Machine Learning Helps Protect the World's Food Supply
An agricultural biotech client needed a way to accurately diagnose crop disease in order to provide customized, environmentally friendly solutions to its community of farmers.
We helped our client build an app that uses machine learning to diagnose crop disease and supply targeted treatment recommendations in near real-time.
A global agricultural biotech company that distributes products designed to help farmers contribute to the world’s food production and biofuel industries in a safe, sustainable way
Among the greatest challenges farmers face are those conditions that are outside of their control, such as weather, soil quality, weeds, and crop disease. These factors inhibit growth of both biofuel crops and healthy produce for consumption.
Losses due to crop disease, whether caused by fungi, bacteria, or viruses, can be disastrous to the economy and dramatically threaten the global population’s access to nutrition.
Crop disease can devastate natural ecosystems, leading to environmental problems, such as habitat loss for certain species. Additionally, in extreme cases, diseased crops can produce toxins that result in serious health problems for consumers.
Our client’s mission is to provide farmers with environmentally-friendly products and services to combat crop disease and other threats.
While farmers spend billions of dollars on crop-disease management, they often do so without adequate diagnostic tools. This can leave them using one-size-fits-all solutions that not only fail to address their specific needs, but often result in undesirable side effects, such as pollution and reduction of the bee population.
Our client knew that accurate diagnosis was the best way to target the exact solutions necessary to maintain crop health. However, without deep subject matter expertise, crop disease is difficult to diagnose. Accurately describing a crop’s symptoms to a plant pathologist over the phone is nearly impossible.
Without a physical examination of each specimen, our client was unable to recommend customized treatment options to customers. Obviously, there was no way for plant pathologists to travel to every farm in need of assistance; the only solution was to bring the data to the pathologists.
We assisted with the architecture and development of a mobile application that allows farmers to photograph diseased crops and receive accurate diagnostics in near real-time.
The diagnostic process occurs through the use of advanced image analytics powered by machine learning.
Advanced Image Analytics: The mobile application uses Google's Cloud Vision API to analyze each crop’s color, size, texture, and decay patterns, then references these data points against a library of 50,000 images. These images are classified into categories and labeled.
Machine Learning: Through pattern-recognition machine-learning techniques, the mobile application is trained to diagnose crop disease in near real-time.
Data Engineering: A reusable platform enables data and model management, along with DevOps support for multi-cloud infrastructure to assist data scientists in performing data cleansing, learning, and service deployment of solutions, utilizing AI analytics techniques at scale.
Today, our client is able to more accurately assess farmers’ needs and provide them targeted tools that more effectively heal and protect their crops, allowing for a more sustainable crop protection strategy.
And in a continuation of its commitment to reducing harmful environmental impact, our client’s efforts in preventing and treating crop disease, along with other threats to farm-produced products, support an integrated pest management (IPM) system, a more effective, environmentally sensitive approach that focuses on pest prevention and uses pesticides only as needed.