Modeling daily chlorophyll a dynamics in a German lowland river using artificial neural networks and multiple linear regression approaches
Modeling daily chlorophyll a dynamics in a German lowland river using artificial neural networks and multiple linear regression approaches
复制标题
DOI：
10.1007/s10201-013-0412-1
复制
发表时间：
2013
期刊：
影响因子：
1.6
通讯作者：
N. Wu;Jiacong Huang;B. Schmalz;N. Fohrer
中科院分区：
文献类型：
--
作者：
N. Wu;Jiacong Huang;B. Schmalz;N. Fohrer
浮游植物生物量是水质的重要指标，其动态预测是河流生态与管理领域的重要问题之一。然而，绝大多数河流系统的模型主要集中在流量预测和水质上，很少应用于叶绿素（Chla）等生物参数。基于1.5年的Chlaand环境变量测量数据集，我们开发了两种建模方法[人工神经网络（ANN）和多元线性回归（MLR）]来模拟德国低地河流的每日Chladynamics。总的来说，所建立的人工神经网络和MLR模型在预测氯浓度的日动态方面取得了令人满意的精度。虽然没有预测到一些峰值和低点，但MLR模型的预测数据与观测数据非常吻合，校正期的决定系数（R2）、Nash-Sutcliffe效率（NS）和均方根误差（RMSE）分别为0.53、0.53和2.75，验证期的均方根误差（RMSE）分别为0.63、0.62和1.94。同样，人工神经网络模型的结果也表明，在校准和验证期间，观测数据和预测数据之间的一致性很好，这一点通过r2、NS和RMSE值得到了证明（校准期间分别为0.68、0.68和2.27，验证期间分别为0.55、0.66和2.12）。敏感性分析表明，氯浓度对溶解态无机氮、硝酸盐氮、自回归Chla、氯化物、硫酸盐和总磷高度敏感。结果表明，基于相关环境因子，采用人工神经网络模型和多变量回归模型均可预测德国低地河流的日chladydynamics。人工神经网络模型非常适合求解非线性和复杂的问题，而MLR模型可以明确地探索自变量和因变量之间的系数。还需要进一步的研究来提高所开发模型的准确性。
Phytoplankton biomass is an important indicator for water quality, and predicting its dynamics is thus regarded as one of the important issues in the domain of river ecology and management. However, the vast majority of models in river systems have focused mostly on flow prediction and water quality with very few applications to biotic parameters such as chlorophylla(Chla). Based on a 1.5-year measured dataset of Chlaand environmental variables, we developed two modeling approaches [artificial neural networks (ANN) and multiple linear regression (MLR)] to simulate the daily Chladynamics in a German lowland river. In general, the developed ANN and MLR models achieved satisfactory accuracy in predicting daily dynamics of Chlaconcentrations. Although some peaks and lows were not predicted, the predicted and the observed data matched closely by the MLR model with the coefficient of determination (R2), Nash–Sutcliffe efficiency (NS), and the root mean square error (RMSE) of 0.53, 0.53, and 2.75 for the calibration period and 0.63, 0.62, and 1.94 for the validation period, respectively. Likewise, the results of the ANN model also illustrated a good agreement between observed and predicted data during calibration and validation periods, which was demonstrated byR2, NS, and RMSE values (0.68, 0.68, and 2.27 for the calibration period, 0.55, 0.66 and 2.12 for the validation period, respectively). According to the sensitivity analysis, Chlaconcentration was highly sensitive to dissolved inorganic nitrogen, nitrate–nitrogen, autoregressive Chla, chloride, sulfate, and total phosphorus. We concluded that it was possible to predict the daily Chladynamics in the German lowland river based on relevant environmental factors using either ANN or MLR models. The ANN model is well suited for solving non-linear and complex problems, while the MLR model can explicitly explore the coefficients between independent and dependent variables. Further studies are still needed to improve the accuracy of the developed models.