Impact of model choice in predicting urban forest storm damage when data is uncertain
Bibliographic Data
| ID | 21469047 |
|---|---|
| Authors | Casey Lambert (University of Alabama), Shawn Landry (0000-0003-3281-2612), Michael G Andreu (0000-0002-7819-9430, University of Florida), Andrew K Koeser (0000-0003-0082-9129, University of Florida), Andrew Koeser, Gregory Starr (0000-0002-7918-242X, University of Alabama), Christina L Staudhammer (0000-0003-1887-418X, University of Alabama, corresponding author), Christina Staudhammer |
| Year | 2022 |
| Volume | 226 |
| Pages | 104467 |
| Publication date | 2022-10-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Landscape and Urban Planning (JOURNAL) |
| Journal identifiers | ISSN: 0169-2046 • E-ISSN: 1872-6062 |
| Publisher | Elsevier BV (PUBLISHER) |
| DOI | 10.1016/j.landurbplan.2022.104467 |
| OpenAlex | W4280597535 |
| Language | EN |
| Citations received | 1 |
| References cited | 43 |
Research that illuminates causes of urban forest storm damage is valuable for planning and management. However, logistical and safety concerns often delay post-storm surveys in urban areas; thus, surveys may include observations with unverified sources of damage. While this uncertainty is often ignored, it can make up a high proportion of the number of damaged trees. The goal of this research was to improve understanding of techniques for modeling storm damage in urban forests. Using urban forest storm damage inventories collected in Florida, post-Hurricane Irma (2017), we tested how different imputation methods, modeling procedures, and damage frequency levels could impact overall model results. We utilized machine learning algorithms Random Forest (RF) and k-Nearest Neighbors (KNN), and generalized linear models (GLM). We found that GLM and RF models gave overall unbiased predictions of damage across all methods and rarity levels, while KNN consistently under-predicted damage. Damage frequency influenced some measures of performance but did not impact variable significance. Imputation methods all identified consistent variables of most significance within each model procedure; however, there was variation among variables ranked moderately important. While both GLM and RF models identified plot tree basal area as highly significant damage predictors, they otherwise disagreed on individual variable importance. These findings suggest that while explanatory models for urban forest storm damage can be achieved by examining linear relationships, more complex relationships such as the ones identified by RF models can have equal explanatory power with different subsets of predictor variables
Basal area · Decision tree · Econometrics · Explanatory power · Generalized linear model · Geography · Machine learning · Meteorology · Random forest · Statistics · Storm · Computer Science · Environmental Science · Forest ecology and management · Mathematics · Remote Sensing and LiDAR Applications · Tree Root and Stability Studies · Forestry
Response Rates and Responsiveness for Surveys, Standards, and the Journal
Permutation importance
A systematic quantitative review of urban tree benefits, costs, and assessment methods across cities in different climatic zones
An Application of Hierarchical Kappa-type Statistics in the Assessment of Majority Agreement among Multiple Observers
Forest biodiversity, ecosystem functioning and the provision of ecosystem services
Random Forests
Interrater reliability
Logistic Regression in Rare Events Data
| Citations per year | 0.25 |
|---|---|
| Citation span | 2022 - 2022 (1) |
| Highly cited | No |