cumulative_admissionsfev / AutoGluon ↗UK COVID-19 National Epidemiological Surveillance
Multi-series national epidemiological surveillance tracking 4 UK nations at daily cadence over a 28-day forecast horizon to project cumulative hospital admissions, infections, and mortality alongside critical ICU capacity constraints.
Business Objective: UK COVID-19 National Epidemiological Surveillance
01Business Context
National health services (NHS England, Scotland, Wales, and Northern Ireland) operate under centralized resource orchestration, requiring rolling monthly projections for acute care bed allocation, staff surge scheduling, and critical care medication procurement during shifting epidemic waves.
02Analytical Objective
Forecast 28 days ahead for cumulative hospital admissions, cumulative confirmed cases, and cumulative deaths across all 4 devolved nations, utilizing past vaccination rollouts and inpatient bed pressure.
03Economic & Decision Impact
Under-forecasting risks critical care collapse, regional ICU triage, and emergency patient diversion, with severe excess mortality. Over-forecasting leads to unnecessary cancellation of elective surgeries, prolonged diagnostic backlogs, and costly surge capacity stand-by overhead.
Classical autoregressive methods (AutoARIMA, ETS) struggle with the monotonic accumulation and structural phase shifts introduced by successive viral variants and vaccine rollouts. LightGBM with recursive multi-step lags and differenced targets captures non-linear hospital saturation effects effectively, while zero-shot foundation models (Mistral's Timestral, MOIRAI, TimesFM) excel at transferring viral growth dynamics zero-shot across nation-level time series without localized retraining.
Target & Feature Column Definitions
Exhaustive business definitions, measurement units, roles, and target variables across all 16 columns.
| Col | Variable / Feature Name | Role | Type | Unit / Scale | Description & Business Meaning |
|---|---|---|---|---|---|
| C | cumulative_admissionsCumulative Hospital Admissions | TARGET | NUM | patients | Total cumulative count of COVID-19 positive patients admitted to secondary care hospitals |
| D | cumulative_casesCumulative Confirmed Cases | TARGET | NUM | cases | Running aggregate of confirmed positive SARS-CoV-2 PCR and rapid antigen test episodes |
| E | cumulative_deathsCumulative Confirmed Deaths | TARGET | NUM | deaths | Total cumulative deaths occurring within 28 days of a positive laboratory test |
| A | idNation / Region | SERIES ID | CAT | — | Identifier denoting the UK devolved nation (England, Northern Ireland, Scotland, Wales) |
| B | timestampSurveillance Date | TIME | TIME | — | Reporting calendar date for the surveillance metrics |
| F | cumulative_vaccinated_1Cumulative 1st Doses | Feature | NUM | doses | Cumulative total of first vaccine doses administered to the eligible population |
| G | cumulative_vaccinated_2Cumulative 2nd Doses | Feature | NUM | doses | Cumulative total of completed primary 2-dose vaccination courses administered |
| H | cumulative_vaccinated_3Cumulative Booster Doses | Feature | NUM | doses | Cumulative total of third booster vaccinations administered across the nation |
| I | hospital_casesInpatient Hospital Bed Occupancy | Feature | NUM | beds | Daily census of confirmed COVID-19 patients actively occupying general acute hospital beds |
| J | icu_ventilator_occupancyMechanical Ventilation Bed Occupancy | Feature | NUM | beds | Daily midnight census count of confirmed COVID-19 patients on invasive mechanical ventilators |
| K | new_casesDaily Confirmed Cases | Feature | NUM | cases/day | Newly reported positive COVID-19 infections published on the reporting date |
| L | new_deathsDaily Confirmed Deaths | Feature | NUM | deaths/day | Newly certified deaths within 28 days of positive test reported on the surveillance date |
| M | new_admissionsDaily Hospital Admissions | Feature | NUM | patients/day | Number of newly admitted COVID-19 patients across hospital trusts during the 24-hour cycle |
| N | new_vaccinated_1Daily 1st Doses Administered | Feature | NUM | doses/day | Total count of first vaccine doses administered on the given date |
| O | new_vaccinated_2Daily 2nd Doses Administered | Feature | NUM | doses/day | Total count of second course vaccinations completed on the given date |
| P | new_vaccinated_3Daily Booster Doses Administered | Feature | NUM | doses/day | Total count of booster doses injected during the recording window |
Interactive Data Table
Explore rows, feature values, and target labels for UK COVID-19 National Epidemiological Surveillance.
Foundation Models vs Traditional ML & Baselines (41 Methods)
Empirical evaluation directly from the AutoGluon fev benchmark suite evaluating zero-shot foundation models against deep learning, gradient-boosted trees, and statistical baselines across 100 evaluation tasks.
| Rank | Method / Model | Family | Organization | SQL Win Rate?Average win rate (%) against all competing models across the benchmark tasks under Scaled Quantile Loss. | SQL Skill?Normalized skill score relative to the Seasonal Naive baseline (0% = baseline, higher is better). | MASE Win Rate?Average win rate (%) under Mean Absolute Scaled Error. | Latency?Median end-to-end execution time per 100 time series in seconds. | Link |
|---|---|---|---|---|---|---|---|---|
| #1 | Timestral-209M | Foundation Model | Mistral AI | 87.7% | +50.4% | 86.0% | 0.51s | Repo ↗ |
| #2 | Timestral-123M (Carla Engine) | Foundation Model | Mistral AI | 86.8% | +50.2% | 85.0% | 0.32s | Repo ↗ |
| #3 | TimeRSI | Closed-Source API | GaTech & SamayLabs | 84.8% | +51.2% | 83.8% | 2512s | Repo ↗ |
| #4 | t0-gamma | Foundation Model | The Forecasting Company | 84.4% | +49.4% | 81.8% | 4.38s | Repo ↗ |
| #5 | Timestral-28M | Foundation Model | Mistral AI | 79.2% | +48.4% | 77.0% | 0.11s | Repo ↗ |
| #6 | timesfm-3 | Foundation Model | 78.5% | +49.0% | 77.0% | 3.41s | Repo ↗ | |
| #7 | ChakraTS | Baseline | Community | 78.2% | +48.1% | 79.5% | 14.22s | Repo ↗ |
| #8 | Lingjiang2.0 | Baseline | Community | 73.9% | +47.0% | 71.3% | 8.89s | Repo ↗ |
| #9 | Chronos-2 | Foundation Model | AWS | 70.4% | +47.3% | 68.4% | 0.84s | Repo ↗ |
| #10 | timeh2o-v1-tiny | Foundation Model | H2O.ai | 69.9% | +45.5% | 67.0% | 0.19s | Repo ↗ |
| #11 | Timestral-5M | Foundation Model | Mistral AI | 69.0% | +46.2% | 67.7% | 40ms | Repo ↗ |
| #12 | Toto-2.0-2.5B | Baseline | Community | 67.5% | +44.4% | 65.7% | 5.58s | Repo ↗ |
| #13 | t0-beta | Foundation Model | The Forecasting Company | 67.4% | +46.6% | 64.5% | 2.29s | Repo ↗ |
| #14 | Toto-2.0-1B | Baseline | Community | 66.4% | +44.4% | 65.5% | 2.48s | Repo ↗ |
| #15 | TiRex-2 | Foundation Model | NX-AI | 65.8% | +45.5% | 63.4% | 0.27s | Repo ↗ |
| #16 | Toto-2.0-313m | Baseline | Community | 65.1% | +44.2% | 63.5% | 1.06s | Repo ↗ |
| #17 | TiRex | Foundation Model | NX-AI | 58.0% | +42.6% | 54.1% | 0.24s | Repo ↗ |
| #18 | Toto-2.0-22m | Baseline | Community | 57.6% | +42.9% | 56.0% | 0.25s | Repo ↗ |
| #19 | TimesFM-2.5 | Baseline | Community | 54.6% | +42.2% | 53.5% | 1.87s | Repo ↗ |
| #20 | TabPFN-TS-3 | Foundation Model | Prior Labs | 52.4% | +43.1% | 51.3% | 235s | Repo ↗ |
| #21 | TS-ICL | Foundation Model | EDF-Lab | 51.2% | +43.1% | 49.8% | 2.49s | Repo ↗ |
| #22 | FlowState | Foundation Model | IBM | 49.3% | +39.9% | 49.9% | 2.29s | Repo ↗ |
| #23 | citras-fm | Foundation Model | Hitachi | 48.8% | +41.2% | 46.9% | 0.60s | Repo ↗ |
| #24 | Toto-1.0 | Baseline | Community | 47.5% | +40.8% | 45.9% | 22.35s | Repo ↗ |
| #25 | TabPFN-TS | Foundation Model | Prior Labs | 47.3% | +41.5% | 45.4% | 109s | Repo ↗ |
| #26 | Toto-2.0-4m | Baseline | Community | 46.2% | +40.7% | 43.6% | 0.20s | Repo ↗ |
| #27 | Moirai-2.0 | Baseline | Community | 41.9% | +39.3% | 40.5% | 0.35s | Repo ↗ |
| #28 | Chronos-Bolt | Foundation Model | AWS | 41.4% | +38.9% | 39.3% | 0.26s | Repo ↗ |
| #29 | TFT | Deep Learning | — | 31.7% | +32.2% | 29.2% | 829s | Repo ↗ |
| #30 | Stat. Ensemble | Baseline | Community | 27.5% | +20.7% | 30.6% | 147s | Repo ↗ |
| #31 | Sundial-Base | Foundation Model | Tsinghua University | 27.4% | +33.4% | 33.6% | 8.01s | Repo ↗ |
| #32 | PatchTST | Deep Learning | — | 26.8% | +30.1% | 25.1% | 664s | Repo ↗ |
| #33 | DeepAR | Deep Learning | — | 26.1% | +29.1% | 23.6% | 1113s | Repo ↗ |
| #34 | AutoARIMA | Statistical Baseline | — | 23.3% | +21.3% | 21.5% | 20.14s | Repo ↗ |
| #35 | AutoETS | Statistical Baseline | — | 20.3% | -26.8% | 22.5% | 3.48s | Repo ↗ |
| #36 | CatBoost | Tree Ensemble | — | 19.1% | +23.0% | 35.1% | 29.48s | Repo ↗ |
| #37 | LightGBM | Tree Ensemble | — | 17.8% | +21.0% | 33.1% | 3.03s | Repo ↗ |
| #38 | AutoTheta | Statistical Baseline | — | 15.6% | +5.5% | 19.8% | 3.28s | Repo ↗ |
| #39 | Seasonal Naive | Baseline | Community | 10.3% | 0.0% | 11.8% | 0.48s | Repo ↗ |
| #40 | Naive | Statistical Baseline | — | 6.7% | -45.4% | 10.9% | 0.47s | Repo ↗ |
| #41 | Drift | Statistical Baseline | — | 6.1% | -45.8% | 10.0% | 0.45s | Repo ↗ |
Variable Schema & Summary Distributions
Observed numerical ranges, category cardinalities, missing rates, and sample values across 2,944 rows.
| Col | Variable Name | Type | Missing | Distinct | Summary Stats / Distribution | Sample Values |
|---|---|---|---|---|---|---|
| C | cumulative_admissionsTARGET | NUM | 85 (0.02887%) | 2,804 | [1, 624443] μ=90344.3 σ=153916.7 | 58612772054 |
| D | cumulative_casesTARGET | NUM | 0 | 2,879 | [1, 15998983] μ=1161179.3 σ=2648332 | 111 |
| E | cumulative_deathsTARGET | NUM | 84 (0.02853%) | 2,377 | [1, 140392] μ=23632.6 σ=40327.1 | 133 |
| A | id | CAT | 0 | 4 | — | EnglandEnglandEngland |
| B | timestamp | CAT | 0 | 757 | — | 2020-01-30T00:00:002020-01-31T00:00:002020-02-01T00:00:00 |
| F | cumulative_vaccinated_1 | NUM | 1,300 (0.44158%) | 1,627 | [78005, 44233368] μ=10100112 σ=14934186 | 195915120802802254556 |
| G | cumulative_vaccinated_2 | NUM | 1,300 (0.44158%) | 1,630 | [79, 41092656] μ=7607276 σ=12917163 | 374613393925407294 |
| H | cumulative_vaccinated_3 | NUM | 2,386 (0.81046%) | 549 | [4742, 31783652] μ=6072926 σ=9805950 | 86346010166201210379 |
| I | hospital_cases | NUM | 107 (0.03635%) | 1,620 | [11, 34336] μ=2380.7 σ=4901.0 | 158021522670 |
| J | icu_ventilator_occupancy | NUM | 133 (0.04518%) | 633 | [0, 3736] μ=241.8 σ=547.9 | 149417881950 |
| K | new_cases | NUM | 0 | 1,970 | [0, 234758] μ=6387.5 σ=17609.6 | 100 |
| L | new_deaths | NUM | 84 (0.02853%) | 346 | [0, 1249] μ=56.4 σ=149.7 | 120 |
| M | new_admissions | NUM | 85 (0.02887%) | 661 | [0, 4134] μ=256.0 σ=542.7 | 586691777 |
| N | new_vaccinated_1 | NUM | 1,304 (0.44293%) | 1,528 | [0, 686424] μ=30703.4 σ=74078.7 | 121129174276239815 |
| O | new_vaccinated_2 | NUM | 1,304 (0.44293%) | 1,519 | [0, 508013] μ=29611.5 σ=70442.3 | 19312133698362 |
| P | new_vaccinated_3 | NUM | 2,390 (0.81182%) | 545 | [0, 830403] μ=66206.5 σ=127887.9 | 15316019375988233 |
Frequently Asked Questions: UK COVID-19 National Epidemiological Surveillance
Common questions regarding the UK COVID-19 National Epidemiological Surveillance dataset, machine learning task formulations, and in-browser tabular inference.
What is the forecasting horizon for the UK COVID-19 surveillance benchmark?
The dataset evaluates a 28-day (4-week) rolling forward forecast horizon, matching the monthly clinical capacity and staffing roster cycles utilized by NHS operational planning boards.
Can I run zero-server forecasts on this dataset in Google Sheets?
Yes, Carla enables zero-server in-context time series forecasting directly in spreadsheets using Mistral's Timestral foundation model without moving patient telemetry off your local workspace.
Which models perform best on UK COVID-19 nation-level forecasting?
Zero-shot foundation models such as Mistral's Timestral and MOIRAI demonstrate superior generalization over shifting epidemiological regimes compared to classical ARIMA and GBDT lag pipelines.
Test TabICLv2 on UK COVID-19 National Epidemiological Surveillance Yourself
Open the pre-loaded Google Sheet and let Carla configure the target and task for local, zero-cloud tabular machine learning.
Launch Carla
Click once to open the spreadsheet and Carla side panel together.
Review the Setup
Carla selects the dataset target and task from this page automatically.
Evaluate & Predict
Run predictions and compute metrics with zero server uploads.
Provenance & Attribution
UK Health Security Agency (2022). Official UK Coronavirus (COVID-19) Disease Surveillance Dashboard. UK Government.