Published November 30, 2021 | Version 1.0.0
Dataset Restricted

BirdScan Community Reference Dataset

  • 1. Swiss Ornithological Institute, Sempach, Switzerland
  • 2. Swiss Birdradar Solution AG, Winterthur, Switzerland
  • 3. Department of Evolutionary and Environmental Biology & Institute of Evolution, University of Haifa, Haifa, Israel
  • 4. School of Zoology, Faculty of Life Sciences, Tel Aviv University, Tel Aviv, Israel


This repository contains the reference dataset of labelled (or otherwise useful) echo samples acquired with a BirdScan MR1 radar. This dataset enables classification of the radar echoes acquired with a BirdScan MR1 into a number of biological groups of interests (as well as the removal of non-biological targets).

Files and their contents:

  • TrainingData.csv and TrainingData.rds files:
    These files contain the actual training dataset, with the labels and all radar-derived features. We use a .csv file as this is compatible cross-platform and programming languages. We also include an .rds file for the R users.
  • ReclassTable.csv:
    This file contains the table that is used to sort the original ‘labelHuman’ labels into the hierarchical label system, i.e., columns ‘labelHa1’ to ‘labelHa6’.
  • MR1_ML_Tool_Documentation_v1.2.pdf:
    This file contains a description of the features in the dataset, as well as the classification and wingbeat frequency estimation algorithms and parameter settings that are currently being used in the SBRS software that is delivered along with the BirdScan radar.
    This zip file contains a folder with the echo signature and north files associated to each of the samples in the TrainingData.csv (and .rds) file.
    Files in the folder follow a strict directory and filenaming structure, i.e., %Y_%m_%d\siteCode-echoID_sig.dat and %Y_%m_%d\siteCode-echoID_north.dat
    For example: 2015_09_07\MOL-echo324_0000001606_sig.dat and 2015_09_07\MOL-echo324_0000001606_north.dat.
  • license.txt:
    This file contains the license applying to the data.



The record is publicly accessible, but files are restricted to users with access.

Request access

If you would like to request access to these files, please fill out the form below.

You need to satisfy these conditions in order for this request to be accepted:

These data are the property of a consortium of university and private entities. While these data are not openly available, please get in touch if you are interested in using these data for non-commercial research purposes. Email contact:

You are currently not logged in. Do you have an account? Log in here