Transfer and Uncertainty for Soil Spectroscopy: A Parsimonious Approach Using Bayesian Mixed Models and Soil Surveys

Paper and Data

This research demonstrates a more reliable way to estimate soil carbon using near-infrared light measurements, making it easier to apply the technology across different farms without requiring extensive soil sampling at each location. By improving prediction accuracy and quantifying uncertainty, the approach could help make soil carbon monitoring more scalable, affordable, and trustworthy for agricultural management and carbon accounting.

Acres Partners: Eric Potash, Colleen Partida, Jose Safanelli, Elizabeth Forbes, Alex Polussa, Tiffany Runge. Matthew Sheffer, Jonathan Sanderman

Data and Resources

Additional Info

Field Value
Source https://github.com/potash/spectroscopy-lmm
Last Updated November 13, 2026, 19:58 (UTC)
Created November 13, 2026, 19:10 (UTC)