An early-warning system against heat and cold. Pick any point in Spain, a day and an hour, and you'll know your cardiovascular risk level: safe, caution or danger. It combines official weather data with real mortality, a calibrated model ensemble and your personal factors — age, health, medication, activity — to tell you the risk you run, not the average. Live forecast from Open-Meteo.
deaths attributable to heat in Spain. 57% occurred in August and 84% were people over 74. The second deadliest summer on record — and the hottest since 1961 (AEMET).
deaths attributable to heat: 18% above 2022's record (4,789) and 48% ahead of 2025's total (3,832). The season doesn't close until Sep 30.
Since 2015, high temperatures have claimed more than 33,000 lives in Spain. Not headlines: excess mortality estimated over civil registries by the MoMo system (Instituto de Salud Carlos III).
Heat doesn't warn twice — and with climate change, every summer will be hotter and deadlier than the last.
Plan shifts and outdoor work with province-and-hour risk before every shift starts.
Sports, festivals, open-air weddings: decide schedules, shade and medical staffing in advance.
Anticipate care demand and position resources before the peak, not during it.
Your personalized cardiovascular risk anywhere in Spain, on the day and hour you choose.
Care homes, day centres and families with elderly: early warnings when a day's risk matters.
Trigger local heat plans with province-level risk levels, not generic alerts.
ERA5 and AEMET for weather; MoMo (Instituto de Salud Carlos III) as the target. Public, verifiable sources — nothing opaque.
Real-time forecast from Open-Meteo: the risk is computed with today's and the coming hours' weather, not yesterday's. Refreshable every hour.
XGBoost for heat, RandomForest for cold, an LSTM with province embedding and a deterministic formula. All the models are explainable and the final decision is an ensemble of the four:
Conformal prediction provides confidence levels: the system warns with the calm of someone who knows what it doesn't know.
Age, sex, comorbidities, medication, acclimatisation and activity adjust your risk, not a population average.
The multipliers that adjust your risk (age, comorbidities, medication, acclimatisation...) come from published, peer-reviewed epidemiology papers, with their ranges and limits documented — not from opinion.
Date-based splits, leakage control and honest published metrics. What can be checked, is checked.
Want the details? Everything is in the technical docs.
All built for the ANFAIA Summer Grants 2026, with support from CESGA, and generated from the dskit template. Architecture and evaluation detail lives in the technical docs.