A Conceptual Approach to Complex Model Management with Generalized Modelling Patterns and Evolutionary Identification

Abstract

Complex systems' modeling and simulation are powerful ways to investigate a multitude of natural phenomena providing extended knowledge on their structure and behavior. However, enhanced modeling and simulation require integration of various data and knowledge sources, models of various kinds (data-driven models, numerical models, simulation models, etc.), intelligent components in one composite solution. Growing complexity of such composite model leads to the need of specific approaches for management of such model. This need extends where the model itself becomes a complex system. One of the important aspects of complex model management is dealing with the uncertainty of various kinds (context, parametric, structural, input/output) to control the model. In the situation where a system being modeled, or modeling requirements change over time, specific methods and tools are needed to make modeling and application procedures (meta-modeling operations) in an automatic manner. To support automatic building and management of complex models we propose a general evolutionary computation approach which enables managing of complexity and uncertainty of various kinds. The approach is based on an evolutionary investigation of model phase space to identify the best model's structure and parameters. Examples of different areas (healthcare, hydrometeorology, social network analysis) were elaborated with the proposed approach and solutions.

Robust Ensemble-Based Evolutionary Calibration of the Numerical Wind Wave Model

“…However, the evolutionary (genetic) algorithms are efficient enough to perform a robust solution search [15] in a complex parameter space with a lack of historical data for quality assessment [21]. The applicability of evolutionary algorithms for SWAN wave model calibration is demonstrated in [13].…”

“…Despite the fact that some modern evolutionary algorithms outperform SPEA2 in some synthetic tasks [14], we decided to base the experiments on a well-studied [13] algorithm to separate the impact from the proposed ensemble-based modifications from other features' influence.…”

Automated Evolutionary Approach for the Design of Composite Machine Learning Pipelines

“…It makes it impossible to automate the design for any custom workflow, but the specialized solutions for specific types of workflows still can be proposed [9]. The workflows that are specialized for modeling tasks are usually referred to as pipelines (linear, variable-shaped [10] or composite models [11]). In large distributed systems, the modeling pipelines are usually used as part of the composite application that controls the evaluation of the models.…”

Towards Generative Design of Computationally Efficient Mathematical Models with Evolutionary Learning

“…To achieve better quality, complex modeling pipelines can be used, that include different pre-processing stages and can contain several types of models. A generalization of ensembling approaches is the composite model concept [ 5 ]. A composite model has a heterogeneous structure, so it can include models of different nature: machine learning (ML), equation-based, etc.…”