[Zimbabwe Chapter] Improving Digital Advisory Services for Rural Farmers using Satellite Imagery

Challenge Background

As the main source of livelihood for the majority of the population, the performance of agriculture is a key determinant of rural livelihood resilience and poverty levels. General challenges facing smallholder farmers (SHF’s) include low and erratic rainfall, low and declining soil fertility, low investment, shortages of farm power - labour and draft animals, poor physical and institutional infrastructure, poverty and recurring food insecurity. Agricultural production is also vulnerable to periodic droughts. The peasant sector, which produces 70 per cent of staple foods (maize, millets, and groundnuts), is particularly vulnerable as it has access to less than 5 per cent of national irrigation facilities.

Resources:

https://www.fao.org/zimbabwe/fao-in-zimbabwe/zimbabwe-at-a-glance/en/

The Problem

We have seen traction in demand for rural digital advisory services, however current systems for digital advisory are focused on the broad delivery of extension services based on a large number of farmers. AI can revolutionize extension services through the provision of individualized advisory based on several data elements (on-farm data, satellite imagery, remote sensing, and GIS) thereby increasing the value for extension services to the individual farmer. Although use cases are being built in other development agencies and countries, we have not seen greater traction on AI and other technology integration in IFAD-supported projects. This could be an opportunity to develop a Proof-of-Concept (POC) and develop a potential use case for scale.

Goal of the Project

• Facilitate predictive analytics on production and expected output thereby allowing farmers to know expected output and potential markets based also predictive analysis of market trends based on publicly available market data.
• Make decisions on the potential expected outputs based on analytics of weather and climate and at the same time support decisions on the best input or crop series to produce based on expected quantity and quality vs Production costs.
• Coupled with satellite data and precision technologies predict on best usage of agriculture inputs, soil, and water.
• Change-detection application with satellite imagery to understand trends over time.
• Backend image-to-text processing supporting farmers understanding for example plant disease and its remedy based on information sent to the feature phone via simple SMS or IVR.

Coupled with satellite imagery and geofencing, farms can be tracked on the amount of forest coverage for afforestation: were any trees planted? Were any buildings built? Are fields being irrigated during a period? And the potential carbon that will be offset. This data can promote investment decisions based on potential tonnage of carbon that will be reduced and credits gained, track and evaluate the carbon or resilience credits. Resilience evolution projection for climate change could be added to the use case to track vulnerability traits.

We encourage applications from teams that can identify, access, and use suitable data to build feasible solutions for any portion of this proposal.

Project Timeline

What you'll learn