TY - JOUR

T1 - Stochastic Model of Conditional Non-stationary Time Series of the Wind Chill Index in West Siberia

AU - Kargapolova, Nina

AU - Ogorodnikov, Vasily

N1 - Funding Information: Conditional model of the wind chill index with point conditions was developed and studied under state contract with ICMMG SB RAS (0251-2021-0002); development of the model with interval conditions was partly financially supported by the Russian Foundation for Basic Research (grant No. 18-01-00149-a), the Russian Foundation for Basic Research and the Government of the Novosibirsk region according to research project No. 19-41-543001-r_mol_a. Publisher Copyright: © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2022/9

Y1 - 2022/9

N2 - In this paper, we propose a stochastic model of the conditional time series of the wind chill index. The model is based on the inverse distribution function method and on the normalization method for simulation of the non-Gaussian non-stationary random processes as well as on the method of conditional distributions for simulation of the conditional Gaussian processes. In the framework of the approach considered, two types of conditions (point conditions and interval conditions) are imposed on the time series. The model in question was verified using the real data collected at the weather stations located in West Siberia (Russia). It is shown that the simulated trajectories are close in their statistical properties to the real time series. The model proposed was used for stochastic forecasting of the wind chill index and the results of the numerical experiments have shown that the accuracy of the short-term forecasts is high enough.

AB - In this paper, we propose a stochastic model of the conditional time series of the wind chill index. The model is based on the inverse distribution function method and on the normalization method for simulation of the non-Gaussian non-stationary random processes as well as on the method of conditional distributions for simulation of the conditional Gaussian processes. In the framework of the approach considered, two types of conditions (point conditions and interval conditions) are imposed on the time series. The model in question was verified using the real data collected at the weather stations located in West Siberia (Russia). It is shown that the simulated trajectories are close in their statistical properties to the real time series. The model proposed was used for stochastic forecasting of the wind chill index and the results of the numerical experiments have shown that the accuracy of the short-term forecasts is high enough.

KW - 65C05

KW - 65C20

KW - 86A10

KW - Conditional random process

KW - Non-stationary random process

KW - Stochastic forecasting

KW - Stochastic simulation

KW - West Siberia

KW - Wind chill index

UR - http://www.scopus.com/inward/record.url?scp=85105940224&partnerID=8YFLogxK

UR - https://www.elibrary.ru/item.asp?id=46094115

UR - https://www.mendeley.com/catalogue/2340639e-e7fe-3d7a-b409-7f35294ded32/

U2 - 10.1007/s11009-021-09861-x

DO - 10.1007/s11009-021-09861-x

M3 - Article

AN - SCOPUS:85105940224

VL - 24

SP - 1467

EP - 1483

JO - Methodology and Computing in Applied Probability

JF - Methodology and Computing in Applied Probability

SN - 1387-5841

IS - 3

ER -