Fog Computing for Intelligent Cloud IoT Systems

4Machine Learning Integration in Agriculture Domain: Concepts and Applications

Ankur Biswas¹* and Rita Banik²

¹ Tripura Institute of Technology, Narsingarh, Tripura, India

² ICFAI University Tripura, Tripura, India

Abstract

Agriculture is a crucial factor in the economic development of a nation such as India because it serves as the primary source of food and money for rural people. Increasing agricultural production is necessary, given the realities of a growing world population and climate change, and choosing which crops to cultivate is a crucial part of agricultural planning.

A subset of artificial intelligence known as “machine learning” uses statistical methods to give computers the ability to learn from data and develop forecasts or choices without having to be formally compiled for this purpose. Machine learning has recently been used in many industries, including agriculture, to boost crop productivity, reliability, and the effectiveness of asset usage. Machine learning methods have been applied in agriculture to assess enormous datasets produced by several sensors, including satellite imaging, weather stations, soil sensors, and drone photography. These data are used to create models that, among other things, may estimate agricultural production, identify crop illnesses, and maximize resource utilization. Crop health can be categorized using machine learning algorithms, weed species can be identified, and their densities quantified and meteorological variables that ...