Automated irrigation systems have become essential for farmers as they conserve water and help farmers better understand the needs of their crops. In this paper, we aimed to reduce water consumption and waste due to agricultural uses, specifically irrigation. The main contribution of this paper is to use pH sensors, light sensors, humidity sensors, soil moisture sensors, and Arduino microcontrollers together with machine learning to predict proper crop needs based on the soil moisture data and weather forecasting. This was worked in a way that if the weather were to be rainy and the plant would receive a small percentage of its water need. As a result, the system would predict this and would give the user the option to save this amount of water. Once the data was collected by the sensors and the Arduino, it would be sent to an IoT server and then onto the processing layer which contains a devised machine-learning model. This model uses semantic knowledge and a programmed algorithm to provide the user with automated control over the water valves that irrigate the crops. The adopted machine-learning model ran using the KNN algorithm and it was able to optimize the accuracy by running statistical analysis. The obtained results indicate that the adopted new sensors and weather prediction yield efficient and economical water usage and reduction in water consumption usage.