Search

Sea surface temperature (SST) prediction plays an important role in global and regional ocean-related research. With the rapid development of remote sensing technology, there are plenty of studies for SST prediction with deep learning to pursue better prediction performance and normalization was used for most studies. However, SST always fluctuates widely, so the denormalization scaled up the difference between normalized observed SSTs and normalized predicted SSTs (OnP-DIFF), and it results in a significant decline in the prediction performance. Therefore, a revision method used to revert the scale-up is proposed in this letter. This method uses cube B-spline interpolation to enhance OnP-DIFF, utilizes Long Short Term Memory network (LSTM) to train and predict OnP-DIFF and generate revision tensor (RT), and finally uses RT to revise denormalized predicted SSTs. To our knowledge, it is the first attempt to use the revision method to solve the problem of performance decline for SST prediction because of wide fluctuations of SST. The experiment results indicate that the proposed method can revert the performance back to and even better than the value before denormalization for deep learning models, significantly improving the prediction performance, and is reliable for SST prediction with high performance for a wide time range and large spatial scope. [ABSTRACT FROM AUTHOR]

We consider in this paper the robust and perfect tracking (RPT) problem for multivariable linear systems with external disturbances. The problem is to design a proper controller such that the resulting overall closed-loop system is asymptotically stable and the controlled output almost perfectly tracks a given reference signal with an arbitrarily fast settling time in the face of external disturbances and initial conditions. The contribution of this paper is two-fold: (1) We derive a set of necessary and sufficient conditions under which the RPT problem is solvable; and (2) Under these solvability conditions, we develop algorithms for constructing state and output feedback laws, explicitly parameterized in epsilon, that solve the RPT problem. In our construction of feedback laws, we propose a controller structure which enables us to design a tracking controller without introducing additional integrators regardless of what type the system is. [ABSTRACT FROM AUTHOR]