IsoTrotter: Visually Guided Empirical Modelling of Atmospheric Convection

The convection analysis is enabled by two main views. In the left view we provide a tool for analysing the parameter-space of the model, as well as for comparing the model results to data from observations. We allow adjustment of the model parameters on the far left; the greyed-out parameter is under automatic control by the anchor point. A gallery of segmented thermals is at the bottom. On the right, a 3D view showing tracks of paragliding flights presents an instance of a thermal in its environment.

Abstract-Empirical models, fitted to data from observations, are often used in natural sciences to describe physical behaviour and support discoveries. However, with more complex models, the regression of parameters quickly becomes insufficient, requiring a visual parameter space analysis to understand and optimize the models. In this work, we present a design study for building a model describing atmospheric convection. We present a mixed-initiative approach to visually guided modelling, integrating an interactive visual parameter space analysis with partial automatic parameter optimization. Our approach includes a new, semi-automatic technique called IsoTrotting, where we optimize the procedure by navigating along isocontours of the model. We evaluate the model with unique observational data of atmospheric convection based on flight trajectories of paragliders.