> For the complete documentation index, see [llms.txt](https://terradapt.gitbook.io/terradapt-cascadia-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://terradapt.gitbook.io/terradapt-cascadia-documentation/methods-and-validation/forest-structure/model-development.md).

# Model Development

We used the random forest classifier ([Breiman 2001](https://link.springer.com/article/10.1023/a:1010933404324)) implemented in Google Earth Engine (GEE) to predict tree height (m), tree diameter (cm), and canopy cover (%) from the [covariates](/terradapt-cascadia-documentation/methods-and-validation/forest-structure/covariates.md) at all [training data](/terradapt-cascadia-documentation/methods-and-validation/forest-structure/training-data.md) locations. We trained 10 replicate models in regression mode per variable in a k-fold approach ([Fushiki 2011](https://link.springer.com/article/10.1007/s11222-009-9153-8)) with a unique 'fold' of 1/10th of the data withheld for [validation](/terradapt-cascadia-documentation/methods-and-validation/forest-structure/model-validation.md). The final model was calculated as the average of the 10 replicates.