A novel deep learning modeling approach guided by mesoscience—MGDL

Deep learning modeling that incorporates physical knowledge is currently a hot topic, and a number of excellent techniques have emerged. The most well-known one is the physics-informed neural networks (PINNs). PINN integrates the residuals of the system’s governing partial differential equations (PDEs) and the initial value/boundary conditions into the loss function, thus the resulting model satisfies the constraints of the physical laws represented by the PDEs. However, PINN cannot work if equations among the key physical quantities of the system have not been established. To model such systems, novel methods must be developed.

MGDL (mesoscience-guided deep learning, a deep learning modeling approach guided by mesoscience, was proposed by Li Guo et al. from Institute of Process Engineering (IPE), Chinese of Academy Sciences (CAS). Mesoscience is a methodology for tackling multilevel complexities. It focuses on the study of mesoscale problems at different levels and correlates the macroscale behavior and intrinsic mechanisms of a system by means of the principle of compromise in competition (CIC) between dominant mechanisms.

When establishing sample dataset based on the same system evolution data, different from the operation of conventional deep learning method, MGDL introduces the treatment of the dominant mechanisms of complex system and interactions between them according to the CIC principle of mesoscience. Mesoscience constraints are then integrated into the loss function to guide the deep learning training. Two methods are proposed to add mesoscience constraints—as a loss regularization term or the learning rate correction. The physical interpretability of the model-training process is improved by MGDL because guidance and constraints based on physical principles are provided. MGDL was evaluated using a bubbling fluidized bed modeling case and compared with traditional techniques. With a much smaller training dataset, the results indicate that mesoscience-constraint-based model training has distinct advantages in terms of convergence stability and prediction accuracy, and it can be widely applied to various neural network configurations.

MGDL, proposed by researchers from IPE, CAS, is a novel strategy and method for utilizing the physical background information during deep learning model training. With the increasingly profound study and widespread application of mesoscience, MGDL is expected to be extensively applied to the modeling of complex systems.

The paper “A Case Study Applying Mesoscience to Deep Learning” is authored by Li Guo, Fanyong Meng, Pengfei Qin, Zhaojie Xia, Qi Chang, Jianhua Chen, and Jinghai Li. Full text of the open access paper: https://doi.org/10.1016/j.eng.2024.01.007. For more information about the Engineering, follow us on Twitter (https://twitter.com/EngineeringJrnl) & like us on Facebook (https://www.facebook.com/EngineeringJrnl).

About Engineering: 

Engineering (ISSN: 2095-8099 IF:12.8) is an international open-access journal that was launched by the Chinese Academy of Engineering (CAE) in 2015. Its aims are to provide a high-level platform where cutting-edge advancements in engineering R&D, current major research outputs, and key achievements can be disseminated and shared; to report progress in engineering science, discuss hot topics, areas of interest, challenges, and prospects in engineering development, and consider human and environmental well-being and ethics in engineering; to encourage engineering breakthroughs and innovations that are of profound economic and social importance, enabling them to reach advanced international standards and to become a new productive force, and thereby changing the world, benefiting humanity, and creating a new future.