Key Laboratory of Geotechnical Mechanics and Engineering of Ministry of Water Resources, Changjiang River Scientific Research Institute, Wuhan, 430010, Hubei, China.
College of New Energy and Environment, Jilin University, Changchun, 130021, China.
Environ Sci Pollut Res Int. 2023 Feb;30(8):22063-22077. doi: 10.1007/s11356-022-23767-2. Epub 2022 Oct 25.
Seawater intrusion is a common groundwater pollution problem, which has a great impact on ecological environment and economic development. In this paper, a numerical simulation model of variable density groundwater was constructed to simulate and predict the future seawater intrusion in Longkou city, Shandong Province of China. The influence of the sensitive parameter uncertainty of the model on the simulation results was evaluated by using the Monte Carlo method. In order to reduce the computational load from repeatedly calling the simulation model, the surrogate model was established by using the support vector regression (SVR) method. After training, the correlation coefficient R of the input-output relationship between the SVR surrogate model and the seawater intrusion simulation model reached 0.9957, with an average relative error of 0.2%, indicating that the surrogate model has a high fitting accuracy. Stochastic simulations of seawater intrusion showed that the seawater intrusion in the Longkou area will gradually aggravate at a slow rate, and the increase of seawater intrusion in the study area after 30 years was expected to range from - 6.03% to 7.37% at the 80% confidence level.
海水入侵是一种常见的地下水污染问题，对生态环境和经济发展有很大的影响。本文构建了变密度地下水数值模拟模型，对中国山东省龙口市未来的海水入侵进行了模拟和预测。采用蒙特卡罗法评价了模型敏感参数不确定性对模拟结果的影响。为了降低反复调用模拟模型的计算负荷，采用支持向量回归（SVR）方法建立了代理模型。经过训练，SVR 代理模型与海水入侵模拟模型之间的输入-输出关系的相关系数 R 达到 0.9957，平均相对误差为 0.2%，表明代理模型具有较高的拟合精度。海水入侵的随机模拟表明，龙口地区的海水入侵将以缓慢的速度逐渐加剧，预计在 30 年后，研究区域内的海水入侵将增加 6.03%至 7.37%，置信水平为 80%。
