Opportunistic emulation of computationally expensive simulations via Deep Learning

Abstract

With the underlying aim of increasing efficiency of computational modelling pertinent for managing and protecting the Great Barrier Reef, we perform a preliminary investigation on the use of deep neural networks for opportunistic model emulation of APSIM models, by repurposing an existing large dataset containing the outputs of APSIM model runs. The dataset has not been specifically tailored for the model emulation task. We employ two neural network architectures for the emulation task: densely connected feed-forward neural network (FFNN), and gated recurrent unit feeding into FFNN (GRU-FFNN), a type of a recurrent neural network. Various configurations of the architectures are trialled. A minimum correlation statistic is employed to identify clusters of APSIM scenarios that can be aggregated to form training sets for model emulation. We focus on emulating four important outputs of the APSIM model: (i) runoff – the amount of water removed as runoff, (ii) soil_loss – the amount of soil lost via erosion, (iii) DINrunoff – the mass of dissolved inorganic nitrogen exported in runoff, and (iv) Nleached – the mass of nitrogen leached in water draining to the water table. The GRU-FFNN architecture with three hidden layers and 128 units per layer provides good emulation of runoff and DINrunoff. However, soil_loss and Nleached were emulated relatively poorly under a wide range of the considered architectures; the emulators failed to capture variability at higher values of these two outputs. While the opportunistic data available from past modelling activities provides a large and useful dataset for exploring APSIM emulation, it may not be sufficiently rich enough for successful deep learning of more complex model dynamics. Design of Computer Experiments may be required to generate more informative data to emulate all output variables of interest. We also suggest the use of synthetic meteorology settings to allow the model to be fed a wide range of inputs. These need not all be representative of normal conditions, but can provide a denser, more informative dataset from which complex relationships between input and outputs can be learned.