Forecasting or prediction of failure or delay of the asset availability used to support the asset managers. Now, a new terminology 'nowcasting' has been tried by the asset managers to monitor and control the asset performability.
How can we define nowcasting and how it is different than the forecation?
This is indeed a very timely question. It is a term used in economics and borrowed from meteorology. It's about getting estimates of low frequency economic data [such as GDP] BEFORE the data is released [which typically lags the actual point of occurrence]. This is done by high frequency sampling from the disjoint but linked masses of data that go into the final metric [so freight, oil usage, employment trends, airline takeoffs, customs and excise taxes, visits to shopping malls, eCommerce websites and many such]. Heuristics are applied to triangulate and form stable estimates. With the advent of real time data and big data computing such estimates can be very precise, as we are seeing in hourly forecasts on weather websites...hence now-casting, hope this helps. Cheers!
"
http://www.radar.mcgill.ca/science/activities/nowcasting-menu.html
The term nowcasting is a contraction of “now” and “forecasting”; it refers to the sets of techniques devised to make short term forecasts, typically in the 0 to 12 hour range. Historically, nowcasting techniques have been based on simplified heuristic approaches where the current echo pattern was tracked in the past and extrapolated into the future, sometimes with some modifications to try to account for storm development and decay and/or for decreasing predictability with time. More and more though, nowcasting techniques are becoming more sophisticated, sometimes up to the point of becoming full-fledged numerical weather prediction models."
http://www.radar.mcgill.ca/science/activities/nowcasting-menu.html
Article Nowcasting US GDP: the role of ISM business surveys
Nowcasting in meteorology is explained at http://www.metoffice.gov.uk/learning/science/hours-ahead/nowcasting as follows:
"Nowcasting is a technique for very short-range forecasting that maps the current weather, then uses an estimate of its speed and direction of movement to forecast the weather a short period ahead — assuming the weather will move without significant changes."
History of nowcasting is explained there, too.
"Nowcasting is a very old technique. When Admiral FitzRoy first produced forecasts at the Met Office [UK} in the 1860s, he did it by collecting reports of storms from around the coast, and then sharing these reports with coastal ports that may be downwind, so that they knew there was bad weather coming. This was a simple form of nowcasting.
"The term 'nowcasting' was actually coined in the 1980s by Met Office scientist Professor Keith Browning, to describe the process of extrapolating a sequence of radar images to produce a very short-range rainfall forecast."
Nowadays, the concept of nowcasting is also used in economics and healthcare. Nowcasting in economics is defined as follows [Ineichen, Alexander (2015) "Nowcasting and financial wizardry," Risk Management Research, IR&M, January; cited at https://caia.org/sites/default/files/AIAR_Q3_2015-08_Nowcasting_Ineichen.pdf):
"Nowcasting is the economic discipline of determining a trend or a trend reversal objectively in real time. Nowcasting is fact-based, focuses on the known and knowable, and therefore avoids forecasting. Nowcasting is the basis of a robust decision-making process."
From the above explanations, the answer to the question about the difference between 'forecasting' and 'nowcasting' in health monitoring would be found.
I am new to the terms defined above, which helped in my understanding so that I can offer a response. I think "nowcasting" would be critical in health monitoring as it can provide known facts about a health condition that would allow the doctors to treat/manage it and possibly prevent it from escalating or cure it completely, all to the benefit of the patient's health.
Best regards,
Debra
Dear Debra, You are right in a way. Though forecasting started with metrology, it was applied to patient's health monitoring. Now it is moving towards plant and machinery's health (condition) monitoring.....
In general, it refers to predicting some value that is happening at the same time as the data used to predict. Other that that, it is simply a regression problem. The origin of the term seems to be in 1971, in this paper referring to forecasting weather conditions right now, maybe at a smaller scale than the usual weather prediction gives.
@inproceedings{tepper1971weather,
title={WEATHER NOW-CASTING},
author={TEPPER, M},
booktitle={BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY},
volume={52},
number={11},
pages={1173},
year={1971},
organization={AMER METEOROLOGICAL SOC 45 BEACON ST, BOSTON, MA 02108-3693}
}
Mathematically, nothing. Grammaticlaly, the term forecasting implies estimating the future, so the term nowcasting is used when we want to estimate the present
The two terms refers to future, BUT:
NOWCASTING refers to a very short time about events...i.e. one day, two or three... based on quantitative data.
Forecasting refers to a very long future.... i.e, one year, a decade, etc. normally based on qualitative data, like Delphi, etc. But, today we have good applications based on A.I. that use quantitative data to predict the future.
Nowcasting in meteorology is short-time forecasting typically referring to a horizon of +0-6h. It commonly uses numerical methods like extrapolation of the most recent observations and assumes Lagrangian or Eulerian persistence to make a prediction. In this sense it relies on computation of the underlying optical flow. This scheme differs from the Numerical Weather Prediction (NWP) algorithms which employ modelling of the physical atmospheric variables incorporating in this sense the interactions/coupling between them which drives the atmospheric flow. In a practical sense now, nowcasting tends to be fast and aims at short term warnings, while NWP is complex and computationally expensive.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Modeling
- Analyses of Variance
- ANOVA