Code, imagery, and annotations for training a deep learning model to detect wildlife in aerial imagery

These data were collected to support the development of detection and classification algorithms to support Bureau of Ocean Energy Management (BOEM) studies and assessments associated with offshore wind energy production. There are 3 child zip files included in this data release. 01_Codebase.zip contains a codebase for using deep learning to filter images based on the probability of any bird occurrence. It includes instructions and files necessary for training, validating, and testing a machine learning detection algorithm. 02_Imagery.zip contains imagery that were collected using a Partenavia P68 fixed-wing airplane using a PhaseOne iXU-R 180 forward motion compensating 80-megapixel digital frame camera with...

Tags: Cape Cod, Information Sciences, Lake Michigan, USGS Science Data Catalog (SDC), Wildlife Biology, All tags... biota, birds, datasets, deep learning, oceans, remote sensing, wildlife, Fewer tags

SAS Code: Estimating Sagittaria mortality and growth from a pond study

This code may be used to estimate the effects of study treatments on mortality among Sagittaria plants raised from small tubers, and growth among Sagittaria plants raised from seeds and small and large tubers. Input data and information about those data may be obtained at https://doi.org/10.5066/F7Q52NW4.

SAS Code: Calculating binomial regression models that analyze the mortality of zebra mussels and the electrical waveform (AC or PDC), temperature, and exposure duration

Introduction The code includes separate logistic regression models for the positive control, negative control, and exposed conditions. The proportion of mortalities (number of dead zebra mussels compared to the total number of zebra mussels in the sample) in the containment bags were modeled with a binomial distribution and a logit link function. A scale parameter was added to the model using the random_residual_statement. Required data includes: test temperature voltage waveform (AC or PDC) mean voltag voltage gradient repetition number exposure duration treatment group total number of animals in the replicate number of mortalities in the replicate Outputs include: Means were calculated for: the percent dead, the...

Multi-species, multi-country analysis reveals North Americans are willing to pay for transborder migratory species conservation, data

Migratory species often provide ecosystem service benefits to people in one country while receiving habitat support in other countries. The multinational cooperation necessary to ensure continued provisioning of these benefits by migrational processes may be informed by understanding the benefits that people in different countries derive from migratory wildlife. We conducted stated preferences surveys to estimate the willingness of respondents from Canada, the U.S., and México to invest in conservation for two migratory species, the northern pintail duck (Anas acuta) and the Mexican free-tailed bat (Tadarida brasiliensis mexicana). These data include characteristics of were conservation payments might occur, of...

Categories: Data, Data Release - In Progress; Types: Map Service, OGC WFS Layer, OGC WMS Layer, OGC WMS Service; Tags: Canada, Ecology, Information Science, Mexican free-tailed bats, Mexico, All tags... North America, United States, Wildlife Biology, biota, contingent value, migratory species, northern pintail ducks, transboundary conservation, willingness to pay, Fewer tags

R Code: Calculating Partial Least Squares Regression, Reduced Subset Regression Models, and Structural Equation Models associated with the analyses of threats to the eastern migratory population of monarch butterflies

The code includes: MonarchThreatsCode.R, which provides all code used in the analysis. Required data includes: FullThreatsData.csv and component_loadings.csv While the code demonstrates how to interpolate the missing data, the FullThreatsData.csv has all missing values filled in. Similarly, the partial least squares demonstrates how the PLS was conducted, but the component_loadings.csv file contains the actual loadings presented in the paper. Outputs include: Partial least squares model results, plots of the partial least squares loadings, exploratory regression analysis, plotting of the parameter estimates from the best model, confounding analysis, structural equation modeling, and other plotting functions depicting...

R Code: Population Objectives Regional Planning Tool for Grassland Birds

Description This software application was created to allow resource managers to coordinate grassland bird management at the regional scale to meet range-wide conservation targets. The application provides a user-interface for generating scenarios of future regional population trends. This application is based on a previously developed Microsoft Excel spreadsheet-based tool for Bobolink conservation planning developed by Herkert and Renfrew. This iteration builds a new R-based (shiny) interface, adds additional species, scenarios, and interactive plots. Shiny App - Eastern Meadowlark and Bobolink Technical Working Group population objectives This data exploration tool is intended to allow resource managers to coordinate...

ArcMap Tool: BatchKernelDensityTool

Batch Kernel Density Tool Author: Timothy Fox, Upper Midwest Environmental Sciences Center, 2630 Fanta Reed Road, La Crosse, Wisconsin 54603 Platform developed: ArcMap 10.5 Addin The Batch Kernel Density Too is an ArcGIS ArcMap add-in developed at UMESC. When using this tool, a user can perform a magnitude-per-unit area analysis using point or polyline input data across multiple search radii (Figure 1). Files -FoxBatchKernelDensityTool.esriAddInn this is the compiled ArcGIS AddIn file that can be added ArcGIS 10.5 Installation: To install this tool: within a session of ArcMap 10.5, open the Add-in Manager dialog click the Options tab add the folder location to where you locally download the file FoxBatchKernelDensityTool.esriAddIn...

R Code: Effects of leg flags on nest survival of Arctic-breeding shorebirds

These R scripts prepare the dataset and run the model to evaluate effects of leg flags on nest survival of four species of shorebirds. Flags_Script1_subset_data.r: Subset the dataset and restructure as needed to run the model. Flags_Script2_run_model.r: Run the model in JAGS. The scripts were developed April 2018 in R v. 3.4.0 Patched. The original dataset is publicly available at: https://arcticdata.io/catalog/#view/doi:10.18739/A2CD5M

fishStan

fishStan is an R package (R Core Team 2020) providing a collection of hierarchical Bayesian models written in the Stan language as called through RStan (Stan Development Team 2020). The package is a USGS software software release. Currently, the project includes multiple models including Growth models A hierarchical von Bertalanffy growth model, A hierarchical von Bertalanffy growth model without $t0$, A hierarchical Gompertz growth model A hierarchical Logistic INdividual Growth (LING) model A hierarchical Galluci and Quinn growth model A hierarchical linear regression A hierarchical logistic regression model that includes both binomial and Bernoulli input options A catch curve model All hierarchical models...

R Code: Mapped and Attributed Data Random Area and Point (MADRAP) Generator

## Description Generate random points and sample areas from polygons in a shapefile with sampling constraints for each map class. Can be used to generate sample areas for accuracy assessment in cartography. ## Pre-requisites Software [R](https://cran.r-project.org/bin/windows/base/old/3.5.3/), [RStudio](https://rstudio.com), and [Rtools](https://cran.r-project.org/bin/windows/Rtools/). ## Installation Install MADRAP as a package using Rtools. Download the repository and unzip `madrap-master.zip`. Open RStudio and... Click File > Open Project > madrap-master/madrap/MADRAP.Rproj > Open Click the build tab in the top right then click "Install and Restart". You may run into installation issues if you do not...

SQL Code: Dwell time, concurrent tag contacts, and receiver bypass analysis of FishTracks telemetry data

Executing the Dwell Time analysis condenses receiver/tag records into readable records of fish movement and receiver effectiveness. Fish movement is described by a temporal sequence of receiver/tag events (durations), where a tag is visible to a specific receiver or collection of receivers. The number and frequency of contacts within a receiver/tag event are summarized by the analysis. A receiver/tag event ends, and a new receiver/tag event begins when the tag is visible to a different set of receivers. Additionally, the Dwell Time analysis identifies which receivers have overlapping detection ranges and identify which receivers are potentially being bypassed by tagged fish. The SQL code included here is run...

Categories: Data Release - In Progress

R Code: North American Landbird Population Size Estimation with Uncertainty

The code to generate Population Size estimates from BBS data according to the approach described in the manuscript is provided in two separate R script files: 1_AssembleBBSdatabySpecies.R - Downloads (if option selected) and formats BBS datafiles used as input in the second file. The BBS Raw data is available at ftp://ftpext.usgs.gov/pub/er/md/laurel/BBS/DataFiles/ 2_CalculatePIF_PSest_withCI.R - Calculates and outputs population size estimates with confidence intervals

R code: R_nest_predetation

These R scripts prepare the dataset and run calculations and analyses on patterns in daily predation rate (DPR) of shorebird nests, as part of a comment on a recent paper (V. Kubelka, M. Šálek, P. Tomkovich, Z. Végvári, R. P. Freckleton, T. Székely.

Python Code: Examples of Data Retrieval and Graphing Using the LTRM Fish Catch GeoJSON Data Service

Variables within the URL*: fsn: denotes field station number begin: the beginning of a date range end: the end of a date range species: denotes LTRM species code lmin: minimum fish length lmax: maximum fish length The URL request returns point features with the following attribute data: barcode, row, gear_code, start_date, finish_date, species_code, length, and catch*. *LTRM fisheries data metadata including relevant code values can be found at: https://www.umesc.usgs.gov/cgi-bin/ltrmp/fish/fish_meta.pl GeoJSON record returned using the example URL shown above: {"type":"FeatureCollection","features":[{"type":"Feature","geometry":{"type":"Point","coordinates":[-91.2409970013,43.7770371996]},"properties":{"barcode":12008087,"row":14,"gear_code":"D","start_date":"20151008","finish_d...

ArcMap Tool: Symbol Tweaker Tool

File name: FoxSymbolTweaker_10_5.esriAddIn this is the compiled ArcGIS AddIn file that can be added ArcGIS 10.5 Overview Symbol Tweaker is an ArcGIS ArcMap add-in tool developed at the UMESC. When using this tool, a user can: Adjust RGB or HSV parameters of selected symbols from feature and raster data layers Create unique color ramps for feature and raster data layers Copy fore, back, and outline colors interchangeably Create equal interval classifications beyond the limitations imposed by ArcMap Remove classes from unique values renderers that do not exist in the underlying data Find the absolute minimum and maximum values from a collection of raster layers En masse, copy a chosen renderer to a group of selected...

R code: Simulation-based power analysis code

This script simulates data for population surveys (e.g., the density of individuals per some unit of area) and fits a model to the simulated data to determine whether the population trend can be detected. The script tests one replicate of one scenario. This example takes lt 1 sec to run on a modern laptop computer. For each scenario, the process would be repeated over a series of replicates (e.g., 100 or 500), and then the proportion of replicates in which the trend was detected would be tallied. That proportion indicates the statistical power. Additional scenarios are then tested by changing the input parameters provided below.

ArcMap Tool: Composite Raster and Divergence Tool

Files -FoxCompositeRasterAndDivergenceTool_10_5.esriAddInn this is the compiled ArcGIS AddIn file that can be added ArcGIS 10.5 Overview The Composite Raster and Divergence Tool is an ArcGIS ArcMap add-in developed at UMESC. When using this tool, a user can: create a date prioritized composite raster from a collection of raster layers create a lookup raster for the composite raster that identifies which input layers were used to create the composite raster create a divergence raster where pixel values represent the divergence from a user specified value Installation: To install this tool: within a session of ArcMap 10.5, open the Add-in Manager dialog click the Options tab add the folder location to where you...