Spatial interpolation using neural fuzzy technique

Spatial interpolation is an important feature of a Geographic Information System, which is the procedure used to estimate values at unknown locations within the area covered by existing observations. This paper constructs fuzzy rule bases with the aid of a Self-organising Map (SOM) and Backpropagation Neural Networks (BPNNs). These fuzzy rule bases are then used to perform spatial interpolation. A case based on the 467 rainfall data in Switzerland is used to test the neural fuzzy technique. The SOM is first used to classify the data. After classification, BPNNs are then use to learn the generalization characteristics from the data within each cluster. Fuzzy rules for each cluster are then extracted. The fuzzy rules base are then used for rainfall prediction.