Home / Improving Digital Advisory Services for Rural Farmers using Predictive Analytics and Satellite Imagery

Local Project

Improving Digital Advisory Services for Rural Farmers using Predictive Analytics and Satellite Imagery

Local Chapter Cracow, Poland Chapter

Coordinated byPoland ,

Aaron Linder

, Vasyl Buchmei

Status: Completed

Project Duration: 27 Mar 2023 - 30 Apr 2023

Open Source resources available from this project

Github Repository

Project background.

Poland is a significant European producer of a diverse range of agricultural products. Small farms in Poland constitute the core of the agricultural sector. Their share in the structure of farms, employment in rural areas, total agricultural production, and utilized agricultural area is relatively high. 73% of Poland’s farms are considered by the Central Statistical Office of Poland to be in the “small” category, i.e. under 10 hectares (ha). They also have a small area of cultivation – farms over 15 ha in size, despite representing only 14.3% of all Polish farms in number, have 60% of all arable area in Poland.

The development of rural areas in Poland requires solving many problems, such as poor agrarian structure, unfavorable land distribution, or lack of local spatial development plans.

One of the biggest challenges the agricultural sector faces in Poland – adapting to changes, such as the reduction of pesticides, or increased food quality requirements. This in turn is associated with the introduction of new technologies in agriculture.

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 of 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.

Project goals.

1. Getting LandSat/Sentinel to work at 10 meters. We aim to explore the satellite API and get a better resolution. Having a spatial resolution of 20 meters might work, but it makes the images appear really zoomed out. To configure the pull-in/out, we need key code and API examples.2. Creating a mask for field boundary delineation.As soon as we receive the images at the correct spatial resolution, we will follow the national GIS paper that was submitted. According to the paper, clustering images must be 4000 pixels by 4000 pixels, which is the spatial resolution required for clustering. Using the clustered images, we can create a mask.3. Making dynamic time wrapping. Once we have the field boundaries, with the Tensorflow autoencoder we can do dynamic time warping (compare the sequences of series of crop growth to non-crops). 4. Training a model for crop recognition. If we have a mask with decent accuracy, we can train the model to recognize crops. Once we are able to identify a crop, we can collect and scrape agricultural data and use multi-feature classification models with an output feature. We can train multi-classification models to predict crop yield, crop growth, etc.5. Developing low-cost commercial products. The farmers can input his GPS location and the number of hectares they arefarming and a predicted yield and fertilizer recommendation will be generated as a result. The application can be enhanced with additional features.