Calibration of a greenhouse climate model using evolutionary algorithms

Density-based evolutionary framework for crowd model calibration

“…Recently, stochastic search methods such as GA has become popular to calibrate computer models [17,[31][32][33]. Take agentbased models (ABMs) for example, Calvez and Hutzler [34,35] proposed to consider the parameter estimation of an ABM as an optimization problem and suggested using GAs to solve the problem.…”

Application of stochastic approximation methods for stochastic computer models calibration

“…The most commonly used objective function in calibration is sum of square error (SSE) [2]. When there are multiple outputs in the objective function, the weighted sum of square error (WSSE) is used [3].…”

“…The basic target of these algorithms is to find the best fitting values of calibration parameters by using heuristic or search methods. Some optimization algorithms, such as genetic algorithm (GA), simulated annealing algorithm (SAA) and shuffled complex evolution algorithm (SCE), have been applied to solve practical calibration problems [2,3]. Several comparison studies indicate that GA can give equal or even better performance than other methods [4].…”

A GENETIC ALGORITHM TO CALIBRATE DYNAMICAL SYSTEMS: Confidence intervals for parameters and residuals

“…Genetic algorithms (GAs) are Evolutionary Algorithms (EAs) (they adapt their parameters according to previous results) that try to imitate Natural Selection inside a population through parent selection, recombination, mutation and migration. About details on GAs and its use in systems calibration, see for instance: Whitley, [14], Guzmán-Cruz et al, [8] and Muraro & Dilao [12]. Nevertheless there are a lot of possible options for their definition, obviously related on how to perform selection, crossover and mutation.…”