No abstract

This paper focuses on the forecast of wind shear and turbulence at the Hong Kong International Airport. It presents a mesoscale prediction model that uses chaotic oscillatory-based neural networks (CONN) to forecast the evolution of wind fields along the glide path in the vicinity of the airport. This model makes use of accurate Doppler velocities measured by light detection and ranging (LiDAR) system and afterward collected by the Hong Kong Observatory. Simulation results show that the CONN model with a new learning algorithm is able to capture the occurrence, evolution, and sudden changes of the winds representing turbulence incidences in the region. Research findings show that Doppler velocities forecast using CONN can be transformed into headwind profiles and processed with the developed algorithm to identify the wind shear occurrence. These are shown to match actual observations made using LiDAR in terms of time, locations, and size of wind shear events with considerable accuracy. The model has better performance compared with that of the traditional multilayered perceptron model neural network. The results encourage further exploration and experimentation in the use of machine learning and chaotic neural network in weather forecast and alerting.Index Terms-Chaotic oscillator, chaotic oscillatory-based neural networks (CONN) model, neural network, turbulence, wind shear.

No abstract

Current research based on various approaches including the use of numerical weather prediction models, statistical models, and machine learning models have provided some encouraging results in the area of longterm weather forecasting. But at the level of mesoscale and even microscale severe weather phenomena (involving very short-term chaotic perturbations) such as turbulence and wind shear phenomena, these approaches have not been so successful. This research focuses on the use of chaotic oscillatory-based neural networks for the study of a mesoscale weather phenomenon, namely, wind shear, a challenging and complex meteorological problem that has a vital impact on aviation safety. Using lidar data collected at the Hong Kong International Airport via the Hong Kong Observatory, it is possible to forecast the Doppler velocities with satisfactory accuracy and validate the prediction model with the potential to generate the wind shear alert. Experimental results are found to be comparable to the actual measurement. Moreover, the selected testing cases and results show that the value of correlation coefficient between the predicted and lidar-measured wind velocities exceeds 0.9 with various window sizes ranging from 1 to 3 h. These provide areas for further research of the proposed model and lidar technology for turbulence and wind shear forecasts.