TEMPORAL FUSION TRANSFORMER: A DEEP LEARNING APPROACH FOR MODELING AND FORECASTING RIVER WATER QUALITY INDEX
Date
2023-07-23
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
International Journal of Intelligent Systems and Applications in Engineering
Abstract
Water quality is a major factor when it comes to human and environmental health. The WQI is a key performance indicator for water management effectiveness. Water quality changes over time due to several seasonal attributes and physiochemical properties. Asthe seasons change at each site, the weather records are transformed into time series data, and the values of the physiochemical parameters shift accordingly. This paper introduces a novel temporal fusion transformer architecture for modelling and forecasting river water quality index. The WQI prediction model for the Bhavani River utilizes the temporal fusion transformer to incorporate temporal features fromvarious scales of time series data obtained from monitoring stations.The performance results of the study are compared with other existing prediction models and demonstrated the effectiveness of the temporal fusion transformer approach for modelling and forecasting river water quality.
Description
Keywords
Deep Learning Architectures, Prediction, River Water Quality, Temporal Fusion Transformer, Time Series Data, Water Quality Index.