Markov Chain transition probability modeling of radon gas records and future projection possibility determination

Markov Chain models serve two purposes firstly, subdivide the main data based on the mean value and one and two standard deviation plus and minus values around the mean value. The second stage of modeling, after calculating the transition probabilities between these categories from the available data, is completed by repeatedly multiplying the categorization date groups until the steady-state transition probability values are obtained. This procedure provides a convenient modeling approach for radon gas transient measurement records. After a brief presentation of Markov Chain procedure in this paper, the application is carried out by considering five categories that lead to a better transition probability matrix. Such a matrix provides information about the probabilities of future transition at the radon data measuring station. In addition, it is possible to associate these transition probabilities with the possibility of an earthquake.

Automated summary

Markov Chain models are used to subdivide data based on mean value and standard deviations. The transition probabilities between these categories are calculated, and the procedure is repeated until steady-state transition probability values are obtained. This modeling approach is convenient for radon gas transient measurement records.