The complicated geological conditions and geological hazards are challenging problems during tunnel construction, which will cause great losses of life and property. Therefore, reliable prediction of geological defective features, such as faults, karst caves and groundwater, has important practical significances and theoretical values. In this paper, we presented the criteria for detecting typical geological anomalies using the tunnel seismic prediction (TSP) method. The ground penetrating radar (GPR) signal response to water-bearing structures was used for theoretical derivations. And the 3D tomography of the transient electromagnetic method (TEM) was used to develop an equivalent conductance method. Based on the improvement of a single prediction technique, we developed a technical system for reliable prediction of geological defective features by analyzing the advantages and disadvantages of all prediction methods. The procedure of the application of this system was introduced in detail. For prediction, the selection of prediction methods is an important and challenging work. The analytic hierarchy process (AHP) was developed for prediction optimization. We applied the newly developed prediction system to several important projects in China, including Hurongxi highway, Jinping II hydropower station, and Kiaochow Bay subsea tunnel. The case studies show that the geological defective features can be successfully detected with good precision and efficiency, and the prediction system is proved to be an effective means to minimize the risks of geological hazards during tunnel construction.