Application of Artificial Neural Network Forecasts to Predict Fog at Canberra International Airport

Abstract

The occurrence of fog can significantly impact air transport operations, and plays an important role in aviation safety. The economic value of aviation forecasts for Sydney Airport alone in 1993 was estimated at $6.8 million (Australian dollars) for Quantas Airways. The prediction of fog remains difficult despite improvements in numerical weather prediction guidance and models of the fog phenomenon. This paper assesses the ability of artificial neural networks (ANNs) to provide accurate forecasts of such events at Canberra International Airport (YSCB). Unlike conventional statistical techniques, ANNs are well suited to problems involving complex nonlinear interactions and therefore have potential in application to fog prediction. A 44-yr database of standard meteorological observations obtained from the Australian Bureau of Meteorology was used to develop, train, test, and validate ANNs designed to predict fog occurrence. Fog forecasting aids were developed for 3-, 6-, 12-, and 18-h lead times from 0600 local standard time. The forecasting skill of various ANN architectures was assessed through analysis of relative operating characteristic curves. Results indicate that ANNs are able to offer good discrimination ability at all four lead times. The results were robust to error perturbation for various input parameters. It is recommended that such models be included when preparing forecasts for YSCB, and that the technique should be extended in its application to cover other similarly fog-prone aviation locations.

LVP conditions at Mohamed V airport, Morocco: Local characteristics and prediction using neural networks

“…Such inequality can cause problems during the development process of ANN-based models (Parikh et al, 1999 [15]). Fabian et al (2007) [7] mentioned that, in cases where the class sizes are unequal, the NNs may converge on a solution by which the largest class is always forecast. In this study, the training and testing samples, extracted from the raw data, verify the condition of equality between the numbers of LVP days and no-LVP days.…”

“…In fact, Artificial Neural Networks (ANN) are computational methodologies capable of establishing non linear relationship between independent variables (predictors) and a dependent variable (predictand) through the experimentation of a multitude of situations (learning data set). Even if ANNs have existed for over 60 year, their first application in atmospheric science was in 1986 (Gardner and Dorling (1998) [4]; Hsieh and Tang (1998) [5]), and their application in fog forecasting is rather limited (Pasini et al (2001) [6]; Fabian et al (2006) [7]; Bremnes and Michaelides (2007) [8]). Marzaban et al (2006) [9] compared neural network with linear and logistic regression in forecasting ceiling and low visibilities.…”

Benefits of Aviation Weather Services: A Review of International Literature

“…Dhal et al (2013) study the problem of forecasting arrival rates of planes landing at airports and note the limitation of TAF weather information in managing airports; they suggest the use of forecasts derived from large scale numerical models integrated with regional scale modelling, as an additional tool to TAFs for the management of aircraft landings, departures and other functions of airports. Fabbian et al (2007) explain that by using weather forecasts together with adopting the latest flight technology in planes, airlines could reduce unexpected costs. Klein et al (2009) reveal from their study on airport capacity that when bad weather events are forecast and observed during the daytime, air traffic volumes at airports tend to be much affected than at night time when air traffic volumes are comparatively low.…”

Application of Artificial Neural Networks for Fog Forecast

“…According to Fabbian et al (2007), the occurrence of fog in aerodromes may negatively impact the air transport operations, thus influencing significantly the overhead activities during this period, with respect to flight safety.…”