Mapping coastal resilience: a Gis-based Bayesian network approach to coastal hazard identification for Queensland’s dynamic shorelines

Abstract

Coastal regions worldwide face increasing threats from climate change-induced hazards, necessitating more accurate and comprehensive vulnerability assessment tools. This study introduces an innovative approach to coastal vulnerability assessment by integrating Bayesian Networks (BN) with the modern coastal vulnerability (CV) framework. The resulting BN-CV model was applied to Queensland's coastal regions, with a particular focus on tide-modified and tide-dominated beaches, which constitute over 85% of the studied area. The research methodology involved beach classification based on morphodynamic characteristics, spatial subdivision of Queensland's coast into 78 sections, and the application of the BN-CV model to analyze interactions between geomorphological features and oceanic dynamics. This approach achieved over 90% accuracy in correlating beach types with vulnerability factors, significantly outperforming traditional CVI applications. Key findings include the identification of vulnerability hotspots and the creation of detailed exposure and sensitivity maps for Gold Coast City, Redland City, Brisbane City, and the Sunshine Coast Regional area. The study revealed spatial variability in coastal vulnerability, providing crucial insights for targeted management strategies. The BN-CV model demonstrates superior precision and customization capabilities, offering a more nuanced understanding of coastal vulnerability in regions with diverse beach typologies. This research advocates for the adoption of the BN-CV approach to inform tailored coastal planning and management strategies, emphasizing the need for regular reassessments and sustained stakeholder engagement to build resilience against climate change impacts.

Recommendations include prioritizing adaptive infrastructure in high-exposure areas like the Gold Coast, enhancing flood management in Brisbane, improving socio-economic adaptive capacity in Redland, and maintaining natural defences in Moreton Bay. This study contributes significantly to the field of coastal risk management, providing a robust tool for policymakers and coastal managers to develop more effective strategies for building coastal resilience in the face of climate change.

References

[1] Aymergen BB (2023) Planning of marine structures with multi-criteria decision-making (MCDM) and estimating design parameters with adaptive network-based fuzzy inference system. MSc Thesis, Gazi University, Institute of Natural Sciences, Ankara

[2] BalsasCJL. Coastal waterfront transformations, fishing structures, and sustainable tourism. Sustainability, 2024, 16(15): 6313

[3] BeuzenT, SplinterKD, MarshallLA, TurnerIL, HarleyMD, PalmstenML. Bayesian Networks in coastal engineering: Distinguishing descriptive and predictive applications. Coast Eng, 2018, 135: 16-30

[4] CeccacciA, LopesAF, MulazzaniL, MalorgioG. Recreation in coastal environments: estimating the non-market value of fishing harbors. Ecol Econ, 2024, 221: 108197

[5] Doğan Y, Ahmet D (2017) Summarizing data sets for data mining by using statistical methods in coastal engineering. Int J Comput Inf Eng 11(6):649–654

[6] DurapA. A comparative analysis of machine learning algorithms for predicting wave runup. Anthropocene Coasts, 2023, 6(1): 17

[7] DurapA, BalasCE. Risk assessment of submarine pipelines: a case study in Turkey. Ocean Eng, 2022, 261: 112079

[8] DurapA, BalasCE. Towards sustainable coastal management: a hybrid model for vulnerability and risk assessment. J Coast Conserv, 2024, 28(4): 66

[9] DurapA, BalasCE, ÇokgörŞ, BalasEA. An Integrated Bayesian risk model for coastal flow slides using 3-D hydrodynamic transport and monte Carlo simulation. J Mar Sci Eng, 2023, 11(5): 943

[10] Gornitz V (1991) Global coastal hazards from future sea level rise. Palaeogeogr Palaeoclimatol Palaeoecol 89(4):379–398

[11] Gornitz V (1990) Vulnerability of the East Coast, USA to future sea level rise. J Coast Res 201–237

[12] Gornitz VM et al (1994) The development of a coastal risk assessment database: vulnerability to sea-level rise in the US Southeast. J Coast Res 327–338

[13] GutierrezBT, PlantNG, ThielerER, TurecekA. Using a Bayesian network to predict barrier island geomorphologic characteristics. J Geophys Res Earth Surf, 2015, 120(12): 2452-2475

[14] 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

[15] HanafiIH, RiryWA. Sosialisasi Hukum Tentang Pengaturan Kewenangan Pengelolaan Wilayah Pesisir. AIWADTHU: Jurnal Pengabdian Hukum, 2024, 4(1): 8

[16] HubbardME, DoddN. A 2D numerical model of wave run-up and overtopping. Coast Eng, 2002, 47(1): 1-26

[17] JacksonDWT, CooperJAG, del RioL. Geological control of beach morphodynamic state. Mar Geol, 2005, 216(4): 297-314

[18] JacksonDWT, ShortAD, LoureiroC, CooperJAG. Beach morphodynamic classification using high-resolution nearshore bathymetry and process-based wave modelling. Estuar Coast Shelf Sci, 2022, 268: 107812

[19] KorogluA, RanasingheR, JiménezJA, DastgheibA. Comparison of Coastal Vulnerability Index applications for Barcelona Province. Ocean Coast Manag, 2019, 178: 104799

[20] KurniatiR, WidjajantiR, DewiSP, SyahriEK. Coastal Area Sustainability. Int Rev Spatial Plann Sustain Dev, 2024, 12(2): 15

[21] LevoyF, AnthonyEJ, MonfortO, LarsonneurC. The morphodynamics of megatidal beaches in Normandy, France. Marine Geology, 2000, 171(1–4): 39-59

[22] MendozaET, JiménezJA. Regional vulnerability analysis of Catalan beaches to storms. Proceedings of the Institution of Civil Engineers - Maritime Engineering, 2009, 162(3): 127-135

[23] ParsonsB, SclaterJG. An analysis of the variation of ocean floor bathymetry and heat flow with age. J Geophys Res, 1977, 82(5): 803-827

[24] Perch-NielsenSL. The vulnerability of beach tourism to climate change—an index approach. Clim Change, 2010, 100(3–4): 579-606

[25] SahinO, StewartRA, FaivreG, WareD, TomlinsonR, MackeyB. Spatial Bayesian Network for predicting sea level rise induced coastal erosion in a small Pacific Island. J Environ Manage, 2019, 238: 341-351

[26] Sandy Beach Morphodynamics. (2020). Elsevier. https://doi.org/10.1016/C2018-0-02420-2

[27] SanuyM, JiménezJA, PlantN. A Bayesian Network methodology for coastal hazard assessments on a regional scale: the BN-CRAF. Coast Eng, 2020, 157: 103627

[28] ShankarNJ, JayaratneMPR. Wave run-up and overtopping on smooth and rough slopes of coastal structures. Ocean Eng, 2003, 30(2): 221-238

[29] Short AD (2020) Wave-dominated, tide-modified and tide-dominated continuum. In Sandy Beach Morphodynamics (pp. 363–389). Elsevier. https://doi.org/10.1016/B978-0-08-102927-5.00016-3

[30] SmitB, WandelJ. Adaptation, adaptive capacity and vulnerability. Glob Environ Chang, 2006, 16(3): 282-292

[31] Sudha RaniNNV, SatyanarayanaANV, BhaskaranPK. Coastal vulnerability assessment studies over India: a review. Nat Hazards, 2015, 77(1): 405-428

[32] Tanim AH & Goharian E (2023) Toward an integrated probabilistic coastal vulnerability assessment: a novel copula‐based vulnerability index. Water Resour Res 59(2). https://doi.org/10.1029/2022WR033603

[33] TürR. Maximum wave height hindcasting using ensemble linear-nonlinear models. Theoret Appl Climatol, 2020, 141(3–4): 1151-1163

[34] TurR, YontemS. A comparison of soft computing methods for the prediction of wave height parameters. Knowl Based Eng Sci, 2021, 2(1): 31-46

[35] TurR, TasE, HaghighiAT, MehrAD. Sea level prediction using machine learning. Water, 2021, 13(24): 3566

[36] ValchevN, EftimovaP, AndreevaN, ProdanovB. APPLICATION OF BAYESIAN NETWORK AS A TOOL FOR COASTAL FLOODING IMPACT PREDICTION AT VARNA BAY (BULGARIA, WESTERN BLACK SEA). Coastal Eng Proc, 2017, 35: 14

[37] WrightLD, ShortAD. Morphodynamic variability of surf zones and beaches: a synthesis. Mar Geol, 1984, 56(1–4): 93-118

[38] YeX. Impacts of Climate Change on Tourism in Coastal Areas. Adv Econ Manage Polit Sci, 2023, 62(1): 271-276