Advertisement

Predicting surf zone injuries along the Delaware coast using a Bayesian network

  • Matthew B. DoelpEmail author
  • Jack A. Puleo
  • Nathaniel G. Plant
Original Paper
  • 24 Downloads

Abstract

More than 2000 surf zone injury (SZI) events, including 196 spinal injuries and 6 fatalities, were recorded at the five most populated beaches along the 25 miles of Atlantic-fronting Delaware coast from 2010 through 2017. The episodic nature of SZI indicates the importance of linking the environmental conditions and human behavior in the surf zone to predict days with high injury rates. Higher order statistics are necessary to effectively consider all associated factors related to SZI. Two unique Bayesian networks were constructed to model SZI and predict changes in injury rate (proportion of injuries to bathers) and injury likelihood (probability of at least one injury occurrence) on an hourly basis. The models incorporate environmental data collected by weather stations, wave gauges, and researcher personnel on the beach as prior (e.g., historic) information to infer relationships between provided parameters. Sensitivity analysis determined the most influential parameters related to injury rates were significant wave height, foreshore slope, and water temperature. Log-likelihood ratio scores indicate the network predicts SZI likelihood during any specified hour with more skill than prior predictions with the best performing model improving prediction 69.1% of the time (log-likelihood ratio = 69.1%). Issues persist with predicting SZI that have a log-likelihood ratio ≪ − 1 (< 5% of 2017 injuries) and occur in conditions different than when most other SZI occur. Better understanding of SZI will improve awareness techniques to educate beachgoers and assist beach patrol decision making during high-risk conditions.

Keywords

Surf zone injuries Hazard Delaware Beach Bayesian network 

Notes

Acknowledgements

This research was supported by National Sea Grant College Program of the US Department of Commerce’s National Oceanic and Atmospheric Administration (Delaware Sea Grant; Grant No. NA14OAR4170087) and the University of Delaware. The authors would like to acknowledge local town managers, Delaware Beach Patrols, and those individuals that assisted with counting beach populations. The authors also express their gratitude to the two anonymous reviewers and Dr. Sara Ziegler for improving the clarity of this manuscript.

Data availability

Data are available upon request from the authors at jpuleo@udel.edu.

References

  1. Aito S, D’Andrea M, Werhagen L (2004) Spinal cord injuries due to diving accidents. Spinal Cord 43:109–116CrossRefGoogle Scholar
  2. Barucq G, Jenkins O, Mokni T, Marcé J-M, Campagne D, Le Jeune D (2009) Surfing-related accidents: epidemiology and prevention. Surf Prev. http://blog.surf-prevention.com/2009/01/21/surfing-related-accidents-epidemiology-and-prevention/. Accessed 3 Nov 16
  3. Bayes T (1763) An essay towards solving a problem in the doctrine of chances. Philos Trans 53:370–418CrossRefGoogle Scholar
  4. Beratan K, Osborne R (1987) Frequency and demographic aspects in shallow-water diving accidents in southern California. In: Shallow-water diving accidents at Southern California Ocean Beaches: Demographic, Sedimentologic, Medical, Legal and Management Perspectives. University of Southern California, Los Angeles, CAGoogle Scholar
  5. Brander R, Bradstreet A, Sherker S, MacMahan J (2011) Responses of swimmers caught in rip currents: perspectives on mitigating the global rip current hazard. Int J Aquat Res Educ 5:476–482Google Scholar
  6. Camacho RA, Martin JL (2013) Bayesian Monte Carlo for evaluation of uncertainty in hydrodynamic models of coastal systems. J Coast Res 26:886–891CrossRefGoogle Scholar
  7. Cao Y, Chen Y, DeVivo M (2011) Lifetime direct costs after spinal cord injury. Top Spinal Cord Inj Rehabil 16:10–16.  https://doi.org/10.1310/sci1604-10 CrossRefGoogle Scholar
  8. Castelle B, Scott T, Brander RW, McCarroll RJ (2016) Rip current types, circulation and hazard. Earth Sci Rev 163:1–21.  https://doi.org/10.1016/j.earscirev.2016.09.008 CrossRefGoogle Scholar
  9. Chang SKY, Tominaga GT, Wong JH, Weldon EJ, Kaan KT (2006) Risk factors for water sports–related cervical spine injuries. J Trauma Inj Infect Crit Care 60:1041–1046CrossRefGoogle Scholar
  10. Doelp MB, Puleo JA, Cowan P, Arford-Granholm M (2018) Characterizing surf zone injuries from the five most populated beaches on the Atlantic-fronting Delaware coast. Am J Emerg Med.  https://doi.org/10.1016/j.ajem.2017.12.053 Google Scholar
  11. Dusek G, Seim H (2013) A probabilistic rip current forecast model. J Coast Res 29:909–925CrossRefGoogle Scholar
  12. Egozcue JJ, Pawlowsky-Glahn V, Ortego MI (2005) Wave-height hazard analysis in Eastern Coast of Spain—Bayesian approach using generalized Pareto distribution. Adv Geosci 2:25–30CrossRefGoogle Scholar
  13. Elsafi SH (2014) Artificial neural networks (ANNs) for flood forecasting at Dongola Station in the River Nile. Sudan Alex Eng J 53:655–662.  https://doi.org/10.1016/j.aej.2014.06.010 CrossRefGoogle Scholar
  14. Falcon J (2016) Evaluating near shore spinal injuries and alternatives to reduce their occurrence. University of Maryland Baltimore County, Baltimore, MDGoogle Scholar
  15. Fienen MN, Plant NG (2015) A cross-validation package driving Netica with python. Environ Model Softw 63:14–23.  https://doi.org/10.1016/j.envsoft.2014.09.007 CrossRefGoogle Scholar
  16. Fienen MN, Masterson JP, Plant NG, Gutierrez BT, Thieler ER (2013) Bridging groundwater models and decision support with a Bayesian network. Water Resour Res 49:6459–6473.  https://doi.org/10.1002/wrcr.20496 CrossRefGoogle Scholar
  17. Fletemeyer J, Leatherman S (2010) Rip currents and beach safety education. J Coast Res 26:1–3CrossRefGoogle Scholar
  18. Gensini VA, Ashley WS (2010) An examination of rip current fatalities in the United States. Nat Hazards 54:159–175.  https://doi.org/10.1007/s11069-009-9458-0 CrossRefGoogle Scholar
  19. Grezio A, Marzocchi W, Sandri L, Gasparini P (2010) A Bayesian procedure for probabilistic Tsunami hazard assessment. Nat Hazards 53:159–174.  https://doi.org/10.1007/s11069-009-9418-8 CrossRefGoogle Scholar
  20. Gutierrez BT, Plant NG, Thieler ER (2011) A Bayesian network to predict coastal vulnerability to sea level rise. J Geophys Res Earth Surf 116: F2.  https://doi.org/10.1029/2010JF001891 CrossRefGoogle Scholar
  21. Gutierrez BT, Plant NG, Thieler ER, Turecek A (2015) Using a Bayesian network to predict barrier island geomorphologic characteristics. J Geophys Res Earth Surf 120:2452–2475.  https://doi.org/10.1002/2015JF003671 CrossRefGoogle Scholar
  22. Hapke C, Plant N (2010) Predicting coastal cliff erosion using a Bayesian probabilistic model. Mar Geol 278:140–149.  https://doi.org/10.1016/j.margeo.2010.10.001 CrossRefGoogle Scholar
  23. Hay CSM, Barton S, Sulkin T (2009) Recreational surfing injuries in Cornwall, United Kingdom. Wilderness Environ Med 20:335–338.  https://doi.org/10.1580/1080-6032-020.004.0335 CrossRefGoogle Scholar
  24. Kalogeromitros A, Tsangaris H, Bilalis D, Karabinis A (2002) Severe accidents due to windsurfing in the Aegean Sea. Eur J Emerg Med 9:149–154CrossRefGoogle Scholar
  25. Liong S-Y, Sivapragasam C (2002) Flood stage forecasting with support vector machines. JAWRA J Am Water Resour As 38:173–186.  https://doi.org/10.1111/j.1752-1688.2002.tb01544.x CrossRefGoogle Scholar
  26. Lushine JB (1991) A study of rip current drownings and related weather factors. Natl Wea Dig 16:13–19Google Scholar
  27. McCarroll RJ, Brander RW, MacMahan JH, Turner IL, Reniers AJHM, Brown JA, Bradstreet A, Sherker S (2014) Evaluation of swimmer-based rip current escape strategies. Nat Hazards 71:1821–1846.  https://doi.org/10.1007/s11069-013-0979-1 CrossRefGoogle Scholar
  28. Meir RA, Zhou S, Rolfe MI, Gilleard WL, Coutts RA (2012) An investigation of surf participation and injury prevalence in Australian surfers: a self-reported retrospective analysis. N Z J Sports Med 39:52Google Scholar
  29. Milheiro-Oliveira P (2007) Bayesian statistical methods for modeling and prediction of major landslides in coastal cliffs. Coast Eng J 49:45–61.  https://doi.org/10.1142/S0578563407001502 CrossRefGoogle Scholar
  30. Moulton M, Dusek G, Elgar S, Raubenheimer B (2017) Comparison of rip current hazard likelihood forecasts with observed rip current speeds. Weather Forecast 32:1659–1666.  https://doi.org/10.1175/WAF-D-17-0076.1 CrossRefGoogle Scholar
  31. Nathanson A, Haynes P, Galanis D (2002) Surfing injuries. Am J Emerg Med 20:155–160.  https://doi.org/10.1053/ajem.2002.32650 CrossRefGoogle Scholar
  32. Norsys Software Corp. - Bayes Net Software [WWW Document] (n.d.) https://www.norsys.com/. Accessed 1 May 18
  33. Palmsten ML, Splinter KD, Plant NG, Stockdon HF (2014) Probabilistic estimation of dune retreat on the Gold Coast, Australia. Shore Beach 82:3543Google Scholar
  34. Passeri DL, Hagen SC, Plant NG, Bilskie MV, Medeiros SC, Alizad K (2016) Tidal hydrodynamics under future sea level rise and coastal morphology in the Northern Gulf of Mexico. Earths Future 4:159–176.  https://doi.org/10.1002/2015EF000332 CrossRefGoogle Scholar
  35. Plant NG, Holland KT (2011a) Prediction and assimilation of surf-zone processes using a Bayesian network: part I: Forward models. Coast Eng 58:119–130.  https://doi.org/10.1016/j.coastaleng.2010.09.003 CrossRefGoogle Scholar
  36. Plant NG, Holland KT (2011b) Prediction and assimilation of surf-zone processes using a Bayesian network: part II: Inverse models. Coast Eng 58:256–266.  https://doi.org/10.1016/j.coastaleng.2010.11.002 CrossRefGoogle Scholar
  37. Plant NG, Stockdon HF (2012) Probabilistic prediction of barrier-island response to hurricanes. J Geophys Res Earth Surf 1:1.  https://doi.org/10.1029/2011JF002326 Google Scholar
  38. Poelhekke L, Jäger WS, van Dongeren A, Plomaritis TA, McCall R, Ferreira Ó (2016) Predicting coastal hazards for sandy coasts with a Bayesian network. Coast Eng 118:21–34.  https://doi.org/10.1016/j.coastaleng.2016.08.011 CrossRefGoogle Scholar
  39. Pollino CA, Woodberry O, Nicholson A, Korb K, Hart BT (2007) Parameterisation and evaluation of a Bayesian network for use in an ecological risk assessment. Environl Model Softw 22(8):1140–1152CrossRefGoogle Scholar
  40. Puleo JA, Hutschenreuter K, Cowan P, Carey W, Arford-Granholm M, McKenna KK (2016) Delaware surf zone injuries and associated environmental conditions. Nat Hazards 81:845–867.  https://doi.org/10.1007/s11069-015-2108-9 CrossRefGoogle Scholar
  41. Roberts TM, Wang P, Puleo JA (2013) Storm-driven cyclic beach morphodynamics of a mixed sand and gravel beach along the Mid-Atlantic Coast, USA. Mar Geol 346:403–421CrossRefGoogle Scholar
  42. Robles LA (2006) Cervical spine injuries in ocean bathers: wave-related accidents. Neurosurgery 58:920–923.  https://doi.org/10.1227/01.NEU.0000209941.18102.35 CrossRefGoogle Scholar
  43. Rubinfeld DL, Rodgers GB (1992) Evaluating the injury risk associated with all-terrain vehicles: an application of Bayes’ rule. J Risk Uncertain 5:145–158.  https://doi.org/10.1007/BF00057568 CrossRefGoogle Scholar
  44. Scott T, Masselink G, Austin MJ, Russell P (2014) Controls on macrotidal rip current circulation and hazard. Geomorphology 214:198–215.  https://doi.org/10.1016/j.geomorph.2014.02.005 CrossRefGoogle Scholar
  45. Scotto MG, Guedes Soares C (2007) Bayesian inference for long-term prediction of significant wave height. Coast Eng 54:393–400.  https://doi.org/10.1016/j.coastaleng.2006.11.003 CrossRefGoogle Scholar
  46. Short AD, Hogan CL (1994) Rip currents and beach hazards: their impact on public safety and implications for coastal management. J Coast Res 12:197–209Google Scholar
  47. Simoncic M (2004) A Bayesian network model of two-car accidents. J Transp Stat 7:13–25Google Scholar
  48. USLA (2016) United States Lifesaving Association—Statistics [WWW Document]. http://arc.usla.org/Statistics/current.asp?Statistics=5. Accessed 10 March 17
  49. van Verseveld HCW, van Dongeren AR, Plant NG, Jäger WS, den Heijer C (2015) Modelling multi-hazard hurricane damages on an urbanized coast with a Bayesian network approach. Coast Eng 103:1–14.  https://doi.org/10.1016/j.coastaleng.2015.05.006 CrossRefGoogle Scholar
  50. Vitabile S, Farruggia A, Pernice G, Gaglio S (2013) Paper assessing coastal sustainability: a bayesian approach for modeling and estimating a global Index for measuring risk 11Google Scholar
  51. Wikle CK, Berliner LM (2007) A Bayesian tutorial for data assimilation. Phys D Nonlinear Phenom 230(1–2):1–16CrossRefGoogle Scholar
  52. Williams MR, Poulter RJ, Fern ED (2006) Skimboarding: a new danger in the surf? Emerg Med J 23:137.  https://doi.org/10.1136/emj.2005.026385 CrossRefGoogle Scholar
  53. Wilson KE, Adams PN, Hapke CJ, Lentz EE, Brenner O (2015) Application of Bayesian Networks to hindcast barrier island morphodynamics. Coast Eng 102:30–43.  https://doi.org/10.1016/j.coastaleng.2015.04.006 CrossRefGoogle Scholar
  54. Wright L, Short A (1984) Morphodynamic variability of surf zones and beaches: a synthesis. Mar Geol 56:93–118.  https://doi.org/10.1016/0025-3227(84)90008-2 CrossRefGoogle Scholar

Copyright information

© Springer Nature B.V. 2019

Authors and Affiliations

  1. 1.Center for Applied Coastal ResearchUniversity of DelawareNewarkUSA
  2. 2.U.S. Geological SurveySt. PetersburgUSA

Personalised recommendations