Monitoring soil degradation using Sentinel-2 imagery and statistical analysis of spectral indices in a semi-arid watershed of the Moroccan High Atlas
Bibliographic record
Abstract
The existence of serious water erosion problems in different parts of a watershed is often evidenced by the presence of high levels of suspended sediment in watercourses. The indirect assessment of erosion through the measurement of suspended sediments transported to catchment outlets serves as a robust indicator of the environmental impact of agricultural practices. The aim of this study is to propose a model for assessing the risk of soil degradation in the upstream Tassaoute watershed (in the Moroccan High Atlas). The methodology is based on the statistical analysis of spectral indices derived from Sentinel-2A satellite images acquired during the year 2021, including four vegetation indices and nine soil indices. These indices are aggregated to form a composite image (the independent variable), which is then subjected to regression analysis against the individual indices (the dependent variable) to determine correlation coefficients and coefficients of determination. Principal Component Analysis (PCA) is then used to condense the information from all the spectral indices, providing factorial coordinates and facilitating the identification of positive and negative correlations. The principal component captures soil-related information, while the secondary component focuses on vegetation characteristics. The final predictive model is developed by assigning weights to each index based on its coefficient of determination and the coordinates of the factors. This approach produces a quantitative map delineating four categories of soil potentially at risk of degradation. The results show that incorporating the spectral bands of Sentinel-2A’s C-MSI sensor into the calculation considerably improves accuracy and provides an accurate representation of ground reality.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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 source (direct Gemma or distilled Codex), 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".