Local Chapter Ethiopia Local Chapter
Coordinated byEthiopia ,
Status: Completed
Project Duration: 14 Mar 2023 - 14 Apr 2023
Corn is one of the most essential crops in the world, and is used for a wide range of purposes. Despite its importance, corn production is often threatened by various diseases that can reduce yield and increase production costs. Traditionally, diagnosing corn diseases has relied on manual inspection by trained experts, which can be time-consuming, labor-intensive and not always accurate. Advances in machine learning have made it possible to identify diseases in corn using algorithms that can quickly and accurately analyze data. These algorithms can be used to diagnose diseases in real-time, which could revolutionize corn production, by allowing farmers to address issues quickly for improved yields, reducing the environmental impact and ultimately contribute to the food security of our world.
Diseases in corn crops have been a longstanding issue in the agriculture industry, seriously affecting the yield and influencing the economy on a local and international level. These diseases have devastating effects on food production, causing ill effects on farmers’ livelihoods, economic development, and ultimately, food and security. Crops affected by diseases can lose as much as 40% of their yield. The problem extends to every part of the world, and it is not isolated to large commercial farms, as it also affects small-scale farmers, urban growers, and even those who tend to a kitchen garden. The effects of diseases on crops have the potential to affect food prices, which can lead to reduced availability of a critical source of nutrition for many people. Food security is not only a concern for farmers, but also for governments, industries, and institutions that rely on the vital yields of crops. Early detection is vital as it can substantially reduce disease-induced crop losses. Current techniques for diagnosis have relied on manual inspection and have several limitations including high costs, low efficiency, and limited accuracy. Furthermore, the symptoms of different diseases may also overlap, further complicating accurate diagnosis. With the increase in technological advancements, it is vital to embrace these innovations to provide fast and accurate detection and effectively address the impact of diseases on crops.
Week 1
Data collection
Week 2
Data preparation
Week 3
Modeling
Week 4
Testing and deploying
– Pytorch
– Computer vision
– Team management