Projects / AI Innovation Challenge

Quantifying Soil Organic Carbon Changes for Different Regenerative Farming Practices

Challenge Completed!


Omdena Featured image

The team developed a data visualization dashboard, which shows and compares regenerative farming practices and their impact on Soil organic carbon (SOC) using historical data. The dashboard functions as a tool to analyze and develop pathways to predict SOC.

The problem

The EU is pursuing ambitious policies to combat climate change. It requires the neutrality of carbon emissions in all sectors. The agricultural industry needs a transition toward a more sustainable model, and the rest of the sectors apply restrictions regarding the activities that emit CO2.

First, farmers are both the cause and the affected part of climate change, the loss of biodiversity, and soil erosion. These impacts are significantly affecting productive activity, especially in Spain. Two major barriers to the transition to a regenerative agriculture model would be the solution: the lack of knowledge on how to make the transition and the lack of financial resources to carry out said transition safely and progressively.

Second, companies need by legal imperative, for competitiveness, and for CSR reasons, to achieve neutrality of emissions. This represents a significant investment, and companies can be accused of doing green-washing if the carbon credits they compensate are not duly certified. For this reason, it is necessary to ensure that the carbon capture is accurately measured. Furthermore, they have to align their activities with the SDGs.

Third, current carbon standards and certification bodies require accurate monitoring of carbon sequestration and soil organic carbon (SOC). Agriculture has a high uptake potential, but monitoring costs are very high, making the process unprofitable. Increasing soil organic carbon (SOC) content is crucial for soil quality and climate change mitigation.

The data

The project partner provided various datasets such as their farming data, SigPac, and WISE-3. The team collected additional data from the ICGC website and the LUCAS topsoil dataset, a European survey collected every three years since 2006.

The project outcomes

We developed and deployed an online data visualization application. The dashboard includes various machine learning models to predict SOC.

Grasslands, Shrublands, and forests represent the highest amount of SOC.

These can alter the prediction results for the agricultural farms, hence they need to be excluded.

Screenshot 1 of dashboard visualization

From the below images it’s feasible that Biomass gets reduced in 2021 apart from the Western Region of Catalunya experiencing High Biomass.

Screenshot 2 of dashboard visualization

First Omdena Project?

Join the Omdena community to make a real-world impact and develop your career

Build a global network and get mentoring support

Earn money through paid gigs and access many more opportunities



Your Benefits

Address a significant real-world problem with your skills

Get hired at top companies by building your Omdena project portfolio (via certificates, references, etc.)

Access paid projects, speaking gigs, and writing opportunities



Requirements

Good English

A very good grasp in computer science and/or mathematics

Student, (aspiring) data scientist, (senior) ML engineer, data engineer, or domain expert (no need for AI expertise)

Programming experience with Python

Understanding of Deep Learning, Computer Vision and/or Feature extraction



This challenge has been hosted with our friends at


Application Form
media card
AI-Driven Temperature Analysis for Educational Environments in Tanzania
media card
Developing an AI-Powered Climate Disclosure Reporting Tool for Sustainable Business Practices
media card
Developing an AI-Driven Sentiment Analysis Tool for Political Actors in El Salvador

Become an Omdena Collaborator

media card
Visit the Omdena Collaborator Dashboard Learn More