Many sensor nodes have been widely deployed in the physical world to gather various environmental information, such as water quality, earthquake, and huge dam safety. Due to the limitation in the batter power, memory, and computational capacity, missing data can occur at arbitrary sensor nodes and time slots. In extreme situations, some sensors may lose readings at consecutive time slots. The successive missing data takes the side effects on the accuracy of real-time monitoring as well as the performance on the data analysis in the wireless sensor networks. Unfortunately, existing solutions to the missing data filling cannot well uncover the complex non-linear spatial and temporal relations. To address these problems, a DNN (Deep Neural Network) multi-view learning method (DNN-MVL) is proposed to fill the successive missing readings. DNN-MVL mainly considers five views: global spatial view, global temporal view, local spatial view, local temporal view, and semantic view. These five views are modeled with inverse distance of weight interpolation, bidirectional simple exponential smoothing, user-based collaborative filtering, mass diffusion-based collaborative filtering with the bipartite graph, and structural embedding, respectively. The results of the five views are aggregated to a final value in a multi-view learning algorithm with DNN model to obtain the final filling readings. Experiments on large-scale real dam deformation data demonstrate that DNN-MVL has a mean absolute error about 6.5%, and mean relative error 21.4%, and mean square error 8.17% for dam deformation data, outperforming all of the baseline methods.