Climate changes are expected to affect bird migration in several aspects including timing changes, breeding and migration orientation. The correlation analysis of several climate conditions (e.g. temperature, wind, humidity, etc) and bird migration trajectory is the key for explaining bird behavior during migration. Moreover, the resulting correlation can be used for predicting new bird behavior according to climate changes. In this paper we propose an integrated solution for correlating bird migration trajectory with climate conditions. This solution is composed by two orthogonal and complementary methods. The first method concerns discovering regions where birds are used to stop during their migration. The second method is based on a machine learning algorithm for classifying bird stops according to climate conditions. A real bird migration scenario was used for assessing the accuracy of the integrated solution.