Dwivedi Dipankar, Mohanty Binayak P, Lesikar Bruce J
Department of Biological and Agricultural Engineering, Texas A&M University, TX 77843.
Water Resour Res. 2013 May;49(5):2896-2906. doi: 10.1002/wrcr.20265.
Microbes have been identified as a major contaminant of water resources. () is a commonly used indicator organism. It is well recognized that the fate of in surface water systems is governed by multiple physical, chemical, and biological factors. The aim of this work is to provide insight into the physical, chemical, and biological factors along with their interactions that are critical in the estimation of loads in surface streams. There are various models to predict loads in streams, but they tend to be system or site specific or overly complex without enhancing our understanding of these factors. Hence, based on available data, a Bayesian Neural Network (BNN) is presented for estimating loads based on physical, chemical, and biological factors in streams. The BNN has the dual advantage of overcoming the absence of quality data (with regards to consistency in data) and determination of mechanistic model parameters by employing a probabilistic framework. This study evaluates whether the BNN model can be an effective alternative tool to mechanistic models for loads estimation in streams. For this purpose, a comparison with a traditional model (LOADEST, USGS) is conducted. The models are compared for estimated loads based on available water quality data in Plum Creek, Texas. All the model efficiency measures suggest that overall loads estimations by the BNN model are better than the loads estimations by the LOADEST model on all the three occasions (three-fold cross validation). Thirteen factors were used for estimating loads with the exhaustive feature selection technique, which indicated that six of thirteen factors are important for estimating loads. Physical factors included temperature and dissolved oxygen; chemical factors include phosphate and ammonia; biological factors include suspended solids and chlorophyll. The results highlight that the LOADEST model estimates loads better in the smaller ranges, whereas the BNN model estimates loads better in the higher ranges. Hence, the BNN model can be used to design targeted monitoring programs and implement regulatory standards through TMDL programs.
微生物已被确认为水资源的主要污染物。（）是一种常用的指示生物。人们普遍认识到，地表水体系统中（）的归宿受多种物理、化学和生物因素的控制。这项工作的目的是深入了解对估算地表溪流中（）负荷至关重要的物理、化学和生物因素及其相互作用。有各种模型可用于预测溪流中的（）负荷，但它们往往针对特定系统或地点，或者过于复杂，无法增进我们对这些因素的理解。因此，基于现有数据，提出了一种贝叶斯神经网络（BNN），用于根据溪流中的物理、化学和生物因素估算（）负荷。BNN具有双重优势，即克服了缺乏高质量数据（关于数据一致性）的问题，并通过采用概率框架来确定机理模型参数。本研究评估BNN模型是否可以成为估算溪流中（）负荷的机理模型的有效替代工具。为此，与传统模型（美国地质调查局负荷估算模型）进行了比较。根据得克萨斯州李子溪的现有水质数据，对这些模型估算的（）负荷进行了比较。所有模型效率指标均表明，在所有三次（三重交叉验证）中，BNN模型估算的总体（）负荷均优于负荷估算模型估算的（）负荷。使用穷举特征选择技术，用13个因素来估算（）负荷，这表明13个因素中有6个对估算（）负荷很重要。物理因素包括温度和溶解氧；化学因素包括磷酸盐和氨；生物因素包括悬浮固体和叶绿素。结果表明，负荷估算模型在较小范围内估算（）负荷效果更好，而BNN模型在较高范围内估算（）负荷效果更好。因此，BNN模型可用于设计有针对性的监测计划，并通过TMDL计划实施监管标准。
