that can extract the rich information of ore-forming regularity and prospecting criteria contained in the textual data to help researchers quickly analyze the mineralization information.

Using observational data to determine the edges of the sources is an important task in the interpretation of potential field data. Extracting the edges of deep and shallow bodies effectively is the key to correctly understanding the underground structure. Based on the good multi-scale decomposition ability of two-dimensional variational mode decomposition (2D-VMD) and the outstanding shape analysis capability of mathematical morphology (MM), a new multi-scale edge detection method for potential field data is proposed. We propose using the variance of this morphological filter as a basis for selecting the optimal structural element (SE) scale. By establishing theoretical models and comparing the results of our method with those of traditional edge detection methods, the proposed method is shown to be effective at detecting edges within potential field data. Taking the Hanmiao area of Chifeng city, Inner Mongolia, China, as an example, 1:50000 aeromagnetic data are processed and analysed by this method. The physical properties of the rocks in the study area are also discussed. The results of theoretical calculations and real data processing show that this method can accurately extract the edges of the sources at different scales. And the real data processing results show that this method is suitable for the identification of structural faults.

The cross section is the basic data for building 3D geological models. It is inefficient to draw a large number of cross sections to build an accurate model. This paper reports the use of multi-source and heterogeneous geological data, such as geological maps, gravity and aeromagnetic data, by a conditional generative adversarial network (CGAN) and implements an intelligent generation method of cross sections to overcome the problem of inefficient modeling data based on CGAN. Intelligent generation of cross sections and 3D geological modeling are carried out in three different areas in Liaoning Province. The results show that: (a) the accuracy of the proposed method is higher than the GAN and Variational AutoEncoder (VAE) models, achieving 87%, 45% and 68%, respectively; (b) the 3D geological model constructed by the generated cross sections in our study is consistent with manual creation in terms of stratum continuity and thickness. This study suggests that the proposed method is significant for surmounting the difficulty in data processing involved in regional 3D geological modeling.

A mineral deposit knowledge graph (KG) based on deep learning and natural language processing (NLP) can unveil the association between the Earth system and mineral formation. It automatically extracts the overarching model of mineral genesis and discovers mineralization laws, aiding researchers in expeditiously analyzing mineralization processes. This study constructs a mineral deposit KG for Jilin Province employing Neo4j. Initially, the Bidirectional Long Short-Term Memory (Bi-LSTM) and Conditional Random Field (CRF) model is employed to identify named entities in the text. Subsequently, the Piecewise Convolutional Neural Network (PCNN) model is employed to extract relationships between entities. Finally, the processed knowledge is imported into the Neo4j graph database for knowledge visualization. Experimental outcomes indicate that the Bi-LSTM+CRF model attains an accuracy of 91.6% and an F1 score of 90.1% in the named entity recognition task. The PCNN model reaches an accuracy of 86.4% and an F1 score of 89.3% in the relation extraction task. Through KG visualization, the correlation between controlling geological factors, prospecting indicators, and mineralization geological elements of typical mineral deposits in Jilin Province is analyzed. This provides novel technological means for the development and utilization of mineral resources in this region.

In recent years, with the continuous development of artificial intelligence, deep learning, as an important method of artificial intelligence learning, has made great progress. At present, deep learning has been successfully applied in many engineering fields. Environmental science itself involves a wide range, among which environmental geochemistry is an important branch. The combination of environmental geochemical problems and deep learning can better study the role of geochemical problems in environmental investigation, and also can use the basic situation of regional environmental elements to predict mineral resources.

Geochemical maps are essential visualization tools for studying the distribution patterns of elements on the Earth’s surface. They provide critical insights into geological structure, mineralization processes, and environmental evolution. Traditional interpolation methods often fail to adequately reconstruct high-frequency details in geochemical maps with low sampling density. This study proposes a super-resolution (SR) reconstruction method for geochemical maps based on an enhanced U-Net architecture, validated in the Gouli area of Qinghai Province. By integrating residual blocks, multi-scale neural networks, and constraints from topographic features (elevation, slope, aspect) and geological map embeddings, our method enhances the resolution of stream sediment geochemical maps from 1:50,000 to 1:25,000 scale. Experimental results demonstrate that the proposed method outperforms SRCNN, VDSR, and standard U-Net models in both peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Specifically, with all constraints incorporated, the method achieves maximum and mean PSNR values of 38.486 and 25.334, respectively, and maximum and mean SSIM values of 0.968 and 0.817. The reconstructed high-resolution (HR) geochemical maps exhibit superior detail clarity and maintain strong spatial correlation with the original HR data. Studies have shown that this method can effectively learn multi-scale geochemical patterns and detect subtle anomalies missed in low-resolution (LR) maps. Moreover, the reconstructed HR geochemical maps exhibit better alignment with the Ag, Cu, and Pb anomalies in known mineralization zones (Maixiulongwa and Sanchakou areas), thereby providing strong support for precise mineral exploration.