Project

Design of an advanced digital solution to improve the energy efficiency and indoor environmental quality of buildings, combining outdoor, indoor and occupancy data through artificial intelligence and digital twins.

InOut is an industrial research project (Phase I) addressing one of the main challenges in the building sector: high energy consumption and poor indoor air quality in public-use buildings. The project develops an experimental platform based on Digital Twins capable of dynamically simulating and optimising ventilation and HVAC systems, integrating multi-source data from outdoor air quality (Lobelia.Air), indoor environmental sensors (IEQ), occupancy data (DDS) and predictive models based on artificial intelligence developed by Intemic.

This solution enables the integrated optimization of energy efficiency and users’ health and wellbeing, reducing energy consumption, CO₂ emissions and indoor pollution, while increasing comfort and environmental quality in public spaces. The project contributes to the transition towards smarter, more sustainable and resilient buildings, minimising environmental impact and improving quality of life.

InOut develops a digital solution that integrates sensors, data analytics and artificial intelligence to optimize ventilation and HVAC systems in public buildings. The goal is to reduce energy consumption, improve indoor air quality, and enhance user comfort.

In Phase I, the project researches and prototypes technologies such as a digital twin, predictive algorithms, and an environmental management platform.

In Phase II, these solutions are deployed in real buildings, operational decisions are automated, and the energy and environmental impact is evaluated to scale the technology.

The project will deliver an advanced digital solution designed to optimise energy efficiency, indoor air quality and user comfort in public buildings. As a result, a system will be developed that can monitor environmental and occupancy data in real time, supported by a central data infrastructure prepared for analysis and modelling. An operational digital twin will also be created to simulate building behaviour and validate ventilation and HVAC strategies before they are implemented.

In addition, predictive models based on artificial intelligence will be developed to anticipate operational needs and help reduce energy consumption while maintaining user comfort. The solution will be validated both in simulated environments and in pilot buildings, ensuring its technical reliability. Finally, the project will produce a digital platform for visualisation and management with key indicators, along with technical documentation, a roadmap for scaling the solution, and a communication plan to disseminate results and support its adoption.