| 一种改进的地下水模型结构不确定性分析方法 |
| |
| 引用本文： | 孙晓卓, 曾献奎, 吴吉春, 孙媛媛. 一种改进的地下水模型结构不确定性分析方法[J]. 水文地质工程地质, 2021, 48(6): 24-33. doi: 10.16030/j.cnki.issn.1000-3665.202012061 |
| |
| 作者姓名： | 孙晓卓 曾献奎 吴吉春 孙媛媛 |
| |
| 作者单位： | 南京大学地球科学与工程学院/表生地球化学教育部重点实验室，江苏 南京 210023 |
| |
| 基金项目： | 国家重点研发计划“场地土壤污染成因与治理技术”重点专项（2018YFC1800604）；国家自然科学基金项目（42072272） |
| |
| 摘 要： | 高斯过程回归（GPR）是一种基于贝叶斯理论的监督学习算法，在基于数据驱动（DDM）的模型结构不确定性分析中具有广泛应用。目前研究中通常假设物理参数和超参独立并进行联立识别，这会导致参数补偿。文章提出两步识别DDM量化模型结构误差，并通过2个地下水模型案例，分别在不考虑模型结构误差、考虑模型结构误差（联立识别DDM、两步识别DDM）的情况下，对比分析了参数识别和模型预测结果。结果表明，不考虑模型结构误差直接进行参数识别时，为补偿结构误差，物理参数会过度拟合，从而影响模型预测效果。基于DDM刻画模型结构偏差时，物理参数和超参的独立性假设会影响参数识别结果。提出的两步识别DDM法没有假设物理参数和超参独立，能够减少参数过度拟合效应，从而更准确刻画结构误差，有效提高了模型的预测性能。
|
| 关 键 词： | 模型结构不确定性 数据驱动 高斯过程回归 马尔科夫链蒙特卡洛模拟 溶质运移 |
| 收稿时间： | 2020-12-15 |
| 修稿时间： | 2021-02-18 |
An improved method of groundwater model structural uncertainty analysis |
| |
| SUN Xiaozhuo, ZENG Xiankui, WU Jichun, SUN Yuanyuan. An improved method of groundwater model structural uncertainty analysis[J]. Hydrogeology & Engineering Geology, 2021, 48(6): 24-33. doi: 10.16030/j.cnki.issn.1000-3665.202012061 |
| |
| Authors: | SUN Xiaozhuo ZENG Xiankui WU Jichun SUN Yuanyuan |
| |
| Affiliation: | Key Laboratory of Surficial Geochemistry of the Ministry of Education/School of Earth Sciences and Engineering, Nanjing University, Nanjing, Jiangsu 210023, China |
| |
| Abstract: | Gaussian Process Regression (GPR) is a supervised learning algorithm based on Bayesian theory, which is widely used in model structural uncertainty analysis based on data-driven method (DDM). In this study, it is usually assumed that the physical parameters and hyperparameters are independent and identified jointly, which will lead to parameter compensation. In this paper, a two-stage based DDM method is proposed to quantify the model structural errors, and two case studies are used to compare and analyze the results of parameter identification and model prediction with considering the model structural errors (joint calibration based DDM and two-stage based DDM) and without considering the model structural errors. The results show that when the parameters are identified directly without considering the model structural errors, the parameters will be overfitted and compensate the model structural errors, thereby affecting the model prediction performance. When considering the model structure deviation based on DDM, the independence assumption of physical parameters and hyperparameters will affect the parameter estimation results. The proposed two-stage based DDM method does not assume that the physical parameters and hyperparameters are independent, and can reduce parameter overfitting caused by the independence assumption of physical parameters and hyperparameters, portraying more accurate structural errors and effectively improving the model prediction performance. |
| |
| Keywords: | model structure uncertainty data-driven method Gaussian process regression MCMC solute transport |
|
| 点击此处可从《水文地质工程地质》浏览原始摘要信息 |
|
点击此处可从《水文地质工程地质》下载免费的PDF全文 |
