Data and supplementary material used for Soundscapes to Landscapes soundscape mapping

This repository contains supporting data products to enable the soundscape mapping outlined in the associated publication (DOI forthcoming). Data were used to extract acoustic recording location environmental data for training random forest models to spatially predict 2021 ecoacoustic metrics. The accompanying code will be linked to the GitHub repository. Files include:

Data:

• clustered_fold_k10.rsd: indices of the model data used if geoCV approach
• extracted_predictors_vif3.csv: site-specific predictor values extracted from predictors_annual_20230223.tif
• final_predictors_vif3.csv: a two column table summarizing the VIF selected predictors
• final_sites_2017-2021.csv: the list of 1,195 potential sites
• predictor_sprmn_corr.csv: correlation matrix for predictors in model data
• predictors_annual_20230223.tif: all predictors 
• response_df_200623.csv: site level ecoacoustic metrics

Results:

• map_correlations.tar: pairwise response map correlations
• pdps.tar: partial dependence plot data
• performance.tar: model performance summaries
• predictions_maps.tar: final median and IQR model prediction surfaces
• variable_importance.tar: summaries for variable importance analyses

Contact Colin Quinn at cq73@nau.edu for questions related to this repository or the underlying work. Original wav recordings are expected to be made publicly available on the NASA DAACs in the near future.