MERGING OF HETEROGENEOUS DATA FOR EMERGENCY MAPPING: DATA INTEGRATION OR DATA FUSION?
Bibliographic record
Abstract
Many terms are used to name and define these data operations: “fusion ” and “integration ” of geospatial data or “integration (or fusion) of digital images and geospatial information”, as well as “revision (or updating) of geospatial (or topographic) information (or data bases). The present paper will try first to delimitate the use of these terms in the context of the research work done for the CIT-O (Centre for Topographic information – Ottawa, Natural Resources Canada). In an emergency situation the authorities in charge of mapping support will face two major challenges: 1) to deliver ‘immediately ’ up-to-date existing topographical information showing the situation before the emergency occurs (position of existing roads, bridges, community facilities, strategic buildings, etc.); 2) to get as quick as possible digital images from the disaster area in order to understand and monitor the situation, to evaluate the damages and the risk for injuries or more damages and to support the rescue operations. To meet these challenges there is a need to deal with a range of heterogeneous geodata consisting for example of various sources, geometries, scales, resolutions, types, accuracies and dates. In an emergency mapping situation, the choice of data sources to be integrated / fused could be limited and the user can be forced to use data and images with a resolution outside the normal limits. The present work evaluates the fusion of images with a significant difference in spatial resolution in the typical framework of an emergency mapping project. It also investigates the fusion possibilities of the various data with respect to their enhancement of feature interpretation and extraction as well as the integration of imagery with existing topographic data. Relations and criteria are
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 | 0.017 | 0.023 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.005 | 0.011 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.007 | 0.016 |
| Open science | 0.003 | 0.008 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".