Machine Learning Analysis of Lifeguard Flag Decisions and Recorded Rescues
Bibliographic record
Abstract
Abstract. Rips currents and other surf hazards are an emerging public health issue globally. Lifeguards, warning flags and signs are important and to varying degrees they are effective strategies to minimize risk. In the United States and other jurisdictions around the world, lifeguards use coloured flags (green, yellow and red) to indicate whether the danger posed by the surf and rip hazard is low, moderate, or high respectively. The choice of flag depends on the lifeguard monitoring the changing surf conditions along the beach and over the course of the day using both regional surf forecasts and careful observation. There is a potential that the chosen flag does not accurately reflect the potential risk, which may increase the potential for rescues or drownings. In this study, machine learning used to determine the potential for error in the flags used at Pensacola Beach, and the impact of that error on the number of rescues. A decision tree analysis suggests that the wrong flag was flown on ~ 35 % of days between 2004 and 2008 (n = 396/1125), and that those differences account for only 17 % of all rescue days and ~ 60 % of the total number of rescues. Further analysis reveals that the largest number of rescue days and total number of rescues is associated with days where the flag deployed over-estimated the surf and hazard risk, such as a red or yellow flag flying when the model would suggest a green flag would be more appropriate based on the wind and wave forcing. Regardless whether this is a result of the lifeguards being overly cautious or the rip and surf hazard is associated with weak rips forced by a transverse-bar and rip morphology, the results suggest that beach users are discounting the lifeguard warnings if it isn't consistent with how they perceive the surf hazard. Results suggest that machine learning techniques have the potential to support lifeguard and thereby reduce the number of rescues and drownings.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".