A Deep Learning Modeling Framework with Uncertainty Quantification for Inflow-Outflow Predictions for Cascade Reservoirs
A Deep Learning Modeling Framework with Uncertainty Quantification for Inflow-Outflow Predictions for Cascade Reservoirs
复制标题
DOI：
10.1016/j.jhydrol.2024.130608
复制
发表时间：
2024-01
影响因子：
6.4
通讯作者：
Vinh Ngoc Tran;V. Ivanov;Giang Tien Nguyen;Anh Ngoc Tran;Phuong Huy Nguyen;Dae-Hong Kim;Jongho Kim
中科院分区：
文献类型：
--
作者：
Vinh Ngoc Tran;V. Ivanov;Giang Tien Nguyen;Anh Ngoc Tran;Phuong Huy Nguyen;Dae-Hong Kim;Jongho Kim
准确预测水库的流入和流出及其不确定性对于水资源管理和建立预警系统至关重要。然而，由于许多不确定性，这可能是一个艰巨的挑战，特别是在梯级水库系统中。为了在一个框架中同时无缝地量化任意的(数据引起的)和认知的(模型网络引起的)不确定性，我们估计了贝叶斯神经网络中参数的后验分布，同时测量预测方差以反映数据中的噪声。通过随机丢弃网络中的某些单元，估计的后验分布可以与新的损失函数相结合。这一针对长期短期记忆网络的复杂深度学习框架还包括先进的支持方法，如输入变量选择、数据转换和超参数优化。在这项研究中训练的模型被应用于越南的两个梯级水库系统，四个水库，从两个不同的来源提供不确定性估计。通过对全球三种水库调度方案的比较，发现所提出的模型在所有情况下都取得了较好的效果，预测中的不确定性主要是由于数据噪声，而不是模型本身的不确定性。使用小波变换对数据进行预处理可以减少模型本身无法分类的噪声，从而提高性能，特别是在提前期较长的情况下。预测结果的令人满意的表现证实了该框架可以有效地利用深度学习来评估水文预测的不确定性。
Accurate prediction of reservoir inflows and outflows and their uncertainties is essential for managing water resources and establishing early-warning systems. However, this can be a formidable challenge due to numerous uncertainties, particularly in cascade reservoir systems. To seamlessly quantify aleatoric (data-caused) and epistemic (model network–caused) uncertainties simultaneously in a single framework, we estimated the posterior distribution of parameters in a Bayesian neural network while measuring prediction variance to reflect the noise in data. By randomly discarding certain units within the network, the estimated posterior distribution can be combined with a new loss function. This sophisticated deep learning framework for a long short-term memory network has also included advanced supporting approaches, such as input variable selection, data transformation, and hyperparameter optimization. The model trained in this study was applied to two cascade reservoir systems with four reservoirs in Vietnam, providing uncertainty estimates from two distinct sources. Comparing three global reservoir operation schemes, we found that the proposed model achieved superior performance in all cases, and uncertainty in the forecasts was due primarily to data noise, rather than uncertainty in the model itself. Preprocessing data using a wavelet transform can reduce noise that the model cannot classify on its own, resulting in improved performance, particular with longer lead times. The satisfactory performance of the prediction results confirms that the framework can effectively assess the uncertainty of hydrologic predictions using deep learning.