[论文解读] Comparison of Machine Learning Methods for Predicting Karst Spring Discharge in North China
本研究利用32年降水与径流数据,评估了三种机器学习模型——多层感知机(MLP)、长短期记忆循环神经网络(LSTM-RNN)和支持向量回归(SVR)——在华北地区岩溶泉流量预测中的表现。MLP与LSTM-RNN显著优于SVR,其中MLP误差指标最低(MSE: 0.0010,MAE: 0.0254,RMSE: 0.0318),表明其在模拟非线性水文动态方面具有显著优势。
The quantitative analyses of karst spring discharge typically rely on physical-based models, which are inherently uncertain. To improve the understanding of the mechanism of spring discharge fluctuation and the relationship between precipitation and spring discharge, three machine learning methods were developed to reduce the predictive errors of physical-based groundwater models, simulate the discharge of Longzici Spring's karst area, and predict changes in the spring on the basis of long time series precipitation monitoring and spring water flow data from 1987 to 2018. The three machine learning methods included two artificial neural networks (ANNs), namely, multilayer perceptron (MLP) and long short-term memory-recurrent neural network (LSTM-RNN), and support vector regression (SVR). A normalization method was introduced for data preprocessing to make the three methods robust and computationally efficient. To compare and evaluate the capability of the three machine learning methods, the mean squared error (MSE), mean absolute error (MAE), and root-mean-square error (RMSE) were selected as the performance metrics for these methods. Simulations showed that MLP reduced MSE, MAE, and RMSE to 0.0010, 0.0254, and 0.0318, respectively. Meanwhile, LSTM-RNN reduced MSE to 0.0010, MAE to 0.0272, and RMSE to 0.0329. Moreover, the decrease in MSE, MAE, and RMSE were 0.0910, 0.1852, and 0.3017, respectively, for SVR. Results indicated that MLP performed slightly better than LSTM-RNN, and MLP and LSTM-RNN performed considerably better than SVR. Furthermore, ANNs were demonstrated to be prior machine learning methods for simulating and predicting karst spring discharge.
研究动机与目标
- 利用机器学习降低物理基地下水模型在岩溶泉流量预测中的误差。
- 基于长期降水与径流数据(1987–2018),模拟并预测华北地区龙子湖泉流量。
- 在真实水文条件下,评估三种机器学习方法(MLP、LSTM-RNN与SVR)的性能。
- 确定最有效的机器学习方法,以模拟和预测岩溶含水层中非线性泉流量动态。
提出的方法
- 应用多层感知机(MLP)与长短期记忆循环神经网络(LSTM-RNN)建模降水与泉流量之间的非线性关系。
- 采用径向基函数(RBF)核的支持向量回归(SVR)作为对比性机器学习方法。
- 对所有三种方法实施数据归一化,以提升模型鲁棒性与计算效率。
- 使用1987年至2012年的历史数据进行模型训练,并在2012年至2018年的数据上测试性能,以评估泛化能力。
- 采用标准指标评估模型性能:均方误差(MSE)、平均绝对误差(MAE)与均方根误差(RMSE)。
- 通过散点图与统计误差分析,将模型预测结果与实测泉流量进行对比。
实验结果
研究问题
- RQ1机器学习模型能否有效降低物理基地下水模型在岩溶泉流量预测中的误差?
- RQ2在使用长期降水与径流数据的条件下,MLP、LSTM-RNN与SVR在月尺度泉流量预测中的表现如何比较?
- RQ3在龙子湖泉岩溶区域,哪种机器学习模型能提供最准确的短期泉流量预测?
- RQ4与传统回归模型相比,人工神经网络(ANN)在多大程度上能够捕捉岩溶水文系统的非线性动态?
主要发现
- MLP的误差指标最低,MSE = 0.0010,MAE = 0.0254,RMSE = 0.0318,表明其具有更高的预测精度。
- LSTM-RNN表现接近MLP,MSE = 0.0010,MAE = 0.0272,RMSE = 0.0329,显示出在序列数据上的强大性能。
- SVR表现出显著更高的误差,MSE = 0.0910,MAE = 0.1852,RMSE = 0.3017,表明其预测能力较弱。
- MLP与LSTM-RNN模型的预测值与实测值高度吻合,散点图显示预测值与实测值点群紧密分布在1:1线附近。
- SVR存在系统性偏差,在低流量条件下略微高估,高流量条件下则低估。
- 与SVR相比,基于人工神经网络的模型(MLP与LSTM-RNN)在模拟与预测岩溶泉流量方面更为有效,因其能够更好地捕捉复杂且非线性的动态特征。
更好的研究,从现在开始
从阅读论文到最终审阅,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。