DATA-DRIVEN REGULARIZATION OF INVERSE PROBLEM FOR SEIR-HCD MODEL OF COVID-19 PROPAGATION IN NOVOSIBIRSK REGION

The inverse problem for SEIR-HCD model of COVID-19 propagation in Novosibirsk region described by system of seven nonlinear ordinary differential equations (ODE) is numerical investigated. The inverse problem consists in identification of coefficients of ODE system (infection rate, portions of infected, hospitalized, mortality cases) and some initial conditions (initial number of asymptomatic and symptomatic infectious) by additional measurements about daily diagnosed, critical and mortality cases of COVID-19. Due to ill-posedness of inverse problem the regularization is applied based on usage of additional information about antibodies IgG to COVID-19 and detailed mortality statistics. The inverse problem is reduced to a minimization problem of misfit function. We apply data-driven approach based on combination of global (OPTUNA software) and gradient-type methods for solving the minimization problem. The numerical results show that adding new information and detailed statistics increased the forecasting scenario in 2 times.

Forecasting Recessions in the US Economy Using Machine Learning Methods

A quantitative analysis of socio-economic characteristics, the set of which is typical in the pre-crisis periods of a market economy, is carried out. An indicator for forecasting the onset of a recession in the US economy over the next 6, 12 and 24 months has been constructed using machine learning methods (k-nearest neighbors, support vector machine, fully connected neural network, LSTM neural network, etc.). Using roll forward cross-validation, it is shown that the smallest error in predicting the onset of future recessions was obtained by a fully connected neural network. It is also shown that all three constructed indicators successfully predict the onset of each of the last six recessions that occurred in the United States from 1976 to 2021 (Early 1980s recession, Recession of 1981-82, Early 1990s recession,.COM bubble recession, Great Recession, COVID-19 recession). The resulting indicators can be used to assess future economic activity in the United States using current macroeconomic indicators. © 2021 IEEE

Mathematical modeling and forecasting of COVID-19 in Moscow and Novosibirsk region

We investigate the inverse problems of finding unknown parameters of the SEIR-HCD and SEIR-D mathematical models of the spread of COVID-19 coronavirus infection based on additional information about the number of detected cases, mortality, self-isolation coefficient and tests performed for the city of Moscow and the Novosibirsk region since 23.03.2020. In the SEIR-HCD model, the population is divided into seven, and in SEIR-D - into five groups with similar characteristics and with transition probabilities depending on a specific region. An analysis of the identifiability of the SEIR-HCD mathematical model was made, which revealed the least sensitive unknown parameters as related to additional information. The task of determining parameters is reduced to the minimization of objective functionals, which are solved by stochastic methods (simulated annealing, differential evolution, genetic algorithm). Prognostic scenarios for the disease development in Moscow and in the Novosibirsk region were developed and the applicability of the developed models was analyzed. В работе исследованы задачи уточнения неизвестных параметров математических моделей SEIR-HCD и SEIR-D распространения коронавирусной инфекции COVID-19 по дополнительной информации о количестве выявленных случаев заболеваний, смертности, коэффициенте самоизоляции и проведенных тестах для города Москвы и Новосибирской области с 23.03.2020. В SEIR-HCD модели популяция разделена на семь, а в SEIR-D -- на пять групп со схожими признаками и с вероятностями перехода между группами, зависящими от конкретного региона. Проведен анализ идентифицируемости математической модели SEIR-HCD, который выявил наименее чувствительные к дополнительной информации неизвестные параметры. Задачи уточнения параметров сведены к задачам минимизации целевых функционалов, которые решены с помощью стохастических методов (имитация отжига, дифференциальная эволюция, генетический алгоритм). Разработаны прогностические сценарии развития заболевания в Москве и Новосибирской области и проведен анализ применимости разработанных моделей.