Next Article in Journal
Preparation, Performances and Mechanisms of [email protected] Composite for Herbicide Atrazine Removal in Water
Previous Article in Journal
Hazards, Vulnerability, and Risk Analysis on Wave Overtopping and Coastal Flooding in Low-Lying Coastal Areas: The Case of Costa da Caparica, Portugal
Open AccessArticle

Application of Convolution Neural Networks and Hydrological Images for the Estimation of Pollutant Loads in Ungauged Watersheds

Department of Policy for Watershed Management, The Policy Council for Paldang Watershed, Yangpyeong 12585, Korea
Water 2021, 13(2), 239; https://doi.org/10.3390/w13020239
Received: 12 December 2020 / Revised: 11 January 2021 / Accepted: 15 January 2021 / Published: 19 January 2021
(This article belongs to the Section Hydrology and Hydrogeology)
River monitoring and predicting analysis for establishing pollutant loads management require numerous budgets and human resources. However, it is general that the number of government officials in charge of these tasks is few. Although the government has been commissioning a study related to river management to experts, it has been inevitable to avoid the consumption of a massive budget because the characteristics of pollutant loads present various patterns according to topographic of the watershed, such as topology like South Korea. To address this, previous studies have used conceptual and empirical models and have recently used artificial neural network models. The conceptual model has a shortcoming in which it required massive data and has vexatious that has to enforce the sensitivity and uncertain analysis. The empirical model and artificial neural network (ANN) need lower data than a conceptual model; however, these models have a flaw that could not reflect the topographical characteristic. To this end, this study has used a convolution neural network (CNN), one of the deep learning algorithms, to reflect the topographical characteristic and had estimated the pollutant loads of ungauged watersheds. The estimation results for the biochemical oxygen demand (BOD) and total phosphorus (TP) loads for three ungauged watersheds were all excellent. However, prediction results with low accuracy were obtained when the hydrological images of a watershed with a land cover status different from the ungauged watersheds were used as training data for the CNN model. View Full-Text
Keywords: ungauged watershed; convolution neural network; hydrological image; curve number; biochemical oxygen demand; total phosphorus ungauged watershed; convolution neural network; hydrological image; curve number; biochemical oxygen demand; total phosphorus
Show Figures

Figure 1

MDPI and ACS Style

Song, C.M. Application of Convolution Neural Networks and Hydrological Images for the Estimation of Pollutant Loads in Ungauged Watersheds. Water 2021, 13, 239. https://doi.org/10.3390/w13020239

AMA Style

Song CM. Application of Convolution Neural Networks and Hydrological Images for the Estimation of Pollutant Loads in Ungauged Watersheds. Water. 2021; 13(2):239. https://doi.org/10.3390/w13020239

Chicago/Turabian Style

Song, Chul M. 2021. "Application of Convolution Neural Networks and Hydrological Images for the Estimation of Pollutant Loads in Ungauged Watersheds" Water 13, no. 2: 239. https://doi.org/10.3390/w13020239

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop