Story of an Innovative App that lets

Farmers Monitor Crops From Eyes in the Sky

Using satellite data from the UN, & the implementation of Machine Learning, PlantVillage monitors biomass on a plot of land, giving farmers insight into how their crops are growing.

Plant Village
About Client
About Client

Client

Associate professor of entomology and biology, Penn State

Region

Region

USA

Solution

Solution

AgroTechnology, Machine Learning, AI

Word from Client

Word from Client

We are providing solutions to farmers and extension workers by leveraging advances in AI, mobile phones, drones, satellites, and nanotechnology. We don’t think technology alone is the solution, but we do believe they have the potential to help smallholder farmers.

Objectives

Help farmers

tackle crop disease, adapt to the changing climatic condition, and save their crops from destruction.

Create a platform for

knowledge providers to share critical information to growers around the world.

Expected Outcome

Application to couple with the device's camera to capture images of diseased plants and provides the user with a preliminary diagnosis with a high degree of accuracy.

Q&A forum for folks around the world to pose questions about farming.

Objectives
RationaleBehind the system
Solution

Solution

covers 154 types of crops

Possibly the world's largest free library of science-based knowledge on plant diseases. The still-growing site covers 154 types of crops and more than 1,800 diseases and now houses the new image database.

algorithm capable of diagnosing 26 diseases

A computerized plant diagnostic system that boasts an algorithm capable of diagnosing 26 diseases in 14 crops with 99 percent accuracy. In essence, computers have been “taught” to diagnose plant diseases by comparing the images of healthy and diseased leaves.

learn about crop varieties

The app offers advice that could help farmers learn about climate-resilient crop varieties, affordable irrigation methods, and flood mitigation and soil conservation strategies, among other best practices.

the app does not require wireless

Once downloaded, the app does not require wireless access to cellular data or remote computing power.

PlantVillage Nuru

"PlantVillage Nuru" can draw in data from the United Nations' WaPOR (Water Productivity through Open access of Remotely sensed derived data) portal, a database that integrates 10 years' worth of satellite-derived data from NASA and computes relevant metrics for crop productivity given the available water.

technical knowledge

Farmers don't need much technical knowledge or literacy to use the app; they simply point a phone at the infested crop and the app will provide an accurate diagnosis using the talking AI assistant, Nuru.

70 countries and 21 languages

Used by United Nations across 70 countries and 21 languages to help growers manage the invasive fall armyworm.

Global Reach

Global Reach

FAO-FAMEWS

Countries

Malawi, Egypt, Togo, Guinea

PlantVillage Nuru

Countries

mainly Kenya

eLocust3m

Countries

Uganda, Kenya, Pakisthan, India

FarmerZone

Countries

India

PlantVillage Global Map
Key Findings

The Penn State researchers rigorously tested the performance of the machine-learning models with locally sourced smartphones in the typical high light and temperature settings of an African farm. In these tests,

the app was shown to be twice as good as human experts at making accurate diagnoses,

and it increased the ability of farmers to discover problems on their farms.

Impact onthe Business

500+

Downloads on a single day

50%

Improvement in Yield

3M+

Impressions

100+

Clicks

50k+

Active Users

Challenging Features

ChallengingFeatures

Diagnose crop diseases

Diagnose crop diseases, even without an internet connection

Integration of TensorFlow

Integration of TensorFlow, open-source software for numerical computation using data flow graphs.

Maintaining a high accuracy

Maintaining high accuracy level for disease detection

Integration of satellite weather

Integration of satellite weather data to predict weather condition

Power BI

Power BI to present recorded disease data on the map so scientists at Penn State can take decisions and inform the respective government to take precautionary action.

Hidden Brains path to the solution
  • Kanban approach to managing work with multiple stakeholders
  • Used Trello Board, to maintain complete transparency of the Work
  • Incremental release of new features that kept the users motivated with new improvements
  • Onsite visits with the client to the targeted countries to understand underlying problems
  • A dedicated team helped a client with the flexibility of scaling up and down
  • A collaborative approach with experts from different countries and university experts from the USA

In Talks

Highlights Highlights

Do you have an innovative idea to

change the lives of people

Let's Talk

and solve it through technology.