SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.02447 · 2021

Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 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 10 have no contract verdict; 0 failures of our instrument; 5 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/2112.02447.json · badge: /api/ran/2112.02447.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
satellitevu/satellitevu-aws-disaster-response-hackathon community (classifier label)
classifier basis not recorded on the link
10 ran · 5 no recorded run
FunctionStatusWhere it lives
bn_act Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/model_resunet.py
code served (permissive licence) · get_code("6e1a94fa80374290")
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, through the batch API) and returned EagerTensor, ndim 2, dtype family float, shape (2, 4) 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 tensorflow as tf
from tensorflow import keras
import numpy as np

# Create a small input tensor for the function
# Using shape (2, 4) - batch size 2, feature dimension 4
input_data = tf.random.normal(shape=(2, 4))

ARGS = {
    'x': input_data,
    'act': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
bn_conv_relu Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/model_satunet.py
code served (permissive licence) · get_code("5347f4722ba41e80")
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, through the batch API) and returned KerasTensor. 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 tensorflow as tf
from tensorflow.keras.layers import BatchNormalization, Conv2D, Conv2DTranspose, MaxPooling2D, UpSampling2D, Input, concatenate
import numpy as np

# Create a small input tensor for the Keras functional API
input_tensor = Input(shape=(4, 4, 3))

# Define arguments for bn_conv_relu function
ARGS = {
    "input": input_tensor,
    "filters": 16,
    "bachnorm_momentum": 0.99,
    "kernel_size": (3, 3),
    "padding": "same",
    "activation": "relu"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type KerasTensor — a KerasTensor output has no array shape of its own; none is 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
bn_upconv_relu Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/model_satunet.py
code served (permissive licence) · get_code("8ca25223d3629d3f")
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, through the batch API) and returned KerasTensor. 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 tensorflow as tf
import numpy as np

# Create a small input tensor for the function
# Using TensorFlow/Keras symbolic input
input_tensor = tf.keras.Input(shape=(4, 4, 3), batch_size=2)

# Define ARGS dictionary with all required parameters
ARGS = {
    'input': input_tensor,
    'filters': 16,
    'bachnorm_momentum': 0.99,
    'kernel_size': (3, 3),
    'strides': (2, 2),
    'padding': 'same'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type KerasTensor — a KerasTensor output has no array shape of its own; none is 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
center_crop_input_and_output_images Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/datagen.py
code served (permissive licence) · get_code("60c72995c84a198d")
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, through the batch API) and returned tuple, ndim 4, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 tensorflow as tf

# Create small input and output images with HWC dimensions
# Height=8, Width=8, Channels=3
input_img = tf.random.normal(shape=(8, 8, 3), dtype=tf.float32)
output_img = tf.random.normal(shape=(8, 8, 3), dtype=tf.float32)

# Sample size for center crop (must be <= input image height)
sample_size = 4

ARGS = {
    "input_img": input_img,
    "output_img": output_img,
    "sample_size": sample_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 4, dtype family float — a tuple output has no array shape of its own; none is stated
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
cluster_fires Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/dataset_preparation/src/data_sources.py
code served (permissive licence) · get_code("91fa360ba81355ab")
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, through the batch API) and returned DataFrame. 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 pandas as pd
import numpy as np
from sklearn.cluster import DBSCAN

# Create a minimal fire dataframe with required columns
fire_data = {
    'acq_date': ['2023-01-01', '2023-01-01', '2023-01-01', '2023-01-01', 
                 '2023-01-02', '2023-01-02', '2023-01-02', '2023-01-02',
                 '2023-01-02', '2023-01-02', '2023-01-02', '2023-01-02',
                 '2023-01-02', '2023-01-02', '2023-01-02', '2023-01-02',
                 '2023-01-02', '2023-01-02', '2023-01-02', '2023-01-02',
                 '2023-01-02', '2023-01-02', '2023-01-02', '2023-01-02',
                 '2023-01-02', '2023-01-02', '2023-01-02', '2023-01-02',
                 '2023-01-02', '2023-01-02'],
    'longitude': np.random.uniform(-120, -119, 30),
    'latitude': np.random.uniform(35, 36, 30),
    'fire_intensity': np.random.uniform(0, 100, 30)
}

fire_dataframe = pd.DataFrame(fire_data)

ARGS = {
    'fire_dataframe': fire_dataframe,
    'min_cluster_points': 25
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
conv_block Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/model_resunet.py
code served (permissive licence) · get_code("9ebda9e9a9e6bed7")
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, through the batch API) and returned EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 8) 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 tensorflow as tf
from tensorflow import keras
import numpy as np

# Create a small input tensor
# conv_block expects a tensor input x with shape (batch, height, width, channels)
batch_size = 2
height = 4
width = 3
input_channels = 1

# Create a random input tensor
input_tensor = tf.random.normal((batch_size, height, width, input_channels))

# Define ARGS dict with all parameters for conv_block
ARGS = {
    'x': input_tensor,
    'filters': 8,
    'kernel_size': (3, 3),
    'padding': 'same',
    'strides': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 8) — shape (2, 4, 3, 8) 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
convert_wgs_to_utm Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/dataset_preparation/src/geospatial.py
code served (permissive licence) · get_code("67dd8ec8c63b0413")
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, through the batch API) 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 math

def convert_wgs_to_utm(lon, lat):
    """
    Stolen from
    https://stackoverflow.com/questions/40132542/get-a-cartesian-projection-accurate-around-a-lat-lng-pair
    :param lon: Longitude float
    :param lat: Latitude float
    :return: The utm code appropriate for this AOI
    """
    utm_band = str(math.floor((lon + 180) / 6) % 60 + 1)
    if len(utm_band) == 1:
        utm_band = '0' + utm_band
    if lat >= 0:
        epsg_code = '326' + utm_band
        return epsg_code
    epsg_code = '327' + utm_band
    return epsg_code

ARGS = {
    'lon': -74.0060,
    'lat': 40.7128
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 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
random_crop_input_and_output_images Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/datagen.py
code served (permissive licence) · get_code("34f689cf51eb73b2")
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, through the batch API) and returned tuple. 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 tensorflow as tf

# Create small input and output image tensors with HWC format
# Using distinct dimensions: 8x6 spatial, 3 input channels, 2 output channels
input_img = tf.random.normal([8, 6, 3], dtype=tf.float32)
output_img = tf.random.normal([8, 6, 2], dtype=tf.float32)

# Set seed for reproducibility
tf.random.set_seed(0)

ARGS = {
    'input_img': input_img,
    'output_img': output_img,
    'sample_size': 4,
    'num_in_channels': 3,
    'num_out_channels': 2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
stem Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/model_resunet.py
code served (permissive licence) · get_code("48305b591734eef2")
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, through the batch API) and returned KerasTensor. 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 tensorflow as tf
from tensorflow import keras
import numpy as np

# Set seed for reproducibility
np.random.seed(0)
tf.random.set_seed(0)

# Create a small input tensor (batch=2, height=4, width=4, channels=3)
x = keras.Input(shape=(4, 4, 3))

# Define parameters for the stem function
filters = 8
kernel_size = (3, 3)
padding = 'same'
strides = 1

ARGS = {
    'x': x,
    'filters': filters,
    'kernel_size': kernel_size,
    'padding': padding,
    'strides': strides
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type KerasTensor — a KerasTensor output has no array shape of its own; none is 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
unzip_csvs Ran
ran on a synthesized input
satellitevu/satellitevu-aws-disaster-response-hackathon/dataset_preparation/src/data_sources.py
code served (permissive licence) · get_code("f108adfd6ec726b4")
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, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 tempfile
import zipfile
from pathlib import Path

# Create a temporary directory and a test zip file with CSV files
temp_dir = tempfile.mkdtemp()
temp_path = Path(temp_dir)

# Create a zip file with some CSV files inside
zip_path = temp_path / "test.zip"
with zipfile.ZipFile(zip_path, 'w') as zf:
    zf.writestr("data1.csv", "col1,col2\n1,2\n3,4\n")
    zf.writestr("data2.csv", "col1,col2\n5,6\n7,8\n")
    zf.writestr("readme.txt", "This is not a csv\n")

ARGS = {
    "zip_file": zip_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
add_sample_weights Not yet run
unverified (harvested, no recorded run)
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/datagen.py
code served (permissive licence) · get_code("2cbc2564c4a905cb")
How it ran

no invocation recorded.

class_tversky Not yet run
unverified (harvested, no recorded run)
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/metrics.py
code served (permissive licence) · get_code("b53707879f1bc5b6")
How it ran

no invocation recorded.

dice_coef Not yet run
unverified (harvested, no recorded run)
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/metrics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from oliverz17/Unet_Keras, is pointer only (licence: NONE) · get_code("eabf975a0dc6af2f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from oliverz17/Unet_Keras, and GitHub detected no licence in that repository 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. No invocation recorded.

focal_tversky_loss Not yet run
unverified (harvested, no recorded run)
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/metrics.py
code served (permissive licence) · get_code("2aba6172688c62bf")
How it ran

no invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
satellitevu/satellitevu-aws-disaster-response-hackathon/deep_learning/model_satunet.py
code served (permissive licence) · get_code("6062621b9646dcef")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 14 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.

FunctionAlso present inEarliest-datedOthers named
dice_coef 1 other paper
1 dated earlier
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation

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

Predicting wildfire spread is critical for land management and disaster preparedness. To this end, we present `Next Day Wildfire Spread,' a curated, large-scale, multivariate data set of historical wildfires aggregating nearly a decade of remote-sensing data across the United States. In contrast to existing fire data sets based on Earth observation satellites, our data set combines 2D fire data with multiple explanatory variables (e.g., topography, vegetation, weather, drought index, population density) aligned over 2D regions, providing a feature-rich data set for machine learning. To demonstrate the usefulness of this data set, we implement a neural network that takes advantage of the spatial information of this data to predict wildfire spread. We compare the performance of the neural network with other machine learning models: logistic regression and random forest. This data set can be used as a benchmark for developing wildfire propagation models based on remote sensing data for a lead time of one day.

For agents

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

get_harvested_code_for_paper("2112.02447")
get_code_for_paper("2112.02447")
have("2112.02447")

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

curl https://syntology.ai/api/ran/2112.02447.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.02447.svg)](https://syntology.ai/paper/2112.02447)

Connect an agent — have() is free.