Predicting jet-grout column diameter to mitigate the environmental impact using an artificial intelligence algorithm

This paper describes an approach for predicting the diameter of a jet-grout column using support vector regression (SVR) technique, which is regarded as novel learning machine based upon recent advances in statistical theory, combined effects construction (construction methods and jetting parameters) soil properties (soil type shearing resistance) are considered. Four different kernel functions, namely, linear function, polynomial radial basis sigmoid integrated into SVR technique. A large amount field measured data on retrieved from published literature training testing purposes. The results indicate that technique with function provides predictions closest to results, whereas prepared design charts enable ability significantly widen application proposed areas ground improvement environmental protection.