SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1706.03458 · 2017

Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 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, 1 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 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/1706.03458.json · badge: /api/ran/1706.03458.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
sxjscience/HKO-7 canonical (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
tianhai123/conv-gru reimplementation (classifier label)
classifier basis: classifier_2025
5 ran · 0 no recorded run
FunctionStatusWhere it lives
conv2_act Ran
ran; our contract draft was wrong, not the code
tianhai123/conv-gru/encoder.py
pointer only (licence: NONE) · get_code("bcf4a8730082002b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tianhai123/conv-gru when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv2_act Ran
ran; our contract draft was wrong, not the code
tianhai123/conv-gru/forecaster.py
pointer only (licence: NONE) · get_code("5cc4268bd2c61345")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tianhai123/conv-gru when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

deconv2_act Ran
ran; our contract draft was wrong, not the code
tianhai123/conv-gru/forecaster.py
pointer only (licence: NONE) · get_code("a49a94bd61a1651f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tianhai123/conv-gru when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

downsmaple Ran
ran; our contract draft was wrong, not the code
tianhai123/conv-gru/encoder.py
pointer only (licence: NONE) · get_code("9096c0546286d0c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tianhai123/conv-gru when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

encode_month Ran
ran, violated the contract we drafted
sxjscience/HKO-7/nowcasting/hko_iterator.py
code served (permissive licence) · get_code("6f090d3364df919e")
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 ndarray, ndim 2, dtype family float, shape (3, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

# Create a small test case for encode_month
# The function expects an np.ndarray of integers between 1 and 12
# with shape (...,) and returns shape (..., 2)

# Test with a simple 1D array of months
month_input = np.array([1, 6, 12], dtype=np.int32)

ARGS = {
    "month": month_input
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 2) — shape (3, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
frame_skip_reshape Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sxjscience/HKO-7/experiments/hko/hko_main.py
code served (permissive licence) · get_code("d7f985f69ed8fefd")
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 ndarray, ndim 5, dtype family float, shape (2, 4, 3, 5, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

# Create a small numpy array with shape (seq_len, B, C, H, W)
# seq_len must be divisible by frame_skip
# Using distinct sizes: seq_len=4, frame_skip=2, B=2, C=3, H=5, W=6
seq_len = 4
frame_skip = 2
B = 2
C = 3
H = 5
W = 6

dat = np.random.randn(seq_len, B, C, H, W).astype(np.float32)

ARGS = {
    "dat": dat,
    "frame_skip": frame_skip,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 5, dtype family float, shape (2, 4, 3, 5, 6) — shape (2, 4, 3, 5, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
frame_skip_reshape_back Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sxjscience/HKO-7/experiments/hko/hko_main.py
code served (permissive licence) · get_code("594f31479418e41f")
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 ndarray, ndim 5, dtype family float, shape (12, 2, 2, 4, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

# Create a small numpy array with shape (seq_len, B, C, H, W)
# where B is divisible by frame_skip
seq_len = 3
B = 8
frame_skip = 4
C = 2
H = 4
W = 5

dat = np.random.randn(seq_len, B, C, H, W).astype(np.float32)

ARGS = {
    "dat": dat,
    "frame_skip": frame_skip,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 5, dtype family float, shape (12, 2, 2, 4, 5) — shape (12, 2, 2, 4, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
get_base_dir Ran
ran; our contract draft was wrong, not the code
sxjscience/HKO-7/experiments/hko/hko_main.py
code served (permissive licence) · get_code("69a7ad6774e73b5c")
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 str. 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 torch
import torch.nn as nn

class Args:
    def __init__(self, save_dir=None):
        self.save_dir = save_dir

# Test case 1: save_dir is None (should return default)
args_none = Args(save_dir=None)

# Test case 2: save_dir is provided
args_with_dir = Args(save_dir='/custom/path')

# Use the first case for ARGS
ARGS = {'args': args_none}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
upsmaple Ran
ran; our contract draft was wrong, not the code
tianhai123/conv-gru/forecaster.py
pointer only (licence: NONE) · get_code("5ec5fba82b1decd8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tianhai123/conv-gru when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

decode_month Not yet run
unverified (harvested, no recorded run)
sxjscience/HKO-7/nowcasting/hko_iterator.py
code served (permissive licence) · get_code("cf999c562f67173a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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

With the goal of making high-resolution forecasts of regional rainfall, precipitation nowcasting has become an important and fundamental technology underlying various public services ranging from rainstorm warnings to flight safety. Recently, the Convolutional LSTM (ConvLSTM) model has been shown to outperform traditional optical flow based methods for precipitation nowcasting, suggesting that deep learning models have a huge potential for solving the problem. However, the convolutional recurrence structure in ConvLSTM-based models is location-invariant while natural motion and transformation (e.g., rotation) are location-variant in general. Furthermore, since deep-learning-based precipitation nowcasting is a newly emerging area, clear evaluation protocols have not yet been established. To address these problems, we propose both a new model and a benchmark for precipitation nowcasting. Specifically, we go beyond ConvLSTM and propose the Trajectory GRU (TrajGRU) model that can actively learn the location-variant structure for recurrent connections. Besides, we provide a benchmark that includes a real-world large-scale dataset from the Hong Kong Observatory, a new training loss, and a comprehensive evaluation protocol to facilitate future research and gauge the state of the art.

For agents

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

get_harvested_code_for_paper("1706.03458")
get_code_for_paper("1706.03458")
have("1706.03458")

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

curl https://syntology.ai/api/ran/1706.03458.json

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

[![Syntology run record](https://syntology.ai/api/ran/1706.03458.svg)](https://syntology.ai/paper/1706.03458)

Connect an agent — have() is free.