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

Williams, Caroline J.; Davidson, Rachel A.; Nozick, Linda K.; Trainor, Joseph E.; Millea, Meghan; Kruse, Jamie L.

doi:https://doi.org/10.5194/nhess-22-1055-2022

Articles | Volume 22, issue 3

https://doi.org/10.5194/nhess-22-1055-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/nhess-22-1055-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 22, issue 3

Research article

|

30 Mar 2022

Research article |

| 30 Mar 2022

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

Caroline J. Williams, Rachel A. Davidson, Linda K. Nozick, Joseph E. Trainor, Meghan Millea, and Jamie L. Kruse

Supplement

https://doi.org/10.5194/nhess-22-1055-2022-supplement

Data sets

Regional county-level housing inventory predictions and the effects on hurricane risk using long-short term memory (LSTM) methods and applied to the southeastern United States (US) C. J. Williams and R. A. Davidson https://doi.org/10.17603/ds2-vd28-pe79

Download

Article (9689 KB)
Full-text XML

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 1 percentage point different than the observed number, which are predictive errors acceptable for most practical purposes. The housing unit projections can help quantify changes in future expected hurricane impacts.