Nowcasting

from Wikipedia, the free encyclopedia
Racine carrée bleue.svg
This item has been on the quality assurance side of the portal mathematics entered. This is done in order to bring the quality of the mathematics articles to an acceptable level .

Please help fix the shortcomings in this article and please join the discussion !  ( Enter article )

Statistical predetermination of new values ​​using the compensation function

Nowcasting is a statistical forecasting method that is often used in meteorology and also in other scientific fields.

In contrast to the classic forecasting , the method refers to the forecast of a current situation based on past, not current or incomplete data. The calculation is based on estimating functions . The value of the current state is estimated in advance by using old values ​​and mathematically extrapolating them. This is e.g. B. necessary if current measured values ​​are not yet available or if they are randomly noisy.

The term has its roots in the English now (now) and forecasting (forecast) and has been used for a long time in meteorology, from the 2000s also in other areas such as economics. It can be defined as predicting the now , the very near future, or the very near past.

Application in meteorology

Forecast (blue lines) from «AutoNowcaster» for a thunderstorm line.

Nowcasting in meteorology means weather forecasts for the next up to 6 hours. In some cases, the entire shortest period (0 to 12 hours) is counted for nowcasting.

The forecasts are read directly from data from weather satellites and station reports. So there is no need to create time series to investigate the further development of the weather , as is necessary for longer-term weather forecasts. Due to the shortness of the forecast period, nowcasting is the safest and most reliable form of weather forecast.

Nowcasting is especially important for the area of ​​local severe weather warnings .

Application in the other areas

Nowcasting is z. B. used in the field of epidemiology to estimate the current number of infections, for example, delay in diagnosis and reporting are taken into account. Another field of application is the estimation of current sales figures, e.g. B. in the sale of sound carriers or opinion formers in the population for example for election forecasts. Nowcasting is important in economics because significant statistical data for the current economic state are often only available with a delay. The gross domestic product is usually determined every quarter and is only published weeks after the end of the quarter.

Individual evidence

  1. a b c Marta Banbura, Domenico Giannone, Michele Modugno, Lucrezia Reichlin, Now-casting and the real-time data flow, European Central Bank, Working Papers Series No. 1564, July 2013, pdf
  2. D. Giannone, L. Reichlin, D. Small: Nowcasting: The real-time informational content of macroeconomic data, Journal of Monetary Economics, Volume 55, 2008, pp. 665-676.
  3. ^ World Meteorological Organization
  4. DWD: Shortest term forecasts and nowcasting
  5. RKI - Archive 2020 - Nowcasting - Epidemiological Bulletin 17/2020 . In: Robert Koch Institute (ed.): RKI.de . April 22, 2020 ( rki.de [PDF; accessed April 22, 2020]).
  6. Andrea Ceron, Luigi Curini, Stefano Maria Iacus, Politics and Big Data. Nowcasting and Forecasting elections with social media, Routledge 2017