Prediction of Chlorophyll-aConcentrations in the Nakdong River Using Machine Learning Methods
Prediction of Chlorophyll-aConcentrations in the Nakdong River Using Machine Learning Methods
复制标题
DOI：
10.3390/w12061822
复制
发表时间：
2020-06-01
期刊：
影响因子：
3.4
通讯作者：
Heo, Tae-Young
中科院分区：
文献类型：
--
作者：
Shin, Yuna;Kim, Taekgeun;Heo, Tae-Young
许多研究试图利用多元回归模型预测叶绿素浓度，并利用滞留技术对其进行验证。本研究利用支持向量回归、Bagging、随机森林、极端梯度增强（XGBoost）、循环神经网络（RNN）和长短期记忆（LSTM）等常用的机器学习模型，构建了一个预测韩国洛东江叶绿素浓度的新模型。我们采用超前一步递归预测来反映时间序列数据的特征。为了提高预测精度，模型构建采用正向变量选择的方法。通过累积学习和滚动窗口学习来验证拟合模型，而不是保留技术。将RNN模型与滚动窗口学习方法相结合进行叶绿素浓度预测，效果最好。结果表明，机器学习模型中解释变量的选择和1步递归预测是提高其预测性能的重要过程。
Many studies have attempted to predict chlorophyll-aconcentrations using multiple regression models and validating them with a hold-out technique. In this study commonly used machine learning models, such as Support Vector Regression, Bagging, Random Forest, Extreme Gradient Boosting (XGBoost), Recurrent Neural Network (RNN), and Long-Short-Term Memory (LSTM), are used to build a new model to predict chlorophyll-aconcentrations in the Nakdong River, Korea. We employed 1-step ahead recursive prediction to reflect the characteristics of the time series data. In order to increase the prediction accuracy, the model construction was based on forward variable selection. The fitted models were validated by means of cumulative learning and rolling window learning, as opposed to the hold-out technique. The best results were obtained when the chlorophyll-aconcentration was predicted by combining the RNN model with the rolling window learning method. The results suggest that the selection of explanatory variables and 1-step ahead recursive prediction in the machine learning model are important processes for improving its prediction performance.