Computational Steering Strategy to Calibrate Input Variables in a Dynamic Data Driven Genetic Algorithm for Forest Fire Spread Prediction?

Abstract. This work describes a Dynamic Data Driven Genetic Algo-rithm (DDDGA) for improving wildfires evolution prediction. We pro-pose an universal computational steering strategy to automatically ad-just certain input data values of forest fire simulators, which works inde-pendently on the underlying propagation model. This method has been implemented in a parallel fashion and the experiments performed demon-strated its ability to overcome the input data uncertainty and to reduce the execution time of the whole prediction process.