A New Approach for Mineral Mapping Using Drill-Core Hyperspectral Image

Article Geochemistry & Geophysics

Region Expansion of a Hyperspectral-Based Mineral Map Using Random Forest Classification with Multispectral Data

Hideki Tsubomatsu et al.

Summary: In this study, a new method was proposed to expand the mineral map of a hyperspectral (HS) image using a multispectral (MS) image. The method utilizes a random forest classification algorithm to iteratively determine the distribution of each mineral and corrects the misalignment between the images. The proposed method showed the highest performance with high precision and accuracy, even for minerals with limited pixels.

MINERALS (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction

Ahmad Ali et al.

Summary: The study proposes a unified dynamic deep spatio-temporal neural network model for predicting crowd flows in different regions of a city. By combining the influences of different time granularities and external properties, the model shows exceptional performance in prediction accuracy, outperforming other methods.

NEURAL NETWORKS (2022)

添加到收藏夹

Article Geology

Mineral prospectivity mapping by deep learning method in Yawan-Daqiao area, Gansu

Yongyang Xu et al.

Summary: Mineral prospectivity mapping, utilizing multi-source geological data for probability prediction, was enhanced in this study with the use of a deep regression neural network. The neural network learned expert knowledge in mineral prospectivity mapping, did not require classified samples, and could be applied for predicting and evaluating mineral resources.

ORE GEOLOGY REVIEWS (2021)

添加到收藏夹

Article Remote Sensing

Identification of minerals in hyperspectral imagery based on the attenuation spectral absorption index vector using a multilayer perceptron

Kewang Deng et al.

Summary: Different minerals show distinct spectra due to varying constituent ions or groups. The variable imaging conditions of hyperspectral imagery can greatly impact mineral spectra, making mineral identification challenging. By utilizing the attenuation spectral absorption index (ASAI) to extract absorption features from diagnostic bands, the proposed ASMLP model achieves a high overall accuracy of 93.62% in mineral identification, outperforming other methods.

REMOTE SENSING LETTERS (2021)

添加到收藏夹

Article Geochemistry & Geophysics

Fusion of Dual Spatial Information for Hyperspectral Image Classification

Puhong Duan et al.

Summary: The research proposes a novel framework for hyperspectral image classification, focusing on extracting spatial information. By fusing dual spatial information, the framework not only accurately extracts discriminative features from HSIs, but also achieves better classification performance through spatial optimization.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

添加到收藏夹

Article Remote Sensing