Abstract
The abilities of Long short-term memory (LSTM), Gated recurrent units (GRU), Adaptive-network-based fuzzy inference system (ANFIS), Artificial neural networks (ANN), and Group method of data handling (GMDH) in predicting water quality time series associated with a cleansing biotope were evaluated. We examined continuous monitoring time series of chlorophyll-a, turbidity, and specific conductivity using YSI EXO datasondes at the Inlet and Outlet. Based on Root Mean Square Errors, Mean Absolute Percentage Errors, Mean Absolute Errors, Correlation Coefficients, and Theil’s U, the GRU generally was the most efficient model in predicting the Outlet water quality. AI models should find increasing implementation the area of ‘smart environment’. Ways forward for enhancing AI model performance were suggested to better consider data periodicity and explore a transfer function approach in which the water quality timeseries of one parameter is forecast based on an ensemble of other parameters.
Additional information
Notes on contributors
Ho Huu Loc
Dr. Ho Huu Loc is currently working as a postdoctoral research fellow at Nanyang Technological University (NTU), Singapore. Water Engineering has been the focal point of his expertise, including water sensitive urban designs and numerical modeling. Dr. Ho is an experience field person, comfortable operating advanced cloud-based monitoring systems (e.g., IoT hydro-meteorological stations, YSI data sondes, water quality auto-samplers). Advanced numerical modeling capability constitutes another important component of Dr. Ho’s practical skill set, including being familiar with a wide range of numerical models, such as PCSWMM, Hec-RAS, Mike, and competent data analytics capability, plus geospatial analysis technologies (GIS, remote sensing).
Quang Hung Do
Dr. Do Quang Hung is a faculty member of University of Transport Technology (Vietnam). He was a researcher and a lecturer at Feng Chia University (Taiwan). He has published more than 50 papers in international journals and conferences. He is a reviewer for several SCI-indexed journals, including Applied Soft Computing, Journal of the Operational Research Society. He also served as a program committee member for several international conferences such as ACITY-2017, CSITY-2018, CSEN-2018 and ITCA-2019. His primary field of research interest is Artificial Intelligence (AI) and its applications in business, management, and engineering.
A.A. Cokro
Dr. A.A. Cokro is a research fellow at the Nanyang Technological University (NTU), Singapore. She has conducted research in the field of wastewater treatment, where she studied the phosphorus removal from the wastewater in the tropics. Her current research aims to examine the performance of Cleansing Biotope system in treating surface runoff and to ultimately improve the efficiency of such system in Singapore. Planning and conducting field sampling activities, controlled experiments, and laboratory scale Sequencing Batch Reactors (SBRs) studies; as well as performing tests and data analyses on water/wastewater samples are part of her research expertise.
Kim N. Irvine
Dr. Kim N. Irvine is a Visiting Associate Professor in the Faculty of Architecture and Planning, Thammasat University, Thailand. Dr. Irvine’s research is applied in nature and focuses on hydrologic process modelling, identifying and quantifying pollutant sources and pathways at the watershed scale, sustainable urban waterscapes, site characterization (physical, chemical, biological) for habitat remediation, and spatial analysis of environmental indicators. This work has included a combination of sampling, long term automated monitoring, and mathematical modelling.