National-scale acoustic monitoring of avian biodiversity and migrationBick et al 2024 *************** Abstract:Birds migrate over large spatial scales and with complex dynamics which play out over extended time periods, making monitoring of phenology challenging with traditional biodiversity survey approaches. In this study, over a complete spring season, we collected 37,429 hours of audio from 28 networked sensors in forests across the latitudinal extent of Norway to demonstrate how acoustic monitoring can transform avian phenology monitoring. We used machine learning to automatically detect and identify bird vocalizations, and with expert validation found we were able to classify 55 species (14 full migrants) with over 80% precision. We compared audio data to existing avian biodiversity datasets and demonstrated that acoustic surveys could fill large data gaps and improve the temporal resolution at which metrics such as date of arrival for individual species could be estimated. Finally, we combined acoustic data with ecoclimatic variables from satellites and were able to map migratory waves of 10 species across the country at fine spatial resolutions (0.2 degrees). Our study demonstrates how acoustic monitoring can inexpensively and reliably complement existing national-scale biodiversity datasets, delivering high quality data which can support the design and implementation of effective policy and conservation measures. **************** Details:This repository contains 5 python notebooks, as well as all necessary data, for generating all Figures from "National-scale acoustic monitoring of avian biodiversity and phenology" by Bick et al 2024. Each notebook is independent and generates each component of its respective Figure: Figure_1.pynb - Generates Figure 1Figure_2.pynb - Generates Figure 2Figure_3.pynb - Generates Figure 3Figure_4.pynb - Generates Figure 4Generate_Weekly_Detections.ipynb - For re-generating aggregated weekly audio detections **************** Data is organized as such: /Data/Detections/: ---audio-export-proj_sound-of-norway-yr2complete.csv: Raw data regarding audio data uploaded from recording sites to the cloud. Used to calculate uptime of recorders. ---birdnet_lite_detections-proj_sound-of-norway-yr2complete-fixedSiteName.csv: Raw data of BirdNET-Lite detections from all sites, including species, model confidence, and locations. The exact GPS latitude and longitude of the locations have been randomized by -0.01 to 0.01 degrees to protect the exact survey points. ---/weekly/: Weekly aggregated audio detections for migratory species ---/BBS_Survey/: Contains raw Norwegian Breeding Bird survey data for three species in 2022. The exact GPS latitude and longitude of these survey points have been randomized by -0.01 to 0.01 degrees to protect the exact survey points. ---/eBird_Survey: Contains all eBird survey checklists in Norway for 2022, as well as sampling effort for each checklist. *** /Data/Covariates/:---/Altitude/: Contains the Norway National Detailed Elevation Model, available at Kartverket.no ---/Forest_Cover/: Contains a mask of forest land cover types from Copernicus 300m Land Cover data, available at https://doi.org/10.24381/cds.006f2c9a ---/Norwegian_Metereological_Institute/: Contains gridded daily min, max, mean temperature, as well as precipitation across Norway, available at https://zenodo.org/records/6965960. Also contains weekly vegetation indices for Norway from MODIS, available at https://doi.org/doi.org/10.5067/MODIS/MCD19A3CMG.06 ---/MODIS_NDVI/: Contains daily NDVI for Norway, available at https://doi.org/doi.org/10.5067/MODIS/MCD19A3CMG.06 *** /Data/Sites/:---clusters_latitudes_45km_box.csv: Contains centroid latitude of each cluster of recorders.---clusters_NDVI_45km_box: Contains coordinates of regional cluster bounds---norway-stanford-jm135gj5367-shapefile: Shapefile with bounds of Norway---order_of_sites.xlsx: Contains order of sites for plotting purposes---site_short_names.xlsx: Contains abbreviated site names for plotting---sites.csv: Contains coordinates and names of each recorder, exact GPS latitude and longitude of these points have been randomized by -0.01 to 0.01 degrees.---sites_weekly_covariates_zeroFill_NDVI.csv: contains weekly mean covariate data for each site *** /Data/Validation/:---tom_roger_annotations_yr1_yr2_50dets_combined.xlsx: Contains expert validation of BirdNET-lite detections for each species **************** Instructions:1. Using .yml file in /conda_environment, create python environment:- conda env create --name envname --file=environments.yml2. Open .ipynb files within environment3. In each notebook, change current working directory variable, "cwd", to the location of your "National_PAM_of_Biodiversity_Bick_et_al_2024" folder4. Run each .ipynb to generate each Figure, adjust hyperparameters at top of each notebook as needed.