Department of Biosystems and Agricultural Engineering, Oklahoma State University, Stillwater, OK 74078, USA.
Department of Biosystems and Agricultural Engineering, Oklahoma State University, Stillwater, OK 74078, USA.
J Contam Hydrol. 2024 Sep;266:104418. doi: 10.1016/j.jconhyd.2024.104418. Epub 2024 Aug 26.
Scarcity of stream salinity data poses a challenge to understanding salinity dynamics and its implications for water supply management in water-scarce salt-prone regions around the world. This paper introduces a framework for generating continuous daily stream salinity estimates using instance-based transfer learning (TL) and assessing the reliability of the synthetic salinity data through uncertainty quantification via prediction intervals (PIs). The framework was developed using two temporally distinct specific conductance (SC) datasets from the Upper Red River Basin (URRB) located in southwestern Oklahoma and Texas Panhandle, United States. The instance-based TL approach was implemented by calibrating Feedforward Neural Networks (FFNNs) on a source SC dataset of around 1200 instantaneous grab samples collected by United States Geological Survey (USGS) from 1959 to 1993. The trained FFNNs were subsequently tested on a target dataset (1998-present) of 220 instantaneous grab samples collected by the Oklahoma Water Resources Board (OWRB). The framework's generalizability was assessed in the data-rich Bird Creek watershed in Oklahoma by manipulating continuous SC data to simulate data-scarce conditions for training the models and using the complete Bird Creek dataset for model evaluation. The Lower Upper Bound Estimation (LUBE) method was used with FFNNs to estimate PIs for uncertainty quantification. Autoregressive SC prediction methods via FFNN were found to be reliable with Nash Sutcliffe Efficiency (NSE) values of 0.65 and 0.45 on in-sample and out-of-sample test data, respectively. The same modeling scenario resulted in an NSE of 0.54 for the Bird Creek data using a similar missing data ratio, whereas a higher ratio of observed data increased the accuracy (NSE = 0.84). The relatively narrow estimated PIs for the North Fork Red River in the URRB indicated satisfactory stream salinity predictions, showing an average width equivalent to 25 % of the observed range and a confidence level of 70 %.
淡水资源匮乏地区的河流盐度数据稀缺，这给理解盐度动态及其对全球水资源短缺且盐分高的地区供水管理的影响带来了挑战。本文提出了一种利用实例迁移学习（TL）生成连续日河流盐度估算值的框架，并通过预测区间（PI）的不确定性量化来评估合成盐度数据的可靠性。该框架是使用美国俄克拉荷马州西南部和得克萨斯州狭长地带的上红河流域（URRB）两个时间上明显不同的电导率（SC）数据集开发的。实例迁移学习方法是通过对美国地质调查局（USGS） 1959 年至 1993 年采集的约 1200 个瞬时抓样的源 SC 数据集进行前馈神经网络（FFNN）校准来实现的。随后，将训练好的 FFNN 应用于由俄克拉荷马水资源委员会（OWRB）采集的 1998 年至今的 220 个瞬时抓样的目标数据集进行测试。通过对数据丰富的俄克拉荷马州鸟溪流域的连续 SC 数据进行处理，模拟训练模型的数据稀缺条件，并使用完整的鸟溪数据集进行模型评估，评估了该框架的泛化能力。利用 FFNN 的下限上限估计（LUBE）方法来估计不确定性的 PI。通过 FFNN 的自回归 SC 预测方法发现，在样本内和样本外测试数据中，纳什效率系数（NSE）值分别为 0.65 和 0.45，具有较高的可靠性。对于使用类似缺失数据比例的鸟溪数据，相同的建模方案导致 NSE 值为 0.54，而观察数据比例的增加则提高了准确性（NSE = 0.84）。在 URRB 的北叉红河上，相对较窄的估计 PI 表明河流盐度预测令人满意，平均宽度相当于观测范围的 25%，置信水平为 70%。
