Quite a few coastal properties in Wamberal (NSW) are at risk of constant coastal erosion. This is again heightened by the threat from two Australian East Coast Lows affecting the NSW coast in recent few weeks.

Two independent approaches, together with high-resolution public data sources, can be used to map the coastal settlement.

1.  LiDAR-based Geospatial Approach

We use LiDAR data available at Geoscience Australia (link). Generalised building footprints are modelled from dense LiDAR point clouds and then average roof heights for individual buildings estimated (Figure 1).

Figure 1: Generalised building footprints modelled from LiDAR data. Location: Wamberal, NSW.

2.  Imagery-based AI Approach

Open imagery data is available at NSW Spatial Services (link). High-resolution aerial imagery and a deep learning technique are used to map building footprints (Figure 2), and our previous blog covers this topic.

Figure 2: Generalised building footprints extracted from high-resolution imagery. Location: Wamberal, NSW.

We have developed workflows to implement each advanced approach above. (A hybrid integrated approach may be explored as well up to the availability of data sources.) Overall, such methods or techniques are generic and can be used to map similar built environment.

P.S. Our previous work of mapping other low-lying coastal areas in Australia using high-resolution tiled web maps on terrain & hydrology can be found in this blog (link). Those web maps cover the overwhelming majority of populated coastal areas, and are readily accessible via API subscriptions or web links.

Related

– Extracting Features from High-resolution Imagery: An AI-based Processing Service link

– Building-level Geocoding of G-NAF (Address Database) for Improved Flood & Bushfire Risk Analysis in Australia link

– Creating Building Footprints and Terrain Features for Web and Desktop Mapping: With Examples from the NSW Coast link

– Products: High-resolution Web Maps on Terrain & Hydrology link