Water Pumping Requirement Prediction in Irrigation System Using Internet of Things-Assisted Machine Intelligence-Based Approach

Irrigation system (IS) is considered as a crucial component in the human society. It plays a crucial role for the supply of water to the cultivation fields. So, it is very much essential to predict the water pumping requirement in IS. In this work, an Internet of Things (IoT)-assisted machine intelligence (MI)-based approach is proposed for the prediction of water pumping requirement in IS. This work is focused on the machine learning (ML)-based models such as random forest (RF), CatBoost (CB), K-nearest neighbors (KNN), and stochastic gradient descent (SGD) to perform the prediction. In this work, the water pumping requirement is monitored using IoT-assisted sensors. Here, the water pumping requirement and non-requirement cases are represented using 1 and 0, respectively. This work is carried out using cross-validation (CRV) by taking the number of folds (NFL) as 3, 5, and 10. These models are evaluated using classification accuracy (CA). This work is implemented using Python-based Orange 3.32.0.