Soil properties predicted from mid-infrared spectral (MIRS) analysis of soil samples collected in 2023 (second year) before and/or after establishing on-farm trials on yield response to lime rates in Rwanda

<p>Selected soil properties were predicted from 524 topsoil samples subjected to spectral analysis (MIRS). A subset of samples were also subjected to wet chemistry analysis, 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.</p>
<p>Unless specified, all properties were predicted. This dataset can be linked with yield data (coming soon) and previous soil analysis data (<a href="https://hdl.handle.net/11529/10549138">https://hdl.handle.net/11529/10549138</a>) through the unique farm identifer "fid".</p>
<p>A link is provided to match terms used in the "terminag" GitHub (<a href="https://github.com/reagro/terminag/">https://github.com/reagro/terminag/</a>) as of June 2025</p>