Earth

The Growth of Precision Agriculture

With the global population expected to hit 9.7 billion by 2050, according to the United Nations Department of Economic and Social Affairs, improvements to agriculture to feed a growing number of people while being environmentally sustainable have become even more critical. 

Precision agriculture, a farming approach involving the application of data analysis to improve farm operations and sustainability, has served as an emerging method of addressing the need for greater crop productivity. The International Society of Precision Agriculture defines precision agriculture as a management strategy that analyzes temporal and spatial data to “support management decisions according to estimated variability for improved resource use efficiency, productivity, quality, profitability and sustainability of agricultural production.” The method emerged in the 1990s with the development of Global Positioning Systems (GPS) as well as Geographic Information Systems (GIS). Recently, artificial intelligence, particularly machine learning, has had a significant impact on such methods of precision agriculture.

One area for application of AI in precision agriculture is in site-specific crop management (SSM). As different fields vary in chemical composition, many crop treatments, which include herbicides and pesticides, irrigation, and fertilizers, are often misjudged, resulting in excess chemicals and large amounts of runoff that damage nearby ecosystems. Algorithms that analyze spatial and temporal data provide important insights to allow for proper adjustment of crop treatment to tailor to each site. As Kathleen Walch details, AI also plays a role in monitoring plant disease and nutrition and can assess where to apply the treatment. 

Interestingly enough, the United States National Institute of Food and Agriculture points out that SSM more closely resembles traditional farming practices as opposed to other modern techniques, in that farmers leverage their understanding of each corner of a field in order to optimize crop treatment in certain areas. On the other hand, the mechanization of agriculture has led to reduced labor costs while pesticide and herbicide waste has risen. Being able to maximize productivity by focusing on each field on a smaller scale has therefore become integral in not only ensuring greater crop productivity but also in reducing such detrimental environmental effects.  

Through analyzing real-time data and applying the insights to optimize farm operations, AI has largely improved crop productivity. In precision agriculture, unmanned aeronautical vehicles (UAVs) have had a significant impact on crop health monitoring as well as soil and field analysis. By combining data analysis of satellite imagery with aerial views provided by the drones, farmers are able to gain valuable insight into the health of their fields and adjust accordingly in order to maximize crop productivity while minimizing environmental impact. As Tanha Talaviya and fellow researchers mention in their article in Artificial Intelligence in Agriculture, it is expected that the agricultural drone method will grow by 38 percent in the next couple of years, which will certainly make a difference in improving farm efficiency. 

In addition to drone technology, another company IntelinAir, based in Champaign, Illinois, has leveraged machine learning and computer vision in developing a platform to provide farmers with critical insight into optimizing the farming process. IntelinAir employs aerial imagery and measurements such as temperature and humidity levels in order to monitor fields over the course of a growing season. They leverage systems of connected sensors and self-learning algorithms to develop their crop intelligence. The company provides such information to farmers through their advanced AGMRI Intelligence platform that ultimately helps in critical farming decision making. Their applications range from monitoring for emergencies on the farm to irrigation management to estimations of pesticide and herbicide use. 

The applications of artificial intelligence in agriculture have also extended into weather forecasting, soil conditions, and machinery automation. Robots and automated drones have also made a large impact on agriculture. PrecisionHawk, for instance, provides drone services as well as geospatial data analytics in order to provide a range of farming professionals, from growers to consultants, with important insights to improve farm efficiency. AI and machine learning when applied to agriculture have enabled significant development in farm management and productivity. 

In order to maximize the impact of such technological development, however, meeting the needs of the entire population must be placed at the forefront. For example, the non-profit Precision Agriculture for Development (PAD) has been focusing on bringing such emerging technologies to farmers in developing countries, such as Ethiopia and Pakistan. Through working with local partners and governments, PAD has been dedicated to transforming the data and information gathered from developing technologies such as AI and machine learning in precision agriculture into real-time insights sent through mobile phones to millions of farmers in such countries. Such work helps farmers in their work to provide sufficient food for the local population. As the need for greater crop production on limited land continues to grow, it is crucial that the important insights as revealed by such emerging technologies are properly distributed in order to ensure that food production is effective and sustainable. 

Written by Emy Li
About the Speaker

Want to get more involved?

Volunteer or  Donate!