Artificial intelligence (AI) and machine learning (ML) will soon come to the aid of Karnataka’s tomato growers, who often face volatile price trends.

IBM is developing for the Karnataka Agricultural Prices Commission (KAPC) an advanced price forecasting system — a dashboard that will predict the market price trends for at least a fortnight and the production pattern of tomatoes. This will be launched in mid-March on a pilot basis.

Multivariate analysis

The dashboard, leveraging IBM’s Watson Decision Platform for Agriculture as well as big data, AI and ML, uses satellite imagery and weather data to assess the acreage and monitor crop health on a real time basis. It will be able to detect pest and disease infestations, estimate the tomato output and yield, and also forecast prices. Currently, the output estimates are based mainly on acreage data.

“The dashboard is something unique considering that it forecasts both the supply situation and also the price using multivariate analysis and other inputs including weather and satellite images,” said Himanshu Goyal, India Sales and Alliances Leader, The Weather Company, an IBM division.

Other key input such as the prices in major markets of neighbouring States will also be factored into the price forecast.

The price forecasting mechanism being developed for Karnataka is claimed to be the first of its kind in the country.

It is initially being launched for the three major tomato- growing districts of Kolar, Chikkaballapur and Belgavi and two key maize-producing districts of Davangere and Haveri. Karnataka is a key producer of tomatoes and maize.

“It can be scaled up to other districts and more crops depending on the success,” said KAPC Chairman Prakash Kammaradi. “Starting mid-March, the price forecast for the next 15 days will be made available on a daily basis till end-December. We propose to also use the price and supply forecast data for any intervention. Eventually, the price forecast will be shared with farmers through crop advisories.”

Last year, IBM had tied up with NITI Aayog to develop a crop yield prediction model using AI to provide real-time advisories to farmers in 10 districts of Assam, Bihar, Jharkhand, Madhya Pradesh, Maharashtra, Rajasthan and Uttar Pradesh in the first phase.

The project proposes to introduce and make available climate-aware cognitive farming techniques and identifying systems of crop monitoring, early warning on pest/disease outbreak based on advanced AI innovation.