A chaotic oscillatory-based neural network (CONN) is applied to the radial wind velocities obtained in sector scans of a Doppler LIght Detection And Ranging (LIDAR) system for very short-term forecasting (in the next 10-20 minutes) of the winds in the vicinity of the Hong Kong International Airport (HKIA). To the knowledge of the authors, this is the first application of CONN to 2D wind forecasting based on LIDAR. It is assumed that, over a very short time interval, the future evolution of the wind at a location is related to the wind distribution in its vicinity. As such, for each data point in the LIDAR's sector scan, a relationship is built up between the velocity at this point and those at the 5 x 5 neighbouring points around (i.e. about 500 m in the radial direction and 5 degrees in the azimuth centred at the data point under consideration) through training of the CONN. Due to the large amount of velocity data but limited availability of computing power, the training is performed using the data in the last 2 hours only. Despite this limitation, the resulting CONN is found to successfully capture the trend of the evolution of the 2D wind pattern around HKIA in selected case studies of terrain-disrupted airflow. Future research direction in the application of CONN to LIDAR data will also be discussed.