AI Case Study
The Government of Karnataka will help small farmers with crop price market predictions by using machine vision to analyse satellite images
The Government of Karnataka and Microsoft are helping small farmers increase their income with machine learning and advanced analytics. They are delivering enhanced agricultural commodity price forecasting models based on historical data such as sowing area, production, yield and weather. Machine vision analyses remote sensing images to predict crop yields.
Public And Social Sector
"The MoU will experiment with the Karnataka Agricultural Price Commission (KAPC), Department of Agriculture to help improve price forecasting practices to benefit farmers. Microsoft with guidance from KAPC is attempting to develop a multivariate agricultural commodity price forecasting model considering the following datasets – historical sowing area, production, yield, weather datasets and other related datasets as relevant. For this season, Tur crop, of which Karnataka is the second largest producer, has been identified for this prediction model. Its price will be predicted three months in advance for major markets in the state. The MoU is also aimed at using digital tools that have the potential to deliver cutting edge innovations and artificial intelligence to help farmers get higher crop yields in the state. Built on the Microsoft Cortana Intelligence Suite including Machine Learning and Power BI, these technology solutions aim at promoting digital farming practices in the state."
Planned; results not yet available
"Microsoft is working on building a multivariate agricultural commodity price forecasting model based on historical data such as sowing area, production, yield and weather." Machine vision analyses remote sensing images to predict crop yields.
Budgeting And Forecasting
"At present, price forecasting for agricultural commodities using historical data and short-term arrivals is being used by the state government to protect farmers from price crash or shield population from high inflation. However, such accurate data collection is expensive and can be subject to tampering."
"The model uses remote sensing data from geo-stationary satellite images to predict crop yields through every stage of farming.
This data along with other inputs such as historical sowing area, production, yield, weather, among other datasets, are used in an elastic-net framework to predict the timing of arrival of grains in the market as well as their quantum, which would determine their pricing."