Multi-Sensing Data-Based Estimation of Isolated Settlements During Disasters: A Case Study Using the 2024 Noto Peninsula Earthquake
Bibliographic record
Abstract
In the event of a disaster, the occurrence of isolated settlements necessitates prompt responses, including rescue operations, medical transport, and the delivery of essential supplies. However, it is often challenging to quickly identify which areas are isolated. This study developed a method for estimating isolated settlements during earthquake disasters using multi-sensing data. An accuracy evaluation based on data from the 2024 Noto Peninsula earthquake revealed an overlook rate of approximately 60% and a mistaken estimation rate of approximately 20%. By incorporating actual road traffic data, the estimation was refined to extract settlements at high risk of isolation. Moreover, the method successfully identified isolated settlements that were not reported in official damage reports, indicating relatively high estimation accuracy. This capability is expected to assist disaster management headquarters in identifying priority areas for emergency response. Because the data used in the proposed method can be obtained during actual disaster events, the estimation process can be initiated promptly across Japan immediately after an earthquake, thereby enabling the timely provision of valuable information for disaster response. This analysis presents the necessary data and computational approaches for improving estimation accuracy and supporting practical implementation in disaster management. In the future, advancements in various sensing technologies and the development of data-sharing frameworks are expected to facilitate even more accurate estimations.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".