Given the interest in accurately predicting the Longitudinal Dispersion Coefficient (D_x) within the fields of hydraulic and water quality modeling, a wide range of methods have been used to estimate this parameter. In order to improve the accuracy of D_x predictions, this paper proposes the use of a Deep Convolutional Network (DCN), a sub-field of machine learning. The proposed deep neural network architecture consists of two parts; first, a one-dimensional convolutional neural network (CNN) to build informative feature maps, and second, a stack of deep, fully connected layers to estimate pollution dispersion (as D_x) in streams. To accurately predict D_x the developed model draws upon a large and diverse array of datasets in the form of three dimensionless parameters: Width/Depth (W/H), Velocity/Shear Velocity (U/u*), and Longitudinal Dispersion Coefficient/(Depth * Shear Velocity)

(D_x /Hu*). The model's accuracy is compared to that of several empirical models using a number of statistical measures. In addition, the DCN model results are compared with artificial neural network (ANN) and support vector machine (SVM) models implemented in this research and also similar studies applying various machine learning models (ML) towards D_x prediction. The statistical evaluation indicates that the DCN model outperforms the tested empirical, ANN, SVM and ML models with a significant difference. Additionally, five-fold cross-validation is performed to analyze the sensitivity and dependency of the DCN model's results on dataset selection, which shows that the dataset selection process does not significantly affect the model's accuracy. Since both ML and empirical models are, in general, poor predictors of the upper and lower ranges of D_x values, the DCN model's predictions of D_x in six different extreme-value ranges are assessed. The DCN model shows excellent accuracy in estimating D_x over the full possible range of data. In comparison with the empirical and ML models mentioned above, the DCN model more accurately predicts D_x values from river geometry and hydraulic datasets, with low errors across all ranges of D_x. The most significant advantage of DCN is that it tries to learn high-level features from data in an incremental manner.

鉴于对准确预测水力和水质建模领域中的纵向弥散系数（D _x）感兴趣，因此已使用多种方法来估算此参数。为了提高精度d _X的预测，本文中提出了深卷积网络（DCN），机器学习的一个子领域。提出的深度神经网络架构包括两部分：首先，是一维卷积神经网络（CNN），以建立信息丰富的特征图；其次，是一叠深的，完全连接的层，以估算流中的污染扩散（以D _x表示）。准确预测D _x所开发的模型以三个无量纲参数的形式利用了各种各样的数据集：宽度/深度（W / H），速度/剪切速度（U / u *）和纵向色散系数/（深度*剪切速度） ）

（D _x / Hu *）。使用多种统计方法将模型的准确性与几个经验模型的准确性进行比较。此外，将DCN模型的结果与本研究中实现的人工神经网络（ANN）和支持向量机（SVM）模型进行了比较，以及将各种机器学习模型（ML）应用于D _x的类似研究也进行了比较预言。统计评估表明，DCN模型优于经测试的经验模型，ANN，SVM和ML模型，但有显着差异。此外，执行五重交叉验证以分析DCN模型结果对数据集选择的敏感性和依赖性，这表明数据集选择过程不会显着影响模型的准确性。因为ML和经验模型两者都是，在一般情况下，上部和下部范围的差预测d _X值，的DCN模型的预测d _X在六个不同的极值范围评估。DCN模型在估计D _x时显示出极好的精度在所有可能的数据范围内。与上述经验模型和ML模型相比，DCN模型可以更准确地从河流几何数据和水力数据集中预测D _x值，并且在所有D _x范围内误差均很小。DCN的最大优势在于，它尝试以增量方式从数据中学习高级功能。