Water quality prediction system using LSTM NN and IoT

Abstract

Drinking water that is both clean and safe is critical to one’s well-being. Checking the quality of water regularly can be an initial step in ensuring pure drinking water. The existing system is time consuming and monotonous manual system. Therefore, we propose a system based on Machine Learning (ML) and Internet of Things(IoT) that can measure and forecast future water quality parameters. For this, the daily water quality data was taken from the Muvattupuzha River in Kerala. Long Short-Term Memory Neural Network (LSTM NN) was used to bring out the time series pattern in the data. The sensors like pH sensor, turbidity sensor and total dissolved solids (TDS) sensor were used to read the current water quality parameters and this data was used to predict the future parameter values. The IoT module which includes the sensors, Arduino and NodeMCU can be installed in the water source to monitor the parameters regularly. The main benefit of this system is that users can be notified ahead of time if there is a risk of pollution, allowing them to disinfect the water before it becomes polluted.