Search

Gated experts (GE) neural networks have been developed in order to retrieve atmospheric liquid water content over ocean from radiometer data. Gated experts neural networks are statistical models, which can model any general class of function. This paper focuses on the case where the complex transfer functions can be split on different simpler functions in order to improve the accuracy. Two atmospheric quantities are considered: the integrated cloud liquid water (iclw) and the surface rain rate (RR). In the case of iclw, the GE neural network finds two modes, splitting the problem into low and high iclw values. The physical meaning of those modes is discussed. A comparison with a standard regression algorithm and a multilayer perceptron neural network is done on simulated data and an “indirect comparison” is done using Special Sensor Microwave Imager (SSM/I) data. In the case of RR, the focus is on the ability of GE neural networks to perform a classification between rainy and nonrainy situations. Tropical Rainfall Measuring Mission (TRMM) data are used for rain-rate validation: rain-rate retrieval from the GE algorithm applied to actual TRMM Microwave Imager (TMI) measurements are compared with collocated precipitation radar (PR) rain rate. [ABSTRACT FROM AUTHOR]

A new algorithm is developed whereby the cloud Liquid Water Path (LWP) and the Total Precipitable Water (TPW) may be determined from SSM/I microwave radiometric data. An artificial Neural Network (NN) with a five-neuron single hidden layer with five neurons yields the best results. The NN algorithm for TPW and LWP is compared with log-linear regression algorithms developed on the same database. The results obtained on the simulated dataset are nearly twice as good with this new algorithm. In particular, this NN seems to be able to give a better fit for large values of LWP. Furthermore, in the case of TPW, a validation and comparison with conventional algorithms is presented, which is based on SSM/I measurements and collocated radiosonde observations (RAOBs). The main conclusion is that the NN algorithm is more regular than most of the other algorithms. Through this particular study, we try to elaborate a general methodology. The conclusions concern the variability of the database used to develop and test retrieval algorithms and the relevant parameters to characterize the performance of an algorithm. [ABSTRACT FROM AUTHOR]