Papers › Predicting Soil Properties from Hyperspectral Satellite Images
Predicting Soil Properties from Hyperspectral Satellite Images
Rıdvan Salih Kuzu, Frauke Albrecht, Caroline Arnold, Roshni Kamath
The AI4EO HYPERVIEW challenge seeks machine learning methods that predict agriculturally relevant soil parameters (K, Mg, P2O5, pH) from airborne hyperspectral images. We present a hybrid model fusing Random Forest and K- nearest neighbor regressors that exploit the average spectral reflectance, as well as derived features such as gradients, wavelet coefficients, and Fourier transforms. The solution is computationally lightweight and improves upon the challenge baseline by 21.9%, with the first place on the public leader- board. In addition, we discuss neural network architectures and potential future improvements.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Seeing Beyond the Visible | HYPERVIEW | RF + KNN | normalized MSE | 0.78113 | #1 of 1 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections