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

So Young Woo,Chung Gil Jung,Seong Joon Kim,Ji Wan Lee

doi:10.3390/su11123397

Abstract

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.

Highlights

Aquatic ecosystem is defined as a complex community where energy and nutrient exchanges occur through the interaction between living organisms and their environment
The purpose of this study is to confirm the applicability of Random Forest algorithm that consists of Soil and Water Assessment Tool (SWAT) water quality, temperature results and aquatic ecosystem health (AEH) data and to evaluate the AEH for Han river watershed streams
There are two main rivers, the Bukhan river and the Namhan river, which is joined at the stream where Paldang Dam (PDD) is located and flows to an outlet of the watershed through Seoul metropolitan city

Summary

Introduction

Aquatic ecosystem is defined as a complex community where energy and nutrient exchanges occur through the interaction between living organisms and their environment. A healthy aquatic ecosystem represents a stable and sustainable aquatic environment that maintains its ecological structure, processes, functions, and resilience to stress within its range of natural variability [1] Multiple stressors, such as organic and inorganic pollution, land use and geomorphological changes, water extraction, invasive species and pathogens, have detrimental effects on aquatic ecosystems including hydrological, chemical, and biological aspects [2]. Diatoms are used as a bioindicator of stream, because it has characteristics such as diverse species, short life spans, rapid response to changes in stream chemistry and habitat quality, and broadly distribution, which make geographical comparison possible [11,12,13] For these reasons, they have been used as an important indicator of ecological environments improvement or deterioration

Objectives

Methods

Results