A Crop Recommendation System using Machine Learning

CRSUML

Abstract

A vast fraction of the population of India considers agriculture as its
primary occupation. The production of crops plays an important role in
our country. Bad quality crop production is often due to either excessive
use of fertilizer or using not enough fertilizer. The proposed system of
IoT and ML is enabled for soil testing using the sensors, is based on
measuring and observing soil parameters. This system lowers the
probability of soil degradation and helps maintain crop health. Different
sensors such as soil temperature, soil moisture, pH, NPK, are used in this
system for monitoring temperature, humidity, soil moisture, and soil pH
along with NPK nutrients of the soil respectively. The data sensed by
these sensors is stored on the microcontroller and analyzed using
machine learning algorithms like random forest based on which
suggestions for the growth of the suitable crop are made. This project
also has a methodology that focuses on using a convolutional neural
network as a primary way of identifying if the plant is at risk of a disease
or not.