Luminescence-based sensors for measuring oxygen concentration are widely used both in industry and research due to the practical advantages and sensitivity of this type of sensing. The measuring principle is the luminescence quenching by oxygen molecules, which results in a change of the luminescence decay time and intensity. In the standard approach, this change is related to an oxygen concentration using the Stern–Volmer equation. This equation, which in most of the cases is non-linear, is parametrized through device-specific constants. Therefore, to determine these parameters every sensor needs to be precisely calibrated at one or more known concentrations. This work explores an entirely new artificial intelligence approach and demonstrates the feasibility of oxygen sensing through machine learning.
The specifically developed neural networks learns very efficiently to relate the input quantities to the oxygen concentration. The results show a mean deviation of the predicted from the measured concentration of 0.5% air, comparable to many commercial and low-cost sensors.
The approach described in this work demonstrates the applicability of artificial intelligence to sensing technology and paves the road for the next generation of sensors.

References that summarize this work can be found at the end of this page. If you are interested to know more please contact Prof. Dr. Venturini at francesca.venturini(at)

Two highly fluorescent substances (Rhodamine, Coumarin) illuminated by a 395nm UV Light.
The substances emits beautiful colours.

Figure 1: Luminophores used for oxygen sensing illuminated with a 395nm UV light.

The determination of oxygen partial pressure is of great interest in numerous areas including medicine, biotechnology, and chemistry. Since oxygen or better dioxygen, plays an important role in many processes, applications range from biomedical imaging, packaging, environmental monitoring, process control, and chemical industry, to mention only a few.


There are different methods used to determine oxygen concentration depending on the application. Among these, optical methods are particularly attractive because they do not consume oxygen, and are therefore reversible, have a fast response time, and allow a good precision and accuracy. Additionally optical sensors can be manufactured with small sizes, mounted on a fiber and allow therefore both remote and in-situ measurements.


I  Optical Oxygen Sensing with Artificial Intelligence; Michelucci, U.; Baumgartner, M.; Venturini, F. . Sensors 2019, 19, 777.

II  New approach for luminescence sensing based on machine learning; Francesca Venturini, Michael Baumgartner, Umberto Michelucci, Proc. SPIE10937, Optical Data Science II, 109370H (1 March 2019); doi:10.1117/12.2508969

III  Multi-Task Learning for Multi-Dimensional Regression: Application to Lumi- nescence Sensing; Michelucci, U.; Venturini, F. Appl. Sci. 2019, 9, 4748.

IV  Dual oxygen and temperature sensing with single indicator using multi-task- learning neural networksVenturini, F., Michelucci, U. and Baumgartner, M., 2020, April. In Optical Sensing and Detection VI, 11354, p. 113541C. International Society for Optics and Photonics.

V Dual Oxygen and Temperature Luminescence Learning Sensor with Parallel InferenceVenturini, F.; Michelucci U., Baumgartner, M.; Sensors 2020, 20(17), 4886

VI New Autonomous Intelligent Sensor Design Approach for Multiple Parameter InferenceVenturini, F.; Michelucci U.; Engineering Proceedings, ECSA-7 Conference