Addressing the challenge of spatiotemporal data sparsity in disasters: predicting flood risks by aggregating distant neighbors on the basis of the principle of geographic similarity
Bibliographic record
Abstract
With floods being among the most frequent disasters of the 21st century, timely prediction of flood risks is crucial for early alerts to governments and residents, thereby reducing potential losses. Owing to the uneven spatiotemporal distribution of disaster data and limited sharing, assessing risks in blind spots without monitoring is challenging. In this paper, we propose a flood risk prediction method that integrates spatial neighbors on the basis of geographic similarity. Considering the correlation between surrounding environments and flood occurrence, this method introduces high-order neighborhoods to model internal and external environments of spatial units. Given the sparse spatiotemporal coverage of monitoring data, we used a semi-supervised approach and graph attention to aggregate many unlabeled spatial units to achieve comprehensive representations of these environments. Subsequently, we constructed a semantic space association graph and established local and global features. Through multistage label propagation, we accounted for changes in spatial unit attributes when predicting flood risks. Applied to the “7.20” Zhengzhou extreme rainstorm event, this approach achieved a micro ROC-AUC of 0.7374 for spatial risk prediction and an accuracy of 0.7888 for temporal risk prediction, proving its effectiveness in identifying risks in data-sparse regions and addressing gaps in flood monitoring.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| 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".