Yuheng Zhou

Mr. Yuheng Zhou


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 March 2026 in Minerals
Verified
Journal Article
Open access
PDF file
YZYuheng Zhou
Yuheng Zhou
Yongzhi WangYongzhi Wang
Yongzhi Wang
SWShibo Wen
Shibo Wen
YNYan Ning
Yan Ning
SWShaohui Wang
Shaohui Wang
JWJingjing Wen
Jingjing Wen
Geochemical anomaly detection is a critical stage in mineral exploration, playing a key role in predicting potential mineral targets. Traditional methodologies often struggle to integrate the spatial structure of geochemical data with underlying geological constraints effectively. To address this limitation, we propose GeoCLA, a geochemical anomaly detection framework that integrates Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (BiLSTM) networks, and an Attention Mechanism (AM). This integrated spatial-attention architecture captures complex correlations among multiple features to improve anomaly identification. The method constructs spatial sequential samples from geochemical data. The CNNs extract local spatial patterns, the BiLSTM models sequential dependencies, and the AM enhances the representation of critical features. Anomaly scores are computed using the reconstruction error between the model output and the original data. In addition, a fault-distance weighting factor is incorporated to build a comprehensive anomaly evaluation index. The proposed model was applied to the Hatu gold district in Xinjiang, China. Both visual analysis and quantitative evaluation demonstrate effectiveness, achieving a ROC-AUC of 0.86 and a mineral occurrence coverage rate of 97% within moderate-to-high anomaly prospective areas, significantly outperforming baseline methods.

24 June 2026 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YZYuheng Zhou
Yuheng Zhou
Yongzhi WangYongzhi Wang
Yongzhi Wang
SWShibo Wen
Shibo Wen
GZGuangpeng Zhang
Guangpeng Zhang
YLYong Li
Yong Li
Modern mineral exploration faces the pivotal challenge of detecting concealed mineral deposits in complex geology, as depleting outcropping ores have driven global exploration to depths where 1000 m deep mining is now commonplace. To address this, this study proposes Geo-U-Mamba, an unsupervised deep learning framework for gold mineral prospectivity mapping. The model integrates multi-source geoscientific data, encompassing geochemistry, remote sensing alteration indicators, topography, and structural distance fields. By incorporating a Mamba-driven four-directional cross-scan mechanism into a U-Net architecture, the framework effectively models the complex nonlinear mapping relationships between metallogenic elements and the geological environment. This approach recognizes gold geochemical anomalies with an 86.11% deposit capture rate, decoupling environmental noise by reconstructing the geochemical background field and extracting anomalies in combination with C-A fractal theory. When applied to China’s Hatu gold belt in Xinjiang, Geo-U-Mamba achieved an AUC of 0.83, consistently outperforming classical baselines such as CAE, U-Net, and ViT. Ultimately, the findings indicate that this framework provides a reliable and high-precision tool for modern mineral exploration, successfully separating mineralization signals from geological backgrounds in complex metallogenic belts to facilitate exploration targeting.

7 September 2026 in Land
Verified
Journal Article
Open access
PDF file
JPJin Pang
Jin Pang
JWJingjing Wen
Jingjing Wen
YZYuheng Zhou
Yuheng Zhou
SWShibo Wen
Shibo Wen
When national-level market-oriented agricultural reforms enter regional agricultural systems with different land-use structures, production infrastructure, and degrees of institutional dependence, they may generate spatially uneven political responses. Focusing on Punjab and Madhya Pradesh, India, this study integrates agricultural reform policy documents, public procurement statistics, MODIS land-cover data for 2013, 2017, 2020, and 2023, irrigation statistics for the 2013–2014 to 2022–2023 agricultural years, and protest-event records from the Global Database of Events, Language, and Tone (GDELT) Event Database for 25 September 2020 to 11 December 2021. We examine agricultural land-use intensity, cropland fragmentation, gross irrigated area, and the district-level coverage, spatial concentration, and cross-quarter persistence of protest events. Punjab maintained an agricultural land-use intensity of approximately 95%, a cropland patch density of 2.50–4.27 patches per 1000 km2, and only a 0.56% increase in gross irrigated area, indicating a mature agricultural space characterized by intensive land use, continuous cropland, and stable irrigation. By contrast, agricultural land-use intensity in Madhya Pradesh increased from 75.24% to 77.63%, cropland patch density declined from 17.40 to 13.15 patches per 1000 km2, and gross irrigated area increased by 70.87%, indicating a transitional agricultural space marked by gradual land expansion, increasing cropland connectivity, and rapid irrigation growth. Protest events were more widespread and persistent in Punjab but more concentrated in Madhya Pradesh. These findings show that agricultural land expansion, cropland fragmentation, or irrigation growth alone cannot explain regional differences in farmer protests. Rather, the observed regional differences are more consistent with an interpretation emphasizing the interaction between differentiated agricultural spaces and existing institutional arrangements, including minimum support prices, public procurement, and Agricultural Produce Market Committee markets. The study develops an integrated institutional–spatial framework for explaining uneven regional responses to uniform agricultural reform.