At Mutus Tech, we have developed a comprehensive soil dataset that combines more than 4,000 real-world soil samples with over 300,000 simulated samples generated using an agricultural process-based model. This integrated dataset forms a robust foundation for understanding soil health and supporting sustainable fertiliser management strategies.

Real-World Soil Samples
Our dataset includes over 4,000 soil samples collected across a variety of agricultural regions and soil types. Each sample is accompanied by detailed metadata, including environmental conditions, cropping history and land use. This provides a solid empirical base for soil health assessments and model calibration.

Simulated Data for Model Training
To expand on the insights provided by the real-world samples, we have generated a large simulation dataset. This process-based model uses weather, soil and management data to simulate fertiliser responses under diverse environmental scenarios. The result is over 300,000 synthetic soil entries, as well as more than one million data points capturing soil greenhouse gas fluxes under different fertiliser practices.

Applications and Ongoing Work
Together, these real and simulated samples support the development of AI models for precision fertiliser management, soil health monitoring and emissions modelling. By combining these complementary datasets, we create decision-support tools that are both grounded in real-world data and adaptable to a range of agricultural environments. We continue to expand the dataset through partnerships with international collaborators and ongoing field surveys.

Data Sample Access
A sample dataset illustrating the structure and scope of this integrated soil data archive is available for download.

👉 Download Sample Dataset (ZIP)