F.G. Bastante

Reforestation planning using Bayesian networks

The aim of this research was to construct a reforestation model for woodland located in the basin of the river Liebana (NW Spain). This is essentially a pattern recognition problem: the class labels are types of woodland, and the variables for each point are environmental coordinates (referring to altitude, slope, rainfall, lithology, etc.). The model trained using data for existing wooded areas will serve as a guideline for the reforestation of deforested areas. Nonetheless, with a view to tackling reforestation from a more informed perspective, of interest is an interpretable model of relationships existing not just between woodland type and environmental variables but also between and among the environmental variables themselves. For this reason we used Bayesian networks, as a tool that is capable of constructing a causal model of the relationships existing between all the variables represented in the model. The prediction results obtained were compared with those for classical linear techniques, neural networks and support vector machines.

Analysis of the goodness of empirical approaches in predicting explosive detonation parameters

Goodness of empirical models for predicting explosive detonation velocity and pressure was analysed using 3 databases consisting of experimental velocity and pressure measurements for different explosives. The first database was used to estimate experimental errors for detonation velocity and pressure measurements. The second database was used to compare residuals obtained by the experimental models and by various thermochemical codes. Finally, the third database, consisting of some 600 data on 130 explosive substances, was used to estimate residual bias and dispersion resulting from the application of the experimental models. Also analysed was model coherence with the ideal detonation theory. Our main conclusion is that all the models introduce bias in their predictions depending on the density and oxygen balance values of the explosive. Of those analysed, the Xiong model was notable for its good results, with residual dispersion comparable to that obtained from application of the best thermochemical codes. Our results would indicate that the Xiong model is the only model that may be compatible with the ideal detonation theory. The pressure equation derived from the ideal detonation theory and calibrated with experimental data had excellent predictive capacity.