Inspiration
SDG #2: Poor yield of crops by most African farmers which leads to poor output. To yield abundant crops, a farmer has to seed the right plant, at the right time, and in the right place. The right place is determined not only by the geographic location and climate peculiarities but types of soil as well.
What it does
Based on location data provided by the farmer, the app generates the PH, Nitrogen levels, Phosphorous levels and Potassium levels of soil in that particular area. It also suggests a list of crops that are suitable for that particular soil. It can be accessed on WhatsApp, Mobile and Desktop webs. The impact is to improve Agriculture systems worldwide by offering a solution for sustainable agricultural practices and food systems.
How we built it
We built it with the iSDAsoil Datasets from AWS ASDI Catalog. iSDAsoil is a resource containing soil property predictions for the entire African continent, generated using machine learning. Maps for over 20 different soil properties have been created at 2 different depths (0-20 and 20-50cm). Soil property predictions were made using machine learning coupled with remote sensing data and a training set of over 100,000 analyzed soil samples. We integrated the dataset with Whatsapp and Web APIs to make the solution accessible to most farmers.
Challenges we ran into
- Inadequate time to add all crops to farmers for quick suggestion.
- Few bugs that we managed to fix.
- Working with a large dataset.
Accomplishments that we're proud of
- Working MVP
- More knowledge on AWS Services
What we learned
- Integration AWS ASDI with PHP
- Soil Information and Crop Recommendation
What's next for SoilVisor - Improving Agriculture Productivity
- Adding more crops
- Extending reach beyond Africa's Soils
- Testing features
- Mentorship with key stakeholders for knowledge transfer.
Log in or sign up for Devpost to join the conversation.