Smart Irrigation Management Using IoT-based Network.
Abstract
Irrigation consumes a maximum amount of water compared to industrial uses and municipal supply. But poor irrigation applications, wastage of water, and insufficient irrigation efficiencies create problems in agriculture management. Improving irrigation management with advanced techniques to preserve the water is necessary. The technology that leads agriculture worldwide toward a more effective and sustainable route is the Internet of Things (IoT). Recent technological breakthroughs like smart irrigation for optimum water utilization in farming landscapes and Wireless Sensor Networks (WSN) for soil moisture prediction may address some opportunities in the agriculture sector. Intelligent data processing and analysis are required to establish a more substantial knowledge base and get deeper insights that improve forecasting, decision-making, and sensor management. This study investigates the use of several machine learning algorithms in sensor data analytics within the agricultural system in depth. In this study, the field experiments on soil moisture with sensors nodes and irrigation scheduling will design based on accurate data for sugarcane and wheat crops. The experiment field is divided into Field A (wheat crop) and Field B (sugarcane crop). This study aims to develop an IoT-based smart irrigation system in India. This smart irrigation system is based on a microcontroller and may control through wireless transmission from remote locations. An IoT includes significant components, hardware, web application, and mobile application. These components facilitate optimizing the real-time monitoring data and utilizing the actual field water requirements. In this approach, the sensors used for wireless sensing; can send required data and forward it through the network. The wireless sensors are used to take soil readings like soil moisture, temperature, humidity, and decision-making controlled by the user (farmer) using a microcontroller.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2022
- Bibcode:
- 2022AGUFMGC45D0996K