A critical analysis of crop management using Machine Learning towards smart and precise farming

Abstract

Agriculture is one of the key industries that use ground-based and aerial drones for crop health evaluation, crop monitoring, crop spraying, planting, soil and field analysis, irrigation, and other fields. Drones can be flown from a ground station or from the air. The term "precision farming," commonly referred to as site-specific crop management, is the use of technology to increase agricultural output and efficiency. Due to the availability of real-time data and insights on crop growth, soil quality, weather patterns, and other crucial elements, the integration of machine learning (ML) and the internet of things (IoT) has completely changed the way farming is done. To put it another way, both plants and animals receive the exact care that they require, which is decided by machines with a precision that exceeds that of a human. Instead of making decisions for an entire field, precision farming enables decisions to be made on a per-square-meter or even per-plant or per-animal basis. This is the primary distinction between traditional farming and precision farming. This article focuses on the creation and application of a hybrid IoT and ML system for precise farming. The ML algorithms can process enormous amounts of data and produce insights that can assist farmers in making defensible decisions regarding their farming methods. The framework's IoT devices are in charge of gathering data from diverse sources and transmitting it to a central system for processing. Due to the hybrid nature of the framework, several technologies can be combined to produce a cohesive and effective system for precise farming.

URN:NBN:sciencein.jist.2024.v12.809