Hybrid Panel Data Forecasting for Coastal Flood Hazard Assessment: A Spatial Data Mining Approach Using Exponential Smoothing and Neural Networks
Abstract
Due to climate change–induced sea level rise, coastal flood risk is increasing significantly, creating an urgent need for improved flood risk assessment and mitigation strategies. Effective flood analysis requires both time series forecasting and hazard risk evaluation, including the determination of appropriate weights for flood-related parameters such as elevation, runoff, distance to the shoreline, and sea level. Traditional forecasting methods like exponential smoothing are limited in capturing relationships between variables, while neural networks can model non-linear interactions but are less commonly applied to long-term forecasting. To address these limitations, this study proposes a hybrid method that integrates Exponential Smoothing (ES) and Neural Networks (NN) for panel data analysis, where ES identifies trends and seasonal patterns and its output is used as additional input for NN. The NN is also employed to objectively determine parameter weights, reducing the subjectivity of conventional AHP-based approaches. The method integrates geographic and climatic variables, including wind speed, temperature, sea surface pressure, and rainfall, and is applied to coastal areas in Semarang, Demak, and Jepara, Indonesia. Results show that the hybrid model outperforms standard ES and NN methods, achieving flood forecasting errors (MAPE) between 3.5% and 8.3% and parameter weighting accuracy of 88–94%, contributing to a more holistic and reliable flood risk analysis.References
UNDP, “Climate change’s impact on coastal flooding to increase 5-times over this century, putting over 70 million people in the path of expanding floodplains, according to new UNDP and CIL data.” Accessed: Nov. 25, 2024. [Online]. Available: https://www.undp.org/press-releases/climate-changes-impact-coastal-flooding-increase-5-times-over-century-putting-over-70-million-people-path-expanding-floodplains
V. Kumar, K. Sharma, T. Caloiero, D. Mehta, and K. Singh, “Comprehensive Overview of Flood Modeling Approaches: A Review of Recent Advances,” Hydrology, vol. 10, no. 7, p. 141, Jun. 2023, doi: 10.3390/hydrology10070141.
F. Aureli, A. Maranzoni, and G. Petaccia, “Advances in Dam-Break Modeling for Flood Hazard Mitigation: Theory, Numerical Models, and Applications in Hydraulic Engineering,” Water, vol. 16, no. 8, p. 1093, Apr. 2024, doi: 10.3390/w16081093.
P. Sibandze, A. M. Kalumba, A. H. Aljaddani, L. Zhou, and G. A. Afuye, “Geospatial Mapping and Meteorological Flood Risk Assessment: A Global Research Trend Analysis,” Environ. Manage., Oct. 2024, doi: 10.1007/s00267-024-02059-0.
FEMA, “Guidance for Flood Risk Analysis and Mapping.” [Online]. Available: https://www.fema.gov/sites/default/files/documents/fema_flood-risk-assessment-guidance.pdf
J. Lin, C. Sreng, E. Oare, and F. A. Batarseh, “NeuralFlood: an AI-driven flood susceptibility index,” Front. Water, vol. 5, 2023, doi: 10.3389/frwa.2023.1291305.
M. Lang et al., “Use of Systematic, Palaeoflood and Historical Data for the Improvement of Flood Risk Estimation. Review of Scientific Methods,” Nat. Hazards, vol. 31, no. 3, pp. 623–643, Mar. 2004, doi: 10.1023/B:NHAZ.0000024895.48463.eb.
K. Yao et al., “A Novel Flood Risk Analysis Framework Based on Earth Observation Data to Retrieve Historical Inundations and Future Scenarios,” Remote Sens., vol. 16, no. 8, p. 1413, Apr. 2024, doi: 10.3390/rs16081413.
Y. Chen, D. Wang, L. Zhang, H. Guo, J. Ma, and W. Gao, “Flood risk assessment of Wuhan, China, using a multi-criteria analysis model with the improved AHP-Entropy method,” Environ. Sci. Pollut. Res., vol. 30, no. 42, pp. 96001–96018, Aug. 2023, doi: 10.1007/s11356-023-29066-8.
S. R. Singh, E. Harirchian, C. E. F. Monjardin, and T. Lahmer, “GIS-Based Risk Assessment of Building Vulnerability in Flood Zones of Naic, Cavite, Philippines Using AHP and TOPSIS,” GeoHazards, vol. 5, no. 4, pp. 1040–1073, Oct. 2024, doi: 10.3390/geohazards5040050.
R. Oyelakin, W. Yang, and P. Krebs, “Analysing Urban Flooding Risk with CMIP5 and CMIP6 Climate Projections,” Water, vol. 16, no. 3, p. 474, Jan. 2024, doi: 10.3390/w16030474.
Z. Yin et al., “Assessing the economic impacts of future fluvial flooding in six countries under climate change and socio-economic development,” Clim. Change, vol. 166, no. 3–4, 2021, doi: 10.1007/s10584-021-03059-3.
D. K. Hakim, R. Gernowo, and A. W. Nirwansyah, “Flood prediction with time series data mining: Systematic review,” Nat. Hazards Res., Oct. 2023, doi: 10.1016/j.nhres.2023.10.001.
A. Mosavi, P. Ozturk, and K. W. K.-W. Chau, “Flood prediction using machine learning models: Literature review,” Water (Switzerland), vol. 10, no. 11, pp. 1–40, 2018, doi: 10.3390/w10111536.
H. D. Nguyen, “Spatial modeling of flood hazard using machine learning and GIS in Ha Tinh province, Vietnam,” J. Water Clim. Chang., vol. 14, no. 1, pp. 200–222, Jan. 2023, doi: 10.2166/wcc.2022.257.
M. Meliho, A. Khattabi, Z. Driss, and C. A. A. Orlando, “Spatial prediction of flood-susceptible zones in the Ourika watershed of Morocco using machine learning algorithms,” Appl. Comput. Informatics, 2022, doi: 10.1108/ACI-09-2021-0264.
M. Meliho, A. Khattabi, and J. Asinyo, “Spatial modeling of flood susceptibility using machine learning algorithms,” Arab. J. Geosci., vol. 14, no. 21, p. 2243, Nov. 2021, doi: 10.1007/s12517-021-08610-1.
A. Arabameri et al., “Modeling Spatial Flood using Novel Ensemble Artificial Intelligence Approaches in Northern Iran,” Remote Sens., vol. 12, no. 20, p. 3423, Oct. 2020, doi: 10.3390/rs12203423.
J. Henson, “Univariate vs Multivariate Time Series Forecasting.” Accessed: Oct. 18, 2023. [Online]. Available: https://medium.com/@jesse.henson/univariate-vs-multivariate-time-series-forecasting-cfcc4150e20a
J. Brownlee, “Taxonomy of Time Series Forecasting Problems,” Machine Learning Mastery. Accessed: Oct. 18, 2023. [Online]. Available: https://machinelearningmastery.com/taxonomy-of-time-series-forecasting-problems/
F. Petropoulos and E. Spiliotis, “The Wisdom of the Data: Getting the Most Out of Univariate Time Series Forecasting,” Forecasting, vol. 3, no. 3, pp. 478–497, Jun. 2021, doi: 10.3390/forecast3030029.
N. Rankovic, D. Rankovic, M. Ivanovic, and L. Lazic, “Improved effort and cost estimation model using artificial neural networks and taguchi method with different activation functions,” Entropy, vol. 23, no. 7, 2021, doi: 10.3390/e23070854.
R. V. Vargas and P. M. P. IPMA-B, “Using the analytic hierarchy process (AHP) to select and prioritize projects in a portfolio,” in PMI global congress, PA: Project Management Institute Washington, DC, 2010, pp. 1–22.
M. Tavana, M. Soltanifar, and F. J. Santos-Arteaga, “Analytical hierarchy process: revolution and evolution,” Ann. Oper. Res., vol. 326, no. 2, pp. 879–907, 2023, doi: 10.1007/s10479-021-04432-2.
P. Madzík and L. Falát, “State-of-the-art on analytic hierarchy process in the last 40 years: Literature review based on Latent Dirichlet Allocation topic modelling,” PLoS One, vol. 17, no. 5, p. e0268777, May 2022, doi: 10.1371/journal.pone.0268777.
BPS Semarang, “Semarang City Area, Measurement Results in 2022.” Accessed: Nov. 01, 2024. [Online]. Available: https://semarangkota.bps.go.id/id/statistics-table/2/MjM5IzI=/luas-wilayah.html
BPS Jepara, “Jepara Area, Measurement Results in 2022.” [Online]. Available: https://jeparakab.bps.go.id/id/statistics-table/2/NDI3IzI=/luas-wilayah-menurut-kecamatan-di-kabupaten-jepara.html
BPS Demak, “Demak Area, Measurement Results in 2020.” [Online]. Available: https://demakkab.bps.go.id/id/statistics-table/2/MzUjMg==/luas-daerah.html
BPS Demak, “Residents of Demak Regency, Projection of the Results of the 2020 Census of the Population of Demak Regency.” Accessed: Nov. 01, 2024. [Online]. Available: https://demakkab.bps.go.id/id/statistics-table/2/MjQ4IzI=/-proyeksi-hasil-lfsp2020--penduduk-kabupaten-demak-menurut-kecamatan--jiwa-.html
BPS Jepara, “Number of Identity Card Required and Ownership of Identity Cary by District in Jepara Regency 2023.”
BPS Semarang, “Semarang City: Area, Number of Population, and Population Density 2021-2023.” [Online]. Available: https://semarangkota.bps.go.id/id/statistics-table/2/NDgjMg==/luas-wilayah--jumlah-penduduk--dan-kepadatan-penduduk--jiwa-km2-.html
M. Buchhorn, M. Lesiv, N.-E. Tsendbazar, M. Herold, L. Bertels, and B. Smets, “Copernicus Global Land Cover Layers—Collection 2,” Remote Sens., vol. 12, no. 6, p. 1044, Mar. 2020, doi: 10.3390/rs12061044.
CivilWeb, “Rational Method Runoff Coefficient.” Accessed: Aug. 09, 2024. [Online]. Available: https://civilweb-spreadsheets.com/drainage-design-spreadsheets/runoff-and-rainfall-intensity-calculator-spreadsheet/rational-method-runoff-coefficient/
SRGI, “Tide Prediction: Indonesian Geospatial Reference System.” Accessed: Nov. 01, 2024. [Online]. Available: https://srgi.big.go.id/map/pasut-prediction-active
J.-N. Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Horányi, A., Muñoz Sabater, J., Nicolas, J., Peubey, C., Radu, R., Rozum, I., Schepers, D., Simmons, A., Soci, C., Dee, D., Thépaut, “ERA5 hourly data on single levels from 1940 to present,” 2023. doi: 10.24381/cds.adbb2d47.
D. F. Hill, “Spatial and Temporal Variability in Tidal Range: Evidence, Causes, and Effects,” Curr. Clim. Chang. Reports, vol. 2, no. 4, pp. 232–241, Dec. 2016, doi: 10.1007/s40641-016-0044-8.
A. T. Devlin, D. A. Jay, E. D. Zaron, S. A. Talke, J. Pan, and H. Lin, “Tidal Variability Related to Sea Level Variability in the Pacific Ocean,” J. Geophys. Res. Ocean., vol. 122, no. 11, pp. 8445–8463, Nov. 2017, doi: 10.1002/2017JC013165.
J. Challis, D. Idier, G. Wöppelmann, and G. André, “Atmospheric Wind and Pressure-Driven Changes in Tidal Characteristics over the Northwestern European Shelf,” J. Mar. Sci. Eng., vol. 11, no. 9, p. 1701, Aug. 2023, doi: 10.3390/jmse11091701.
C. Buta, G. Mihai, and M. Stănescu, “Flood Risk Assessment Based on Flood Hazard and Vulnerability Indexes,” Ovidius Univ. Ann. Constanta - Ser. Civ. Eng., vol. 22, no. 1, pp. 127–137, Dec. 2020, doi: 10.2478/ouacsce-2020-0014.
FEMA, “Guidance for Flood Risk Analysis and Mapping Flood Depth and Analysis Grids,” no. May, 2014.
FEMA, “Guidance for Flood Risk Analysis and Mapping. Hydrology: Rainfall-Runoff Analysis,” 2019. [Online]. Available: https://www.fema.gov/sites/default/files/2020-02/Hydrologic_Rainfall_Runoff_Analysis_Feb_2019.pdf
T. Tingsanchali and T. Promping, “Comprehensive Assessment of Flood Hazard, Vulnerability, and Flood Risk at the Household Level in a Municipality Area: A Case Study of Nan Province, Thailand,” Water, vol. 14, no. 2, p. 161, Jan. 2022, doi: 10.3390/w14020161.
UNISDR, “Flood Hazard and Risk Assessment,” 2017. [Online]. Available: https://www.unisdr.org/files/52828_04floodhazardandriskassessment.pdf
C. R. de Sá, “Variance-Based Feature Importance in Neural Networks,” 2019, pp. 306–315. doi: 10.1007/978-3-030-33778-0_24.
H. Zhou, Learn Data Mining Through Excel: A Step-by-Step Approach for Understanding Machine Learning Methods. Berkeley, CA: Apress, 2020. doi: 10.1007/978-1-4842-5982-5.
H. C. C., E. E. H., and H. I. C., “Evaluation of auto regressive integrated moving average (arima) and artificial neural networks (ann) in the prediction of effluent quality of a wastewater treatment system,” Glob. J. Pure Appl. Sci., vol. 28, no. 1, pp. 83–90, Jun. 2022, doi: 10.4314/gjpas.v28i1.10.
J. Schmuller, Statistical Analysis with Excel 5th Edition. Canada: John Wiley & Sons, Inc, 2022.
S. Prasad, “Time Series,” in Advanced Statistical Methods, Singapore: Springer Nature Singapore, 2024, pp. 109–162. doi: 10.1007/978-981-99-7257-9_3.
C. Fieberg, D. Metko, T. Poddig, and T. Loy, “Machine learning techniques for cross-sectional equity returns’ prediction,” OR Spectr., vol. 45, no. 1, pp. 289–323, Mar. 2023, doi: 10.1007/s00291-022-00693-w.
F. Duval, J.-P. Boucher, and M. Pigeon, “Telematics combined actuarial neural networks for cross-sectional and longitudinal claim count data,” ASTIN Bull., vol. 54, no. 2, pp. 239–262, May 2024, doi: 10.1017/asb.2024.4.
DOI:
https://doi.org/10.31449/inf.v50i5.8164Downloads
Published
How to Cite
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
