Search

Abstract: When modelling urban expansion dynamics, cellular automata models focus mostly on the physical environments and cell neighbours, but ignore the 'human' aspect of the allocation of urban expansion cells. This limitation is overcome here using an intelligent self-adapting multiscale agent-based model. To simulate the urban expansion of Auckland, New Zealand, a total of 15 urban expansion drivers/constraints were considered over two periods (2000–2005, 2005–2010). The modelling takes into consideration both a macro-scale agent (government) and micro-scale agents (residents of three income levels), and their multi-level interactions. In order to achieve reliable simulation results, ABM was coupled with an artificial neural network to reveal the learning process and heterogeneity of the multi-sub-residential agents. The ANN-ABM accurately simulated the urban expansion of Auckland at both the global and local scales, with kappa simulation value at 0.48 and 0.55, respectively. The validated simulation result shows that the intelligent and self-adapting ANN-ABM approach is more accurate than an ABM with a general type of agent model (kappa simulation = 0.42) at the global scale, and more accurate than an ANN-based CA model (kappa simulation = 0.47) at the local scale. Simulation inaccuracy stems mostly from the outdated master land use plan. [ABSTRACT FROM AUTHOR]

Lava flows can cause substantial and immediate damage to the built environment and affect the economy and society over days through to decades. Lava flow modelling can be undertaken to help stakeholders prepare for and respond to lava flow crises. Traditionally, lava flow modelling is conducted on a digital elevation model, but this type of representation of the surface may not be appropriate for all settings. Indeed, we suggest that in urban areas a digital surface model may more accurately capture all of the obstacles a lava flow would encounter. We use three effusive eruption scenarios in the well-studied Auckland Volcanic Field (New Zealand) to demonstrate the difference between modelling on an elevation model versus on a surface model. The influence of surficial features on lava flow modelling results is quantified using a modified Jaccard coefficient. For the scenario in the most urbanised environment, the Jaccard coefficient is 40%, indicating less than half of the footprints overlap, while for the scenario in the least urbanised environment, the Jaccard coefficient is 90%, indicating substantial overlap. We find that manmade surficial features can influence the hazard posed by lava flows and that a digital surface model may be more applicable in highly modified environments. [ABSTRACT FROM AUTHOR]

As populations around volcanoes grow, the potential for society to be impacted by lava flows is increasing. While lava flows are known to ignite, bulldoze and/or bury structures, little is known about potential impacts to buried infrastructure. We measure temperature profiles below molten rock to constrain a heat transfer model. Thermomagnetic and palaeomagnetic measurements on soil samples from beneath a 2014 Hawaiian lava flow are then used to verify the model. Finally, we illustrate the model's utility in lava flow hazard assessments by modelling a hypothetical lava flow active for 4 weeks in Auckland (New Zealand). The modelling predicts the upper 1.7 m of dry soil would exceed 100 °C after 1 week, and the upper 3.8 m of soil would exceed 100 °C after 4 weeks. Determining the depth profile of substrate heating has important implications for planning and preparedness (e.g. siting buried infrastructure), volcanic impact and risk assessments, and decision-making before and during lava flow crises (e.g. mitigation measures to be employed). [ABSTRACT FROM AUTHOR]

Accurate simulations and predictions of urban expansion are critical to manage urbanization and explicitly address the spatiotemporal trends and distributions of urban expansion. Cellular Automata integrated Markov Chain (CA-MC) is one of the most frequently used models for this purpose. However, the urban suitability index (USI) map produced from the conventional CA-MC is either affected by human bias or cannot accurately reflect the possible nonlinear relations between driving factors and urban expansion. To overcome these limitations, a machine learning model (Artificial Neural Network, ANN) was integrated with CA-MC instead of the commonly used Analytical Hierarchy Process (AHP) and Logistic Regression (LR) CA-MC models. The ANN was optimized to create the USI map and then integrated with CA-MC to spatially allocate urban expansion cells. The validated results of kappa and fuzzy kappa simulation indicate that ANN-CA-MC outperformed other variously coupled CA-MC modelling approaches. Based on the ANN-CA-MC model, the urban area in South Auckland is predicted to expand to 1340.55 ha in 2026 at the expense of non-urban areas, mostly grassland and open-bare land. Most of the future expansion will take place within the planned new urban growth zone. [ABSTRACT FROM AUTHOR]

Predicting recreational water quality is one of the most difficult tasks in water management with major implications for humans and society. Many data-driven models have been used to predict water quality indicators to allow a real time assessment of public health risk. This assessment is most commonly based on Faecal Indicator Bacteria (FIB), with the value of FIB compared with thresholds published in guidelines. However, FIB values usually tend to be unbalanced within water quality datasets, with small proportions of data exceeding guideline thresholds and far larger numbers that do not. This can be a limiting factor in the uptake of model predictions since, even if the overall accuracy is high, the sensitivity of the predictions can be low. To address this issue, this paper proposes an adaptive synthetic sampling algorithm (ADASYN) to generate synthetic above-threshold FIB instances and test the validity of the approach for the prediction of recreational water quality. The models in this paper are based on four machine learning techniques: k-mean nearest neighbour, boosting decision tree, support vector machine, and multi-layer perceptron artificial neural network and are applied to five different locations in Auckland, New Zealand. Aside from support vector machine, all models provide favourable predictions with relatively high sensitivity (around 75%) and overall accuracy (over 90%), indicating that both the compliant and exceedance conditions can be effectively predicted through the use of more sophisticated model training which involves artificial data. Considering the model accuracy and stability, boosting decision trees (BDT) and multi-layer perceptron artificial neural (MLP-ANN) network are the best two models and the multi-layer perceptron is the most efficient with the shortest computation time. Image 1 • Applied ADASYN to address the problem of unbalanced water quality datasets. • Ssessed the ability of machine learning models when using a balanced dataset. • Compared results at different locations using different machine learning models. [ABSTRACT FROM AUTHOR]