weathernext-download
weathernext-download downloads paired tropical-cyclone forecast files from
Google DeepMind Weather Lab. It supports ensemble and ensemble-mean products,
CSV and ATCF formats, and the OPER, WNV3, and FNV3 model families.
Installation
pip install --upgrade weathernext-download
Or from source:
git clone https://github.com/CongGao-CG/weathernext-download.git
cd weathernext-download
pip install .
Available products
Weather Lab provides experimental cyclone predictions paired with observed
tracks for verification. Every model below is available as an ensemble mean
(--ensemble_mean), a full ensemble of member tracks (--ensemble), or both
(--both), in CSV (--csv) or ATCF (--atcf) format.
| Model | Model long name | Option | Products | Formats | Initialization cycles | Temporal coverage |
|---|---|---|---|---|---|---|
| OPER | WeatherNext Cyclones Operational | --oper (default) |
Ensemble mean and ensemble members | CSV and ATCF | 00, 06, 12, and 18 UTC | 2025-06-12 onward |
| WNV3 | WeatherNext 3 Cyclones | --wnv3 |
Ensemble mean and ensemble members | CSV and ATCF | 00, 06, 12, and 18 UTC; 2025 only: 06 and 18 UTC | 2024-01-01 onward |
| FNV3P2 | WeatherNext 2 Cyclones (r2) | --v3p2 |
Ensemble mean and ensemble members | CSV and ATCF | 00, 06, 12, and 18 UTC | 2022-01-01 onward |
| FNV3P1 | WeatherNext 2 Cyclones (r1) | --v3p1 |
Ensemble mean and ensemble members | CSV and ATCF | 00, 06, 12, and 18 UTC | 2022-01-01 onward |
| FNV3P0 | WeatherNext 2 Cyclones (r0) | --v3p0 |
Ensemble mean and ensemble members | CSV and ATCF | 00, 06, 12, and 18 UTC | 2022-01-01 through 2026-05-28 12 UTC |
| FNV3 large ensemble | WeatherNext 2 Cyclones (r2, 1000 members) | --v3p2LE |
Ensemble mean and ensemble members | CSV and ATCF | 00, 06, 12, and 18 UTC | 2025-10-18 onward; some cycles are unavailable |
Coverage was checked against the Weather Lab download endpoints on 2026-09-03 and may expand or contain isolated gaps. An unavailable upstream file is reported as a failed download. See Google's Weather Lab guide for its description and terms for experimental cyclone forecast data.
Usage
Download one forecast cycle:
weathernext-download --time 2026070100 --ensemble_mean
Download both products for all four cycles on one day:
weathernext-download --date 20260701 --both
Download a month or year:
weathernext-download --date 202607 --both
weathernext-download --date 2026 --both
Download ATCF files from the FNV3P2 model:
weathernext-download --date 20220101 --v3p2 --both --atcf
Time selection
--time YYYYMMDDHHdownloads one cycle. The hour must be00,06,12, or18.--date YYYYMMDDdownloads all four cycles on one day.--date YYYYMMdownloads all four cycles for every day in one month.--date YYYYdownloads all four cycles for every day in one year.- Date selections are capped at the date obtained from current UTC time minus 24 hours and restricted to the selected model's temporal coverage. A period with no overlap exits with an error instead of sending invalid requests.
- With neither option, all cycles within the selected model's temporal coverage are downloaded through the date obtained from current UTC time minus 24 hours.
Product selection
--ensemble_meanor--ensemble-mean--ensemble--both(default)
File format
--csv(default)--atcf
Model selection
--operforOPER(default)--wnv3forWNV3--v3p2forFNV3P2--v3p1forFNV3P1--v3p0forFNV3P0--v3p2LEor--v3p2leforFNV3_LARGE_ENSEMBLE
Files are stored under ./ensemble_mean and ./ensemble in the directory
where the command is run. Existing non-empty files are skipped. Each new file
is first written to a temporary file and moved into place only after the
download completes.
Run weathernext-download --help for all options, including timeout and retry
settings.
License
MIT
Metadata
Release files for weathernext-download 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| weathernext_download-0.1.3.tar.gz | 9.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| weathernext_download-0.1.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 17.7 kB
Release files / weathernext_download-0.1.3.tar.gz
| Download URL | weathernext_download-0.1.3.tar.gz |
|---|---|
| Size | 9.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
1f403fb5d9bf97aded6f55e14b1f4f2975a534599764095bcc1297347e0f74ff
|
|
BLAKE2b-256 checksum How to use checksums |
c8ea10fa82e067d27d31a9b44c1ae141ce68abe9eb6f815e7182e8a762b36649
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.10.16
|
Release files / weathernext_download-0.1.3-py3-none-any.whl
| Download URL | weathernext_download-0.1.3-py3-none-any.whl |
|---|---|
| Size | 8.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6be861c2325c57e122fb4551d4b3de97767a7f0ddc393f9e46bf4258bb176a98
|
|
BLAKE2b-256 checksum How to use checksums |
00311b930132c1bfd2f36b241f6b1170ae6dd67fe743fda380e84cc4ec5a8c59
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.10.16
|