Scalable Ag Data Through Conversational Farm Record Keeping
The Bill and Melinda Gates Foundation recently funded a collaboration between NASA Harvest partners of 6th Grain and colleagues of farm.ink, two digital technology companies working throughout Africa. Funded in July 2020 and supported as part of the Bill and Melinda Gates Foundation's ‘Enabling Crop Analytics at Scale’ project managed by Tetra Tech, the AGDATA Acceleration Facility aims to catalyze improved collection, processing, storage, and use of ground-truth data, targeting key bottlenecks and technical challenges that inhibit the large-scale collection of ground-truth datasets and their use. This project seeks to determine the quality and cost of agriculture ground-truthing data gathered using mobile phones in Kenya.
The 12-month project focuses on combining 6th Grain’s digital agriculture tool FieldFocus and high quality cropped area maps in Kenya with farm.ink’s chatbot platform and training expertise. The team will demonstrate how the two applications together can gather high quality field management data that can be used to develop yield models and new cropped area maps from satellite data. Farm.ink will help Kenyan farmers use FieldFocus, which has significant barriers to use, to facilitate the gathering of relevant, high quality farm management information that can be transformed into analytical decision support products for the international community. The project will combine multiple mobile phone applications to gather high quality field data and digital boundaries while simultaneously delivering value to farmers at a radically lower cost per datapoint than is possible with standard household survey techniques.
This project targets farmers and landowners in Kenya who manage their farms while working in Nairobi. Using innovative mobile chatbot technologies, we can train a large base of smartphone-owning farmers to enter ground data including field boundaries, crop type, crop variety and previous year production in exchange for high quality farm record display and remote management of farms via FieldFocus. Geospatial modeling and analytical tools will then turn this ground data into high quality, crop management recommendations which will be delivered directly to the farmer and help us transform maize cropped area maps into yield estimate maps. This solution capitalizes on the rapidly growing base of smartphone-owning farmers throughout the region. In Kenya, 93% of the population is now covered by 3G or 4G with approximately 70% of mobile subscribers in Kenya using mobile data. We will use a conversational interface (chatbot) to train this group in how to collect data and interpret recommendations, with a focus on a first-class user experience to drive engagement.
Studies have shown that social networks are the most effective way to disseminate information about new agricultural practices and this social forum will enable farmers to learn and engage with their peers. Once the data is obtained, the researchers will generate yield maps to demonstrate the utility of the approach for transforming satellite data into agricultural statistics over complex agroecosystems.