Afternoon 22 June
Note: Workshops are open to all conference attendees regardless of background knowledge. Registration for workshops is incoming. Conference attendees already have access to workshops included in their ticket. However, workshops have different capacities. Space is limited!
Workshop 1: Deep Dive into New Scenario Planning Toolkits – What if? & RAISE
This session will explore two scenario planning tools being developed by the City Futures Research Centre at UNSW Sydney, Australia. These are (i) The Online What if? PSS (recoded), for future urban growth scenarios and the Rapid Analytics Interactive Scenario Explorer (RAISE) toolkit for exploring likely land value outcome through the provision of new city infrastructure and changes to planning controls and density.
Both PSS are designed to help planners and government decision makers explore different data-driven planning scenarios. With respect to the RAISE toolkit the impacts are displayed to users through an online mapping interface, with results provided through rapid calculations based on existing property values produced by a machine learning-based automated valuation model, infrastructure-related value uplift through applying outputs of a regression analysis, and planning-related value uplift through a residual land value model, allowing the user to quickly explore different scenarios.
Participants will get an orientation on the toolkits for their potential use cases using the City of Ipswich and Sydney as real world examplars. Feedback on the toolkits and their potential uses in the various world-wide contexts which the participants practice in is encouraged during the workshop.
Maximum capacity: 15
Workshop 2: Cellular Automata and Agent Based Modelling for Urban Densification Studies
Complex systems are esembles made up of multiple, often heterogeneous, components that interact with each other and with the system’s environment. Irregular networks of micro-scale interactions in these systems can create feedback loops and cause macro-scale non-linear behavior, emergent patterns and structures, learning, adaptation and self-organization. Considering the above, complex systems modelling is a powerful approach in the study and simulation of urban systems. The objective of this workshop is to introduce the participants to two methods of modelling complex systems – namely Cellular Automata and Agent Based Modelling – and their application in simulating urban densification dynamics. The workshop is offered in two sections, each dedicated to one of the above modelling methods. In each section, participants learn the principles of bottom-up modelling in its respective method, and they apply those principles to build an urban densification model. In each section of the workshop, instructors guide the participants to develop their models step-by-step, from simple to detailed. Then, the participants use their models to perform hypothetical experiments and simulate densification dynamics under various settings and scenarios. The workshop concludes with a discussion of how bottom-up modelling can lead to gaining insight about the complexity of urban systems.
Maximum capacity: 20
Workshop 3: Modelling and Mapping Transit Accessibility for Sustainable City Planning
Understanding transit (public transport) accessibility is important for a range of urban issues including transport sustainability, housing markets and spatial inequalities. Many cities currently have ambitious targets for modal shift away from private vehicles towards transit and active travel, and for improving accessibility to local services through policies such as the 15 Minute City. Analysing pedestrian and public transport accessibility is necessary for tracking progress towards these targets. Modelling transit accessibility can however be methodologically challenging due to the need to capture multiple trip stages, incorporate service frequencies and include destination opportunities. It is not possible to perform this kind of analysis using standard GIS and network software. Recently several open-source solutions have been developed for modelling transit accessibility using full timetable data. This workshop will use the R5 software by Conveyal (https://github.com/conveyal/r5), ported to R by Rafael Pereira at IPEA (https://github.com/ipeaGIT/r5r/). We will show how to measure pedestrian and transit accessibility to retail and local services, and the results will then be mapped using QGIS. While the workshop example data will be for London UK, the methodology can be transferred to any city where timetable (GTFS) and basic road network data is available.
Maximum capacity: 20
Workshop 4: GGP-GAMS - The Fast, Accurate and Transparent (i.e. easily understood outputs) Approach to AI for Urban Planning Using Spatial GAMs
GAM (General Additive Models) are emerging as the go-to approach for all kinds of data science activities. GAMS perform as well or better than most machine learning models and they are relatively fast. They are powerful and quick but critically they offer a middle ground between overly simple but interpretable standard statistical approaches, and efficient but opaque machine leaning algorithms, where it is difficult to understand how one variable relates to an outcome. Their beauty is that they can handle and model different types of statical relationships, and provide an intuitive approach for modelling relatively complex relationships in data with complex interactions and non-linearities. The outputs provide easily understood measures of the relationship between predictor and response variables, and how the outcome is modelled. Crucially for the spatial sciences, including urban planning and management, they can be adapted to generate spatial outputs that show how and where the relationship with outcome vary in space and time, in Gaussian Process (GP) splines are included in the GAM model..
This hands workshop will introduce GAMs, provide the opportunity for attendees to undertake a GAM analysis of data describing processes related to an urban informatics case study, to interpret and visualize the outputs, to apply a location aware GAM. The workshop will demonstrate how to quantify the varying spatial relationships between different driving factors and an outcome, and support users in applying a spatial GAM to their problem (please bring data!).
The workshop will have a strong hands-on element and attendees will need to have a basic understanding of R/ RStudio.
At the end of this master class attendees will:
be able to apply and a tune a GAM with GP splines
understand what constitutes a "good " GAM model
be able to undertake spatially varying coefficient modelling using GP GAMs and interpret and visualize (map) the outputs
have a robust understanding of how to apply GAMs to urban and regional systems
Maximum capacity: 30