Soil properties predicted from mid-infrared spectral (MIRS) analysis of 366 soil samples collected in 2024 before and/or after establishing on-farm trials on yield response to lime rates in Zambia

Selected soil properties were predicted from 366 topsoil samples subjected to spectral analysis (MIRS).
A subset of samples were also subjected to wet chemistry analysis (see link in the PDF report), and results were used to calibrate a machine-learning algorithm developed by the International Centre for Research in Agroforestry (ICRAF) in Kenya. Coordinates were truncated to protect farmer's privacy.
Unless specified, all properties were predicted. This dataset can be linked with yield data (coming soon) through the unique farm identifer "fid".
A link is provided to match terms used in the "terminag" GitHub (https://github.com/reagro/terminag/) as of January 2026