AI Enables the Future of Farming

Climate change is considered by many to be the greatest crisis confronting us globally. Most people focus on the melting glaciers, rising flood waters engulfing coastal cities, and species becoming extinct.

But another challenge is feeding the world's growing populace. There are currently about 7.7 billion people living on Earth, and that number is projected to increase to almost 10 billion by 2050. Estimates put the number of those people who are chronically hungry at almost 1 billion even now.

Changes in the weather impact farmers worldwide every day. Cycles that have been consistent for as long as anyone can remember are changing radically, requiring farmers to become far more sophisticated about how they manage land use, crop rotation, and fertilization processes. For crop yields to become more robust, sustainability of soil, water, and nutrients must improve.

Changes in the weather impact farmers worldwide every day. Cycles that have been consistent for as long as anyone can remember are changing radically, requiring farmers to become far more sophisticated about how they manage land use, crop rotation, and fertilization processes. For crop yields to become more robust, sustainability of soil, water, and nutrients must improve.

AI as farmer's assistant

As part of its $50 million AI for Earth program, Microsoft has partnered with a variety of innovative scientists, conservationists, farmers, and other groups to explore the implications of artificial intelligence technologies on agricultural efforts.

The projects that have been inspired by this program combine innovative technologies -- including self-driving tractors, GPS, satellite imagery, crowdsourced image processing, ground sensors, and more -- to better inform farmers as they irrigate plant, fertilize, sow, and harvest their crops.

Here are some of the programs that rely on Microsoft hardware, software, Azure resources, and related AI services to drive their success:

ICRISAT – The nonprofit International Crop Research Institute for Semi-Arid Tropics is working with Microsoft to enable farmers to increase yields using AI. A sowing application they've developed together draws on more than 30 years of climate data, combined with real-time weather information, and then uses sophisticated forecasting models powered by Azure AI to determine the optimal time to plant, the ideal sowing depth, how much manure to apply, and so on. That information is shared with rural farmers through text messages that they receive on a basic feature phone.
ACM, a dairy facility in Australia, monitors the freshness and quality of 200 million liters of milk using information systems built on Microsoft Dynamics 365 and Azure Cognitive Services. As milk is pumped from tanker trucks to silos to bottling to retail, the systems create a rich data trail so the milk can be tracked from the farm to the store.

ACM has also implemented a sophisticated temperature-monitoring system that employs sensors and Microsoft technologies to detect temperature fluctuations in storage tanks and trucks, sending alerts to farmers and drivers. If the system senses an electrical failure on a farm, for example, it can automatically dispatch trucks to collect milk before it spoils.

Ag-Analytics partners with Microsoft, the Environmental Systems Research Institute (ESRI), the LSU AgCenter, and the National Corn Growers Association to collect soil, tillage, and yield data from specific farmland properties. It then uses machine-learning models and other algorithms to provide intelligent forecasting for farmers. Ag-Analytics combines this data with public data from the US Geological Survey (USGS) and NASA, storing it all in Azure. APIs let farmers access the insights and visualize the results.

FarmBeats started in Microsoft Research, and was also an AI for Earth flagship project. Microsoft recently announced Azure FarmBeats as a product for agri-businesses.. FarmBeats uses low-cost sensors, drones, satellites, and image-based machine learning algorithms to increase the productivity and profitability of farms. Cloud-based AI models provide a precise, up-to-the-minute picture of the conditions on the farm, down to the square meter.

This level of knowledge enables farmers to pinpoint decisions about when to plant, when to water, how much fertilizer to apply, and when to harvest -- for each section of the farm. This approach is saving labor, reducing costs, and improving output.

Such precision farming technology augments and extends farmers' deep knowledge about their land, making production more sustainable. In fact, some Microsoft-powered agriculture projects are increasing farm productivity by 45 percent while reducing water intake by 35 percent.
Thanks to the use of machine learning, activities like water and fertilizer allocation and pest control become smarter and smarter over time. Farmers now forecast the year ahead using historic production data, long-term weather forecasts, genetically modified seed information, commodity pricing predictions, and other inputs to recommend how much seed to sow. 

The future of farming
Increases in population mean more mouths to feed and the effects of climate change may make the job of growing crops much more difficult and risky. Farmers will be more successful if they are able to more efficiently use natural resources. It has been said that "The farmer's shadow is the best fertilizer." When you see that shadow today, don't be surprised if it is holding a smartphone, a tablet, or a drone controller.

To learn more about how Microsoft AI is changing the world for the better, please visit https://www.microsoft.com/en-us/ai/empowering-innovation.