SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.11544 · 2021

Deep Learning-based Damage Mapping with InSAR Coherence Time Series

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 9 have no contract verdict; 1 failure 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/2105.11544.json · badge: /api/ran/2105.11544.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
olliestephenson/dpm-rnn-public canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
opera-adt/distmetrics community (classifier label)
classifier basis not recorded on the link
9 ran · 3 no recorded run
FunctionStatusWhere it lives
compile_model Ran
ran on a synthesized input
opera-adt/distmetrics/src/distmetrics/model_load.py
code served (permissive licence) · get_code("b87a34572c6d5bc8")
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 OptimizedModule. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import math

torch.manual_seed(0)

class MockTransformer(nn.Module):
    def __init__(self):
        super().__init__()
        self.num_patches = 16
        self.patch_size = 4
        self.data_dim = 64
        self.max_seq_len = 32
        self.linear = nn.Linear(64, 64)
    
    def forward(self, x):
        return self.linear(x)

transformer = MockTransformer()
dtype = "float32"
device = "cpu"
batch_size = 2
cuda_latest = False

ARGS = {
    "transformer": transformer,
    "dtype": dtype,
    "device": device,
    "batch_size": batch_size,
    "cuda_latest": cuda_latest,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch, torch_tensorrt — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type OptimizedModule — a OptimizedModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OptimizedModule 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
compute_cusum_1d Ran
ran on a synthesized input
opera-adt/distmetrics/src/distmetrics/cusum.py
code served (permissive licence) · get_code("26003403f1efde48")
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 CuSumDist. 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 numpy as np

# Create small test data for pre_arrs (list of 3 pre-images, each 4x3)
pre_arrs = [
    np.random.rand(4, 3) * 0.5 + 0.2,  # Random values between 0.2-0.7 for logit safety
    np.random.rand(4, 3) * 0.5 + 0.2,
    np.random.rand(4, 3) * 0.5 + 0.2,
]

# Create post_arr with same spatial dims (4x3)
post_arr = np.random.rand(4, 3) * 0.5 + 0.2

ARGS = {
    "pre_arrs": pre_arrs,
    "post_arr": post_arr,
    "temporal_drift": "mean",
    "transform_data_to": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pydantic, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CuSumDist — a CuSumDist output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CuSumDist 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
compute_log_ratio_decrease_metric Ran
ran on a synthesized input
opera-adt/distmetrics/src/distmetrics/logratio.py
code served (permissive licence) · get_code("acf574d22fa3258b")
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 LogRatioDecrease. 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 numpy as np

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

# Create small test arrays
# pre_arrs: list of ndarrays representing pre-scene images
pre_arrs = [
    np.random.rand(4, 3).astype(np.float32) + 0.1,  # avoid zeros for log
    np.random.rand(4, 3).astype(np.float32) + 0.1,
    np.random.rand(4, 3).astype(np.float32) + 0.1,
]

# post_arr: single ndarray representing post-scene image
post_arr = np.random.rand(4, 3).astype(np.float32) + 0.1

# window_size: must be odd integer or 1
window_size = 1

# qual_stat_for_pre_imgs: either 'mean' or 'median'
qual_stat_for_pre_imgs = 'median'

# max_db_decrease: float clipping value
max_db_decrease = 10.0

ARGS = {
    'pre_arrs': pre_arrs,
    'post_arr': post_arr,
    'window_size': window_size,
    'qual_stat_for_pre_imgs': qual_stat_for_pre_imgs,
    'max_db_decrease': max_db_decrease,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pydantic — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LogRatioDecrease — a LogRatioDecrease output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LogRatioDecrease 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
compute_log_ratio_raw Ran
ran on a synthesized input
opera-adt/distmetrics/src/distmetrics/logratio.py
code served (permissive licence) · get_code("51391fa8ec64c5cf")
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 3, 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 numpy as np

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

# Create small pre-images (list of 2D arrays)
pre_arrs = [
    np.random.rand(4, 3).astype(np.float32) + 0.1,
    np.random.rand(4, 3).astype(np.float32) + 0.1,
    np.random.rand(4, 3).astype(np.float32) + 0.1,
]

# Create a single post image with same spatial dimensions
post_arr = np.random.rand(4, 3).astype(np.float32) + 0.1

# Define arguments
ARGS = {
    'pre_arrs': pre_arrs,
    'post_arr': post_arr,
    'window_size': 1,
    'qual_stat_for_pre_imgs': 'median'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, 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
compute_prob_cusum_1d Ran
ran on a synthesized input
opera-adt/distmetrics/src/distmetrics/cusum.py
code served (permissive licence) · get_code("d1f6c42fef3fd4dc")
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 CuSumDist. 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 numpy as np

# Create small sample arrays with values between 0 and 1 (suitable for logit)
# Using values slightly away from 0 and 1 to avoid logit domain issues
np.random.seed(0)

# Create pre_arrs: list of 3 arrays, each of shape (4,)
pre_arrs = [
    np.random.uniform(0.1, 0.9, size=(4,)),
    np.random.uniform(0.1, 0.9, size=(4,)),
    np.random.uniform(0.1, 0.9, size=(4,))
]

# Create post_arr: single array of shape (4,)
post_arr = np.random.uniform(0.1, 0.9, size=(4,))

ARGS = {
    "pre_arrs": pre_arrs,
    "post_arr": post_arr
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pydantic, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CuSumDist — a CuSumDist output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CuSumDist 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
get_exterior_nodata_mask Ran
ran on a synthesized input
opera-adt/distmetrics/src/distmetrics/nd_tools.py
code served (permissive licence) · get_code("edfe246780053786")
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 ndarray, ndim 2, dtype family int, shape (4, 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 numpy as np
from scipy.ndimage import label as labeler

# Create a simple 2D image with some nodata values (NaN)
image_with_nan = np.array([
    [1.0, 2.0, np.nan, 4.0],
    [5.0, 6.0, 7.0, np.nan],
    [np.nan, 8.0, 9.0, 10.0],
    [11.0, np.nan, 12.0, 13.0]
], dtype=float)

ARGS = {
    "image": image_with_nan,
    "nodata_val": np.nan
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 int, shape (4, 4) — shape (4, 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
get_url_tif Ran
ran on a synthesized input
opera-adt/distmetrics/src/distmetrics/asf_burst_search.py
code served (permissive licence) · get_code("f059953116fda4aa")
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 pandas as pd

# Create a sample pandas Series with the required attributes
row = pd.Series({
    'url': 'https://example.com/data_VH.tif',
    'additionalUrls': [
        'https://example.com/data_VV.tif',
        'https://example.com/data_HH.tif'
    ],
    'opera_id': 'opera_123'
})

ARGS = {
    'row': row,
    'polarization': 'crosspol'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — 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
iterative_linear_interpolate Ran
ran on a synthesized input
opera-adt/distmetrics/src/distmetrics/nd_tools.py
code served (permissive licence) · get_code("21adcef1c039073c")
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 ndarray, ndim 2, dtype family float, shape (4, 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 numpy as np

# Create a 2D array with some NaN values to interpolate
arr = np.array([
    [1.0, 2.0, np.nan, 4.0],
    [5.0, np.nan, np.nan, 8.0],
    [9.0, 10.0, 11.0, np.nan],
    [np.nan, 14.0, 15.0, 16.0]
], dtype=float)

ARGS = {
    'arr': arr,
    'max_iter': 10,
    'preserve_exterior_mask': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 (4, 4) — shape (4, 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
load_json Ran
ran; our contract draft was wrong, not the code
olliestephenson/dpm-rnn-public/generate_dpm.py
code served (permissive licence) · get_code("80f7689e7087217d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned dict. 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 json
import os
import tempfile

# Create a temporary JSON file for testing
temp_dir = tempfile.mkdtemp()
json_path = os.path.join(temp_dir, "test_file.json")

# Write a simple JSON object to the file
test_data = {"key": "value", "number": 42, "list": [1, 2, 3]}
with open(json_path, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "json_path": json_path
}
Setup block drafted by
a language model, Claude Sonnet 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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
nn_interpolate Ran
ran on a synthesized input
opera-adt/distmetrics/src/distmetrics/nd_tools.py
code served (permissive licence) · get_code("9c10176d94ec0c95")
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 ndarray, ndim 2, dtype family float, shape (4, 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 numpy as np

# Create a simple 2D array with some NaN values for testing
# The array should have some interior NaN values and some exterior NaN values
arr = np.array([
    [np.nan, np.nan, 1.0, 2.0],
    [np.nan, 3.0, 4.0, np.nan],
    [5.0, 6.0, np.nan, 7.0],
    [np.nan, np.nan, 8.0, np.nan]
], dtype=float)

ARGS = {
    "arr": arr,
    "preserve_exterior_mask": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 (4, 4) — shape (4, 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
compute_scores Not yet run
unverified (harvested, no recorded run)
olliestephenson/dpm-rnn-public/generate_dpm.py
code served (permissive licence) · get_code("9c50f551d8c3877d")
How it ran

no invocation recorded.

get_device Not yet run
unverified (harvested, no recorded run)
olliestephenson/dpm-rnn-public/generate_dpm.py
code served (permissive licence) · get_code("9d65b96001e83302")
How it ran

no invocation recorded.

load_library_model_config Not yet run
unverified (harvested, no recorded run)
opera-adt/distmetrics/src/distmetrics/model_load.py
code served (permissive licence) · get_code("174343a0b45a4ffb")
How it ran

no invocation recorded.

load_weights_from_path Not yet run
unverified (harvested, no recorded run)
opera-adt/distmetrics/src/distmetrics/model_load.py
code served (permissive licence) · get_code("565016e91dea1047")
How it ran

no invocation recorded.

read_bytes Not yet run
unverified (harvested, no recorded run)
opera-adt/distmetrics/src/distmetrics/asf_io.py
code served (permissive licence) · get_code("6d25b34006692bf9")
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, 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 15 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

Satellite remote sensing is playing an increasing role in the rapid mapping of damage after natural disasters. In particular, synthetic aperture radar (SAR) can image the Earth's surface and map damage in all weather conditions, day and night. However, current SAR damage mapping methods struggle to separate damage from other changes in the Earth's surface. In this study, we propose a novel approach to damage mapping, combining deep learning with the full time history of SAR observations of an impacted region in order to detect anomalous variations in the Earth's surface properties due to a natural disaster. We quantify Earth surface change using time series of Interferometric SAR coherence, then use a recurrent neural network (RNN) as a probabilistic anomaly detector on these coherence time series. The RNN is first trained on pre-event coherence time series, and then forecasts a probability distribution of the coherence between pre- and post-event SAR images. The difference between the forecast and observed co-event coherence provides a measure of the confidence in the identification of damage. The method allows the user to choose a damage detection threshold that is customized for each location, based on the local behavior of coherence through time before the event. We apply this method to calculate estimates of damage for three earthquakes using multi-year time series of Sentinel-1 SAR acquisitions. Our approach shows good agreement with observed damage and quantitative improvement compared to using pre- to co-event coherence loss as a damage proxy.

For agents

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

get_harvested_code_for_paper("2105.11544")
get_code_for_paper("2105.11544")
have("2105.11544")

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

curl https://syntology.ai/api/ran/2105.11544.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.11544.svg)](https://syntology.ai/paper/2105.11544)

Connect an agent — have() is free.