In the era of big data with more available massive data, a series of data-driven advances have enabled more complex problems and phenomena to be observed from different angles. However, the data observation and solution validation of many current real-world problems is still limited by their enormous economic, temporal, and spatial computational cost, thereby requiring more simulated approaches to lower the threshold for experimentation and application. Currently, these growing demands have encouraged the studies and implementations of digital simulation based on intelligent computation methods such as data mining, soft sensors, and data-driven techniques in wireless networks. These techniques can be used to provide implicit but important pieces of information regarding the current states of the target process, allowing for advanced monitoring, control, and optimization. Furthermore, the recent advances of deep learning methods such as graph neural networks, deep reinforcement learning, self-supervised learning and few-shot learning present novel perspective towards deep and fine-grained simulation and computation.

However, when the simulation system faces complex real-world problems, it will inevitably produce a series of massive data and signals that are difficult to analyze. How to use intelligent computing methods to comprehensively analyze these multimodal and simultaneous data requires an important breakthrough. Also, in specific fields, the relationship between the signal used as the simulation basis or generated by the simulation system and the internal mechanism of the system is also to be systematically revealed. In addition to the utilization on the conventional signals from physical and cyber space such wireless network and mobile network, the signals from wider novel sources such as social media, crowdsourcing and IoT also urge more powerful and efficient analyzing tools as well as application scenarios.

Given these challenges, this Special Issue seeks to provide a venue for ongoing research in novel studies applicable to a wide range of digital simulation and intelligent computing including innovation in data acquiring, modeling, analysis, computation, and applications. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

• Novel deep learning network and structure for simulation and intelligent computing
• AI-native networks
• Structure and application of decentralized AI
• Machine learning in wireless networks
• Signal processing and analyzing in simulation systems
• Multimodal signal and data processing and fusion
• Soft sensor and social signal mining
• Theory, methods, and applications in Cyber-Physical spaces (CPS) and Cyber-Physical-Social Spaces (CPSS)
• Graph neural network for data simulation and data augmentation
• Digital twins and parallel computing
• Simulation-based information retrieval and recommendation system
• General/Domain knowledge guided deep digital simulation and intelligent computing
• Applications of deep learning-empowered digital simulation
• Survey on deep digital simulation and intelligent computing