Spatial Feature Classification Research Articles

Mineral Prospectivity Mapping Based on Spatial Feature Classification with Geological Map Knowledge Graph Embedding: Case Study of Gold Ore Prediction at Wulonggou, Qinghai Province (Western China)

Prospectivity mapping based on deep learning typically requires substantial amounts of geological feature information from known mineral deposits. Due to the limited spatial distribution of ore deposits, the training of predictive models is often hampered by insufficient positive samples. Meanwhile, data-driven mineral prospectivity mapping often overlooks domain knowledge and expert experience, leading to poor interpretability of predictive results. To address this problem, we employed the Gaussian mixture model (GMM) for spatial feature classification to expand the number of positive samples. The approach integrated the embedding of geological map knowledge graphs with geological exploration data to enhance the knowledge constraints of the prospecting model, which enabled the integration of knowledge with data. Considering the complex spatial structure of geological elements, a bi-branch utilizing the 1-dimensional convolutional neural network (CNN1D) and graph convolutional network (GCN) was used to extract geological spatial features for model training and prediction. To validate the effectiveness of the method, a gold mineralization prediction study was conducted in the Wulonggou area (Qinghai province, western China). The results indicate that, when the number of GMM spatial feature classifications was 17, the positive-to-negative sample ratio was optimal, and the embedding of the knowledge graph controlled the prediction area distribution effectively, which demonstrated strong consistency between the prospecting area and the known mineral deposits. Compared with the predictions by CNN1D, the fused prediction model of CNN1D and GCN yielded higher accuracy. Our model identified 11 classes of mineralization potential areas and provides geological interpretations for different prediction categories.

Denoising of Uncertain Type Noise Images by Spatial Feature Classification in Nonsubsampled Shearlet Transform

Most denoising methods are designed to deal standard images with specific type noise, which do not perform well when denoising real noisy images contain uncertain types of noise. However, underwater image is a typical uncertain type noise image. To solve this problem, this paper presents a method using spatial feature classification jointing nonsubsampled shearlet transform (NSST) for denoising uncertain type noise images. Justifiable granule is employed to solve the problem of parameter selection. The raw image was decomposed by using the NSST to get one low frequency subband and several high frequency subbands. Then, the preliminary binary map is built, the binary map is employed to decide whether a coefficient contains spatial feature or not. And we employ justifiable granule to solve the difficulty of parameter selection. The high subbands coefficients are classified into two classes by fuzzy support vector machine classification: the texture class and the noise class. At last, the adaptive Bayesian threshold is used to shrink the coefficients. Simulation results show the proposed method is effective in uncertain type noise images(also have good performance in specific type noise). The method we proposed has been compared with other popular denoising methods and get excellent subjective performance and PSNR improvement.

Morphological Profiles Based on Differently Shaped Structuring Elements for Classification of Images With Very High Spatial Resolution

Morphological profiles (MPs) have been proposed for the segmentation and classification of high spatial resolution (HSR) images. A shortcoming of the originally proposed MPs is that the profiles were only based on structuring elements (SEs) of one particular shape, suggesting that such MPs may not be suitable for detecting different shapes in images. To better fit several shapes in a given image, a new approach based on mathematical morphology is proposed to extract structural information from HSR images and consequently yield new versions of MPs. The classification results for the new MPs are compared with the classification of spatial features extracted with the use of pixel shape index, gray level co-occurrence matrix, and previously proposed MPs. The experimental results suggest the following: 1) structural and spectral features can complement each other and their integration can improve classification accuracy and 2) MPs constructed by differently shaped SEs are less sensitive to salt-and-pepper noise than those constructed by fixed-shaped SEs.

Spectral and spatial feature classification of hyperspectral images based on particle swarm optimisation

This paper addresses the problem of feature selection and SVM kernel parameter optimisation for hyperspectral remote sensing image. First, we propose an evolutionary classification algorithm based on particle swarm optimisation (PSO) to improve the generalisation performance of the SVM classifier. For this purpose, we have optimised the SVM classifier design by searching for the best value of the kernel parameters of SVM that tune its discriminant function, and upstream by looking for the best subset of features that feed the classifier. Second, we propose a feature fusion approach based on the joint use of spectral and spatial information provided by texture features extracted from the grey level co-occurrence matrix (GLCM). Experimental results prove that spectral feature and GLCM texture features can obtain higher classification accuracy than only spectral feature classification for hyperspectral image classification.