ionis-validate 0.2.0

IONIS V20 — HF Propagation Model Validation Suite

ionis-validate

Validation suite for the IONIS V20 HF propagation model. Run 62 physics tests, predict SNR for any HF path, or validate the model against your own QSO log — all from the command line, on any platform.

IONIS (Ionospheric Neural Inference System) predicts HF radio signal strength from WSPR, RBN, and contest data. The V20 model was trained on 31 million propagation observations spanning 2008-2025.

Install

pip install ionis-validate

Requires Python 3.9+ and PyTorch 2.0+. Works on Windows, macOS, and Linux.

Quick Start

# Show model and system info
ionis-validate info

# Run the full 62-test validation suite
ionis-validate test

# Predict SNR for a single path
ionis-validate predict \
    --tx-grid FN20 --rx-grid IO91 --band 20m \
    --sfi 150 --kp 2 --hour 14 --month 6

Validate Your Log

Export your QSO log from eQSL, LoTW, or QRZ as an ADIF (.adi) file, then check how often the model agrees the band was open for each contact.

ionis-validate adif my_log.adi --my-grid DN26

All processing happens locally. Callsigns are stripped at parse time and never leave your machine. The tool extracts only grid pairs, band, mode, and time — no personal information.

Batch Predictions

Define a set of paths in a JSON file and run them all at once:

ionis-validate custom my_paths.json

See the documentation for the JSON format.

Beta Test Reports

Generate a structured report for filing as a GitHub Issue:

ionis-validate report

Privacy

IONIS processes only grid-pair geometry, band, time, and solar indices. No callsigns, names, or personal data are used by the model or stored by this tool. ADIF log validation strips all PII at parse time.

Full privacy policy: https://ionis-ai.com/ethos/

License

GPL-3.0-or-later. See LICENSE.

Links

• Documentation: https://ionis-ai.com/testing/
• Source: https://github.com/IONIS-AI/ionis-validate
• Issues: https://github.com/IONIS-AI/ionis-validate/issues
• IONIS Project: https://ionis-ai.com/