Model-based optimization and control strategies are continuously facing technical challenges and difficulties, under parametric and/or structural uncertainties, undesired external disturbances, fast-varying references, sensor noise, nonlinearities, etc. Data is of great interest in research since it reflects the system dynamics while it can provide a direct way to know and understand the system. For example, the social system exhibits many different phenomena. However, the result is not easy to analyze and the modeling is quite difficult. Moreover, for the engineering system, although the mechanical dynamics can be obtained but the precise model is not available. How to use the data for model correction and control application is also of great importance.

Fortunately, with the fast development of advanced sensing, measurement, and data science and automation technologies, large amounts of data are easy to be obtained and further used in various complex systems. Using the mature techniques for extracting useful information from measured data, data-driven optimization and control strategies have demonstrated their promising advantages for complex systems and its engineering applications. This enables data-driven researches to be applicable and attractive. Due to the advantage of computation intelligence, especially neural networks, the data can be classified and analyzed or even the system dynamics can be constructed for optimization and control.

The main objective of this Special Issue is to highlight the recent innovations, developments, and challenges in data-based dynamics modeling and analysis using neural networks, i.e., social systems, engineering systems, etc. We are soliciting original high-quality research papers and reviews on the topics of information processing, optimization methods, modeling, and dynamics analysis using neural networks for systems in nature and society.

Potential topics include but are not limited to the following:

• Data-driven system modelling using neural networks
• Discrete optimization and control using neural networks
• Neural network-based phenomenon analysis using data
• Neural network-based social study with data collection and analysis
• Engineering analysis of sensor data using neural model
• Regulation control in nature and society using neural networks
• Development of broad learning or deep learning related techniques with applications