Can you build a model for mobile phones to identify diseases on tomatoes, corn, and peppers?

Description

In Sub-Saharan Africa, it is estimated that crop diseases and pests can reduce yields by up to 40% annually, with significant impacts on the food security and the economy of the region. This is a major concern, considering that agriculture employs more than 60% of the population and accounts for about 23% of the region's GDP.

Crop diseases are on the rise, exacerbated by climate change and the lack of access to advanced agricultural technologies. Diseases like tomato leaf curl virus and pepper blight have significantly impacted the yields of these essential crops.

The objective of this challenge is to develop robust machine learning models that can accurately predict all diseases present in images of corn, pepper, and tomato crops. Participants are tasked with creating models that can a) generalise well, even when encountering new diseases not seen in the training set, and b) operate efficiently on edge devices such as the entry-level smartphones used by most subsistence farmers in Africa.

By harnessing the power of machine learning, we aim to develop advanced solutions for detecting and identifying multiple diseases in three vital crops: corn, pepper, and tomatoes. The models and solutions developed in this challenge will support accurate and timely disease detection, enhance agricultural productivity and sustainability, and ensure food security for millions of people.

Note: This challenge is only open to citizens of African countries. Winners will be expected to demonstrate proof of citizenship.

Read more!