Predicting suspended sediment load in Peninsular Malaysia using support vector machine and deep learning algorithms

Ahmed H Birima,Yuk Feng Huang,Yusuf Essam,Ahmed El-Shafie,Ali Najah Ahmed

doi:10.1038/s41598-021-04419-w

Abstract

High loads of suspended sediments in rivers are known to cause detrimental effects to potable water sources, river water quality, irrigation activities, and dam or reservoir operations. For this reason, the study of suspended sediment load (SSL) prediction is important for monitoring and damage mitigation purposes. The present study tests and develops machine learning (ML) models, based on the support vector machine (SVM), artificial neural network (ANN) and long short-term memory (LSTM) algorithms, to predict SSL based on 11 different river data sets comprising of streamflow (SF) and SSL data obtained from the Malaysian Department of Irrigation and Drainage. The main objective of the present study is to propose a single model that is capable of accurately predicting SSLs for any river data set within Peninsular Malaysia. The ANN3 model, based on the ANN algorithm and input scenario 3 (inputs consisting of current-day SF, previous-day SF, and previous-day SSL), is determined as the best model in the present study as it produced the best predictive performance for 5 out of 11 of the tested data sets and obtained the highest average RM with a score of 2.64 when compared to the other tested models, indicating that it has the highest reliability to produce relatively high-accuracy SSL predictions for different data sets. Therefore, the ANN3 model is proposed as a universal model for the prediction of SSL within Peninsular Malaysia.

Highlights

The conservation of river water quality is important for human civilization as river water often represents a source of potable water while being used for irrigation purposes in many regions, including Peninsular Malaysia[1,2,3,4]
Time series data sets on daily SF and suspended sediment load (SSL) were obtained for 11 different rivers throughout Peninsular Malaysia and used to develop machine learning (ML) models for SSL prediction using three ML algorithms, namely support vector machine (SVM), artificial neural network (ANN), and long short-term memory (LSTM)
The ANN3 model, which utilises the ANN algorithm and input scenario 3 is the best performing SSL-predicting model

Summary

Introduction

The conservation of river water quality is important for human civilization as river water often represents a source of potable water while being used for irrigation purposes in many regions, including Peninsular Malaysia[1,2,3,4]. In 2016, it was reported by Malaysia’s Natural Resources and Environment Minister that a major Malaysian river recorded a Nephelometric Turbidity Unit (NTU) of 6000, indicating a significantly high concentration of suspended sediments causing poor water quality. In 2021, Sungai Pinang was reported to be polluted with sediments consisting of broken-down organic matter, causing the river to have a black appearance. This sediment-based pollution was a source of foul stench affecting a nearby food court and condominium within the vicinity of the Karpal Singh Drive.

Objectives

Methods

Results

Conclusion