Pipeline details
1. Data preparation
kedro run --pipeline data_preparation
Description
Reads field and audio data to standardize metadata using the pamDP standard. It outputs media and deployment formats, ensuring coherence between field sheets and collected audio files for later analysis and exchange.
Parameters
This pipeline requires no parameters. Adjustments to the field deployment sheet structure can be set using the Catalog entry field_deployments_sheet@pandas.
Nodes
Node name |
Description |
Inputs |
Outputs |
|---|---|---|---|
|
Retrieves media files from the specified audio root directory and links them with field deployment sheet data. |
|
|
|
Generates a summary of the media files (e.g., counts, durations, metadata). |
|
|
|
Converts the field deployments sheet and media summary into structured deployment data. |
|
|
2. Quality control
kedro run --pipeline quality_control
Description
Allows a quick data exploration to flag underperforming sensors and ensure data integrity for reliable ecological analysis. It summarizes survey effort, plotting sensor locations, and checking recording timelines.
Nodes
Node name |
Description |
Inputs |
Outputs |
|---|---|---|---|
|
Generates visualizations and summary data of sensor performance metrics based on media data. |
|
|
|
Creates a map or plot showing sensor deployment locations using summarized media and deployment data. |
|
|
|
Produces a plot summarizing survey effort (e.g., recording hours or deployment durations). |
|
|
|
Generates timelapse audio samples and corresponding spectrogram images for visual and acoustic analysis. |
|
|
Parameters
Group |
Name |
Description |
Default Value |
|---|---|---|---|
|
|
Figure height (in inches) |
|
|
|
Figure width (in inches) |
|
|
|
Size of the location markers |
|
|
|
Color of the location markers |
|
|
|
Size of the text annotations (if 0 or negative, no text is shown) |
|
|
|
Transparency level of the markers |
|
|
|
Figure height (in inches) |
|
|
|
Figure width (in inches) |
|
|
|
Number of data points per segment |
|
|
|
Number of overlapping points |
|
|
|
Frequency limits (Hz) |
|
|
|
Dynamic range in decibels |
|
|
|
Colormap options: ‘grey’, ‘viridis’, ‘plasma’, ‘inferno’, ‘cividis’ |
|
|
|
Length of each sample for timelapse (in seconds) |
|
|
|
Time interval between samples (e.g., ‘30min’) |
|
|
|
Specific date for timelapse (YYYY-MM-DD). If null, the date with the most data will be used. |
|
3. Species detection
Description
Automates species detection using a TensorFlow or BirdNET model. It filters observations based on target species, then saves customized audio segments for revision. All data follows pamDP standards.
kedro run --pipeline species_detection
Nodes
Node name |
Description |
Inputs |
Outputs |
|---|---|---|---|
|
Runs the species detection algorithm in parallel using media and deployment data to generate unfiltered species observations. |
|
|
|
Filters unfiltered observations based on target species, minimum number of observations, and segment size parameters. |
|
|
|
Creates time or frequency segments from observations and associated media based on segment size. |
|
|
|
Generates an audio folder dataset from created segments for downstream processing or manual validation. |
|
|
|
Produces manual annotation files from segment data for human validation or annotation tools. |
|
|
|
Creates summary plots visualizing total and temporal patterns of species observations relative to media data. |
|
|
|
Plots the number or distribution of observations per species to visualize detection results. |
|
|
Parameters
Group |
Name |
Description |
Default Value |
|---|---|---|---|
|
|
Number of cores used in parallelization. |
|
|
|
Minimum number of detections required for a species to be included in the observations format. |
|
|
|
Number of sample segments generated per species. |
|
|
|
Prefix for manual annotation files, formatted as |
|
4. Acoustic indices
kedro run --pipeline acoustic_indices
Description
Processes audio files to calculate various acoustic indices. These indices provide a quantitative overview of the soundscape, useful for a wide range of analyses.
Nodes
Node name |
Description |
Inputs |
Outputs |
|---|---|---|---|
|
Computes acoustic indices from media data based on provided parameters, generating partitioned datasets for further ecological or acoustic analysis. |
|
|
Parameters
Group |
Name |
Description |
Default Value |
|---|---|---|---|
|
|
Length of each segment for FFT during preprocessing. |
|
|
|
Number of points to overlap between FFT segments. |
|
|
|
Sampling rate for acoustic index analysis. |
|
|
|
Type of filter applied to the audio signal (e.g., bandpass). |
|
|
|
Frequency cutoff range for the filter in Hz. |
|
|
|
Filter order defining the steepness of the filter roll-off. |
|
|
— |
Acoustic Complexity Index (no additional parameters). |
— |
|
|
Minimum frequency (Hz) for index calculation. |
|
|
|
Maximum frequency (Hz) for index calculation. |
|
|
|
Frequency bin width (Hz) used in analysis. |
|
|
|
Diversity index type used (e.g., shannon). |
|
|
|
Threshold level (in dB) for inclusion in the index computation. |
|
|
|
Frequency range (Hz) for BI index computation. |
|
|
— |
Spectral entropy in the frequency domain (no parameters). |
— |
|
— |
Temporal entropy index (no parameters). |
— |
|
— |
Overall acoustic entropy combining temporal and spectral dimensions (no parameters). |
— |
|
|
Frequency range (Hz) for biophony band. |
|
|
|
Frequency range (Hz) for anthrophony band. |
|
|
|
Peak detection mode used (e.g., linear). |
|
|
|
Minimum amplitude threshold for peaks. |
|
|
|
Minimum frequency distance (Hz) between detected peaks. |
|
|
|
Slope values for spectral peak analysis (if applicable). |
|
|
|
Minimum prominence value for peak detection. |
|
|
— |
Root Mean Square energy index (no parameters). |
— |
|
|
Threshold level (in dB) for spectral cover index computation. |
|
|
|
Frequency range (Hz) for low-frequency band. |
|
|
|
Number of CPU cores used for parallel processing. |
|
5. Graphical soundscape
kedro run --pipeline graphical_soundscape
Description
Computes a representation of the most prominent spectro-temporal dynamics over a 24-hour window per each deployment.
Nodes
Node name |
Description |
Inputs |
Outputs |
|---|---|---|---|
|
Generates graphical representations of the soundscape using media data and visualization parameters, producing both data outputs and image plots for analysis. |
|
|
Parameters
Group |
Name |
Description |
Default Value |
|---|---|---|---|
|
|
Target sampling frequency used when processing audio data. |
|
|
|
Window size used to compute the spectrogram. |
|
|
|
Overlap between consecutive windows in the spectrogram computation. |
|
|
|
Dynamic range in decibels for spectrogram visualization. |
|
|
|
Minimum distance between detected peaks in the spectrogram. |
|
|
|
Absolute threshold (in dB) for peak detection. |
|
|
|
Number of CPU cores used for parallelization. |
|