ABSTRACT
As the global population grows, and environmental safety is ever-increasing focus, precision farming plays a critical role in this initiative by increasing agricultural productivity. This study also develops and applies intelligent-machine learning models in the context of an IoT framework via an automatic plant-watering system. The other is in the controlled-environment greenhouses with real-time environmental sensors monitoring the crop conditions and then processed by models such as SVM, RF, CNN, ANN etc. Writer Bio Co-author Ratna Reddy said: “These models estimate agricultural yield and regulate irrigation, revolutionising agriculture. Best for smart agriculture applications, CNN has 98.55% accuracy, same as with ANN and SVM, where also scored high accuracy rates of 88–93%, and RF 90.43% accurate. This method is a step towards promoting data-driven agriculture and sustainable agricultural practices, which will improve the health of a crop and food security.