Agricultural productivity in India is lower than in some other countries. For example, wheat output is approximately 2.7 tons a hectare in India, compared to 6 tons in China.
Technological tools such as drones and sensors help agricultural production to act, but artificial intelligence (machine learning) can turn out to be an even larger game exchanger, especially when determining which crops should then grow for improved yields and profit.
‘ML-based crop recommendation systems’ is today the next big thing in agriculture. With more than 145 million small farms in India, most under 1.1 hectares, farmers need clear, data -based guidelines to choose the right crops for better income and resilience against climate change.
In it, two independent investigations have concluded that the ‘random Forest’ ML model has the highest prediction accuracy. The ‘Random Forest’ model combines several ‘decision-making trees’ -ML algorithms that use tree-like structures to make predictions.
The first study was by scientists Steven Sam and Silima Marshal d’Abreo of Brunel University, London. They investigated 12,389 data points of 19 crops in 15 Indian states in 2011-14.
“We have combined environment and economic input parameters to develop and evaluate the accuracy of two machine learning models (‘Random Forest’ and ‘Support Vector Machines’) for recommending high-efficiency and profitable crops to farmers,” the authors say in a still rated paper.
They concluded that ‘random forest on the basis of lay variables’ (values from the past that is used to predict the future) is the most accurate.
Various circumstances
The researchers tested two computer -based models to see how well they could suggest the right crops. One method showed high accuracy but was not realistic because it did not consider how crop conditions change over time.
In order to balance the accuracy with Real-World usability, the researchers introduced ‘LaG variables’, who improved the performance of the model. In the end, the model worked with the random forest method with the time -conscious approach the best for crop recommendations in India.
The study emphasizes that a study by both market and environmental factors provides better advice for farmers. It also suggests that future improvements must include more data, such as market demand, prices and returns, to make the recommendations even more suitable for the various agricultural conditions of India.
Another research paper, entitled ‘Crop Recommendation System Use Machine Learning’, by researchers from the Prakasam Engineering College in Kandukur, Andhra Pradesh, has also concluded that the random forest model is best, with an accuracy of 99.3 percent.
“The system successfully recommends optimum crops in 22 different gain categories, which contributes to improved agricultural productivity and sustainable agricultural practices,” say the authors of the article, Dr. ir. M Lakshma Rao and his student Soprala Naveena.
“The crop recommendation system represents a successful integration of Machine Learning technology with agricultural science, creating a tool that bridges the gap between advanced analytical possibilities and practical agricultural applications,” they say, adding that the system “serves as a proof of concept for the wider potential of artificial potential of artificial potential of artificial potential of artificial potential of artificial potential of artificial potential of artificial potential of artificial potential of artificial potential of artificial potential of artificial potential of artificial potential, potential of artificial potential, potential of artificial potential, potential of artificial potential, potential of artificial potential potential, potential potential potential potential potential potential potential potential potential potential potential potential potential potential potential potential potent is Support Equitable -agricultural systems “.
More so
Published on June 29, 2025
#machines #learn #recommend #correct #crash #season