GBM models, constructed from historical data

• Format: Dataset
• Language: unknown
• Published: Arctic Data Center 2015
• Subjects: EARTH SCIENCE > BIOSPHERE > ECOLOGICAL DYNAMICS > FIRE ECOLOGY > FIRE MODELS; EARTH SCIENCE > AGRICULTURE > FOREST SCIENCE > FOREST FIRE SCIENCE; EARTH SCIENCE > BIOSPHERE > ECOLOGICAL DYNAMICS > FIRE ECOLOGY > FIRE OCCURRENCE; EARTH SCIENCE > BIOSPHERE > TERRESTRIAL ECOSYSTEMS > ALPINE/TUNDRA; OTHER; GRID; 1 KILOMETER TO 10 KILOMETERS; DECADAL; Tundra
• Online Access: https://search.dataone.org/view/urn:uuid:721fba12-6ce0-49df-977f-b5d8437b16f5

Datasets used in: Young, A.M., Higuera, P.E., Duffy, P.A., and F.S. Hu. Climatic thresholds shape northern high-latitude fire regimes and imply vulnerability to future climate change. In Review at Ecography as of 10/2015. ---------------------------------------------------------------------- ----------------------- Description ---------------------------------- ---------------------------------------------------------------------- These data are the raw results/output from the boosted regression tree modeling conducted in Young et al. (In Review). Results for each of the three models (AK, BOREAL, and TUNDRA) are located separate folders. Each folder contains 100 RData files which contain the output/results from running the 'gbm()' function in R v3.2.0 100 times. Each of the 100 gbms was built using a different subsample of available data. The 'gbm()' function is available in the 'gbm' package in R (https://cran.r-project.org/). Details regarding meta-parameter selection and model building can be found in Young et al. (In Review). ---------------------------------------------------------------------- ------------------------ File Naming --------------------------------- ---------------------------------------------------------------------- 'MODEL_gbm_xx.RData' 'MODEL_' - Three different sets of GBM models: 'AK', 'BOREAL', and 'TUNDRA' 'gbm' - Generalized boosting model '_xx' - Model number (1-100) '.RData' - File Extension