SciTransfer
SQAT · Project

AI-Powered Robotic Soil Mapping for Precision Farming and Carbon Credit Verification

environmentTestedTRL 6

Imagine a robot that acts like a mobile laboratory, driving across a field to test soil chemistry and hardness on the spot. It combines these ground-level tests with satellite images to create a high-definition map of the land. This helps farmers know exactly where to put seeds or fertilizer instead of treating the whole field the same way.

By the numbers
7
SMEs leading use cases
5
Smart farming applications validated
12
Total project partners
The business problem

What needed solving

Current soil mapping is too expensive and complex for most farmers. This prevents the precise application of nutrients and hinders the verification of carbon storage for environmental credits.

The solution

What was built

An autonomous robotic platform equipped with NIR sensors, a sampling drill, and an in-situ chemical analysis chamber, integrated with a Copernicus-based AI mapping engine.

Audience

Who needs this

Precision agriculture service providersCarbon credit verification agenciesLarge-scale commercial farmsAgricultural machinery OEMs
Business applications

Who can put this to work

Precision Agriculture
SME
Target: Agri-service provider

If you are an agri-service provider dealing with high costs of manual soil sampling — this project developed a robotic sensing toolbox and AI mapping engine that reduces laboratory and labour costs.

Environmental Services
any
Target: Carbon farming consultant

If you are a carbon farming consultant dealing with difficult proof of soil carbon storage — this project developed a carbon farming MRV application that provides high-resolution soil property maps for compliance.

Farm Machinery
mid-size
Target: Variable-rate equipment manufacturer

If you are a machinery manufacturer dealing with low adoption of precision tools — this project developed demand-driven application maps for variable-rate liming, fertilisation, and seeding to increase farmer productivity.

Frequently asked

Quick answers

How does this reduce the cost of soil mapping?

The system uses autonomous robots and a 'Lab in the Field' chamber for in-situ analysis, which reduces the need for expensive manual sampling and external laboratory processing.

Can this be scaled to industrial farming levels?

Based on available project data, the project is testing the system across 7 use cases in different European regions using autonomous robotic platforms to increase productivity.

What is the IP or licensing model for the AI engine?

Based on available project data, the project aims for results to be commercialised by the end of the project, involving 7 SMEs in the value chain.

Does this help with environmental regulations?

Yes, it provides compliancy proof for eco schemes and supports carbon farming MRV (Monitoring, Reporting, and Verification).

When will the commercial version be available?

The project period runs until 2027-07-31, with a goal to ensure results can be commercialised by the project end.

Consortium

Who built it

The consortium is heavily market-oriented with a 58% industry ratio, comprising 7 industrial partners and 5 SMEs. This structure, combined with 8 countries involved, suggests a strong focus on commercial viability and regional scalability rather than pure academic research.

How to reach the team

Contact UDRUZENJE EKO-INOVACIJA NA BALKANU in Serbia

Next steps

Talk to the team behind this work.

Contact us to connect with the SQAT consortium for pilot integration.

More in Environment & Climate
See all Environment & Climate projects