The global warming and climate change is a one of the main reason for shortage of water. Therefore, smart use of water resources is necessary for long-term sustainability. In different large-scale water consumer industries, the agriculture is one of the key consumers. The utilized water in this industry has polluted and not being utilized as fresh water. Therefore, optimization in water management systems in agricultural irrigation system is required. In this paper, we provide a study of the components utilized for designing a smart irrigation system. The key components are: (1) soil moisture and temperature based water prediction (2) weather prediction module and (3) the application of both in irrigation system automation is simulated. The problem of water management has formulated as proactive resource management. Therefore, the prediction of weather conditions and sensor readings has used to map these readings to water supply treatment. The Artificial Neural Network (ANN) and Support Vector Regression (SVR) algorithm has used for classification task. The model has evaluated against two datasets and performance has measured in terms of accuracy and training time. The different experimental scenarios has considered for discussing the performance of the proposed irrigation management system. The result shows the ANN is accurate as compared to SVR, but SVR is efficient in training as compared to ANN. Finally, the conclusion of the work has provided and future extension of the work proposed

Machine learning, algorithm designs, support system, irrigation system, sensor network, prediction, automation.