Interactive Control of Large-Scale Ecosystem Simulation

Plant ecosystems are an essential element in bringing virtual worlds to life. However, current modeling methods do not scale well to large virtual environments due to the complexity of the interactions between individual trees required to accurately model realistic plant distributions. The resulting lengthy run-times also hamper authoring. To address the twin demands of scalability and interactive authoring, we introduce a hybrid grid-based simulation that distinguishes between the individual modeling of mature trees, whose interactions are encoded with convolution-like operations, and the aggregate modeling of small trees (encompassing saplings and bushes), which are encoded using a per-cell mean-tree representation. Our simulation model is well-suited to parallelization and operates efficiently on graphics hardware, outperforming existing ecosystem simulation approaches by three orders of magnitude without sacrificing ecological consistency and fundamental emergent phenomena. It also enables a full range of interactive control: artists and designers can directly steer the simulation through a painting interface, tune global ecological or climate parameters on the fly, and immediately observe the impact of their choices, making the system suitable for interactive authoring of virtual ecosystems, at a landscape scale of up to 8 × 8 km 2 and 100 million trees (at update rates below 47 ms per simulated year). Much larger ecosystems ( e.g. , 24 × 24 km 2 with 975 million trees) can still be simulated in about 413 ms per simulated year.