Next Article in Journal
Mother-Related Determinants of Children At-Home Fruit and Vegetable Dietary Patterns in a Polish National Sample
Previous Article in Journal
Study on the Evolution of Water Resource Utilization Efficiency in Tibet Autonomous Region and Four Provinces in Tibetan Areas under Double Control Action
Previous Article in Special Issue
Application of SWAT Model with a Modified Groundwater Module to the Semi-Arid Hailiutu River Catchment, Northwest China
Open AccessArticle

Evaluation of Watershed Scale Aquatic Ecosystem Health by SWAT Modeling and Random Forest Technique

1
School of Civil and Environmental Engineering, College of Engineering, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul 05029, Korea
2
Agricultural and Water Resources Engineering, Texas A&M AgriLife Research Center at El Paso, 1380 A&M Circle, El Paso, TX 79927-5020, USA
*
Author to whom correspondence should be addressed.
Sustainability 2019, 11(12), 3397; https://doi.org/10.3390/su11123397
Received: 27 March 2019 / Revised: 18 June 2019 / Accepted: 18 June 2019 / Published: 20 June 2019
In this study, we evaluated the aquatic ecosystem health (AEH) with five grades (A; very good to E; very poor) of FAI (Fish Assessment Index), TDI (Trophic Diatom Index), and BMI (Benthic Macroinvertebrate Index) using the results of SWAT (Soil and Water Assessment Tool) stream water temperature (WT) and quality (T-N, T-P, NH4, NO3, and PO4). By applying Random Forest, one of the machine learning algorithms for classification analysis, each AEH index was trained and graded from the SWAT results. For Han river watershed (34,418 km2) in South Korea, the 8 years (2008~2015) observed AEH data of Spring and Fall periods at 86 locations from NAEMP (National Aquatic Ecological Monitoring Program) were used. The AEH was separately trained for Spring (FAIs, TDIs, and BMIs) and Fall (FAIa, TDIa, and BMIa), and the AEH results of Random Forest with SWAT (WT, T-N, T-P, NH4, NO3, and PO4) as input variables showed the accuracy of 0.42, 0.48, 0.62, 0.45, 0.4, and 0.58, respectively. The reason for low accuracy was from the weak strength of the individual trees and high correlation between the trees composing the Random Forest due to the data imbalance. The AEH distribution results showed that the number of Grade A of total FAI, TDI, and BMI were 84, 0, and 158 respectively and they were mostly located at the upstream watersheds. The number of Grade E of total FAI, TDI, and BMI were 4, 50, and 13 and they were shown at downstream watersheds. View Full-Text
Keywords: Aquatic Ecosystem Health; Fish Assessment Index; Trophic Diatom Index; Benthic Macroinvertebrate Index; SWAT; Random Forest Aquatic Ecosystem Health; Fish Assessment Index; Trophic Diatom Index; Benthic Macroinvertebrate Index; SWAT; Random Forest
Show Figures

Figure 1

MDPI and ACS Style

Woo, S.Y.; Jung, C.G.; Lee, J.W.; Kim, S.J. Evaluation of Watershed Scale Aquatic Ecosystem Health by SWAT Modeling and Random Forest Technique. Sustainability 2019, 11, 3397. https://doi.org/10.3390/su11123397

AMA Style

Woo SY, Jung CG, Lee JW, Kim SJ. Evaluation of Watershed Scale Aquatic Ecosystem Health by SWAT Modeling and Random Forest Technique. Sustainability. 2019; 11(12):3397. https://doi.org/10.3390/su11123397

Chicago/Turabian Style

Woo, So Y.; Jung, Chung G.; Lee, Ji W.; Kim, Seong J. 2019. "Evaluation of Watershed Scale Aquatic Ecosystem Health by SWAT Modeling and Random Forest Technique" Sustainability 11, no. 12: 3397. https://doi.org/10.3390/su11123397

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