A neural network approach to estimating rainfall from spaceborne microwave data

Rainfall is a key parameter in the study of global climate budget and climate change, Various techniques use microwave (MW) brightness temperature (BT) data, obtained from remote sensing orbiting platforms, to calculate rain rates, The most commonly used techniques are based on regressions or other statistical methods, An emerging tool in rainfall estimation using satellite data is artificial neural networks (NN's), NN's are mathematical models that are capable of learning complex relationships, They consist of highly interconnected, interactive data processing units, NN's are implemented in this study to estimate rainfall, and backpropagation is used as a learning scheme, The inputs for the training phase are BT's and the outputs are rainfall rates, all generated by three dimensional (3-D) simulations based on a 3-D stochastic, space-time rainfall model, and a 3-D radiative transfer model, Once training is complete the NN's are presented with multi-frequency and polarized (horizontal and vertical) BT data, obtained from the Special Sensor Microwave/Imager (SSM/I) instrument onboard the F10 and F11 polar-orbiting meteorological satellites, Bence, rainrates corresponding to real BT measurements are generated, The rainfall rates are also estimated using a log-linear regression model, Comparison of the two approaches, using simulated data, shows that the NN can represent more accurately the underlying relationship between BT and rainrate than the regression model, Comparison of the rates, estimated by both methods, with radar-estimated rainrates shows that NN's outperform the regression model, This study demonstrates the great potential of NN's in estimating rainfall from remotely sensed data.