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

Abstract

Abstract. This work describes a Dynamic Data Driven Genetic Algorithm (DDDGA) for improving wildfires evolution prediction. We propose an universal computational steering strategy to automatically adjust certain input data values of forest fire simulators, which works independently on the underlying propagation model. This method has been implemented in a parallel fashion and the experiments performed demonstrated its ability to overcome the input data uncertainty and to reduce the execution time of the whole prediction process.

A Review of Genetic Algorithm Approaches for Wildfire Spread Prediction Calibration

“…Each algorithm was executed 10 times up to 1000 iterations. The fire lines were compared using the Hausdorff distance H (22), which measures the degree of mismatch between two sets of points F 1 and F 2 , representing the fire line simulated based on the optimized parameters and the fire line generated with known input parameters for comparison. H ( 22) is given by…”

“…The obtained wind speed and direction values were used to steer the search for an optimal input parameter set carried out by the genetic algorithm. Afterwards, in [22], the same research group proposed a new calibration steering method as an improvement to the previous strategy. Since this was highly dependent on the underlying simulator, the new approach consisted of generating a database with fire evolution information from both real and simulated (synthetic) fires.…”

“…In [24], the two methods introduced in [16,22] were compared. The method introduced in [16] is named as the "analytical method" and, as was described above, is based on the inversion of a fire simulator.…”

“…The method introduced in [16] is named as the "analytical method" and, as was described above, is based on the inversion of a fire simulator. The method introduced in [22] is named as the "computational method" and relies on a database with information from past fires. Both of these methods use ongoing fire propagation data to obtain wind speed and direction values and use them to steer the genetic algorithm's search.…”

Assimilation of Perimeter Data and Coupling with Fuel Moisture in a Wildland Fire–Atmosphere DDDAS

“…A suitable perturbation algorithm is the key to a successful application. The perturbation methods used in wildland fire modeling range from random modifications of the burn area [9] to genetic algorithms, which evolve the shape of the fire by simulated evolution, where the states with fire regions closer the the data are more likely to survive [11]. While SMC methods with tens of thousands of particles may be feasible for 2D cell models, with relatively small state vectors, they are definitely out of question for a coupled atmosphere-fire model.…”