In ULISSES we are developing data-driven calibration algorithms for autonomous CO2 sensor calibration. This has been done by developing an approach where a Hidden Markov model (HMM) is used to predict on a calibration coefficient to compensate for remaining dependencies of environmental impacts such as temperature on the sensor measurement output. The HMM model is learned from the past sensor data in an unsupervised way using the expectation maximization algorithm. For such an approach, convergence and sample complexity are critical factors.

In ULISSES we are developing networked data-driven calibration algorithms for autonomous CO2 sensor calibration. In a network each sensor has an own belief on the measurement. Sensors that have been recently calibrated using a reference might have a better calibrated sensor model than other sensors that have not been calibrated for long time and their model has become outdated. The idea of networked calibration approaches is to fuse the beliefs of individual sensors and use this fused belief to update the own sensor model.

In ULISSES we are actively researching its use for photodetectors. Its main strength is that, in contrast to many other materials, it can be synthesized at a relatively low temperature compatible to common CMOS processing, without strict substrate requirements. We have studied the nanocrystalline nature of the material to better understand how it influences its properties and to provide insights for tailoring the material properties as desired.

One thing that has become clear in the last decade of graphene research is that it is necessary to protect the surface of graphene from external contaminants, to preserve its exceptional electronic properties and be able to exploit them into novel devices. The depositions of dielectric materials on top of graphene is therefore an essential step of manufacturing graphene-based electronic and photonic devices.

Platinum atomic layer deposition and thermal assisted conversion are combined to conformally and selectively coat structured substrates with layered PtSe2.

Gas sensors are an essential component for a broad range of applications, for example in the medical and diagnostic fields, indoor and outdoor air quality monitoring systems, environmental studies, and the automotive industry. They are gaining importance as the desire for rapid detection of toxic or organic gases is growing among the population.

ULISSES project played a big role in the discovering of a new technique for integrating 2D materials into semiconductors, a revolutionary technique, with huge potential for providing devices with much smaller size and extended functionalities with respect to what can be achieved with today’s silicon technologies.

The ULISSES project has developed a set of carbon dioxide loggers equipped with GPS. The purpose is to already now explore the potential of future systems, and to prepare for the big data challenges we will experience with real-time air quality data.