A MULTI-LAYER DELTA LAKEHOUSE FOR EPIDEMIOLOGICAL MONITORING AND FORECASTING UNDER EMERGENCIES
Bibliographic record
Abstract
Public health emergencies demand fast, dependable analytics that combine real-time signals with trustworthy historical data. Open, interoperable platforms that support streaming and batch workflows can shorten the time from detection to action while preserving data quality and auditability. Aim: To design and justify an information system architecture for analyzing epidemic threats under emergency conditions that is scalable, reliable, and fit for integration with clinical and non-traditional data sources. Methods: We conducted a structured review of three data analytics architectures (Lambda, Kappa, Delta) and mapped their strengths and limits to crisis surveillance needs. Based on functional and non-functional requirements, we specified a Delta Lake–based lakehouse with bronze-silver-gold tiers, unified batch/stream ingestion with Spark Structured Streaming, ACID tables with time travel and schema control, and an analytics layer that supports forecasting with MLOps for monitoring, drift checks, retraining, and lineage. Results: The proposed architecture meets core emergency needs for timeliness, integrity, and reproducibility through ACID transactions, versioned datasets, and curated tiers; supports standards-based interoperability and the inclusion of wastewater, mobility, and other environmental feeds; provides a single code path for batch and streaming to reduce reconciliation burden; and sets operational guardrails for latency versus cost when running many near-real-time tables. We outline practical considerations for quality checks in the silver tier, promotion rules to gold, and model governance. Conclusions: A Delta-based lakehouse offers a clear path to an emergency-ready surveillance platform that scales with data growth, integrates heterogeneous sources, and supports reliable forecasting. The next steps are a pilot deployment with public health partners, live latency and cost measurements, and prospective validation of forecasting and alerting in real-world settings.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".