The goal of the Agralert Project is to provide farmers in both developed and emerging economies a means to proactively respond to threats to their livelihoods. This will include crowdsourcing data on current problems, alerting farmers to potential problems and providing them with possible solutions.

This project is solving the Crop Alert – Learning From the Growers challenge.


User Story:

Utilizing Agralert’s simple 5-step process, farmers can share information about agricultural losses caused by outbreaks and natural disasters. For example, a farmer who discovers they have lost crops due to pests would go through the following process:

1.  Farmer sends a text to Agralert.
2.  Farmer receives a message asking what the problem is. 
3.  Farmer selects an insect icon to indicate a pest infestation. 
4.  Farmer receives a second message asking what has been affected. 
5.  Farmer selects a plant icon to indicate his crops have been damaged.


Data collected through Agralert’s crowdsourcing efforts will give farmers, local governments, NGOs, and IGOs access to localized maps that not only display current agricultural challenges in a particular region, but also provide predictions about their potential impact and spread. Farmers will also receive text message alerts that both warn them of problems in neighboring areas and offer potential solutions, allowing them to react proactively and limit their losses.

Due to varying access to Internet and cellphones across the globe, Agralert will be available in two formats: a simple SMS-based version and an interactive version that relies on smartphones and web browsers.

Anticipated benefits:

  • Catching outbreaks in early stages, resulting in increased yields and higher profit margins
  • Better management of cooperative, national and international food management resources
  • Crowdsourcing data collection leads to improved prediction of local and regional agricultural shortfalls and windfalls
  • Scientists have increased access to both the real time and historical data required to improve predictive and reactive analytic analysis

Project Information

License: MIT license (MIT)

Source Code/Project URL:



  • Orianna Luv Abueg
  • Bryan Perez
  • Cesar Abueg
  • Adam Karbiener
  • Krystal Klumpp
  • Nelson De Young