Soil laboratory data interpretation using generalized regression neural network

Artificial intelligence techniques which incorporate empirical knowledge an d/or pattern matching techniques are ideally suited to assist engineers to interpret information from site and laboratory investigations because of th e "imprecise" nature of soil. This paper explores the pattern matching and prediction capabilities of neural networks to interpret laboratory test dat a. The neural network paradigm used in this paper is the generalized regres sion neural network (GRNN) algorithm. Detailed examples are given of the us e of this approach to assist engineers to interpret laboratory test data fr om consolidation tests and to characterize soil types from laboratory parti cle size distribution information. The main advantage of the GRNN technique in comparison to the widely used backpropagation neural network algorithm is the speed at which the optimal neural network configuration is determine d, since this process only involves adjusting one variable.