Application of genetic algorithm optimization technique for fitting non-linear Richards growth model.

摘要

Utility of genetic algorithm optimization methodology for fitting of non-linear Richards growth model is highlighted. The proposed procedure is successfully applied for modelling and forecasting India's foodgrain production time-series data. This methodology is applicable even in those cases in which non-linear estimation procedures fail to converge. The possibility of modifying the methodology in the presence of outliers is currently being explored and the results shall be reported separately.