WaterNet: A Network for Monitoring and Assessing Water Quality for Drinking and Irrigation Purposes

Water is a fundamental requirement for human, animal, and plant survival. Despite its importance, quality water not always fit drinking, domestic and/or industrial use. Numerous factors such as industrialization, mining, pollution, natural occurrences impact the of water, they introduce or alter various parameters present therein, thus, affecting suitability human consumption general The World Health Organization has guidelines which stipulate threshold levels in samples intended irrigation. Quality Index (WQI) Irrigation WQI (IWQI) are metrics used to express level these determine overall quality. Collecting from different sources, measuring present, bench-marking measurements against pre-set standards, while adhering during transportation measurement can be extremely daunting. To this end study proposes network architecture collect data on real-time use machine learning (ML) tools automatically drinking irrigation purposes. developed monitoring based LoRa takes land topology into consideration. Results simulations done Radio Mobile revealed partial mesh most adequate. Due absence large open datasets usable training ML models were developed. Three -Random Forest (RF), Logistic Regression (LR) Support Vector Machine (SVM) considered classification results obtained showed that LR performed best SVM was better suited water. Recursive feature elimination then combined with three reveal had greatest influence accuracies respective model.