期刊
WATER
卷 15, 期 12, 页码 -出版社
MDPI
DOI: 10.3390/w15122222
关键词
artificial neural network; ant colony optimization; groundwater quality; prediction
The quality of groundwater is crucial for human health and the environment, especially as it is the main source of drinking water in many parts of the world. Traditional water-quality monitoring methods are expensive and time-consuming, but data-driven models using artificial intelligence offer a more efficient way to predict groundwater quality. This study aims to build an optimized neural network using ant colony optimization and artificial neural network techniques for predicting groundwater quality parameters.
The quality of groundwater is of utmost importance, as it directly impacts human health and the environment. In major parts of the world, groundwater is the main source of drinking water, hence it is essential to periodically monitor its quality. Conventional water-quality monitoring techniques involve the periodical collection of water samples and subsequent analysis in the laboratory. This process is expensive, time-consuming and involves a lot of manual labor, whereas data-driven models based on artificial intelligence can offer an alternative and more efficient way to predict groundwater quality. In spite of the advantages of such models based on artificial neural network (ANN) and ant colony optimization (ACO), no studies have been carried out on the applications of these in the field of groundwater contamination. The aim of our study is to build an ant colony optimized neural network for predicting groundwater quality parameters. We have proposed ANN comprising of six hidden layers. The approach was validated using our groundwater quality dataset of a hard rock region located in the northern part of Karnataka, India. Groundwater samples were collected by us once every 4 months from March 2014 to October 2020 from 50 wells in this region. These samples were analyzed for the pH, electrical conductivity, Na+, Ca+, K+, Mg2+, HCO3,- F-, Cl- and U+. This temporal dataset was split for training, testing and validation of our model. Metrics such as R-2 (Coefficient of Determination), RMSE (Root Mean Squared Error), NSE (Nash-Sutcliffe efficiencies) and MAE (Mean Absolute Error) were used to evaluate the prediction error and model performance. These performance evaluation metrics indicated the efficiency of our model in predicting the temporal variation in groundwater quality parameters. The method proposed can be used for prediction and it will aid in modifying or reducing the temporal frequency of sample collection to save time and cost. The study confirms that the combination of ANN with ACO is a promising tool to optimize weights while training the network, and for prediction of groundwater quality.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据