This　paper　describes　an　application　of　artificial　neural　networks　(ANNs)　based　on　improved　Radial　Basis　Function　(NNCA-RBF)　to　predict　performance　of　a　horizontal　ground-coupled　heat　pump　(GCHP)　system.　Performance　forecasting　is　the　precondition　for　the　optimal　control　and　energy　saving　operation　of　heat　pump　systems.　ANNs　have　been　used　in　varied　applications　and　they　have　been　shown　to　be　particularly　useful　in　system　modeling　and　system　identification.　In　this　study　NNCA-RBFNN　predictions　usually　agree　well　with　the　experimental　values　with　correlation　coefficients　in　the　range　of　0.9967-0.9998,　mean　relative　errors　in　the　range　of　1.02-4.83%　and　root　mean　square　errors　in　the　range　of　0.0147-0.058.　The　NNCA-RBFNN　approach　shows　high　accuracy　and　reliability　for　predicting　the　performance　of　GCHP　systems.　©　2013　IEEE.