Soil Spectroscopy
Rapid and affordable soil characterization is becoming increasingly important in modern agriculture. DALab is developing comprehensive soil spectral libraries that provide the foundation for next-generation soil monitoring systems.
Using visible, near-infrared, and hyperspectral technologies, combined with advanced machine learning techniques, we are creating predictive models capable of estimating soil organic carbon, nutrients, texture, and other indicators of soil health.
Schematic explanation of diffuse reflectance spectroscopy for soil analysis.
https://docs.soilspectroscopy.org/img/drs-schematic.jpeg
These spectral libraries enable faster and more cost-effective analyses compared with conventional laboratory methods while supporting precision agriculture and environmental monitoring initiatives. Our vision is to establish intelligent soil information systems that facilitate large-scale assessments and contribute to global efforts focused on soil security and climate mitigation.
Team Members/ Collaborators
Publications
Prediction of total organic matter in marsh sediments: integrating reflectance clustering, spectral subranges, and color coefficients Dastgheib, Z.A., Goharrokhi, M., Clark, S. et al., J Soils Sediments 26, 211 (2026).https://doi.org/10.1007/s11368-026-04414-6
Significance of Planet SuperDove and refined Sentinel-2 imagery fusion for enhanced soil organic carbon prediction in croplands James Kobina Mensah Biney, Jakub Houška, Olha Kachalova, Jiří Volánek, Prince Chapman Agyeman, David Kwesi Abebrese, Ehsan Chatraei Azizabadi, Nasem Badreldin, CATENA, Volume 254, 2025, 108902, https://doi.org/10.1016/j.catena.2025.108902
Is the estimation of soil organic carbon using the colour space model, based on visible spectroscopy range, a reliable approach? Biney, J. K. M., Houška, J., & Badreldin, N. (2024). Soil Use and Management, 40, e13147. https://doi.org/10.1111/sum.13147