MétaCan
Menu
Back to cohort

Building Damage Detection in Post-Event High-Resolution Imagery Using Deep Transfer Learning

2021· article· en· W3207491876 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicRemote-Sensing Image Classification
Canadian institutionsUniversity of New Brunswick
Fundersnot available
KeywordsOrthophotoComputer scienceEvent (particle physics)Deep learningArtificial intelligenceGeospatial analysisTransfer of learningResidualImage resolutionRemote sensingConvolutional neural networkComputer visionGeography

Abstract

fetched live from OpenAlex

One of the most important disaster management requirements is accurate damage map generation to support rescue and reconstruction efforts. In this application, remote sensing images play a significant role because of the great details provided by their high spatial, spectral, and temporal resolutions; thus, the literature is rich with studies that use pre- and post-event images along with geospatial machine learning techniques for automatic damage mapping. However, acquiring proper pre-event data can be challenging due to the unpredictable nature of hazards. In this paper, we customize a pre-trained version of the residual neural network with 34 layers (ResNet-34) to identify damaged buildings by using only post-event high-resolution remote sensing images. For evaluating the damage detection framework efficiency, airborne orthophotos of the 2010 Haiti earthquake and the 2018 Woolsey fire are utilized. The network identified damaged and non-damaged buildings with over 91 % overall accuracy.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.445
Threshold uncertainty score0.750

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.013
GPT teacher head0.231
Teacher spread0.219 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations10
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicRemote-Sensing Image ClassificationFrench-language works237,207