基于cDC-GAN替代模型的物理-化学非均质矿层CO2+O2地浸采铀过程模拟

刘殿广; 杨蕴; 章勇; 邱文杰; 吴剑锋; 王锦国; 吴吉春

PDF(4090 KB)

中国环境科学 ›› 2024, Vol. 44 ›› Issue (8) : 4547-4556.

环境生态

基于cDC-GAN替代模型的物理-化学非均质矿层CO₂+O₂地浸采铀过程模拟

刘殿广¹, 杨蕴¹, 章勇², 邱文杰², 吴剑锋², 王锦国¹, 吴吉春²

作者信息 +

Predicting CO₂+O₂ in-situ leaching process in physico-chemical heterogeneous sandstone-type uranium ore using a cDC-GAN-based proxy model

LIU Dian-guang¹, YANG Yun¹, ZHANG Yong², QIU Wen-jie², WU Jian-feng², WANG Jin-guo¹, WU Ji-chun²

Author information +

文章历史 +

摘要

基于物理过程的CO₂+O₂地浸采铀反应性溶质运移模型需要采用高分辨率网格来捕获介质物理-化学参数空间变异性和对流-弥散-化学反应多过程耦合特征,往往面临巨大的模型计算挑战.传统的替代模型处理高维数据空间分布预测时面临精度和维数诅咒问题,基于条件深度卷积生成对抗网络(conditional Deep Convolutional Generative Adversarial Network,cDC-GAN),本文提出了一种多重输入图像到输出图像回归的cDC-GAN替代建模组件,建立了高维物理-化学非均质场(渗透率场和铀矿物品位场)和铀浸出浓度分布场之间的映射关系,训练集和测试集样品中结构相似性指数的中值达0.98以上,可以作为砂岩型铀矿CO₂+O₂溶浸过程数值模型的替代方案.cDC-GAN替代建模不受底层物理模型的限制,进而可为复杂反应性溶质运移模型的参数识别、不确定性分析、全局敏感性分析和模拟优化方案设计等提供通用框架.

Abstract

A CO₂+O₂ in-situ leaching uranium reactive solute transport model based on physical processes requires high-resolution grids to capture the spatial variability of medium physical-chemical parameters and the multi-process coupling characteristics of advection-dispersion-chemical reactions. This often faces significant computational challenges. Traditional surrogate models encounter precision and curse of dimensionality issues when predicting high-dimensional data spatial distributions. In this paper, a conditional Deep Convolutional Generative Adversarial Network (cDC-GAN) is proposed as a surrogate modeling component for multi-input image to output image regression. The mapping relationship between high-dimensional physical-chemical heterogeneous fields (permeability fields and uranium mineral grade fields) and uranium leaching concentration distribution fields is established. The median structural similarity index in the training and test sample sets exceeds 0.98, making it a viable alternative to numerical models of the CO₂+O₂ in-situ leaching process for sandstone-hosted uranium deposits. The cDC-GAN surrogate modeling is not constrained by the underlying physical model, thereby providing a general framework for parameter identification, uncertainty analysis, global sensitivity analysis, and simulation optimization design of complex reactive solute transport models.

导出引用

刘殿广, 杨蕴, 章勇, 邱文杰, 吴剑锋, 王锦国, 吴吉春. 基于cDC-GAN替代模型的物理-化学非均质矿层CO₂+O₂地浸采铀过程模拟[J]. 中国环境科学. 2024, 44(8): 4547-4556

LIU Dian-guang, YANG Yun, ZHANG Yong, QIU Wen-jie, WU Jian-feng, WANG Jin-guo, WU Ji-chun. Predicting CO₂+O₂ in-situ leaching process in physico-chemical heterogeneous sandstone-type uranium ore using a cDC-GAN-based proxy model[J]. China Environmental Science. 2024, 44(8): 4547-4556

中图分类号： X753 P641

参考文献

[1] 苏学斌,李喜龙,刘乃忠,等.环境友好型地浸采铀工艺技术与应用[J]. 中国矿业, 2016,25(9):97-100. Su X B, Li X L, Liu N Z, et al. Application of the environment friendly technology of in-situ leaching of uranium [J]. China Mining Magazine, 2016,25(9):97-100.
[2] 曾晟,谭凯旋,桑潇,等.原地浸出采铀多场多过程耦合动力学数值模拟[J]. 原子能科学技术, 2011,45(4):500-505. Zeng S, Tan K X, Sang X, et al. Numerical simulation on multi-field and multi-process coupling dynamics of in-situ leaching of uranium [J]. Atomic Energy Science and Technology, 2011,45(4):500-505.
[3] 李衡,周义朋.地浸采铀溶质运移研究进展及展望[J]. 稀有金属, 2019,43(3):319-330. Li H, Zhou Y P. Process and prospect of research on solute transport during in-situ leaching of uranium [J]. Chinese Journal of Rare Metals, 2019,43(3):319-330.
[4] Collet A, Regnault O, Ozhogin A, et al. Three-dimensional reactive transport simulation of Uranium in situ recovery: Large-scale well field applications in Shu Saryssu Bassin, Tortkuduk deposit (Kazakhstan) [J]. Hydrometallurgy, 2022,211:105873.
[5] Yang Y, Qiu W, Liu Z, et al. Quantifying the impact of mineralogical heterogeneity on reactive transport modeling of CO₂+ O₂ in-situ leaching of uranium [J]. Acta Geochimica, 2022:1-14.
[6] 邱文杰,刘正邦,杨蕴,等.砂岩型铀矿CO₂+O₂地浸采铀的反应运移数值模拟[J]. 中国科学:技术科学, 2022,52(4):627-638. Qiu W J, Bnag L Z, Yang Y, et al. Reactive transport numerical modeling of CO₂+O₂ in-situ leaching in sandstone-type uranium ore [J]. Scientia Sinica (Technologica), 2022,52(4):627-638.
[7] 刘春雨,李寻,罗跃,等.酸法浸铀过程中Fe³⁺与浸出铀之间关系的数值模拟[J]. 有色金属(冶炼部分), 2023,(3):88-94. Yu L C, Xun L, Yue L, et al. Numerical simulation of relationship between Fe³⁺ and leached uranium during acid leaching [J]. Nonferrous Metals (Extractive Metallurgy), 2023,(3):88-94.
[8] 杨蕴,南文贵,邱文杰,等.非均质矿层CO₂+O₂地浸采铀溶浸过程数值模拟与调控[J]. 水动力学研究与进展A辑, 2022,37(5):639- 649. Yang Y, Nan W G, Qiu W J, et al. Numerical simulation and regulation of CO₂+O₂ in-situ leaching process in heterogeneous sandstone-type uranium ore [J]. Chinese Journal of Hydrodynamics, 2022,37(5): 639-649.
[9] 纪文贵,罗跃,刘金辉,等.考虑渗透系数不确定性的地浸过程溶浸范围随机模拟[J]. 原子能科学技术, 2023,57(6):1099-1110. Ji W G, Luo Y, Liu J H, et al. Stochastic simulation of leaching range in in-situ leaching process considering uncertainty of permeability coefficient [J]. Atomic Energy Science and Technology, 2023,57(6): 1099-1110.
[10] Cui T, Peeters L, Pagendam D, et al. Emulator-enabled approximate Bayesian computation (ABC) and uncertainty analysis for computationally expensive groundwater models [J]. Journal of hydrology, 2018,564:191-207.
[11] Luo J N, Lu W X, YANG Q C, et al. An adaptive dynamic surrogate model using a constrained trust region algorithm: Application to DNAPL-contaminated-groundwater-remediation design [J]. Hydrogeology Journal, 2020,28(4):1285-1298.
[12] Wang B, Luo Y, Qian J Z, et al. Machine learning-based optimal design of the in-situ leaching process parameter (ISLPP) for the acid in-situ leaching of uranium [J]. Journal of Hydrology, 2023:130234.
[13] 罗建男,李雪利,王鹤,等.基于局部-全局混合自适应替代模型的地下水污染源反演识别[J]. 中国环境科学, 2023,43(7):3664-3671. Luo J N, Li X L, Wang H, et al. Groundwater pollution sources inversion based on local-global hybrid adaptive surrogate model [J]. China Environmental Science, 2023,43(7):3664-3671.
[14] 葛渊博,卢文喜,白玉堃,等.基于SSA-BP与SSA的地下水污染源反演识别[J]. 中国环境科学, 2022,42(11):5179-5187. Ge Y B, Lu W X, Bai Y K, et al. Inversion and identification of groundwater pollution sources based on SSA-BP and SSA [J]. China Environmental Science, 2022,42(11):5179-5187.
[15] 贾顺卿,卢文喜,李久辉,等.基于U-D分解卡尔曼滤波地下水污染源溯源辨识[J]. 中国环境科学, 2021,41(2):713-719. Jia S Q, Lu W X, Li J H, et al. Inversion identification of groundwater contamination source based on U-D factorization Kalman filter [J]. China Environmental Science, 2021,41(2):713-719.
[16] 罗成明,卢文喜,潘紫东,等.基于替代模型和流向算法的地下水污染源反演识别[J]. 中国环境科学, 2023,43(11):5823-5832. Luo C M, Lu W X, Pan Z D, et al. Inversion and identification of groundwater pollution sources based on surrogate model and flow direction algorithm [J]. China Environmental Science, 2023,43(11): 5823-5832.
[17] 徐亚宁,卢文喜,王梓博,等.考虑参数和边界条件不确定性的地下水污染随机模拟[J]. 中国环境科学, 2022,42(7):3244-3253. Xu Y N, Lu W X, Wang Z B, et al. Stochastic simulation of groundwater pollution considering uncertainty of parameters and boundary conditions [J]. China Environmental Science, 2022,42(7): 3244-3253.
[18] 董广齐,卢文喜,范越,等.不确定性条件下地下水污染监测井网优化设计——基于XGBoost替代模型[J]. 中国环境科学, 2022, 42(5):2144-2152. Dong G Q, Lu W X, Fan Y, et al. Optimal design of groundwater pollution monitoring network under uncertainty [J]. China Environmental Science, 2022,42(5):2144-2152.
[19] 罗成明,卢文喜,王梓博,等.地下水污染模拟模型的不确定性分析[J]. 中国环境科学, 2022,42(7):3224-3233. Luo C M, Lu W X, Wang Z B, et al. Uncertainty analysis of groundwater pollution simulation model [J]. China Environmental Science, 2022,42(7):3224-3233.
[20] Mostafaei-Avandari M, Ketabchi H. Coastal groundwater management by an uncertainty-based parallel decision model [J]. Journal of Water Resources Planning and Management, 2020,146(6): 4020036.
[21] Asher M J, Croke B F, Jakeman A J, et al. A review of surrogate models and their application to groundwater modeling [J]. Water Resources Research, 2015,51(8):5957-5973.
[22] Lin G, Tartakovsky A M. An efficient, high-order probabilistic collocation method on sparse grids for three-dimensional flow and solute transport in randomly heterogeneous porous media [J]. Advances in Water Resources, 2009,32(5):712-722.
[23] Mo S X, Lu D, Shi X Q, et al. A Taylor expansion-based adaptive design strategy for global surrogate modeling with applications in groundwater modeling [J]. Water Resources Research, 2017,53(12): 10802-10823.
[24] 莫绍星.基于深度学习的地下水模拟高维不确定性分析和反演[D]. 南京:南京大学, 2019. Mo S X. Towards Effcient High-Dimensional Uncertainty Quantification and Inverse Analysis in Groundwater Modeling Using Deep Learning [D]. Nanjing: Nanjing University, 2019.
[25] 战庆亮,刘鑫,晁阳,等.基于稀疏环境监测点的流动时程重构模型精度研究[J]. 中国环境科学, 2023,43(12):6592-6600. Liang Z Q, Liu X, Chao Y, et al. Accuracy of environmental flows time history reconstruction model based on sparse observation [J]. China Environmental Science, 2023,43(12):6592-6600.
[26] Tang M, Liu Y, Durlofsky L J. A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems [J]. Journal of Computational Physics, 2020,413:109456.
[27] Zhong Z, Sun A Y, Wang Y Y, et al. Predicting field production rates for waterflooding using a machine learning-based proxy model [J]. Journal of Petroleum Science and Engineering, 2020,194:107574.
[28] Du J W, Shi X Q, Mo S, et al. Deep learning based optimization under uncertainty for surfactant-enhanced DNAPL remediation in highly heterogeneous aquifers [J]. Journal of Hydrology, 2022,608:127639.
[29] Zhong Z, Sun A Y, Jeong H. Predicting CO₂plume migration in heterogeneous formations using conditional deep convolutional generative adversarial network [J]. Water Resources Research, 2019, 55(7):5830-5851.
[30] Zhu Y H, Zabaras N. Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification [J]. Journal of Computational Physics, 2018,366:415-447.
[31] Xu T F, Sonnenthal E, Spycher N, et al. TOUGHREACT—a simulation program for non-isothermal multiphase reactive geochemical transport in variably saturated geologic media: applications to geothermal injectivity and CO₂ geological sequestration [J]. Computers & geosciences, 2006,32(2):145-165.
[32] Mo S X, Zhu Y H, Zabaras N, et al. Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media [J]. Water Resources Research, 2019, 55(1):703-728.
[33] Remy N, Boucher A, WU J. Applied geostatistics with SGeMS: A user's guide [M]. Cambridge: Cambridge University Press, 2009: 164-169.