Earth Observation Open Science and Innovation by Pierre-Philippe Mathieu & Christoph Aubrecht
Author:Pierre-Philippe Mathieu & Christoph Aubrecht
Language: eng
Format: epub, pdf
Publisher: Springer International Publishing, Cham
Fig. 10UrbIS workspace manager interface
Fig. 11HPC computations for analysis and modeling
Fig. 12UrbIS visualization interface
After finding the needed data the user defines the region of interest and spatial resolution of his study area. At the same time in the background the system starts retrieval and sub-setting of the requested data from the external data stores. After the data has been placed into UrbIS scratch disk space the user will be notified and the records about downloaded subsets will appear in the workspace manager interface (Fig. 10). Here users can check the statistics of the downloaded data and verify completion of the download and conversion processes. All the retrieved data will be stored cloud-side and will not be downloaded to the user’s workstation unless requested. Internally the data will be converted into application-specific representations optimized for further processing and access through UrbIS web services.
At the next stage of the workflow the user will be able to choose from a library of the analytical and modeling functionality (Fig. 11). As a part of the initial UrbIS development we are implementing high-performance clustering algorithms for building typologies of the cities based on a large number of input parameters. After specifying input parameters the user will submit a task to one of the high-performance computers. UrbIS will prepare the data in the form suitable for the selected processing method and create a batch configuration file containing commands for the target high-performance platform. The user will be able to initiate processing on the target system directly from UrbIS interface. After the job completion UrbIS will retrieve the results and convert them into the formats that are used internally.
The final step of the workflow is the visualization of the results in the geographic context. For that purpose we are using WebWorldWind (https://webworldwind.org/)—a modern javascript version of NASA WorldWind that utilizes WebGL. It can be launched from within popular browsers without the need to download any plugins or desktop applications. Visualization section of UrbIS (Fig. 12) has user interface typical for a digital globe like Google Earth or NASA WorldWind. Here the user can visualize the input and output data in the geographic context. The data is fed to the visualization component with WMS and WFS services from the internal UrbIS storage. Also the user can pull the data from any other data source supported by the NASA WebWorldWind including default WorldWind layers. The user will have an ability to switch between 3D and 2D views and choose the background and portrayal methods most suitable for his visualization purposes.
Current implementation of UrbIS is being developed using nodejs for the server side components. As a spatial data storage we are using PostgreSQL with PostGIS extensions. High-performance processing components are implemented as external modules and they use languages and tools most appropriate for the specific algorithms and platform. UrbIS should be accessible from any modern browser with WebGL support enabled (for visualization component). Internally UrbIS relies on service-oriented architecture with most functionality exposed through RESTful programming interface.
Currently UrbIS is in the active development and is available for testing to internal users.
Download
Earth Observation Open Science and Innovation by Pierre-Philippe Mathieu & Christoph Aubrecht.pdf
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.
Algorithms of the Intelligent Web by Haralambos Marmanis;Dmitry Babenko(8332)
Azure Data and AI Architect Handbook by Olivier Mertens & Breght Van Baelen(7022)
Building Statistical Models in Python by Huy Hoang Nguyen & Paul N Adams & Stuart J Miller(7010)
Serverless Machine Learning with Amazon Redshift ML by Debu Panda & Phil Bates & Bhanu Pittampally & Sumeet Joshi(6892)
Data Wrangling on AWS by Navnit Shukla | Sankar M | Sam Palani(6674)
Driving Data Quality with Data Contracts by Andrew Jones(6638)
Machine Learning Model Serving Patterns and Best Practices by Md Johirul Islam(6367)
Learning SQL by Alan Beaulieu(6030)
Weapons of Math Destruction by Cathy O'Neil(5824)
Big Data Analysis with Python by Ivan Marin(5507)
Data Engineering with dbt by Roberto Zagni(4516)
Solidity Programming Essentials by Ritesh Modi(4163)
Time Series Analysis with Python Cookbook by Tarek A. Atwan(4033)
Pandas Cookbook by Theodore Petrou(3735)
Blockchain Basics by Daniel Drescher(3326)
Hands-On Machine Learning for Algorithmic Trading by Stefan Jansen(2925)
Feature Store for Machine Learning by Jayanth Kumar M J(2833)
Learn T-SQL Querying by Pam Lahoud & Pedro Lopes(2820)
Mastering Python for Finance by Unknown(2759)
