Multi-objective optimisation framework for calibration of Cellular Automata land-use models Charles P. Newland a, c, * , Holger R. Maier a, c , Aaron C. Zecchin a, c , Jeffrey P. Newman a, c , Hedwig van Delden a, b, c a Civil, Environment and Mining Engineering, University of Adelaide, Adelaide, Australia b Research Institute of Knowledge Systems, Maastricht, The Netherlands c Bushfire and Natural Hazards Cooperative Research Centre, Melbourne, Australia article info Article history: Received 19 June 2017 Received in revised form 28 September 2017 Accepted 9 November 2017 Keywords: Cellular Automata Land-use model Automatic calibration Automatic parameter adjustment Multi-objective optimisation abstract Modelling of land-use change plays an important role in many areas of environmental planning. How- ever, land-use change models remain challenging to calibrate, as they contain many sensitive parameters, making the calibration process time-consuming. We present a multi-objective optimisation framework for automatic calibration of Cellular Automata land-use models with multiple dynamic land-use classes. The framework considers objectives related to locational agreement and landscape pattern structure, as well as the inherent stochasticity of land-use models. The framework was tested on the Randstad region in the Netherlands, identifying 77 model parameter sets that generated a Pareto front of optimal trade- off solutions between the objectives. A selection of these parameter sets was assessed further based on heuristic knowledge, evaluating the simulated output maps and parameter values to determine a final calibrated model. This research demonstrates that heuristic knowledge complements the evaluation of land-use models calibrated using formal optimisation methods. © 2017 Elsevier Ltd. All rights reserved. Software availability Name of software: Parallel-NSGAII Developer: Jeffrey Newman Contact address: The University of Adelaide and BNHCRC North Terrace, ADELAIDE, SA 5005 Contact email: jeffrey.newman.au@gmail.com Year first available: 2016 Hardware & software required: Cross-platform; compiles under clang, visual studio and the GNU compiler chain. Hardware requirements dependent on land-use model used Program language: Cþþ Program size: 13 MB Availability and cost: GPL-2.0 Open source software Downloadable from: https://github.com/jeffrey-newman/parallel- nsgaII-backend 1. Introduction Modelling of land-use change plays an important role in many areas of environmental planning, such as river basin management (Van Delden et al., 2007), natural area preservation (Hewitt et al., 2014), the development of sustainable agricultural practises (Murray-Rust et al., 2014a; 2014b), and the influence of urban dy- namics on surrounding regions (Haase et al., 2012; Lauf et al., 2012). To better understand the influences of land-use changes, models are increasingly being used as part of decision support systems to evaluate policy that influences spatial planning (Van Delden et al., 2011) To represent land-use dynamics realistically, such models must incorporate complex socio-economic and biophysical drivers with human-environment interactions (Lambin et al., 2001). As a result, Land-Use Cellular Automata (LUCA) have become a popular modelling framework for evaluating land-use changes, as they are able to simulate the behaviour of complex systems with a high degree of realism (Hewitt et al., 2014). Historically, Cellular Automata methods were proposed for application to geographic systems by Tobler (1979), with LUCA models first used to replicate observed fractal patterns of urban evolution (Couclelis, 1985, 1989; Batty and Longley, 1994), followed * Corresponding author. Engineering North Room N223, The University of Ade- laide, SA 5005, Australia. E-mail addresses: charles.p.newland@adelaide.edu.au, charlesnewlandprofessional@outlook.com (C.P. Newland). Contents lists available at ScienceDirect Environmental Modelling & Software journal homepage: www.elsevier.com/locate/envsoft https://doi.org/10.1016/j.envsoft.2017.11.012 1364-8152/© 2017 Elsevier Ltd. All rights reserved. Environmental Modelling & Software 100 (2018) 175e200