Satellite and Statistical Approach for the Characterization of Coastal Storms Causing Damage on the Dakar Coast, Capital of Senegal (West Africa)
Bibliographic record
Abstract
Today, coastal storms represent one of the most formidable environmental challenges, causing significant impacts on coastal communities. This situation underscores both the importance and urgency of studying storms and their characterization. This study proposes an innovative approach combining Principal Component Analysis (PCA) and machine learning (Classification and Regression Trees, CART) to characterize and distinguish damaging storms from non-damaging ones along the coast of Dakar, Senegal. The analysis revealed that among several hydrometeorological variables studied (wave height, period, direction, runup, wave energy, sea level anomaly, tide, etc.), the variables SLA and tide play a central role in the occurrence of damage, although they are weakly correlated with the others. By cross-analyzing these variables, critical thresholds were established, such as Tide > 0.53 m combined with SLA ≥ 0.061 m, Tide > 0.53 m and ECWL ≥ 1.3 m, as well as Runup ≤ 0.64 m associated with a high wave period (Tp), allowing accurate differentiation of potentially damaging storms. The CART method validated these results and identified three key combinations: (1) Tide–SLA, where no damage is observed if Tide < 0.53 m, and damage occurs beyond this threshold when SLA ≥ 0.061 m; (2) Tide–ECWL, where storms are damaging if Tide > 0.53 m and ECWL ≥ 1.3 m; (3) Runup–Tp, where storms are damaging if Runup ≤ 0.64 m or if Runup > 0.82 m with Tp ≥ 16 s. These results constitute the first application of machine learning for storm classification on the Senegalese coast, providing a novel quantitative foundation for better understanding the hydrodynamic conditions associated with damaging storms. The findings of this study could be valuable for risk management and the development of early warning systems
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 | 0.000 | 0.000 |
| 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 | 0.000 |
| 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 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".