AGRORADAR - AGRORADAR

You are here

Objectives of the service

With the AgroRadar service, we provide information to farmers on soil problems, definition of homogeneous management zones, productivity estimates with 95% accuracy (average) anywhere in the world regardless of weather conditions.

Users and their needs

The solution serves farmers, whatever their size or crop, who need reliable information to improve their processes. Among other things, we can help anyone who wants to:

  • Identify soil types
  • Have regular indications of the ideal places to make samples (soil, plants, water)
  • Improve your financial management, with better forecasts

The solution was improved and demonstrated in different crops, in 5 countries in different climates: Portugal, Guatemala, Brazil, El Salvador. Nicaragua and Mozambique.

Service/ system concept

When the service is deployed the user is able to delineate management zones in terms of: weeds, soil fertility, plant density, plant nutrition, plant health, plant water stress management and food quality. It will also be able to delineate soil, plant and fruit smart sampling, registering all the production processes with the developed traceability tools (coordinates, text, documents, audio, and video) in order to store the production history.

The system works considering Copernicus (Sentinel 1, 2 and 5P), meteorological 2nd generation satellites (MSGS) and 3rd parties’ data integration. With this particular data several processes and models are used in order to produce agronomic outcomes (intelligence) with value for decision. At the same time the infrastructure integrates, stores and secure all the user data.

Space Added Value

Sentinel 2 is the most used satellite when it comes to agricultural applications, however, such use is limited when clouds are present. In the absence of clouds, this type of satellite is widely used in the management of plant nutrition and in the analysis and detection of anomalies associated with soil / water / plant relationships. The areas of the world with great relevance in food production normally present a very strong cloud dynamics, preventing the systematic use of Sentinel 2.

In view of the above, a serious research investment was made in Sentinel 1 in order to overcome the difficulties mentioned above with Sentinel 2. Sentinel 1 has great potential in the study of soil quality and its fertility, as well as in estimating Agro – Forestry production.

Sentinel 5P will also be used in order to guarantee the air quality of the areas where the food is produced and also from the perspective of food traceability. Second generation meteorological satellites will also be used in order to measure the land surface temperature as well as its influence on aspects associated with pests, diseases, plants water needs and plants phenology.

Current Status

Agroradar = Agriculture + Big data

The idea that people can manually keep pace with the number of data sources that are coming into people’s live it’s just not realistic any more. We have to find ways to take complexity away (Figure 1), and that tends to mean that we should automate. The expectation is that algorithms can help persons and companies to accelerate the onboarding of data and automatically classify it, profile it, organize it, and make it easy to find and to understand.

With the previous in mind and after 13 months of hard work executing the Agroradar project, inclusivelly with covid19 situation, Agroinsider was able to test it’s technology on several pilots around the world considering several crops (sugar cane, corn, rice, soy, pasture…).

Copernicus/agronomic “Big data” was produced for thousands of hectares and as a result of this hard work, field research and installed capacity in terms of machine learning algorithms (Figure 2), Agroinsider will soon launch several new services with affordable costs for different players in the Agro value chain (eg. anomalies detection related with plants behaviour, irrigation machinery dysfunction, soil management zones, smart sampling, smart nutrition, etc).

Figure 1 – For a human prespective, “Big data” complexity.

 

Figure 2 – Detecting anomalies on millions of parcels with machine learning algorithms. 

Prime Contractor(s)

Status Date

Updated: 05 February 2021 - Created: 08 October 2020