Case Study: Diagnosing Crop Disease with AI

Case Study

Targeted Product Recommendations through the power of AI

Mobile app uses image analytics and machine learning to diagnose crop disease and provide accurate treatment recommendations in real time.

Without access to on-site plant pathologists, farmers can find themselves attempting to battle crop disease with one-size-fits-all solutions that not only fail to address their specific needs, but often result in undesired side effects.

Relevant Background

Farmers spend billions of dollars a year on crop-disease management, but until recently, they've generally done so without access to adequate diagnostic tools. 


Targeted treatments are available to eradicate many strains of crop disease, but it's critical that the correct treatment be applied.


Armed with inaccurate diagnoses, farmers may turn to solutions that are at best, ineffectual, and at worst, as harmful as the diseases they're attempting to treat. From pollution to reduction of beneficial pollinator species, such as bees and butterflies, the environmental impact of these inadvertent errors can be devastating.

The Challenge 

Without deep subject matter expertise, crop disease is nearly impossible to diagnose. A crop disease treatment manufacturer recognized that its products could not be used effectively as long as customers lacked the critical data they needed to make informed purchasing decisions. 


Treatment recommendations are valuable only if the disease being treated has been diagnosed accurately.


Without a physical examination of each specimen, customers could not be supplied with customized treatment recommendations. 

There is no way for plant pathologists to travel to every farm in need of assistance.

The Solution: Bring the data to the pathologists

A 21st Century Solution to a Centuries-Old Problem

That's where we came in.

The biochemical company engaged our team to help build a digital solution that would make it possible to deliver accurate product recommendations to farmers worldwide without sending plant pathologists into the field every time a diagnosis was needed. 

Our engineers collaborated with our client's team to architect and develop a groundbreaking mobile application that enables farmers to photograph diseased crops and receive accurate diagnostics via their mobile devices in near real time. The app can then identify the correct solution and make a truly useful product recommendation.

Solution Overview

The diagnostic process occurs through the use of advanced image analytics powered by machine learning.

Machine Learning Crop Disease Diagnosis and Product Recommendation Application

Machine Learning (ML): Disease classification capabilities were implemented using the advanced deep learning capabilities of Google's ML Engine. We used Google's high-performance platform and more than 50,000 images to train the neural network. With Google's Tensorflow Processing Units (TPUs), the training time of the neural network is greatly reduced, allowing for rapid and cost-efficient model updates as additional images are collected and curated.

Mobile Application: The mobile application allows a farmer to take photographs of the diseased leaves of their crops. These images are passed to the GCP-hosted ML services, and a diagnosis is returned to the farmer immediately. As a hosted, serverless platform, ML Engine provides scalability without the need to manage a set of servers.

Data Engineering: A reusable platform enables data and model management, along with DevOps support for multi-cloud infrastructure. This infrastructure assists data scientists in performing data cleansing, learning, and service deployment of solutions, utilizing AI analytics techniques at scale. The solution leverages GCP Cloud Storage for managing plant images and generated models, along with GCP Data Flow for the machine learning pipeline and image processing.

Business Outcomes

Our client dramatically improved its level of customer service by providing the exact recommendation needed to solve each farmer's individual problem. 

Farmers save time and money by making informed purchasing decisions that work right the first time. 

Overall, in addition to beneficial environmental impacts, this solution significantly enhanced consumer trust in the brand and ensured more positive company-to-customer interactions.

Global Impact

The volatile combination of a rapidly growing population with an increasingly variable climate poses a serious threat to the agriculture industry. These complex challenges require innovative solutions that enable efficient production of food in environmentally responsible, yet practical and economical, ways.

Crop disease, whether caused by fungi, bacteria, or viruses, can be disastrous to the grower and the economy, devastate natural ecosystems, and threaten the global population’s access to biofuel crops and healthy produce for consumption.

Today, farmers around the globe can more effectively diagnose and treat crop disease, allowing for more sustainable crop protection strategies, greater yields, and strengthened economic prosperity.

Contact us today to explore the practical business applications of artificial intelligence, machine learning, and data science.

insights blue

Insights at Scale

Uncover new ways to harness the power of your data in unconventional ways.

data classification blue

Data Classification & Transformation

Transform your unstructured data into useful information optimized for analytics.

predictive modeling blue

Predictive Modeling

Access our unique algorithms and accelerators that identify opportunities and prescribe action.