Scholarlink

<p>Hydrogeochemical response lag complicates process control in uranium in-situ leaching (ISL), particularly within heterogeneous wellfields. To address the multi-timescale dynamics and spatial coupling in uranium in-situ leaching operations, this study proposes a physics-guided state-space modeling (PG-SSM) framework for forecasting production concentration dynamics within a heterogeneous operational signal environment of a sandstone-hosted seven-spot ISL unit. In this work, the term physics-guided refers to the incorporation of soft hydrogeochemical constraints within a data-driven learning framework, rather than to a calibrated reactive-transport simulator. The model encodes seven-spot wellfield topology and separates fast operational perturbations from slower concentration dynamics while incorporating soft physical constraints to enhance hydrogeochemical plausibility. Evaluated on field data, PG-SSM achieves strong predictive performance (R<sup>2</sup> = 0.928, RMSE = 0.043&#xa0;mg&#xa0;L<sup>−1</sup>) and reduces peak-timing lag to approximately + 1.5&#xa0;days, consistently outperforming baseline models under the limited peak events observed in the test period. These findings suggest that integrating topological priors with physics-informed regularization can improve lag alignment and provide a more stable and physically consistent basis for proactive ISL monitoring and process control.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Physics-guided multi-well forecasting of uranium concentration in pregnant leach solutions from in-situ leaching wellfields: reducing hydrogeochemical peak-lag for process optimization

  • 期刊论文

  • 发表日期：

    2026年5月13日

查看全文
  • Qiang Li,
  • Zhifeng Liu,
  • Yipeng Zhou,
  • Jianfeng He,
  • Zhenhua Wei

摘要

Hydrogeochemical response lag complicates process control in uranium in-situ leaching (ISL), particularly within heterogeneous wellfields. To address the multi-timescale dynamics and spatial coupling in uranium in-situ leaching operations, this study proposes a physics-guided state-space modeling (PG-SSM) framework for forecasting production concentration dynamics within a heterogeneous operational signal environment of a sandstone-hosted seven-spot ISL unit. In this work, the term physics-guided refers to the incorporation of soft hydrogeochemical constraints within a data-driven learning framework, rather than to a calibrated reactive-transport simulator. The model encodes seven-spot wellfield topology and separates fast operational perturbations from slower concentration dynamics while incorporating soft physical constraints to enhance hydrogeochemical plausibility. Evaluated on field data, PG-SSM achieves strong predictive performance (R2 = 0.928, RMSE = 0.043 mg L−1) and reduces peak-timing lag to approximately + 1.5 days, consistently outperforming baseline models under the limited peak events observed in the test period. These findings suggest that integrating topological priors with physics-informed regularization can improve lag alignment and provide a more stable and physically consistent basis for proactive ISL monitoring and process control.