AI-Farm: A crop recommendation system

Contributing to about 17% of India’s total GDP and providing employment to more than 60% of net population, crop cultivation or agriculture plays an essential role in Indian economy. With the advent of technologies like vertical farming etc, evolution in this domain has been pretty evident. But, even when farming has such a massive command over the country, Indian farmers still rely on conventional methods and beliefs in order to exploit their land. Depending on the weather to comply with their farming method, for instance, and not vice versa is something which is found in every farmer’s trait. The intent of our research is to make possible crop suggestions for farmers by predicting which crop suits their situation and surroundings the best through an analysis of influential factors such as composition of Nitrogen, Phosphorous and Potassium in the soil, its pH value, humidity and rain fall using various models namely Decision tree, Gaussian Naive Bayes, Logistic Regression, Random Forests and XGBoost which fall under the domain of Machine Learning. Deployment has been done on an Android Application using TensorFlow Lite to ensure accessibility and ease of use for all the farmers at their fingertips.