The web-enabled awareness research network (WARN) project early earthquake and tsunami warning at Ocean Networks Canada
Bibliographic record
Abstract
The Web-enabled Awareness Research Network project (WARN) implements the data acquisition, event detection and correlation aspects of an integrated geo-hazard alert system. Among its innovative aspects, it enables a rapid integration of real or simulated data with research and operational models of tsunami and earthquake impacts prediction. The intent of the project is to lead to the delivery of early warning to urban areas, coastal communities and key infrastructure operators. Figure 1 provides the overview of a generic alert system toplevel architecture and situates WARN in this context. WARN relies on the existence of sensors installed both underwater and on land. Warn also relies on data acquisition performed by Ocean Networks Canada's Oceans 2.0 data management system. Event detection/correlation are the key parts of WARN. The Ocean Networks Canada (ONC) infrastructure, consisting among other assets of the NEPTUNE and VENUS observatories around Vancouver Island in British Columbia is host to the various sensors required to perform the detections. The sensors include, but are not limited to, accelerometers (installed off- and on-shore), coastal radars to detect incoming near-field tsunami waves, bottom pressure recorders and other underwater pressure sensors to complete the network. This infrastructure can be expanded geographically both on land and WARN takes the quasi real-time data sources and performs on-the-fly identification and filtering of telltale signs of earthquakes and tsunamis in each individual data stream. The individual detections are subsequently matched against those obtained from different sensors during a constrained time window. This coordination of events avoids false positives and allows for the calculation of an epicentre and of a magnitude assessment in the case of an earthquake; or of a direction, speed and amplitude in the case of a tsunami. WARN's specification is to perform all detections and confirmation calculations within 2 seconds for earthquake and 2 minutes for tsunamis. Running impact assessment models is not in WARN's scope. Impact assessments are the subject of other projects in and outside of ONC. Those models are however the primary consumers of confirmed events as detected by WARN. The models use WARN's event notifications as triggers to quickly look up databases of pre-calculated impacts scenarios and notify authorities of the predicted impact. Notification of detected events are transmitted in the XML-based “Common Alerting Protocol” (CAP) format (see www.oasis-open.org/standards#capv1.2). This data payload structure (adapted to Canada's standard CAP-CP) is transmitted following a publisher-subscriber model. This project is supported in full by CANARIE Inc. (www.canarie.ca), through its Network-Enabled Platform program.
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 distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.004 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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 teacher head, 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".