I. Introduction
Accurate time-series prediction is of crucial importance in the era of Big Data, which is widely used in many fields of modern industry, such as prediction on energy consumption, weather change, disease spreading, traffic flow and economic evolution [1], [2], [3], [4], [5]. It has attracted widespread attention of scientists ranging from mathematics, computer science, and other related specific engineering fields. Therein, a large number of achievements have been obtained and show appreciable performance. However, long (e.g., more than one thousand steps) and stable prediction has still been a tricky but significant problem to untangle due to the lack of deep understanding of the hidden mechanism in the targeted physical system [6]. Moreover, most existing methods are proposed in a deep learning framework, which cannot meets the requirement of reliable mechanism to be used in large-scale industrial systems. This motivates us to further investigate the mechanism of the system evolution with a white-box format and get rid of the usage of a black-box neural network module.