SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.00860 · NeurIPS · 2022

Insight into cloud processes from unsupervised classification with a rotation-invariant autoencoder

Ian Foster, Takuya Kurihana, James Franke, Ziwei Wang, Elisabeth Moyer

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2211.00860.json · badge: /api/ran/2211.00860.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
rdcep/clouds canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_args Ran
ran; our contract draft was wrong, not the code
rdcep/clouds/train/autoencoder/train_cloud_tf2_custom.py
code served (permissive licence) · get_code("8ba3439bd178461b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Namespace. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import argparse
import sys
from io import StringIO

def get_args(verbose=False):
    p = argparse.ArgumentParser()
    p.add_argument('--logdir', type=str, default='./')
    p.add_argument('--figdir', type=str, default='./')
    p.add_argument('--input_datadir', nargs='+', default='list of clouds tfrecord data directories')
    p.add_argument('--output_modeldir', type=str, default='./')
    p.add_argument('--lr', type=float, default=0.001)
    p.add_argument('--expname', type=str, default='new')
    p.add_argument('--num_epoch', type=int, default=5)
    p.add_argument('--batch_size', type=int, default=32, help='number of pictures in minibatch')
    p.add_argument('--npatches', type=int, default=2000, help='number of patches/tfrecord')
    p.add_argument('--height', type=int, default=32)
    p.add_argument('--width', type=int, default=32)
    p.add_argument('--channel', type=int, default=1)
    p.add_argument('--nblocks', type=int, default=5)
    p.add_argument('--base_dim', type=int, help='coef for size of filter at first convolutional layer in first block in encoder. 2**(base_dim)', default=4)
    p.add_argument('--nstack_layer', type=int, help='Number of convolution layers/block', default=3)
    p.add_argument('--retrain', action='store_true', help='attach this FLAGS if you need retraining from trained code', default=False)
    p.add_argument('--retrain_datadir', type=str, help='you should express directory if you retrain from a trained model', default='./')
    p.add_argument('--save_every', type=int, default=10)
    p.add_argument('--copy_size', type=int, default=32)
    p.add_argument('--f_lambda', type=float, help='lambda coef for transform invariant term', default=1.0)
    p.add_argument('--c_lambda', type=float, help='lambda coef for restoration term', default=1.0)
    p.add_argument('--s_lambda', type=float, help='lambda coef for sparse term', default=1.0)
    p.add_argument('--degree', type=int, help='how much degree you rotate in loss term', default=1)
    p.add_argument('--resnet', action='store_true', help='attach this FLAGS if you want to train resnet model; then nblocks -1 ', default=False)
    args = p.parse_args()
    if verbose:
        for f in args.__dict__:
            print('\t', f, (25 - len(f)) * ' ', args.__dict__[f])
        print('\n')
    return args

ARGS = {
    'verbose': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Clouds play a critical role in the Earth's energy budget and their potential changes are one of the largest uncertainties in future climate projections. However, the use of satellite observations to understand cloud feedbacks in a warming climate has been hampered by the simplicity of existing cloud classification schemes, which are based on single-pixel cloud properties rather than utilizing spatial structures and textures. Recent advances in computer vision enable the grouping of different patterns of images without using human-predefined labels, providing a novel means of automated cloud classification. This unsupervised learning approach allows discovery of unknown climate-relevant cloud patterns, and the automated processing of large datasets. We describe here the use of such methods to generate a new AI-driven Cloud Classification Atlas (AICCA), which leverages 22 years and 800 terabytes of MODIS satellite observations over the global ocean. We use a rotation-invariant cloud clustering (RICC) method to classify those observations into 42 AI-generated cloud class labels at ∼100 km spatial resolution. As a case study, we use AICCA to examine a recent finding of decreasing cloudiness in a critical part of the subtropical stratocumulus deck, and show that the change is accompanied by strong trends in cloud classes.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2211.00860")
get_code_for_paper("2211.00860")
have("2211.00860")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2211.00860.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2211.00860.svg)](https://syntology.ai/paper/2211.00860)

Connect an agent — have() is free.