WCWeichang Chen

Weichang Chen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Weichang Chen has a total of 11 co-authors. Here are the top co-authors by number of shared publications:

  • Guoqiang Xue

    Key Laboratory of Deep Petroleum Intelligent Exploration and Development, Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing 100029, China

    2 shared publications
  • Afolagboye Lekan Olatayo

    Institute of Geology and Geophysics, Chinese Academy of Sciences, Key Laboratory of Shale Gas and Geoengineering, Beijing, China.

    1 shared publication
  • Kang Chen

    Institute of Geology and Geophysics, Chinese Academy of Sciences, Key Laboratory of Mineral Resources, Beijing, China.

    1 shared publication
  • Linbo Zhang

    Key Laboratory of Mineral Resources, Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing, China

    1 shared publication
  • Muhammad Younis Khan

    Department of Earth Sciences, College of Science, Sultan Qaboos University, Muscat, Oman

    1 shared publication
  • Pengfei Lv

    State Key Laboratory of Deep Petroleum Intelligent Exploration and Development, Institute of Geology and Geophysics, Chinese Academy of Sciences, Beijing, China

    1 shared publication

Latest Publications

  • A deep-learning approach for augmenting tabular geoscience data

    by Pengfei Lv, Guoqiang Xue, Weiying Chen, Ya Yu, Shupeng Lu, Wanting Song

    In recent years, artificial intelligence has been increasingly applied in geosciences; however, the scarcity of labeled data limits its effectiveness. Existing data augmentation methods using conditional generative adversarial networks (cGANs) have succeeded in fields such as finance and medicine but often struggle to account for the multiscale features and strong correlations inherent in geoscience data, making direct adaptation challenging. This study introduces an improved cGANs — improved conditional geoscience GAN (ICG-GAN) — specifically designed for augmenting tabular geoscience data. ICG-GAN uses continuous features as conditional inputs to preserve their physical properties and correlations, using a classification-based voting mechanism to predict and impute discrete features. This approach effectively overcomes the limitations of traditional cGANs when learning from sparse samples. To systematically assess the model’s performance, we developed a comprehensive, multidimensional evaluation framework. Using core analysis data as a case study, experimental results show that ICG-GAN more accurately replicates the original data distribution and achieves significant performance improvements compared with the leading CTGAN model across six evaluation metrics. This study presents a novel method for augmenting tabular geoscience data, with broad applications in resource exploration, geologic mapping, and environmental monitoring, while providing insights for enhancing the performance and robustness of data-driven geoscientific models.


  • A comparison of loop time-domain electromagnetic and short-offset transient electromagnetic methods for mapping water-enriched zones — A case history in Shaanxi, China

    by Weiying Chen, Guoqiang Xue, Afolagboye Lekan Olatayo, Kang Chen, Muhammad Younis Khan, Weichang Chen, Linbo Zhang, Wen Chen

    Increases in the mining depth of coal pose a significant challenge to the conventional loop source time-domain electromagnetic (TEM) method that requires significant enlargement of the loop size and transmitting current to realize the deeper sounding results required. As an alternative, TEM devices based on a grounded wire source are generally used to solve detections deeper than several hundred meters. To map the water-enriched zones buried underneath approximately 1000 m at a coal mine in Shaanxi, China, loop TEM and short-offset transient electromagnetic (SOTEM) measurements were conducted. We carried out 1D forward modeling and inversion constrained by drilling informa-tion, and the results reveal that the resolution capability of loop TEM and SOTEM is almost the same in detecting a conductive layer in the absence of any noise. However, for a given noise level and decay time, the SOTEM method provides a deeper investigation than loop TEM without compromising sensitivity. The field examples validated the synthetic results. The loop TEM with dimensions of [ ] realized a maximum depth of 1000 m, whereas the reliable detection depth of 1500 m was achieved by using a 723 m long grounded wire source using the SOTEM method. Moreover, the labor required is significantly reduced, and the efficiency is dramatically raised using the SOTEM method. Our results predict that the SOTEM method should play a more important role in deep hydrogeophysical investigations.