SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.13583 · 2020

Mapping New Informal Settlements using Machine Learning and Time Series Satellite Images: An Application in the Venezuelan Migration Crisis

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 5 have no contract verdict; 0 failures of our instrument; 2 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/2008.13583.json · badge: /api/ran/2008.13583.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
thinkingmachines/geoai-immap canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
imports2 Ran
ran on a synthesized input
thinkingmachines/geoai-immap/utils/gee.py
code served (permissive licence) · get_code("f0692ff379cc25d7")
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 MockEEImage. 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 numpy as np

class MockEEImage:
    """Mock Earth Engine Image object with select, divide, addBands, set, and get methods"""
    
    def __init__(self):
        self.bands = {
            'B1': np.random.rand(10, 10),
            'B2': np.random.rand(10, 10),
            'B3': np.random.rand(10, 10),
            'B4': np.random.rand(10, 10),
            'B5': np.random.rand(10, 10),
            'B6': np.random.rand(10, 10),
            'B7': np.random.rand(10, 10),
            'B8': np.random.rand(10, 10),
            'B8A': np.random.rand(10, 10),
            'B9': np.random.rand(10, 10),
            'B11': np.random.rand(10, 10),
            'B12': np.random.rand(10, 10),
            'QA60': np.random.rand(10, 10)
        }
        self.properties = {
            'MEAN_SOLAR_AZIMUTH_ANGLE': 45.5,
            'MEAN_SOLAR_ZENITH_ANGLE': 30.2
        }
        self.selected_bands = None
    
    def select(self, band_list):
        """Select specific bands from the image"""
        new_img = MockEEImage()
        new_img.bands = {b: self.bands[b] for b in band_list if b in self.bands}
        new_img.properties = self.properties.copy()
        new_img.selected_bands = band_list
        return new_img
    
    def divide(self, value):
        """Divide all selected bands by a value"""
        new_img = MockEEImage()
        new_img.bands = {b: arr / value for b, arr in self.bands.items()}
        new_img.properties = self.properties.copy()
        new_img.selected_bands = self.selected_bands
        return new_img
    
    def addBands(self, other_img):
        """Add bands from another image"""
        new_img = MockEEImage()
        new_img.bands = self.bands.copy()
        new_img.bands.update(other_img.bands)
        new_img.properties = self.properties.copy()
        return new_img
    
    def set(self, key, value):
        """Set a property on the image"""
        new_img = MockEEImage()
        new_img.bands = self.bands.copy()
        new_img.properties = self.properties.copy()
        new_img.properties[key] = value
        new_img.selected_bands = self.selected_bands
        return new_img
    
    def get(self, key):
        """Get a property from the image"""
        return self.properties.get(key)

img = MockEEImage()

ARGS = {
    'img': img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockEEImage — a MockEEImage output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockEEImage 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
intersect_membership Ran
ran on a synthesized input
thinkingmachines/geoai-immap/utils/model_utils.py
code served (permissive licence) · get_code("ccd0403995bc4f12")
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 float, ndim 0, dtype family float, shape () 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 pandas as pd
import numpy as np

# Create two sample DataFrames with grid_id and y_pred columns
np.random.seed(0)

results1 = pd.DataFrame({
    'grid_id': [f'grid_{i}' for i in range(20)],
    'y_pred': np.random.rand(20)
})

results2 = pd.DataFrame({
    'grid_id': [f'grid_{i}' for i in range(10, 30)],
    'y_pred': np.random.rand(20)
})

ARGS = {
    'results1': results1,
    'results2': results2,
    'percent': 0.1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
rename_ind_cols Ran
ran on a synthesized input
thinkingmachines/geoai-immap/utils/geoutils.py
code served (permissive licence) · get_code("569683165282f56f")
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

# Create a sample dataframe with indicator columns
df = pd.DataFrame({
    'I1_band1': [0.5, 0.6],
    'I2_band2': [0.3, 0.4],
    'I3_extra': [0.7, 0.8],
    'I10_data': [0.2, 0.25],
    'other_col': [1, 2],
    'I5_metric': [0.9, 0.95]
})

ARGS = {
    'df': df
}
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 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
rescale Ran
ran on a synthesized input
thinkingmachines/geoai-immap/utils/gee.py
code served (permissive licence) · get_code("6af7e6830bed5f52")
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 TensorLike. 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

torch.manual_seed(0)

# The function expects:
# - img: an object with .subtract() and .divide() methods that return values
# - thresholds: a sequence with at least 2 elements (indices 0 and 1)

# Create a simple tensor-like object with subtract and divide methods
class TensorLike:
    def __init__(self, data):
        self.data = data
    
    def subtract(self, value):
        return TensorLike(self.data - value)
    
    def divide(self, value):
        return TensorLike(self.data / value)

# Create small tensors
img = TensorLike(torch.randn(2, 4))
thresholds = [0.5, 1.5]

ARGS = {
    "img": img,
    "thresholds": thresholds,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TensorLike — a TensorLike output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TensorLike 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
run_cmd Ran
ran on a synthesized input
thinkingmachines/geoai-immap/utils/geoutils.py
code served (permissive licence) · get_code("7ef83003ed4630fb")
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 CompletedProcess. 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 subprocess

# The function run_cmd takes a single parameter: command (a string)
# It executes the command using subprocess.run with shell=True
# The command should be a valid shell command that can be executed

# Create a simple, safe shell command that will succeed
command = "echo 'Hello, World!'"

ARGS = {
    "command": command
}
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 CompletedProcess — a CompletedProcess output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CompletedProcess 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
load_neg_sample_results Not yet run
unverified (harvested, no recorded run)
thinkingmachines/geoai-immap/utils/model_utils.py
code served (permissive licence) · get_code("a4f26ab4ec6e320c")
How it ran

no invocation recorded.

train_model Not yet run
unverified (harvested, no recorded run)
thinkingmachines/geoai-immap/utils/model_utils.py
code served (permissive licence) · get_code("8b0570c4f44a7a0c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

Since 2014, nearly 2 million Venezuelans have fled to Colombia to escape an economically devastated country during what is one of the largest humanitarian crises in modern history. Non-government organizations and local government units are faced with the challenge of identifying, assessing, and monitoring rapidly growing migrant communities in order to provide urgent humanitarian aid. However, with many of these displaced populations living in informal settlements areas across the country, locating migrant settlements across large territories can be a major challenge. To address this problem, we propose a novel approach for rapidly and cost-effectively locating new and emerging informal settlements using machine learning and publicly accessible Sentinel-2 time-series satellite imagery. We demonstrate the effectiveness of the approach in identifying potential Venezuelan migrant settlements in Colombia that have emerged between 2015 to 2020. Finally, we emphasize the importance of post-classification verification and present a two-step validation approach consisting of (1) remote validation using Google Earth and (2) on-the-ground validation through the Premise App, a mobile crowdsourcing platform.

For agents

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

get_harvested_code_for_paper("2008.13583")
get_code_for_paper("2008.13583")
have("2008.13583")

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

curl https://syntology.ai/api/ran/2008.13583.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.13583.svg)](https://syntology.ai/paper/2008.13583)

Connect an agent — have() is free.