Agriculture is regarded as the backbone of any country’s economy and heavily relies on water resources. To optimize the use of water resources, farmers employ various irrigation systems, such as drip, sprinkler, and linear motion models, to achieve better cultivation and improved crop yields. However, uncertain water distribution and the lack of adoption of intelligent techniques often result in the inefficient utilization of water resources, leading to excessive absorption that hampers agricultural sustainability. To address this challenge, Automated Irrigation Systems (AIS) have been introduced, significantly enhancing water conservation and promoting crop yields. In recent advancements, AIS has been further improved through the incorporation of the Internet of Things (IoT) and Artificial Intelligence (AI). While existing AIS models often suffer from high computational latency due to complex data processing and algorithmic demands, our proposed model tackles this challenge through streamlined data handling and a more efficient learning framework. This research article introduces an innovative framework incorporating IoT and a Feed Forward Learning Model (FFLM) to maximize efficiency in water conservation and provide farmers with actionable insights into sustainable water usage. The framework consists of four key components: IoT-based data collection using NodeMCU and soil sensors, data cleaning and preprocessing, predictive analysis using FFLM, and a control system for motor activation based on sensor input. Data are stored in the ThingSpeak cloud for further diagnosis. Extensive experimentation showed that the proposed model achieved 99% accuracy, 98.6% precision and recall, 99% F1-score, and a 2.6-second response time. These results demonstrate that AIS, powered by IoT and FFLM platforms, enables farmers to remotely monitor and control irrigation systems while gaining valuable knowledge about water conservation techniques.
Rani et al. (Tue,) studied this question.