What question did this study set out to answer?

The aim is to develop a neural network that predicts water quality parameters from real-time sensor data.

January 18, 2026Open Access

Water Quality Prediction using LSTM: A Deep Learning Approach at Wat Makham Station, Chao Phraya River, Thailand

Key Points

The aim is to develop a neural network that predicts water quality parameters from real-time sensor data.
Developed a Long Short-Term Memory (LSTM) neural network model.
Collected real-time water quality data from IoT sensors over nine months.
Applied data cleansing techniques, specifically the Interquartile Range (IQR) for outlier detection.
Achieved high prediction accuracy for stable indicators such as pH and salinity.
Prediction accuracy for pH: MSE = 0.0064, MAPE = 0.89%.
Difficulties in predicting highly volatile parameters like turbidity and chlorophyll, with MAPE = 32.87% and 38.64%, respectively.

Abstract

This study develops a Long Short-Term Memory (LSTM) neural network for forecasting water quality parameters at the Wat Makham Station based on data collected from the Chao Phraya River, Thailand, for nine months. The study used IoT sensors to collect real-time values for ten water quality indicators: Turbidity (TURBNTU), Optical Dissolved Oxygen (HDO), Dissolved Oxygen Saturation (HDOSAT), Spatial Conductivity (SPCOND), Acidity/Basicity (pH), Total Dissolved Solids (TDS), Salinity (SALINITY), Temperature (TEMP), Chlorophyll (CHL), and Depth (DEPTH). The study identified water quality indicators through the implementation of an LSTM model following application of data cleansing techniques, using mainly the Interquartile Range (IQR) method for outlier detection. The results confirm that prediction accuracy varied across parameters. For stable indicators, very high prediction accuracy was achieved: for pH, MSE = 0. 0064, MAPE = 0. 89%, RMSE = 0. 0800, and RMSPE = 1. 12%; for salinity, MSE = 0. 0006, MAPE = 10. 55%, RMSE = 0. 0246, and RMSPE = 41. 14%. Temperatures were predicted with high confidence also: MAPE = 2. 59% and RMSPE = 3. 24%. In contrast, highly volatile parameters were difficult to predict; Turbidity MAPE = 32. 87% and RMSPE = 109. 22%; Chlorophyll MAPE = 38. 64% and RMSPE = 190. 15%.

Water Quality Prediction using LSTM: A Deep Learning Approach at Wat Makham Station, Chao Phraya River, Thailand

Key Points

Abstract

Cite This Study