AI Case Study
ICRISAT and Microsoft advise farmers on when to sow crops resulting in a 10-30% yield per hectare increase by using machine learning
In collaboration with ICRISAT, Microsoft has developed an app which sends crop sowing advisories to farmers in India. Using machine learning and historical weather data, along with daily rainfall measurements, the app gives farmers the optimal sowing date. On average, farmers who use the app have a 10-30% higher yield per hectare rate than those who do not.
Microsoft has partnered with the International Crop Research Institute for the Semi-Arid Tropics (ICRISAT) and ran a pilot program in 2016 with 175 farmers whereby they received sowing advisories via text message. The messages included sowing date and land preparation information. "To calculate the crop-sowing period, historic climate data spanning over 30 years, from 1986 to 2015 for the Devanakonda area in Andhra Pradesh was analyzed using AI. To determine the optimal sowing period, the Moisture Adequacy Index (MAI) was calculated. MAI is the standardized measure used for assessing the degree of adequacy of rainfall and soil moisture to meet the potential water requirement of crops.
The real-time MAI is calculated from the daily rainfall recorded and reported by the Andhra Pradesh State Development Planning Society. The future MAI is calculated from weather forecasting models for the area provided by USA-based aWhere Inc. This data is then downscaled to build predictability, and guide farmers to pick the ideal sowing week, which in the pilot program was estimated to start from June 24 that year.
Ten sowing advisories were initiated and disseminated until the harvesting was completed. The advisories contained essential information including the optimal sowing date, soil test based fertilizer application, farm yard manure application, seed treatment, optimum sowing depth, and more. In tandem with the app, a personalized village advisory dashboard provided important insights into soil health, recommended fertilizer, and seven-day weather forecasts.
In 2017, the program was expanded to touch more than 3,000 farmers across the states of Andhra Pradesh and Karnataka during the Kharif crop cycle (rainy season) for a host of crops including groundnut, ragi, maize, rice and cotton, among others."
The pilot farmers experienced on average, a 30% higher yield per hectare than other farmers. In the expanded 2017 program, yield increase was from 10-30%.
The app was developed with Microsoft Cortana Intelligence Suite and uses machine learning.
Farmers in Andhra Pradesh in India sow crop seeds traditionally at the beginning of June, but changing climate patterns have meant
that the optimal date to do so varies and is difficult to predict. “Sowing date as such is very critical to ensure that farmers harvest a good crop. And if it fails, it results in loss as a lot of costs are incurred for seeds, as well as the fertilizer applications”.says Dr. Suhas P. Wani, Director, Asia Region, of the with a wide array of partners throughout the world."
Historic climate and daily rainfall data.