Open data for "Predicting dominant terrestrial biomes at a Global Scale: Assessments of machine learning algorithms, climate variables indexing, and extreme climate"

______________________________________________________<br> This page contains public-domain data required to reconstruct simulation results in the manuscript "Predicting dominant terrestrial biomes at a Global Scale: Assessments of machine learning algorithms, climate variables indexing, and extreme climate," submitted by the following author. Author: Hisashi SATO (JAMSTEC) <br> email : hsatoscb_(at)_gmail.com ______________________________________________________<br> 1. Folder "Code"<br> Detailed descriptions are available on the code. 1-1. MachineLearningComparison.R<br> Machine learning programs using random forest (RF), naive Bayes classifier (NV), and support vector machine (SVM) algorithms. 1-2. Analyse_MapSimilarity.R<br> Calculate coincidences of simulated potential natural vegetation (PNV) maps simulated by different models. 1-3. Visualize_VCE.R<br> Generating VCE (Visualize Climate Image) for training CNN models. 1-4. Visualize_Maps.R<br> Visualizing global PNV maps. 1-5. Visualize_ClimateHistgrams.R<br> Visualizing histograms of climate datasets. ______________________________________________________<br> 2. Folder "Input" 2-1. Unified_BIOCLIM_WorldClim.csv<br> Input data for the current climate.<br> This file contains the following variables.<br> lon Longitude at the center of the grid<br> lat Latitude at the center of the grid<br> bio1~19 Average climate indices from BIOCLIM (AveI)<br> CDD~WSDI Extreme climate indices (CEI)<br> c1~c16 Fraction of PNV from MODIS data<br> tavg01~tavg12 Monthly mean air temperature from January to December (Ave)<br> prec01~prec12 Monthly precipitation from January to December (Ave) 2-2. Unified_BIOCLIM_WorldClimFutureRCP85.csv<br> Input data for future climate (@RCP8.5)<br> Including variables are the same as Unified_BIOCLIM_WorldClim.csv 2-3. BIOCLIM_RefNo.csv<br> This CSV file contains the following information for each grid.<br> lat: Latitude at the center of the grid<br> lon: Longitude at the center of the grid<br> latNo: Latitude number corresponding to the image file name<br> lonNo: Longitude number corresponding to the image file name<br> lineNo: No use. Don't mind.<br> vegNo: Most dominant PNV based on the Unified_BIOCLIM_WorldClim.csv ______________________________________________________<br> 3. Folder "Output" 3-1. PNV_sim<br> 3-2. PNV_sim_RCP85.csv<br> Current and future PNV maps from various models. These files are the main output files from the code MachineLearningComparison.R. For PNV maps from CNN models (m4p1~6) were supplemented. Detailed methods to build CNN models, please refer to the following manuscript.<br> Sato, H. &amp; T. Ise (2022). "Predicting global terrestrial biomes with the LeNet convolutional neural network." Geoscientific Model Development 15(7): 3121-3132. Labels indicate combinations of machine-learning-algorithm and dataset for training the model. For example, In case of "m1p1", that column shows the simulation result of models trained with randomForest (RF) algorithm and Ave dataset.<br> m1: randomForest (RF)<br> m2: Support vector machine (SVM)<br> m3: Naive Bayes (NB)<br> m4: Convolutional Neural Network (CNN), which is NOT analysed in this code<br> p1: Ave<br> p2: Ave + CEI<br> p3: Ave + CEIpart<br> p4: AveI <br> p5: AveI + CEI<br> p6: AveI + CEIpart