Preprints
https://doi.org/10.5194/nhess-2021-335
https://doi.org/10.5194/nhess-2021-335

  10 Nov 2021

10 Nov 2021

Review status: this preprint is currently under review for the journal NHESS.

Regional county-level housing inventory predictions and the effects on hurricane risk

Caroline J. Williams1, Rachel A. Davidson1, Linda K. Nozick2, Joseph E. Trainor3, Meghan Millea4, and Jamie L. Kruse4 Caroline J. Williams et al.
  • 1Department of Civil and Environmental Engineering, University of Delaware, Newark, DE, 19716, USA
  • 2School of Civil and Environmental Engineering, Cornell University, Ithaca, New York, 14850, USA
  • 3Biden School of Public Policy and Administration, University of Delaware, Newark, DE, 19716, USA
  • 4Department of Economics, East Carolina University, Greenville, North Carolina, 27858, USA

Abstract. Regional hurricane risk is often assessed assuming a static housing inventory, yet a region’s housing inventory changes continually. Failing to include changes in the built environment in hurricane risk modeling can substantially underestimate expected losses. This study uses publicly available data and a long short-term memory (LSTM) neural network model to forecast the annual number of housing units for each of 1,000 individual counties in the southeastern United States over the next 20 years. When evaluated using testing data, the estimated number of housing units was almost always (97.3 % of the time), no more than one percentage point different than the observed number, predictive errors that are acceptable for most practical purposes. Comparisons suggest the LSTM outperforms ARIMA and simpler linear trend models. The housing unit projections can help facilitate a quantification of changes in future expected losses and other impacts caused by hurricanes. For example, this study finds that if a hurricane with similar characteristics as Hurricane Harvey were to impact southeast Texas in 20 years, the residential property and flood losses would be nearly US$4 billion (38 %) greater due to the expected increase of 1.3 million new housing units (41 %) in the region.

Caroline J. Williams et al.

Status: open (until 22 Dec 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Caroline J. Williams et al.

Caroline J. Williams et al.

Viewed

Total article views: 139 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
109 27 3 139 17 1 2
  • HTML: 109
  • PDF: 27
  • XML: 3
  • Total: 139
  • Supplement: 17
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 10 Nov 2021)
Cumulative views and downloads (calculated since 10 Nov 2021)

Viewed (geographical distribution)

Total article views: 136 (including HTML, PDF, and XML) Thereof 136 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 04 Dec 2021
Download
Short summary
A neural network model based on publicly available data was developed to forecast the number of housing units for each of 1000 counties in the southeastern United States in each of the next 20 years. The estimated number of housing units is almost always (97 % of the time), less than one percentage point different than the observed number, predictive errors acceptable for most practical purposes. The housing unit projections can help quantify changes in future expected hurricane impacts.
Altmetrics