Date: March 2019

Author: Robbi Bishop-Taylor, Stephen Sagar, Leo Lymburner (Digital Earth Australia, Geoscience Australia)

License: CC BY Attribution 4.0 International License

Scientific reference: Bishop-Taylor et al. 2019 (https://doi.org/10.1016/j.ecss.2019.03.006)

Product description and metadata: https://knowledge.dea.ga.gov.au/data/old-version/dea-intertidal-elevation-landsat-1.0.0 (deprecated)

The National Intertidal Digital Elevation Model (NIDEM; Bishop-Taylor et al. 2018, 2019) is a continental-scale elevation dataset for Australia's exposed intertidal zone. NIDEM provides the first three-dimensional representation of Australia's intertidal sandy beaches and shores, tidal flats and rocky shores and reefs at 25 m spatial resolution, addressing a key gap between the availability of sub-tidal bathymetry and terrestrial elevation data. NIDEM was generated by combining global tidal modelling with a 30-year time series archive of spatially and spectrally calibrated Landsat satellite data managed within the Digital Earth Australia (DEA) platform. NIDEM complements existing intertidal extent products, and provides data to support a new suite of use cases that require a more detailed understanding of the three-dimensional topography of the intertidal zone, such as hydrodynamic modelling, coastal risk management and ecological habitat mapping.

Intertidal environments support important ecological habitats (e.g. sandy beaches and shores, tidal flats and rocky shores and reefs), and provide many valuable benefits such as storm surge protection, carbon storage and natural resources for recreational and commercial use. However, intertidal zones are faced with increasing threats from coastal erosion, land reclamation (e.g. port construction), and sea level rise. Accurate elevation data describing the height and shape of the coastline is needed to help predict when and where these threats will have the greatest impact. However, this data is expensive and challenging to map across the entire intertidal zone of a continent the size of Australia.

The rise and fall of the ocean can be used to describe the three-dimensional shape of the coastline by mapping the land-sea boundary (or 'waterline') across a range of known tides (e.g. low tide, high tide). Assuming that these waterlines represent lines of constant height relative to mean sea level (MSL), elevations can be modelled for the area of coastline located between the lowest and highest observed tide. To model the elevation of Australia's entire intertidal zone, 30 years of satellite images of the coastline (between 1986 and 2016 inclusive) were obtained from the archive of spatially and spectrally calibrated Landsat observations managed within the Digital Earth Australia (DEA) platform. Using the improved tidal modelling framework of the Intertidal Extents Model v2.0 (ITEM 2.0; Sagar et al. 2017, 2018), each satellite observation in the 30 year time series could be accurately associated with a modelled tide height using the global TPX08 ocean tidal model. These satellite observations were converted into a water index (NDWI), composited into discrete ten percent intervals of the observed tide range (e.g. the lowest 10% of observed tides etc), and used to extract waterlines using a spatially consistent and automated waterline extraction procedure. Triangulated irregular network (TIN) interpolation was then used to derive elevations relative to modelled mean sea level for each 25 x 25 m Landsat pixel across approximately 15,387 sq. km of intertidal terrain along Australia's entire coastline.

NIDEM differs from previous methods used to model the elevation of the intertidal zone which have predominately focused on extracting waterlines from a limited selection of satellite images using manual digitisation and visual interpretation (e.g. Chen and Rau 1998; Zhao et al. 2008; Liu et al. 2013; Chen et al. 2016). This manual process introduces subjectivity, is impractical to apply at a continental-scale, and has inherent restrictions based on the availability of high quality image data at appropriate tidal stages. By developing an automated approach to generating satellite-derived elevation data based on a 30 year time series of observations managed within the Digital Earth Australia (DEA) platform, it was possible to produce the first continental-scale three-dimensional model of the intertidal zone.

To generate NIDEM datasets:

1. Set the locations to input datasets in the NIDEM_configuration.ini configuration .ini file
2. On the NCI, run the NIDEM_pbs_submit.sh shell script which iterates through a set of ITEM polygon tile IDs in parallel. This script calls NIDEM_generation.py, which conducts the actual analysis.

The National Intertidal Digital Elevation Model (NIDEM) consists of four raster datasets (NIDEM, c and f below; unfiltered NIDEM, b and e below; NIDEM mask, a and d below; and NIDEM uncertainty) and two vector datasets (NIDEM waterline contours and ITEM v2.0 tidal modelling polygons). For convenience, the four raster datasets are provided both as individual geotiff/NetCDF files, and continental-scale geotiff mosaics.

The NIDEM dataset provides elevation in metre units relative to modelled Mean Sea Level for each pixel of intertidal terrain across the Australian coastline. The DEMs have been cleaned by masking out non-intertidal pixels and pixels where tidal processes poorly explain patterns of inundation (see NIDEM mask below). This is the primary output product, and is expected to be the default product for most applications. The dataset consists of 306 raster files corresponding to the 306 ITEM v2.0 tidal modelling polygons, and a continental-scale mosaic.

Naming convention:

• NIDEM_{polygon_id}_{tidalmodelling_coords}
• e.g. NIDEM_33_130.91_-12.26.tif
• Continental mosaic: NIDEM_mosaic.tif

Attributes:

• Single band float raster
• -9999: NoData
• All other values: elevation in metre units relative to modelled Mean Sea Level

The unfiltered NIDEM dataset provides un-cleaned elevation in metre units relative to modelled Mean Sea Level for each pixel of intertidal terrain across the Australian coastline. Compared to the default NIDEM product, these layers have not been filtered to remove noise, modelling artefacts or invalid elevation values (see NIDEM mask below). This supports applying custom filtering methods to the raw NIDEM data. The dataset consists of 306 raster files corresponding to the 306 ITEM v2.0 tidal modelling polygons, and a continental-scale mosaic.

Naming convention:

• NIDEM_unfiltered_{polygon_id}_{tidalmodelling_coords}
• e.g. NIDEM_unfiltered_33_130.91_-12.26.tif
• Continental mosaic: NIDEM_unfiltered_mosaic.tif

Attributes:

• Single band float raster
• -9999: NoData
• All other values: elevation in metre units relative to modelled Mean Sea Level

The NIDEM mask dataset flags non-intertidal terrestrial pixels with elevations greater than 25 m, and sub-tidal pixels with depths greater than -25 m relative to Mean Sea Level. Pixels where tidal processes poorly explain patterns of inundation are also flagged by identifying any pixels with ITEM confidence NDWI standard deviation greater than 0.25. The NIDEM mask was used to filter and clean the NIDEM dataset to remove modelling artefacts and noise (e.g. intertidal pixels in deep water or high elevations) and invalid elevation estimates caused by coastal change or poor model performance. The dataset consists of 306 raster files corresponding to the 306 ITEM v2.0 tidal modelling polygons, and a continental-scale mosaic.

Naming convention:

• NIDEM_mask_{polygon_id}_{tidalmodelling_coords}
• e.g. NIDEM_mask_33_130.91_-12.26.tif
• Continental mosaic: NIDEM_mask_mosaic.tif

Attributes:

• Single band integer raster
• 1: Non-intertidal terrestrial pixels with elevations greater than 25 m
• 2: Sub-tidal pixels with depths greater than -25 m
• 3: ITEM confidence NDWI standard deviation greater than 0.25 (pixels where tidal processes poorly explain patterns of inundation)
• -9999: NoData

The NIDEM uncertainty dataset provides a measure of the uncertainty (not to be confused with accuracy) of NIDEM elevations in metre units for each pixel. The range of Landsat observation tide heights used to compute median tide heights for each waterline contour can vary significantly between tidal modelling polygons. To quantify this range, the standard deviation of tide heights for all Landsat images used to produce each ITEM interval and subsequent waterline contour was calculated. These values were interpolated to return an estimate of uncertainty for each individual pixel in the NIDEM datasets: larger values indicate the waterline contour was based on a composite of images with a larger range of tide heights. The dataset consists of 306 raster files corresponding to the 306 ITEM v2.0 tidal modelling polygons, and a continental-scale mosaic.

Naming convention:

• NIDEM_uncertainty_{polygon_id}_{tidalmodelling_coords}
• e.g. NIDEM_uncertainty_33_130.91_-12.26.tif
• Continental mosaic: NIDEM_uncertainty_mosaic.tif

Attributes:

• Single band float raster
• -9999: NoData
• All other values: standard deviation of tide heights of all Landsat imagery used to generate each ITEM tidal interval in metre units

The NIDEM waterline contour dataset provides a vector representation of the boundary of every ten percent interval of the observed intertidal range. These contours were extracted along the boundary between each ITEM v2.0 tidal interval, and assigned the median and standard deviation (see NIDEM uncertainty above) of tide heights from the ensemble of corresponding Landsat observations. These datasets facilitate re-analysis by allowing alternative interpolation methods (e.g. kriging, splines) to be used to generate DEMs from median tide heights. The dataset consists of 306 shapefiles corresponding to polygons of the ITEM v2.0 continental scale tidal model.

Naming convention:

• NIDEM_contours_{polygon_id}_{tidalmodelling_coords}
• e.g. NIDEM_contours_33_130.91_-12.26.shp

Attributes:

• Polyline shapefile
• elev_m: median tide height of the ensemble of Landsat observations for each ten percent tidal interval
• uncert_m: standard deviation tide height of the ensemble of Landsat observations for each ten percent tidal interval

The ITEM v2.0 tidal model polygon dataset describes the multi-resolution tidal framework developed by Sagar et al. (2018). The framework uses partitioning methods to allow spatial variability in the tidal model to drive the size and locations of a Voronoi polygon mesh. The 306 resulting tidal modelling polygons are then used as analysis units for tidal modelling, with tide height predictions defined at the nodes of each Voronoi cell. To evaluate the representativeness of NIDEM data compared to the full tidal range, the spread of tidal heights coincident with the input Landsat imagery was compared against the full range of modelled tide heights present within each tidal modelling polygon. Three indices were calculated: spread (the proportion of the full modelled tidal range observed by Landsat), low tide offset (the proportion of the lowest tidal heights not observed by Landsat) and high tide offset (the proportion of the highest tidal heights not observed by Landsat). This evaluation of the observed tidal range at a particular location provides valuable information to users about the 'fitness for purpose' of NIDEM at a given location for their specific application (see Bishop-Taylor et al. 2019).

Naming convention:

• ITEMv2_tidalmodel.shp

Attributes:

• Polygon shapefile
• polygon_id: tidal modelling polygon ID (ranges from 1 to 306)
• lat: latitude of the Voronoi point used to derive tidal heights for polygon
• lon: longitude of the Voronoi point used to derive tidal heights for polygon
• spread: proportion of the full modelled tidal range observed by Landsat for polygon
• offset_low: low tide offset; the proportion of the lowest tidal heights not observed by Landsat for polygon
• offset_high: high tide offset; the proportion of the highest tidal heights not observed by Landsat for polygon

To assess the accuracy of NIDEM, we compared modelled elevations against three independent elevation and bathymetry validation datasets: the DEM of Australia derived from LiDAR 5 Metre Grid (Geoscience Australia, 2015), elevation data collected from Real Time Kinematic (RTK) GPS surveys (Danaher & Collett, 2006; HydroSurvey Australia, 2009), and 1.0 m resolution multibeam bathymetry surveys (Solihuddin et al., 2016). We assessed overall accuracy across three distinct intertidal environments: sandy beaches and shores, tidal flats, and rocky shores and reefs:

NIDEM covers the exposed intertidal zone which includes sandy beaches and shores, tidal flats and rocky shores and reefs. The model excludes intertidal vegetation communities such as mangroves.

Areas with comparatively steep coastlines and small tidal ranges are poorly captured in the 25 m spatial resolution input Landsat data and resulting NIDEM model. This includes much of the south eastern and southern Australian coast (e.g. New South Wales, Victoria, Tasmania).

Poor validation results for rocky shore and reef sites within the southern Kimberly region highlighted limitations in the NIDEM model that occur when the global OTPS TPX08 Atlas Tidal Model was unable to predict complex and asynchronous local tidal patterns. This is likely to also reduce model accuracy in complex estuaries and coastal wetlands where river flow or vegetative resistance causes hydrodynamic attenuation in tidal flow.

The complex temporal behaviour of tides mean that a sun synchronous sensor like Landsat does not observe the full range of the tidal cycle at all locations (see ITEM v2.0 tidal modelling polygons above). This causes spatial bias in the proportion of the tidal range observed in different regions, which can prevent NIDEM from providing elevation data for areas of the intertidal zone exposed or inundated at the extremes of the tidal range. Accordingly, NIDEM provides elevation data for the portion of the tidal range observed by Landsat, rather than the full tidal range.

While image compositing and masking methods have been applied to remove the majority of noise and non-tidal artefacts from NIDEM, issues remain in several locations. It is recommended that the data be used with caution in the following areas:

• The Recherche Archipelago in southern Western Australia
• Port Phillip Bay in Victoria
• The south-eastern coast of Tasmania and King Island
• Saunders Reef and surrounds in the northern Coral Sea

Bishop-Taylor, R., Sagar, S., Lymburner, L., 2018. National Intertidal Digital Elevation Model 25m 1.0.0 [WWW Document]. Geoscience Australia. URL http://pid.geoscience.gov.au/dataset/ga/123678

Bishop-Taylor, R., Sagar, S., Lymburner, L., Beaman, R.L., 2019. Between the tides: modelling the elevation of Australia's exposed intertidal zone at continental scale. Estuar. Coast. Shelf Sci. https://doi.org/10.1016/j.ecss.2019.03.006

Chen, Y., Dong, J., Xiao, X., Zhang, M., Tian, B., Zhou, Y., Li, B., Ma, Z., 2016. Land claim and loss of tidal flats in the Yangtze Estuary. Sci. Rep. 6, 24018. https://doi.org/10.1038/srep24018

Danaher, T., Collett, L., 2006. Development, optimisation and multi-temporal application of a simple Landsat based water index, in: Proceeding of the 13th Australasian Remote Sensing and Photogrammetry Conference, Canberra, ACT, Australia.

Geoscience Australia, 2015. Digital Elevation Model (DEM) of Australia derived from LiDAR 5 Metre Grid [WWW Document]. URL http://pid.geoscience.gov.au/dataset/ga/89644 (accessed 9.25.18).

HydroSurvey Australia, 2009. Report for bathymetric and benthic survey of the proposed East Point outfall (No. Part 2), Bathymetric Report No. Survey No. 018_08. Power and Water Corporation/GHD.

Liu, Y., Li, M., Mao, L., Cheng, L., Li, F., 2013. Toward a method of constructing tidal flat digital elevation models with MODIS and medium-resolution satellite images. J. Coast. Res. 438-448. https://doi.org/10.2112/JCOASTRES-D-12-00088.1

Sagar, S., Roberts, D., Bala, B., Lymburner, L., 2017. Extracting the intertidal extent and topography of the Australian coastline from a 28 year time series of Landsat observations. Remote Sensing of Environment 195, 153-169. doi:10.1016/j.rse.2017.04.009

Sagar, S., Phillips, C., Bala, B., Roberts, D., Lymburner, L., 2018. Generating continental scale pixel-based surface reflectance composites in coastal regions with the use of a multi-resolution tidal model. Remote Sens. 10, 480. https://doi.org/10.3390/rs10030480

Solihuddin, T., O'Leary, M.J., Blakeway, D., Parnum, I., Kordi, M., Collins, L.B., 2016. Holocene reef evolution in a macrotidal setting: Buccaneer Archipelago, Kimberley Bioregion, Northwest Australia. Coral Reefs 1-12. https://doi.org/10.1007/s00338-016-1424-1

Zhao, B., Guo, H., Yan, Y., Wang, Q., Li, B., 2008. A simple waterline approach for tidelands using multi-temporal satellite images: A case study in the Yangtze Delta. Estuar. Coast. Shelf Sci. 77, 134-142. https://doi.org/10.1016/j.ecss.2007.09.022