A Multi-Temporal LiDAR-Derived Geospatial Dataset for Coastal Hazard Assessment

High-resolution topographic data is crucial for effective environmental monitoring and disaster management. This paper presents a multi-temporal LiDAR dataset and processing methodology for assessing hurricane impacts on coastal communities. We detail the complete workflow for converting raw aerial Light Detection and Ranging (LiDAR) data from the National Oceanic and Atmospheric Administration (NOAA) into a comprehensive geospatial dataset. The processing pipeline involves point cloud classification to separate ground and non-ground features, geometric refinement and regularization of building footprints, followed by 3D mesh generation and validation. We present a comparative analysis of Siesta Key, Florida, using LiDAR acquisitions from 2022 (pre-Hurricane Milton) and 2024 (post-Hurricane Milton). Our multi-temporal change detection reveals significant impacts on both the built and natural environments. Quantitative analysis shows a 25.3% reduction in urban canopy cover (from 17.8% to 13.3%) and substantial changes in building morphology, with aspect ratios decreasing from 0.180 to 0.141, indicating shifts toward horizontally elongated building footprints. These findings demonstrate how the dataset can be used to assess structural damage, quantify ecosystem loss, and inform recovery planning. Our work aims to lower barriers for research in disaster assessment and coastal resilience. The dataset serves as a benchmark for researchers and practitioners in fields ranging from disaster response and urban planning to forestry and coastal management, while the documented methodology provides a replicable framework for future multi-temporal LiDAR analysis.

• Publication year

  2025

• Venue

  International Conference on Systems for Energy-Efficient Built Environments

• Publication date

  2025-11-11

• Fields of study

  Geography, Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1145/3736425.3771961
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A hybrid actor- and microservices-based platform for scalable smart building application deployment

  2024cited by this paper
• Measuring Urban and Landscape Change Due to Sea Level Rise: Case Studies in Southeastern USA

  2024cited by this paper
• A Critical Review of Household Water Datasets

  2024cited by this paper
• BD3: Building Defects Detection Dataset for Benchmarking Computer Vision Techniques for Automated Defect Identification

  2024cited by this paper
• Green Infrastructure

  2021cited by this paper
• SDNET2018: An annotated image dataset for non-contact concrete crack detection using deep convolutional neural networks

  2018cited by this paper
• Automatic extraction of building roofs using LIDAR data and multispectral imagery

  2013cited by this paper
• Airborne and terrestrial laser scanning

  2011cited by this paper

• No citing papers are available for this paper.