This work proposes a new automatic calibration method for the sensor network which measures the distribution of physical fields. In case of these sensor networks, the regular calibration of the sensors is necessary for obtaining reliable information. However, it is not an easy task in the case of a large scale sensor network, because the manual calibration is time consuming and costly. To solve this problem, this present study proposes a new method which is based on the two concepts of regression analysis and cross validation. In this paper, the new method is explained and the efficient extension is also proposed, and the performance of the proposed methods is verified by a simulation.