Python tool for aircraft Doppler audio geolocation using historical ADS-B flight data (Source-available)
Python acoustic-geolocationads-baircraft-trackingairplaneaudio-forensicsdoppler-effectdoppler-shiftgeolocationosintsignal-processing
#!/usr/bin/env python3
"""Write a point-in-time catalog of real Eclipse Soundscapes scanner outcomes."""
import argparse
import collections
import csv
from datetime import datetime, timezone
import json
from pathlib import Path
def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument('--root', type=Path, required=True)
args = parser.parse_args()
selection = json.loads((args.root / 'selection.json').read_text())
review_path = args.root / 'manual-reviews.json'
reviews = json.loads(review_path.read_text()) if review_path.exists() else {}
fields = ['site', 'record_url', 'status', 'error', 'audio_path', 'source_filename_timestamp_utc',
'clip_duration_s', 'source_sha256', 'location_status', 'location_reference',
'location_uncertainty', 'publisher_clock_setting', 'clock_uncertainty', 'proposal_count', 'proposal_group_count',
'scanner_interpretation', 'visual_review', 'review_plot', 'alternate_review', 'alternate_plot']
rows = []
for source in selection['sites']:
site = source['site']
path = args.root / 'clips' / site / 'result.json'
result = json.loads(path.read_text()) if path.exists() else {'status': 'not_scanned'}
review = reviews.get(site, {})
truth = args.root / 'truth' / (site + '.csv')
clock_setting = result.get('publisher_clock_setting')
if truth.exists() and clock_setting is None:
with truth.open(encoding='utf-8-sig', newline='') as stream:
clock_setting = next(csv.DictReader(stream), {}).get('WAV Files Time & Date Settings')
rows.append({'site': site, 'record_url': source['record_url'],
'status': result.get('status'), 'error': result.get('error'),
'audio_path': result.get('audio_path'),
'source_filename_timestamp_utc': result.get('source_filename_timestamp_utc', result.get('clip_start_utc')),
'clip_duration_s': result.get('clip_duration_s'),
'source_sha256': result.get('recording', {}).get('source_sha256'),
'location_status': result.get('location_status'),
'location_reference': result.get('location_reference'),
'location_uncertainty': result.get('location_uncertainty'),
'publisher_clock_setting': clock_setting,
'clock_uncertainty': 'filename time is unverified; site-specific clock error is unknown',
'proposal_count': result.get('proposal_count'),
'proposal_group_count': result.get('proposal_group_count'),
'scanner_interpretation': result.get('interpretation'),
'visual_review': review.get('visual_review', 'pending'),
'review_plot': review.get('plot'),
'alternate_review': review.get('alternate_review', {}).get('visual_review'),
'alternate_plot': review.get('alternate_review', {}).get('plot')})
directory = args.root / 'reports'
directory.mkdir(exist_ok=True)
stamp = datetime.now(timezone.utc).strftime('%Y%m%dT%H%M%SZ')
path = directory / ('catalog-' + stamp + '.csv')
with path.open('x', newline='', encoding='utf-8') as stream:
writer = csv.DictWriter(stream, fieldnames=fields)
writer.writeheader()
writer.writerows(rows)
counts = collections.Counter(row['status'] for row in rows)
positives = sum(row['status'] == 'scanned' and (row['proposal_group_count'] or 0) > 0 for row in rows)
print(json.dumps({'catalog': str(path), 'selected': len(rows), 'statuses': counts,
'unreviewed_or_reviewed_proposal_positives': positives,
'note': 'proposals are not confirmed aircraft; coordinates stay in separate source files'}))
if __name__ == '__main__':
main()