Navigation List

Role of Artificial Intelligence (AI) in Agriculture

Most farmers in every country are getting older, with their average age just over 55. As farming in general faces challenges such as a labor shortage, they are now trying to find a solution with the help of Artificial Intelligence technology. Artificial Intelligence (AI) helps us meet the needs of today, so we're prepared for tomorrow. By 2050, we need to produce at least 60% more food to feed population. So, how are we going to feed the world without wrecking the planet? Using AI, we can reduce waste and produce more food. Any grower will tell you, every crop is different. By installing cloud-connected sensors on a farm and analyzing the data using Artificial Intelligence, this way will make local predictions for farmers about light, wind and rain. So they can understand not only what is happening on their land, but what is about to happen. This helps farmers know exactly when to plant, irrigate, and  when to harvest to create more food and less waste. It's making a difference. Artificial Intelligence helps farmers grow more while wasting less.

Role of Artificial Intelligence (AI) Revolutionizing Farming Industry

If we look back, the 20th century it was all about making agricultural machines bigger. But this clearly couldn't continue forever. What we really need to be doing is looking after plants of soil what's a more individual level: so to do this we need to make machines smarter.

Smarter farm machine means taking care of plants individually - weeding, spraying and thinning. Or identifying fruit - not just counting them but providing yield and size estimates. But, what's missing is the ability for machines to discern plant health, or to spot weeds amongst a crop. The artificial intelligence is about to change this machines can now be trained to recognize shapes and textures.

Artificial intelligence can help us as a farmer to much earlier understand that there is a new disease or pest coming into field. The example you're seeing is using the texture of leaves to single them out: as weeds, or, as plants that need special treatment. The commercial success of systems like these depend on taking into consideration the whole package, the software, hardware and the business case. We've seen these technologies make huge steps forward and we're already using them to deliver systems that just a few years ago would not have been possible.

In addition to monitor crops, they also can mount cameras in the barn to monitor cows. After six seconds, the camera is able to recognize the cow's face. It will then continuously check the cows for signs of disease, or other issues. The AI flags any changes to the cows like eating habits or weight gain. Farmers are then notified and can tend to the cow. Less interaction with humans reduce stress, and improves the animal's health.

By the year 2026, technology will be used in almost every aspect of farming. Drones will fly overhead to determine crop and soil health. Satellites using AI will be used for accurate, and extremely detailed weather reports. Artificial Intelligence is making new means of farming possible - not just the machines, but the ways in which farming is done. So the question isn't how will AI affect your business. It's how will AI prove your business. All this technology will allow farmers to work smarter rather than harder.

AI and Robotics for Precision Agriculture

There are 5 broad categories that robotics and AI companies work together in farm industry. They are expanding these business models.

1. Analyzing satellite imagery

Analyzing satellite images provides a macro-level understanding of agricultural tasks. Geo-spatial data offers information on crop distribution patterns across the globe and the impact of weather condition on agriculture, among other applications. This business category is using machine learning and computer vision algorithms to classify data and extract meaningful information from millions of such satellite images.

Orbital Insight has raised $78.7M in totally funding, including a $50M Series C round in Q1’17 backed by investors including Lux Capital, Sequoia Capital, and Google Ventures. Their solutions for agriculture includes a model for predicting crop yield.

2. In-field monitoring

Startup here includes drone manufactures with a focus on aerial surveillance & monitoring, as well as startups working on computer vision algorithms to process the data captured by drones and other on-field cameras.

Drone machinery and manufacturing startups focused on tasks like site inspection and surveying for industries like precision agriculture, search and rescue, and construction saw 41 deals last year — the largest number of deals among the enterprise robotics categories in 2016 — up from 22 in 2015.

On the software side, companies like Prospera use deep learning-based computer vision technology for monitoring crops in real time.

3. Assess crop and soil heat

Business models here are using machine learning to predict the effect of various microbes on plant health (Indigo Agriculture) and identify genetic mutations in pathogens that may be harmful for the plant, among other things.

In Q2’17, Benson Hill Biosystems raised $25M in Series C. This business category uses a cognitive engine, CropOS, to identify genetic pathways in plants that can improve photosynthesis. In Q3’16, Massachusetts-based Indigo raised a $100M Series C round from the  Alaska Permanent Fund and Flagship Pioneering.

4. Agricultural robots

This agricultural robot includes ground robots that perform various agricultural tasks.

Blue River Technology is developing robots that use computer vision and artificial intelligence to detect, identify, and make management decisions about every single plant in the field. The National Science Foundation grantee is backed by smart money VCs Data Collective and Khosla Ventures.

Another startup, Abundant Robotics, which spun out of SRI International last year, raised $10M from investors like Google Ventures and Yamaha Motor Ventures to develop apple-picking robots.

5. Predictive analytics

Predictive analytics can be used to make smarter decisions about the future events in farming field. These startups are using machine learning, data mining techniques for agricultural R&D, seasonal analysis, modeling different market scenarios, and optimizing business costs, among other applications.

Spain-based ec2ce raised $1.06M in Q1’17. Colorado-based aWhere raised $7M from AgFunder, Aravaipa Ventures, and Elixir Capital in Q3’14, and a $3M convertible note round the following year.