Multi-frequency SAR and optical data integration for continental-scale digital mapping of soil chemical properties across Europe
Bibliographic record
Abstract
Timely and accurate spatial information on soil properties is essential for addressing global challenges, including climate change, food security, and ecosystem degradation. Despite advances in digital soil mapping (DSM), current approaches remain limited by reliance on optical satellite data and insufficient exploration of synthetic aperture radar (SAR) potential at continental scales. Here, we advance DSM by integrating multi-frequency SAR and optical satellite observations to map four key soil chemical properties—soil organic carbon, pH, extractable potassium, and total nitrogen—across Europe. Eleven scenarios with different data integrations, combined with two machine learners (support vector machine and random forest algorithms) and measurements from the LUCAS 2018 soil module, were employed to construct prediction models. The results confirm that continental-scale DSM is feasible using long-term optical and SAR observations. For all soil properties, C-band Sentinel-1 outperformed L -band PALSAR-1/2, and the integration of multi-frequency SAR data achieved prediction accuracies comparable to or even exceeding those of optical data, with R² improvements of approximately 29 %–87 % compared with using only L -band backscatter bands. The joint use of radar and optical observations produced the best performance, improving predictions of all soil properties compared to using optical data alone, with R² values ranging approximately from 0.31 to 0.60—highest for soil pH and lowest for soil total nitrogen. The relative importance of SAR features in the predictions varied with specific polarization modes and band frequencies, and radar indices were found to be more influential in models than backscatter bands. The generated soil property maps showed spatial patterns consistent with previous efforts based on multi-source environmental data. This study demonstrates that multi-frequency SAR data can both substitute for and complement optical data in DSM, offering new insights and practical directions for future model development. • C-band Sentinel-1 outperformed L -band PALSAR-1/2 in predictive performance. • Multi-frequency SAR achieved comparable or higher accuracy than optical data. • Microwave observations can replace or complement optical data in DSM. • The GEE platform efficiently supported DSM model development. • Radar indices were better predictors than raw backscatter bands.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".