Search for: All records

This one-day workshop will bring together a diverse group of practitioners and researchers within the CHI community to discuss and explore data's increasing use as a material for design. This workshop encourages the submission of design exemplars, i.e., physical or digital works (in progress), design processes, or provocative or controversial pieces on the topic of data as a design material. If we are to continue to explore what data means as a design material and how we will continue to co-exist with them in our everyday lives through new and exciting ways and means, we must develop new strategies, tactics, tools, and outcomes. By bringing together products, processes, and provocations, this workshop will nurture and extend the continuation of research inquiring into data as a design material in its many forms. Our workshop will be conducted through physical and digital activities before, during, and after the onsite event at CHI 2023. 

Abstract Many studies of Earth surface processes and landscape evolution rely on having accurate and extensive data sets of surficial geologic units and landforms. Automated extraction of geomorphic features using deep learning provides an objective way to consistently map landforms over large spatial extents. However, there is no consensus on the optimal input feature space for such analyses. We explore the impact of input feature space for extracting geomorphic features from land surface parameters (LSPs) derived from digital terrain models (DTMs) using convolutional neural network (CNN)‐based semantic segmentation deep learning. We compare four input feature space configurations: (a) a three‐layer composite consisting of a topographic position index (TPI) calculated using a 50 m radius circular window, square root of topographic slope, and TPI calculated using an annulus with a 2 m inner radius and 10 m outer radius, (b) a single illuminating position hillshade, (c) a multidirectional hillshade, and (d) a slopeshade. We test each feature space input using three deep learning algorithms and four use cases: two with natural features and two with anthropogenic features. The three‐layer composite generally provided lower overall losses for the training samples, a higher F1‐score for the withheld validation data, and better performance for generalizing to withheld testing data from a new geographic extent. Results suggest that CNN‐based deep learning for mapping geomorphic features or landforms from LSPs is sensitive to input feature space. Given the large number of LSPs that can be derived from DTM data and the variety of geomorphic mapping tasks that can be undertaken using CNN‐based methods, we argue that additional research focused on feature space considerations is needed and suggest future research directions. We also suggest that the three‐layer composite implemented here can offer better performance in comparison to using hillshades or other common terrain visualization surfaces and is, thus, worth considering for different mapping and feature extraction tasks.