Groundwater is like dark matter - we know very little apart from the fact that it is hugely important. Given the scarcity of data, mathematical modelling can come to the rescue but existing groundwater models are mainly restricted to simulate the transport and degradation of contaminants on the scale of whole contaminated field sites by averaging out the effect of spatial heterogeneity on the availability of the pollutant to the degrading organisms. These coarse-scale mean-field models therefore tend to rely on fitting to data rather than being predictive. Also, they are less suited to incorporate spatial variability and non-linear kinetics and feedbacks. We propose to solve the two mutually exacerbating problems of environmental patchiness and data scarcity by developing a flexible and robust distributed simulation framework that uses an ensemble of small scale simulations running on different processors/computers to scale-up, i.e. to feed the effect of small-scale patchiness into a concurrent site-scale simulation of the dynamics of groundwater pollutant degradation. Our scaling approach solves problem #1 by simulating dynamics also on the small scale where some of the patchiness resides, and problem #2 by enabling rigorous validation of our small-scale model and scaling approach with laboratory data, which are high quality at low cost.