TDNN Approach to Measuring Raindrop Sizes and Velocities

The paper describes a TDNN solution to a signal processing problem in the meteorological and telecommunications domains. Optical disdrometers measure raindrop sizes and velocites by registering changes in photodiode current as the droplets pass through a collimated light beam. In an improved dual-beam device being built at CETP, feature extraction MLPs applied to 20-sample windows of photodiode current provide input to a higher-level network which reconstructs droplet velocities and diameters in real time. In tests on simulated data, measurement precision is quite good for droplets as small as .05 mm radius. The algorithm can be executed either directly on the acquisition PC, or on a neural net coprocessor for additional speedup.