跳转到内容
News

Estimating coastal bathymetry from both Sentinel-1 and Sentinel-2 using image processing and machine learning techniques

Bathymetry retrieval in coastal waters is a particularly interesting application of satellite Earth Observation. In fact, creating a bathymetry map from traditional data (shipborne sonar or airborne lidar) is both costly and time consuming, while satellite data can provide maps over large areas in a very short time. However the processing involved in bathymetry retrieval and the interpretation of the results is mastered only by a handful of experts today. This may be about to change, thanks to some recent work on the Coastal TEP.

The Coastal TEP is a cloud-based ‘one-stop shop’ that gathers coastal-zone satellite data, processing algorithms and computing power. Obviously coastal bathymetry has been one of the main topics of interest for the Coastal TEP project.

In the frame of the ESA project ECOBAW, Céline Danilo from Univ. of Trento, has implemented in the Coastal TEP an algorithm which retrieves coastal bathymetry using Sentinel-2 images. In collaboration with Prof. Farid Melgani at Univ. of Trento, this project aims to develop applications for estimating coastal bathymetry without any ancillary data (wave period or pre-information of the bathymetry) from both Sentinel-1 and Sentinel-2 using image processing and machine learning techniques.

The algorithm implemented in Coastal TEP, depends on a first estimation of coastal bathymetry with a coarse resolution and on the reflectance of the four spectral bands of the visible and near infrared domain. In the ECOBAW project, this first estimation is provided by a model based on wave propagation and described in an IEEE TGRS publication[1]. Such estimation is successively improved by means of an innovative approach using a Gaussian Process Regression (GPR) model. In particular, it uses these first estimations as target values to train a GPR model which has as input the four spectral bands. The GPR model learned is then able, given the reflectance of the four spectral bands, to estimate the water depth and a related confidence value (estimate variance).  The theoretical principle relies then on the light extinction with water depth. This approach is thus capable to improve the knowledge of the coastal water depth, especially regarding the resolution and the coverage of the training values. Besides, the algorithm can be applied to any cloudless image and is completely unsupervised and automatic.

After validation of her processor, Céline was able to integrate the processor on the Coastal. It is now available to other users as a “contributed” processor in the Coastal TEP catalogue. In this way, all users will be able to reproduce Céline’s results.

The good thing about Coastal TEP is that it provides an easy interface to integrate a processor, so algorithms developers can work autonomously with minimal support from the Coastal TEP team. Within some weeks, Céline has been able to process some Sentinel-2 images on the platform and compute a bathymetry map for the beach of Waimanalo in Hawaii.

This first success has generated many ideas for the future.

We could extend the capabilities of the current processing to be able to handle any geographical zone. Even if the model providing the first estimation is not yet available on the platform, any other kind of first estimations could be exploited as well for training the model. 

We could also provide other bathymetry retrieval algorithms and allow users to choose between different approaches. Indeed each algorithm has its benefits and drawbacks, so having a set of processors can improve the reliability of the EO-based retrieval. A benchmark of algorithms on a given site where reference in-situ measurements are available could make a lot of sense for the future. It would help provide guidelines and recommendations and help promote the use of EO-derived bathymetry maps.

 

[1] Céline Danilo and Farid Melgani, “Wave Period and Coastal Bathymetry Using Wave Propagation on Optical Images,” IEEE Transactions on Geoscience and Remote Sensing 54, no. 11 (2016): 6307–6319.

Space helps forest regenerate

In Finland, conifers are not only the most common native species of tree, but economically the most important. Once the trees have been felled, seedlings are planted as part of the regeneration process. Read more here

Exploitation Platforms Open Architecture released

The first version of the Exploitation Platforms Open Architecture has been released. You can find it on this website document repository (for registered users, under the "Public/Exploitation Platforms Open Architecture 1.0" folder) or download it directly from this link.

The Exploitation Platforms Open Architecture is a joint effort of all the Thematic Exploitation Platforms to produce an high-level architecture for the building of an Exploitation Platform, based on Open Source Software components and Open Interfaces. The document is released under CC BY-SA license, freely usable for commercial and non-commercial use.

Satellites guide ships in icy waters through the cloud

In late August, the 60 m-long US Coase Guard Cutter Maple completed its navigation through the Arctic's ice-ridden Northwest Passage. While this was not the first time ships had taken this route, it was the first time that the International Ice Patrol had provided iceberg information based exclusively on satellite imagery. Read the full story here

TEPs @EO Open Science

 


There was a good amount of interest towards TEPs in the EO Open Science 2017 conference last week, and many demos and interesting discussions were held with the visitors. 

You can revisit TEPs session at the following link: 

https://livestream.com/ESA/OpenScience2017/videos/163370875

With the majority of TEPS now in the pre-operations phase we look forward for other opportunities to meet all interested users.

TEPs @ Land Training Course

The "7th Advanced Training Course on Land Remote Sensing" has just concluded and we had the opportunity to join with the participants at the Szent István University, Gödöllő, Hungary.

The course was attended by more than 70 students from both academic and industrial sectors, representing more than 30 different countries. 

During the event a practical class on "Cloud Computing and the ESA Exploitation Platforms" was provided for the students and we had the opportunity to explain the challenges that the TEPs have faced and to give them the opportunity to experiment for themselves with the beta versions of the platforms, currently in pre-operations.

The students expressed interest in the usage of the TEPs for their research objectives and have now been invited to submit proposals to become early adopters and benefit from the expansion of the TEP user community.

The next opportunity to meet the TEP experts will be at the ESA EO Open Science where there will also be the possibility to join "hands on sessions" with each TEP.

Ad majora

Geohazard TEP (GEP) expanding users' base

The GEP (Geohazard Thematic Exploitation Platform) Early Adopters programme is now welcoming new institutions with their users to take advantage of the platform capabilities.

Started in 2015 with 29 users, the GEP Early Adopters programme now includes 61 users and 54 different organisations from 19 countries, read more about this on the the GEP blog.

Users interested in geohazard analysis, GEP tools and the related products are invited to visit the Geohazard Portal.

Urban TEP in pre-operation phase

The Urban Thematic Exploitation Platform (U-TEP) has now entered the pre-operations phase.

Due to a new set of products with unique precision and consistency such as the Global Urban Footprint and the TimeScan, the U-TEP will enable analysis of the large-scale transformation occurring on the Earth: the Urban Era.

If you are interested in Urban analysis, U-TEP tools and the related products, please visit the Urban TEP website.

Coastal TEP Starts Pre-Operations

The Coastal Thematic Exploitation Platform  (C-TEP) has now entered the pre-operations phase.The existing pilot projects will be focused on exploitation of the Earth Observation data to generate and analyze indicators for aquaculture, water quality, integration of tools for information extraction from Earth Online data archives and altimetry analysis.

The C-TEP is currently inviting applications from the users interested in testing of the platforms capabilities and/or developing other relevant pilot projects.

If you are interested in testing the platform or taking part in validation activity, please contact and/or view.

Forestry TEP enters pre-operations phase

Forestry TEP has now entered the pre-operations phase, providing initial services for Forest Change, Land Cover, Biomass and Vegetation Indices as well as interactive toolboxes. Data is available from Sentinel-1, Sentinel-2 and Landsat.

Two pilot projects will be executed for forest mapping with users in Mexico and Finland. For more information visit forestry-tep.eo.esa.int or contact forestry-tep@esa.int

 

VIDEO
Urban TEP aims to promote new opportunities to enable the creation and safeguarding of liveable cities.