Deep Tech for Climate Adaptation

Protecting people from extreme heat

We predict dangerous heat exposure before it happens—giving individuals, workers, and cities the time to act and save lives.

Made in Luxembourg
EIC Deep Tech
Climate Adaptation
9:41
Good morning, Maria
Current Risk Level
LOW
Est. core temp: 36.8°C
Heart Rate
72 bpm
Outside
28°C
☀️
Safe until 2pm
Risk increases after 2pm today
489K
Annual deaths from heat globally
62,775
Deaths in Europe in 2024
30 min
Early warning saves lives
80%→0%
Mortality when detected early

How we protect different people

From elderly individuals to construction workers to entire cities—our technology adapts to every use case.

👵

Maria, 72, has hypertension

Maria lives alone in Lisbon. On a 38°C day, her smartwatch detects rising heart rate and skin temperature. PHDZN alerts her 25 minutes before danger—she rests indoors with water. Her daughter receives a "Maria is safe" notification.

Heat emergency prevented
👷

João, 35, construction worker

João works on a building site in Porto. At 11am, his employer's PHDZN dashboard flags him as "approaching risk." His supervisor rotates him to indoor tasks. João avoids heat exhaustion and stays productive.

Zero lost work days
🏛️

Dr. Costa, city health official

Lisbon's heat dashboard shows 847 heat stress incidents at one intersection last month—92% elderly. Dr. Costa requests shade structures. Next summer, incidents drop 73%. She has proof for the budget committee.

Evidence-based policy
🏭

Miguel, factory manager

Miguel's automotive plant runs UPTOE. The system predicts Zone B will exceed safe temperature in 45 minutes. It automatically increases cooling and suggests moving 5 workers to Zone C. Production continues without interruption.

12% productivity increase

A day in the life with MetaEnterprise

Follow real users through their day and see exactly how our technology protects them.

👵
Maria Santos
Retired teacher, 72 years old
Lisbon, Portugal
Hypertension, takes medication
Lives alone, daughter in Porto
Wears Apple Watch daily
1
7:30 AM
Morning check
Maria opens PHDZN and sees today's forecast: "Safe until 2pm, HIGH risk 2-5pm." She plans to do her grocery shopping in the morning.
Plans day around heat risk
2
10:15 AM
Walking to market
Her watch syncs heart rate (78 bpm) and skin temperature to PHDZN. The app shows "LOW risk" with an estimated core temperature of 36.9°C. She walks confidently.
3
2:45 PM
Unexpected errand
Maria needs to visit the pharmacy. Before leaving, she checks PHDZN: "MODERATE risk now. Est. core temp: 37.4°C rising." The app suggests waiting until 5pm or shows the nearest air-conditioned pharmacy.
Early warning received
4
3:30 PM
Risk escalation
Maria decided to go anyway. Walking back, her watch vibrates: "Your risk is HIGH. Core temp approaching 37.8°C. Find shade and hydrate now." The app shows a shaded bench 50m away.
Alert triggered before danger
5
3:45 PM
Recovery confirmed
Maria rests on the bench, drinks water. After 15 minutes, PHDZN shows her estimated core temp dropping to 37.2°C. "You're recovering. Safe to continue in 10 minutes."
Crisis averted
6
8:00 PM
Daily summary
Maria receives her evening summary: "Today you spent 23 minutes in HIGH risk. 1 alert received. You responded correctly. Tomorrow: similar conditions expected."
Meanwhile in Porto...
Daughter stays informed
Ana, Maria's daughter, has the caregiver view. She received a notification at 3:30pm: "Maria's risk elevated" and another at 3:50pm: "Maria recovered, all clear." She didn't need to call—but she could have with one tap.
Family peace of mind
👷
João Ferreira
Construction worker, 35 years old
Porto, Portugal
Works for BuildCorp Construction
Outdoor work 8+ hours/day
Healthy, but high exertion work
1
6:45 AM
Shift start check-in
João clocks in and his company-provided wearable syncs to PHDZN. The supervisor's dashboard shows all 25 workers as "GREEN." Today's site forecast: HIGH risk 11am-4pm.
2
10:30 AM
Automated hydration reminder
João's watch buzzes: "You've been in sun for 2 hours. Drink 500ml water now." He's been busy and forgot. Quick water break at the station.
Proactive care
3
11:45 AM
Risk elevation detected
João's heart rate is elevated and HRV is dropping. PHDZN moves him from GREEN to YELLOW on the supervisor's dashboard. His estimated core temp: 37.6°C and rising.
Early detection
4
11:50 AM
Supervisor intervention
Supervisor Carlos sees the alert on his tablet. He radios João: "Take your break now, rotate to indoor rebar work after." João gets 20 minutes in shade before anyone feels unwell.
Crisis prevented
5
5:00 PM
Shift complete
End of day: João completed a full shift with zero heat incidents. PHDZN logs his exposure for compliance records. BuildCorp's monthly report shows 100% heat safety compliance.
Employer benefit
BuildCorp has reduced heat-related incidents by 89% since deploying PHDZN. Workers comp claims down, productivity up, and they easily pass safety audits with automated compliance reporting.
89% fewer incidents
👩
Ana Santos
Marketing manager, 45 years old
Porto, Portugal
Mother (Maria, 72) lives in Lisbon
Works full-time, can't check in constantly
Worries about mom during heatwaves
1
Setup
Connected to mom's account
Maria invited Ana as a caregiver. Ana's PHDZN app shows a "Family" tab with Maria's status. She chose to receive alerts only for MODERATE risk or higher—not every small fluctuation.
2
9:00 AM
Quick morning check
Ana glances at her phone while getting coffee. Family tab shows: "Maria: LOW risk, 36.8°C, at home." Green checkmark. No action needed. She heads to her meeting.
Peace of mind in 2 seconds
3
3:32 PM
Alert received
Ana's phone buzzes during a meeting: "Maria's risk is HIGH (37.7°C). She was walking outside and has been notified to rest." Ana can see Maria received the alert.
Notified automatically
4
3:35 PM
Monitoring remotely
Ana watches Maria's status from her phone. She sees Maria has stopped moving (resting). One-tap option to call—but she waits. No need to interrupt her mother if she's handling it.
5
3:51 PM
All clear notification
"Maria has recovered. Risk level: MODERATE and falling." Ana breathes easier and goes back to work. She'll call mom tonight for their regular chat—not out of worry, but out of love.
Relationship preserved
The real benefit
Ana used to call Maria 3-4 times on hot days, interrupting both their lives. Now she checks the app in seconds. Maria maintains her independence. Ana maintains her sanity. Everyone's happier.
Independence + safety
🏛️
Dr. Sofia Costa
Public Health Director, Lisbon Municipality
Lisbon, Portugal
Responsible for 500K+ residents
€2M annual heat mitigation budget
Needs evidence for budget approval
1
The problem
Heat deaths increasing, but where?
Lisbon had 1,247 excess deaths during last summer's heatwave. The city council wants action, but Dr. Costa can't justify spending €2M on trees and shade structures without knowing WHERE they'll have the most impact.
2
Year 1
Deploy PHDZN citywide
Lisbon partners with PHDZN. 15,000 residents (mostly elderly) download the app. Over the summer, anonymized data reveals exactly which streets, intersections, and times have the most heat stress incidents.
Data collection begins
3
September
Shocking discovery
The city dashboard shows: Rua Augusta near Rossio had 847 heat stress incidents—92% were elderly. The adjacent shaded street: only 12 incidents. One intersection is 70x more dangerous than another 50m away.
Hidden danger zones revealed
4
Budget meeting
Evidence-based proposal
Dr. Costa presents: "Here are the 12 most dangerous locations in Lisbon, ranked by actual incidents. Here's what interventions will cost. Here's projected impact." The council approves €1.8M for targeted shade structures and trees.
Budget approved with data
5
Year 2
Before/after measurement
Shade structures installed at Rua Augusta. Next summer, PHDZN data shows: incidents at that intersection dropped from 847 to 228—a 73% reduction. Average core temp increase walking through: down from +0.8°C to +0.3°C.
73% reduction proven
The flywheel effect
Dr. Costa's success attracts €5M in EU climate adaptation funding. PHDZN's AI now recommends: "Trees at intersections = 3x more effective than mid-block. North-side shade on east-west streets = 2x better than south-side." Other cities want in.
Lisbon becomes a model
🏭
Miguel Almeida
Plant Manager, AutoParts Manufacturing
Setúbal, Portugal
150 workers, 20 robots
Multiple heat zones (welding, paint, assembly)
Cooling = 35% of energy costs
1
6:00 AM
Morning dashboard check
Miguel opens UPTOE. The digital twin shows the entire plant: all zones green, all 150 workers checked in, 18 of 20 robots online. Today's prediction: Zone B (welding) will hit thermal limits by 11am unless action taken.
45-minute advance warning
2
10:15 AM
Predictive alert
UPTOE: "Zone B will exceed 34°C in 45 minutes at current production rate. Recommended actions: (1) Increase HVAC in Zone B by 20%, (2) Move 5 workers to Zone C, (3) Assign high-heat task to Robot 7 instead of Worker 23."
3
10:20 AM
One-click optimization
Miguel approves UPTOE's recommendations. The system automatically adjusts HVAC, sends rotation notifications to supervisors, and re-assigns the welding task to Robot 7. Workers never hit dangerous conditions.
Human-robot task balancing
4
2:30 PM
Robot thermal management
Robot 12's thermal sensors show it approaching throttle temperature. UPTOE automatically reduces its duty cycle and redistributes work to cooler robots. Production continues at 98% capacity instead of stopping.
5
6:00 PM
Shift report
End of day: Zero heat incidents. Zero production stops. UPTOE's Pareto dashboard shows today's tradeoffs: "Spent €340 extra on cooling, gained €2,100 in avoided downtime and productivity. Net benefit: €1,760."
12% productivity gain
Monthly summary
This month: 0 heat-related incidents (down from 7 last year). 15% reduction in cooling costs through optimization. 12% productivity increase. OSHA compliance report auto-generated. Insurance premium reduced 8%.
Complete ROI visibility

From wearable to warning in seconds

Wearable syncs data

Heart rate, HRV, skin temperature from any compatible smartwatch

🧠

AI predicts risk

Algorithms estimate core temperature 15-60 minutes ahead

⚠️

Alert if needed

User, caregiver, or supervisor notified before danger

📍

Guide to safety

Show nearest cooling, recommend actions, confirm recovery

The AI technology that makes it possible

Our platform combines multiple advanced technologies to predict heat stress before it becomes dangerous—a capability that didn't exist until now.

🧠
Core Innovation

Predictive Thermal AI

Our proprietary algorithm estimates core body temperature from wearable sensor data (heart rate, HRV, skin temperature) combined with environmental conditions. Using Kalman filtering and physiological modeling, we predict dangerous heat stress 15-60 minutes before it occurs—enough time to take preventive action.

38°C Critical threshold detection
15-60 min Advance warning time
<0.3°C Prediction accuracy
🏭

Multi-Asset Digital Twin

A real-time 3D thermal model of facilities that simultaneously tracks humans, robots, servers, and HVAC systems. The first platform to treat all thermal assets as one unified optimization problem.

⚖️

Pareto Optimization Engine

Multi-objective optimization that balances competing goals: worker safety, robot efficiency, energy costs, and productivity. Finds the optimal tradeoff in real-time.

🤖

Human-Robot Task Allocation

Intelligent workload distribution that assigns heat-intensive tasks to robots and moves humans to cooler zones—automatically, based on real-time thermal conditions.

🔗

Federated Learning

Privacy-preserving AI that learns across facilities and users without sharing raw data. The system gets smarter with every deployment while protecting individual privacy.

🗺️

Collective Heat Intelligence

Anonymized, aggregated data from thousands of users reveals hidden urban heat danger zones. The first system that can prove which city interventions actually work.

📡

Universal Wearable Integration

Works with existing smartwatches—Apple Watch, Fitbit, Samsung, Garmin—through HealthKit and Health Connect APIs. No proprietary hardware required.

EIC Accelerator Challenge

Deep Tech for Climate Adaptation

MetaEnterprise directly addresses the EIC's priority of "Combating extreme heat in urban environments"—developing climate-neutral solutions that address urban heat island effects through AI-powered monitoring, predictive analytics, and evidence-based urban cooling strategies.

Deep Tech: Predictive thermal AI, digital twins, federated learning
Key Enabling Technologies: AI/ML, IoT sensors, cloud computing
Climate Impact: Personal protection + city-level intelligence
EU Mission Alignment: Climate Adaptation Mission network

One integrated ecosystem

B2C + B2G

PHDZN

Personal Heat Danger Zone Navigator

Who it's for
👵 Elderly 👷 Workers 👨‍👩‍👧 Families 🏛️ Cities
Personal heat risk prediction from wearables
Alerts before reaching dangerous temperature
Caregiver monitoring for peace of mind
City heat mapping and intervention analytics
B2B Industrial

UPTOE

Unified Productive Time Optimization Engine

Who it's for
🏭 Factories 📦 Warehouses 🖥️ Data Centers 🏗️ Construction
Digital twin of facility with thermal overlay
Predictive alerts 15-60 minutes ahead
Human + robot + HVAC unified optimization
Compliance reporting and ROI tracking

Measurable outcomes

80→0%
Mortality reduction
When heat stress is detected and treated within 30 minutes
73%
Fewer heat incidents
At locations where data-driven interventions were installed
12%
Productivity increase
Through optimized worker rotation and HVAC management

Ready to protect your people from extreme heat?

Whether you're a city, employer, or healthcare provider—let's discuss how MetaEnterprise can help.