Knowledge-Informed Data-Driven Modeling of Coupled Human-Built–Natural Systems: The Case of Hurricane-Induced Debris
Abstract
Debris is one of the most challenging cascading effects posed by hurricane events, causing large financial and logistical burdens to coastal communities. Moreover, disaster debris can have cascading consequences on the safety and functionality of infrastructure, inhibit community recovery efforts, and lead to public health concerns. However, existing debris predictive models have shown an unsatisfactory performance, with errors up to 50% in debris estimates, and only consider a limited set of predictive variables. Given the importance of debris in coastal community resilience, this study leveraged a convergent research strategy to propose a knowledge-informed data-driven methodology by developing a comprehensive database that expands across human-built–natural systems to inform a probabilistic data-driven model of debris volume. A Gaussian process model was used to generate the debris volume model from a debris removal database for Hurricane Ike and the human-built–natural systems predictors. Moreover, different spatial resolutions (500, 250, and 125 m) were tested to analyze their effect on the model performance. Results showed that the low-resolution (500 m) and the intermediate-resolution (250 m) models have the best performance with a normalized root-mean squared error (RMSE) of 0.49 and 0.50, respectively. These two models were then used to explore the relative variable importance of the predictive variables in the model in order to get insights on the drivers of the debris process and propose more flexible lower-dimensionality models. The influence of different predictors and the trade-offs of resolution and model performance were also discussed before demonstrating application of the model for a synthetic storm in the Galveston, Texas, region. The proposed methodology and the probabilistic estimates of debris quantities are key to develop comprehensive risk estimates of storm impacts on coastal communities and can support informed decision making and mitigation planning strategies.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some data used during the study were provided by a third party (wind field intensity parameters and the debris removal database). Direct requests for these materials may be made to the provider as indicated in the Acknowledgments. All the other data (human-built–natural system parameter database), models, and codes that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The authors gratefully acknowledge the support of this research by the National Science Foundation under Awards OISE-1545837 and CMMI-2002522. In addition, the second author is supported in part by the NIST Center of Excellence for Risk-Based Community Resilience Planning under Cooperative Agreement 70NANB15H044 between the National Institute of Standards and Technology (NIST) and Colorado State University. Any opinions, findings, and conclusions, or recommendations expressed in this paper are those of the authors and do not necessarily reflect the views of the sponsors. The authors give a special acknowledgement to Dr. Genevera Allen, who gave important guidance on the development of the models and their interpretation. In addition, Miku Fukatsu and Henry Ulrich, undergraduate students doing internships in Padgett’s Research group, are also gratefully acknowledged for their support in the preprocessing of the data used in this study. Rice University’s Fondren Library GIS center is acknowledged for their support in identifying the data used in the testbed analysis, along with the resources of the NHERI DesignSafe Cyberinfrastructure CMMI-2022469. The authors also acknowledge Dr. Kayode Atoba for providing the data associated to the HAZUS debris model. Finally, the authors gratefully acknowledge RMS for providing the HWind data used to inform the wind field parameters and Tetra Tech for providing the debris removal database. Maps throughout this paper were created using ArcGISsoftware by Esri. ArcGIS and ArcMap are the intellectual property of Esri.
References
Beatley, T. 2012. Planning for coastal resilience: Best practices for calamitous times. Washington, DC: Island Press.
Berkovic, S. 2018. “Wind regimes and their relation to synoptic variables using self-organizing maps.” Adv. Sci. Res. 15 (Jan): 1–9. https://doi.org/10.5194/asr-15-1-2018.
CGH (Computational Hydraulics Group at the University of Texas at Austin). 2017. “The computational hydraulics group.” Accessed April 3, 2022. https://chg.oden.utexas.edu/.
Charvet, I., J. Macabuag, and T. Rossetto. 2017. “Estimating tsunami-induced building damage through fragility functions: Critical review and research needs.” Front. Built Environ. 3 (Aug): 36. https://doi.org/10.3389/fbuil.2017.00036/full.
Cutter, S. L., B. J. Boruff, and W. Lynn Shirley. 2012. “Social vulnerability to environmental hazards.” In Hazards vulnerability and environmental justice, 143–160. London: Routledge.
DeltaIV. 2017. “Why is the mean function in Gaussian process uninteresting?” Accessed July 1, 2022. https://stats.stackexchange.com/q/222304.
Dukes, B. 2019. “Undergraduate Research Experience (REU), NHERI 2019: A data processing and visualization framework for hurricane debris modeling.”Accessed September 1, 2022. https://search.datacite.org/works/10.17603/ds2-jt8d-sx39.
Ebersole, B. A., T. C. Massey, J. A. Melby, N. C. Nadal-Caraballo, D. L. Hendon, T. W. Richardson, and R. W. Whalin. 2015. Interim report—Ike dike concept for reducing hurricane storm surge in the Houston-Galveston region. Jackson, MS: Jackson State Univ.
Escobedo, F. J., C. J. Luley, J. Bond, C. Staudhammer, and C. Bartel. 2009. “Hurricane debris and damage assessment for Florida urban forests.” Arboriculture Urban For. 35 (2): 100–106. https://doi.org/10.48044/jauf.2009.018.
FEMA. 2009. Hurricane Ike in Texas and Louisiana: Mitigation Assessment Team report, building performance observations, recommendations, and technical guidance. FEMA P-757. Washington, DC: FEMA.
FEMA. 2012. HAZUS–MH 2.1 Hurricane model technical manual. Washington, DC: FEMA.
FEMA. 2019. FEMA public assistance funded projects detail—Open government initiative. Washington, DC: FEMA.
Fereshtehnejad, E., I. Gidaris, N. Rosenheim, T. Tomiczek, J. E. Padgett, D. T. Cox, S. Van Zandt, and W. Gillis Peacock. 2021. “Probabilistic risk assessment of coupled natural-physical-social systems: Cascading impact of hurricane-induced damages to civil infrastructure in Galveston, Texas.” Nat. Hazards Rev. 22 (3): 04021013. https://doi.org/10.1061/(ASCE)NH.1527-6996.0000459.
Galveston Central Appraisal District. 2020. “2020 Galveston CAD Roll.” Data Set. Accessed September 1, 2020. http://www.galvestoncad.org/index.php/Appraisal_Exports.
Gelfand, A. E., and E. M. Schliep. 2016. “Spatial statistics and Gaussian processes: A beautiful marriage.” Spatial Stat. 18 (Nov): 86–104. https://doi.org/10.1016/j.spasta.2016.03.006.
GeoDa. 2018. “Applications of spatial weights.” Accessed February 1, 2022. https://geodacenter.github.io/workbook/4d_weights_applications/lab4d.html.
Gonzalez Duenas, C., C. Bernier, and J. Padgett. 2019. “Probabilistic assessment of bridges subjected to waterborne debris.” In Proc., Coastal Structures Conf., 356–365. Karlsruhe, Germany: Bundesanstalt für Wasserbau. https://doi.org/10.18451/978-3-939230-64-9_036.
González-Dueñas, C., C. Bernier, and J. E. Padgett. 2022. “A data-driven approach to hurricane debris modeling.” In Proc., IMAC-XXXVIII Conf. Bethel, CT: Society for Experimental Mechanics.
Green, D., D. Yu, I. Pattison, R. Wilby, L. Bosher, R. Patel, P. Thompson, K. Trowell, J. Draycon, and M. Halse. 2017. “City-scale accessibility of emergency responders operating during flood events.” Nat. Hazards Earth Syst. Sci. 17 (1): 1–16. https://doi.org/10.5194/nhess-17-1-2017.
Guo, S. 2021. “Implement a Gaussian process from scratch.” Accessed July 1, 2022. https://towardsdatascience.com/implement-a-gaussian-process-from-scratch-2a074a470bce.
H-GAC (Houston-Galveston Area Council). 2011. Regional storm debris management assessment. Houston: H-GAC.
H-GAC (Houston-Galveston Area Council). 2018. “LiDAR building footprints 2018.” Accessed November 1, 2020. http://www.h-gac.com/gis-applications-and-data/datasets.aspx.
H-GAC (Houston-Galveston Area Council). 2022. “Houston-Galveston Area Council (H-GAC).” Accessed May 1, 2019. https://www.h-gac.com/Home.
Hoffer, J. G., A. B. Ofner, F. M. Rohrhofer, M. Lovrić, R. Kern, S. Lindstaedt, and B. C. Geiger. 2022. “Theory-inspired machine learning—Towards a synergy between knowledge and data.” Weld. World 66 (7): 1291–1304. https://doi.org/10.1007/s40194-022-01270-z.
Jia, B., X. C. Jianzhong Zhou, Z. He, and H. Qin. 2019. “Deriving operating rules of hydropower reservoirs using Gaussian process regression.” IEEE Access 7 (Oct): 158170–158182. https://doi.org/10.1109/ACCESS.2019.2948760.
Kameshwar, S., H. Park, D. T. Cox, and A. R. Barbosa. 2021. “Effect of disaster debris, floodwater pooling duration, and bridge damage on immediate post-tsunami connectivity.” Int. J. Disaster Risk Reduct. 56 (Feb): 102119. https://doi.org/10.1016/j.ijdrr.2021.102119.
Luther, L. G., and Science Resources and Industry Division. 2006. Disaster debris removal after Hurricane Katrina: Status and associated issues. Washington, DC: Congressional Research Service, Library of Congress.
Marchesini, G., H. Beraud, and B. Barroca. 2021. “Quantification of disaster waste: Review of the available methods.” Int. J. Disaster Risk Reduct. 53 (Feb): 101996. https://doi.org/10.1016/j.ijdrr.2020.101996.
Matthews, A. G., M. Van Der Wilk, T. Nickson, K. Fujii, A. Boukouvalas, P. León-Villagrá, Z. Ghahramani, and J. Hensman. 2017. “GPflow: A Gaussian process library using tensorflow.” J. Mach. Learn. Res. 18 (40): 1–6.
Mauti, G., T. Takabatake, J. Stolle, I. Nistor, N. Goseberg, and A. Mohammadian. 2020. “Experimental investigation of loading due to debris dams on structures.” J. Hydraul. Eng. 146 (5): 04020029. https://doi.org/10.1061/(ASCE)HY.1943-7900.0001731.
Molina, R., C. Gonzalez, and J. Padgett. 2019. Undergraduate Research Experience (REU), NHERI 2019: A data processing framework for the advancement of hurricane debris modeling. Seattle: DesignSafe-CI. https://doi.org/10.17603/ds2-tzhh-7w14 v1.
NOAA (National Oceanic and Atmospheric Administration). 2007. “Galveston, Texas, coastal digital elevation model.” Accessed February 1, 2022. https://www.ncei.noaa.gov/metadata/geoportal/rest/metadata/item/gov.noaa.ngdc.mgg.dem:403/html#.
NOAA (National Oceanic and Atmospheric Administration). 2018. “2018 TPWD Lidar: Coastal Texas.” Accessed February 1, 2022. https://coast.noaa.gov/dataviewer/#/lidar/search/.
NOAA (National Oceanic and Atmospheric Administration). 2022. “National shoreline vector data.” Accessed February 1, 2022. https://www.ngs.noaa.gov/NSDE/.
Paananen, T., J. Piironen, M. Riis Andersen, and A. Vehtari. 2020. “Variable selection for Gaussian processes via sensitivity analysis of the posterior predictive distribution.” In Proc., AISTATS 2019—22nd Int. Conf. on Artificial Intelligence and Statistics, 1743–1752. Maastricht, The Netherlands: ML Research Press.
Park, H., and D. T. Cox. 2019. “Effects of advection on predicting construction debris for vulnerability assessment under multi-hazard earthquake and tsunami.” Coastal Eng. 153 (Sep): 103541. https://doi.org/10.1016/j.coastaleng.2019.103541.
Park, H., D. T. Cox, P. J. Lynett, D. M. Wiebe, and S. Shin. 2013. “Tsunami inundation modeling in constructed environments: A physical and numerical comparison of free-surface elevation, velocity, and momentum flux.” Coastal Eng. 79 (Sep): 9–21. https://doi.org/10.1016/j.coastaleng.2013.04.002.
Peek, L., J. Tobin, R. M. Adams, H. Wu, and M. Clay Mathews. 2020. “A framework for convergence research in the hazards and disaster field: The natural hazards engineering research infrastructure CONVERGE facility.” Front. Built Environ. 6 (Jul): 110.
Powell, M. D., S. H. Houston, L. R. Amat, and N. Morisseau-Leroy. 1998. “The HRD real-time hurricane wind analysis system.” J. Wind Eng. Ind. Aerodyn. 77 (Sep): 53–64. https://doi.org/10.1016/S0167-6105(98)00131-7.
Rasmussen, C. E., and C. K. Williams. 2006. Gaussian processes for machine learning. Cambridge, MA: MIT Press.
Rathje, E. M., et al. 2017. “DesignSafe: New cyberinfrastructure for natural hazards engineering.” Nat. Hazards Rev. 18 (3): 1–7. https://doi.org/10.1061/(ASCE)NH.1527-6996.0000246.
Reible, D. D., C. N. Haas, J. H. Pardue, and W. J. Walsh. 2006. “Toxic and contaminant concerns generated by Hurricane Katrina.” J. Environ. Eng. 132 (6): 565–566. https://doi.org/10.1061/(ASCE)0733-9372(2006)132:6(565).
Santi, P. M., K. Hewitt, D. F. VanDine, and E. Barillas Cruz. 2011. “Debris-flow impact, vulnerability, and response.” Nat. Hazard. 56 (1): 371–402. https://doi.org/10.1007/s11069-010-9576-8.
Song, J., R. De Risi, and K. Goda. 2017. “Influence of flow velocity on tsunami loss estimation.” Geosciences 7 (4): 114. https://doi.org/10.3390/geosciences7040114.
SSPEED Center. 2022. “Severe storm prediction, education, & evacuation from disasters center.” Accessed July 1, 2022. https://www.sspeed.rice.edu/publications.
Stearns, M., and J. E. Padgett. 2012. “Impact of 2008 Hurricane Ike on bridge infrastructure in the Houston/Galveston region.” J. Perform. Constr. Facil. 26 (4): 441–452. https://doi.org/10.1061/(ASCE)CF.1943-5509.0000213.
Stolle, J., N. Goseberg, I. Nistor, and E. Petriu. 2018. “Probabilistic investigation and risk assessment of debris transport in extreme hydrodynamic conditions.” J. Waterw. Port Coastal Ocean Eng. 144 (1): 04017039. https://doi.org/10.1061/(ASCE)WW.1943-5460.0000428.
Stolle, J., I. Nistor, N. Goseberg, and E. Petriu. 2020. “Multiple debris impact loads in extreme hydrodynamic conditions.” J. Waterw. Port Coastal Ocean Eng. 146 (2): 04019038. https://doi.org/10.1061/(ASCE)WW.1943-5460.0000546.
Tetra Tech. 2022. “About.” Accessed May 1, 2019. https://www.tetratech.com/en/about.
Thompson, B. K., F. J. Escobedo, C. L. Staudhammer, C. J. Matyas, and Y. Qiu. 2011. “Modeling hurricane-caused urban forest debris in Houston, Texas.” Landscape Urban Plann. 101 (3): 286–297. https://doi.org/10.1016/j.landurbplan.2011.02.034.
Tomiczek, T., A. Kennedy, and S. Rogers. 2014. “Collapse limit state fragilities of wood-framed residences from storm surge and waves during Hurricane Ike.” J. Waterw. Port Coastal Ocean Eng. 140 (1): 43–55. https://doi.org/10.1061/(ASCE)WW.1943-5460.0000212.
TxDOT (Texas DOT). 2022. “TxDOT roadway inventory.” Accessed February 1, 2022. https://gis-txdot.opendata.arcgis.com/datasets/TXDOT::txdot-roadway-inventory/explore?location=31.057868%2C-100.081515%2C6.50.
Umpierre, D., and G. Margoles. 2005. “Broward county’s web-based hurricane debris estimation tool (HurDET).” In Proc., 2005 ESRI Int. User Conf. Redlands, CA: ESRI.
USACE. 2017. “Disaster impact models.” Accessed June 1, 2022. http://www.usace.army.mil/Missions/Emergency-Operations/Disaster-Impact-Models/.
US Census Bureau. 2009. “American community survey 5-year estimates: Population (Table DP05).” Accessed February 1, 2022. https://data.census.gov/cedsci/table?q=DP05&g=0100000US&y=2009&tid=ACSDP5Y2009.DP05&hidePreview=true.
US Census Bureau. 2019. “American community survey 5-year estimates: Population (Table DP05).” Accessed February 1, 2022. https://data.census.gov/cedsci/table?q=DP05&g=0100000US&y=2019&tid=ACSDP5Y2019.DP05&hidePreview=true.
USEPA. 2008. Planning for natural disaster debris. Washington, DC: USEPA.
US Geological Service. 2008. “National land cover dataset 2008.” Accessed February 1, 2022. https://www.mrlc.gov/data.
US Geological Service. 2020. “National land cover dataset 2020.” Accessed February 1, 2022. https://www.mrlc.gov/data.
West, A. J., C. W. Lin, T. C. Lin, R. G. Hilton, S. H. Liu, C. T. Chang, K. C. Lin, A. Galy, R. B. Sparkes, and N. Hovius. 2011. “Mobilization and transport of coarse woody debris to the oceans triggered by an extreme tropical storm.” Limnol. Oceanogr. 56 (1): 77–85. https://doi.org/10.4319/lo.2011.56.1.0077.
Zhu, C., R. H. Byrd, P. Lu, and J. Nocedal. 1997. “Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization.” ACM Trans. Math. Software 23 (4): 550–560. https://doi.org/10.1145/279232.279236.
Information & Authors
Information
Published In
Natural Hazards Review
Volume 24 • Issue 2 • May 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Jul 18, 2022
Accepted: Jan 6, 2023
Published online: Mar 7, 2023
Published in print: May 1, 2023
Discussion open until: Aug 7, 2023
ASCE Technical Topics:
- Business management
- Computing in civil engineering
- Databases
- Debris
- Disaster risk management
- Disasters and hazards
- Engineering fundamentals
- Environmental engineering
- Errors (statistics)
- Gaussian process
- Human and behavioral factors
- Hurricanes, typhoons, and cyclones
- Information Technology (IT)
- Mathematics
- Natural disasters
- Pollutants
- Practice and Profession
- Probability
- Public administration
- Public health and safety
- Solid wastes
- Statistics
- Stochastic processes
- Wastes
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.