Projects / Programmes source: ARIS

Method for the forecasting of local radiological pollution of atmosphere using Gaussian process models

Research activity

Code Science Field Subfield
2.06.02  Engineering sciences and technologies  Systems and cybernetics  System theory and control systems 

Code Science Field
T125  Technological sciences  Automation, robotics, control engineering 

Code Science Field
2.02  Engineering and Technology  Electrical engineering, Electronic engineering, Information engineering 
Nonlinear dynamical system modelling, system identification, radiological air pollution, prediction of signal values
Evaluation (rules)
source: COBISS
Researchers (10)
no. Code Name and surname Research area Role Period No. of publicationsNo. of publications
1.  11773  PhD Marija Zlata Božnar  Physics  Researcher  2017 - 2020  271 
2.  34686  PhD Irina Elena Cristea  Mathematics  Researcher  2018 - 2020  152 
3.  27664  PhD Boštjan Grašič  Physics  Researcher  2017 - 2020  175 
4.  05807  PhD Nadja Hvala  Systems and cybernetics  Researcher  2017 - 2020  208 
5.  08351  PhD Vladimir Jovan  Systems and cybernetics  Researcher  2017 - 2020  381 
6.  10598  PhD Juš Kocijan  Systems and cybernetics  Head  2017 - 2020  450 
7.  38788  PhD Sergey Kryzhevich  Mathematics  Researcher  2017  36 
8.  04290  PhD Primož Mlakar  Physics  Researcher  2017 - 2020  268 
9.  29924  PhD Matija Perne  Systems and cybernetics  Researcher  2017 - 2020  131 
10.  36713  Martin Stepančič  Computer science and informatics  Technical associate  2017 - 2020  21 
Organisations (3)
no. Code Research organisation City Registration number No. of publicationsNo. of publications
1.  0106  Jožef Stefan Institute  Ljubljana  5051606000  90,590 
2.  1540  University of Nova Gorica  Nova Gorica  5920884000  14,053 
3.  2574  MEIS environmental cosulting d.o.o.  Šmarje - Sap  2271478  304 
The accidents in Chernobyl and Fukushima have shown that the dispersion of radioactive air pollution in the air is the critical way for this kind of danger to reach masses of inhabitants. Consequently, a method for pollution-dispersion modelling is proposed in the project proposal that will show the dispersion a day or two ahead. With this model the efficiency of the population safety measures will be significantly improved. The modelling will be based on Gaussian processes (GPs). The model based on the GP is a probabilistic and non-parametric model based on Bayes’ theorem on probability. It differs from other methods of identification based on a black box, because in the process of modelling, we do not optimize the parameters of the preselected basic functions but we are looking for links between the measured data. At the output of the models based on the GP, the prediction is obtained in the form of normal distribution, which may be expressed by its mean value and variance. The method of modelling based on the GP is particularly suitable for complex nonlinear processes, which are defined with uncertain and missing data. The meteorological state of the atmosphere is such a complex process.  To ensure the correct action in case of a nuclear accident, we need a good prediction about where the radioactive cloud would move to. In this modelling, many important steps have already been sufficiently scientifically solved. The prediction of input signals about the atmospheric variables, which are of key importance for the dispersion, is, however, still an open question. Instead of local predictions and the simultaneous improvement of the radionuclides’ concentration value this project is focused on meteorological dynamics in the assigned 3D space.  The objective of this research is to make signals' predictions that significantly improve the 3D description of the atmosphere dynamics in the vicinity of the nuclear power plant over the existing forecasting models. Consequently, a better forecast of the radionuclides' concentration in the atmosphere as a consequence of an accident with the atmospheric release will be enabled.  Since meteorological measuring stations are required in the surroundings of the nuclear plants, there are a number of measurements available. These stations describe the historical development of the weather. All this information, contained in the measurements of the history of signals, can be used for modelling and predictions of their future values. We estimate that models for precise predictions of target signals can be built with GP-based methods from the history of measurements and meteorological predictions (made by numerical weather prediction models) which will sufficiently describe the 3D condition of the atmosphere in the future, so that the appropriate air pollution dispersion model will reliably and sufficiently forecast the development of air pollution dispersion. Such forecasts of the dispersion of the radionuclide concentrations in the air are of key importance for the timely, appropriate and effective protection of the inhabitants.   We expect that the advanced GP methods will significantly improve the predictions, since they have also been very successful in the related field of modelling ozone in the atmosphere. We expect that the GP-model-based identification methodology will be improved for problems where large amounts of data, signals’ periodicity and spatio-temporal modelling appear. The dynamic-system identification problem is tackled as a fusion of signals from heterogeneous data sources into the targeted prediction. A guarantee for the stability of the developed models plays an important role. The proposed method for the dispersion forecast of the radionuclide-polluted cloud based on meteorological variables is an important novelty for the assurance of safety in the case of a nuclear accident. This was confirmed by the International Atomic Energy Agency IAEA, which included
Significance for science
Methods based on the GP for predicting signal values describing meteorological variables will be a very important data-fusion method in the modelling of weather conditions and elsewhere. Our method for improving forecasts of the potential dispersion of air pollutants on the basis of predictions of meteorological variables and using the available historical databases is an innovation in the field and, as such, will be very important.   In addition to the above, the proposed project would introduce GP-based modelling in a completely new research and professional field. The following results are expected in the development of signal fusion for the prediction of meteorological variables using GP models: - evaluation of GP model identification methodology for a new scientific domain; - improvement of existing methodology for identifying regular and online GP models for problems with very large amounts of data and periodical signals and problems with spatio-temporal modelling; - evaluation of alternative GP-based modelling methods for the above problems; - a method of analysis for determining the stability of dynamic GP models. Each of these results constitutes an important step forward in the modelling of dynamic systems, which forms the basis and a very important part of systems theory.
Significance for the country
The improved and localized forecasts enable greatly improved protection of inhabitants in exceptional safety situations on a global level. The impact of nuclear power plants as inevitable energy source in the case of accidents reaches beyond the borders. We should also not forget about terrorist threats, which are seriously discussed at the level of the International Atomic Energy Agency (IAEA) and its MODARIA programme.   Since MEIS researchers participate in the IAEA MODARIA programme, we will be able to communicate the results of this project directly to the interested scientific and professional public responsible for the effective protection of the population in the event of a nuclear power plant accident. The Chernobyl and the Fukushima accidents have also shown that there are key deficiencies in this segment.   The IAEA uses the reports from the MODARIA as a basis to prepare technical guidance for the entire world. In the long-term, we expect the findings of the proposed project to be implemented in engineering recommendations for everyday use in nuclear power plants (TECDOC series). This makes the presentation of the results in the MODARIA II project important for the long term and enables the application of the best scientific achievements in the assurance of radiological protection. The findings of this project and the practical application of its results will be of exceptional importance for the Krško Nuclear Power Plant, which has endorsed the project. Nuclear power plants must maintain a system for assessing the potential impact of any accidental emissions into the atmosphere, but the actual systems are still often quite rigid. The Slovenian nuclear power plant is very advanced in this respect, taking first place in the overall assessment at the EU level after the accident in Fukushima. The localized and improved forecasts of relative concentration, which will be one of the key practically applied results of this project, will significantly further improve its level in this segment. By means of regular international inspections, we will spread awareness of the new system worldwide as an example of good practice (similarly to the environmental system, which was recognized as an example of good practice in the OSART inspection). To MEIS, this project represents a means and opportunity to significantly expand its activity in the field of radiological protection. We have done work in the past for Chernobyl and we hope to expand to other markets. Due to the complexity of the subject, this science project will be essential in achieving new levels of development.   The project as such and the results applied in a test environment for the Krško Nuclear Power Plant will constitute an exceptional reference for MEIS in its activities both in the market and in international organizations.
Most important scientific results Interim report, final report
Most important socioeconomically and culturally relevant results Interim report, final report
Views history