Land Analytics Earth Observation Platform

GSTP: Make Project: Land Analytics Earth Observation Platform

 

Company	Country	Website
Indra Sistemas S.A.	Spain	http://www.indracompany.com

 

With the advent of Sentinel data, Land Monitoring is entering in a new era with unprecedented combined spatial and temporal resolution data freely available. Moreover, the data deluge should be promptly and intelligently addressed to extract useful information from different sources without the risk of being flooded by data.

The Land Analytics Earth Observation Platform is the tool to address both challenges. It combines the capacity of processing big volumes of satellite imagery with the capacity of extract meaningful information form data using analytics tools.

Objectives

The objectives of the project are:

• To create a flexible platform that is capable to process big volumes of Satellite-borne data in an efficient manner to produce Land-related Earth Observation information
• To boost the value of Sentinel 1 and 2 and to explore the possibilities of using Sentinel together with data from other constellations
• To use analytics capabilities to add value to traditional land monitoring products
• To enhance the quality of land monitoring products making use of a wide array of ancillary scientific and non-scientific information, penetrating in sources not used traditionally in Earth Observation
• To advance in the use of Location-Based Social Networks for the improvement of land monitoring products
• To create a platform flexible enough to address different industrial requirements and able to be marketed as a built-up solution

Features

The architecture of the system is based in two different components: the processing subsystem and the analytics subsystem.

The Processing Subsystem is in charge of retrieve and download satellite imagery, ingest and cataloguing the data, orchestrate the processors in charge of generating the EO parameters and disseminate the generated products.

The design of the platform allows to deploy it on regular cloud infrastructure, being able to process vast amounts of data due to their scalability (including continuous update of the final output if it is demanded). It is modular and allows the flexibility of access data from different constellations and change the Earth Observation processors so it produces different thematic outputs just by making use of different algorithms.

The Analytics Subsystem is in charge of retrieving ancillary information from multiple sources, ingest the intermediate EO product, and orchestrate the processors to apply the analytics algorithms, disseminate the generated products and feedback the processing subsystem to improve algorithms of the Processing Subsystem.

The analytics capabilities of the platform are able to provide added value to the traditional Earth Observation product. Information hidden in the satellite data, relations between satellite data and other scientific sources and finally, the innovative use of IoT and Location-Based Social Networks allow the platform to be able to extract useful information from apparently undecipherable datasets.

Project Plan

Phase 1: Design

• To find the technological solution to deploy the platform in a cloud infrastructure
• To ensure an efficient interaction between Earth Observation and analytics methodologies
• To provide a solution flexible enough to: ingest EO and non-EO data from different sources and  to produce a variety of land monitoring outputs

Phase 2: Development

• To develop and modify software components to have the platform up and running in a cloud environment.
• To optimize the processing capacities of the platform
• To optimize the cost-benefit analysis both meeting the specifications of the demonstrator and the specifications of foreseen industrial uses of the platforms

Phase 3: Demonstration

• The platform must provide meaningful outputs. Thus, the demonstration phase is mainly focused on making the platform run with real data and producing land monitoring layers (Water and Wetness, according to one of the most demanded land products) that can be validated using ground-truth information (also provided automatically by the platform)

Key issues

The key issues of the project are:

• The use of commercial cloud services for a platform deployment
• The use of analytics functions to get the most of scientific and social-borne data
• To identify and unlock hidden value in satellite data and scientific big data databases (atmospheric, climatic)
• To improve the use of non-conventional information to boost the value of land monitoring products
• To provide the framework of validation of land monitoring products using Location Based Social Networks information
• To produce a layer on Water and Wetness according to the specifications of the European Environment Agency High Resolution Layer

Expected Main Benefits

The use of analytics functions with EO and non-EO data will bring the following benefits:

• Production of thematically enhanced land monitoring products by extracting information hidden in the EO data itself and exploiting relations between EO and non-EO data.
• Production of ad-hoc outputs for a selected time-lapse, for instance by selection a time frame of an event like flooding.
• Production of outputs in a daily, 10-day, seasonal and year-long basis, suited to take into account seasonal and phenological changes (water and wetness layer will be more meaningful if it is linked to the seasons, especially in certain climatic zones of Europe)
• Generation of continuous update of a land monitoring product, instead of fixed-date products
• Production of a wide arrange of enhanced EO products from a variety of satellites, structured and un-structured ancillary sources

Current Status (12/7/2018)

The Land Analytics Earth Observation Platform activity has been successfully completed with the Final Review on 4^th July 2018, meeting all the objectives of the project. The main achievements are:

• Alignment of the processing capacity of Indra with the state-of-the art in Earth Observation downstream services using the EO+cloud+analytics formula.
• Refinement of the water and wetness extraction processors by using time series and other sources for statistical cleansing.
• Fully industrial implementation of the platform in a cloud environment using virtual machines.
• Improvement of the performance of the platform by refining the alignment between cloud architecture and the platform components.
• Extraction of time series waterbodies for real industrial needs as several offers and projects related to topics as emergencies and security.

Contacts

Project Manager:	Alberto Lorenzo Alonso	alorenzoa@indra.es
	C/ Mar Egeo 4, 28830 San Fernando de Henares (Madrid)	Indra Sistemas S.A.
	+34916273292
Additional Contact:	Marino Palacios	mpalacios@indra.es
	C/ Mar Egeo 4, 28830 San Fernando de Henares (Madrid)	Indra Sistemas S.A.
	+34916273292
ESA Technical Officer:	Nicolas Girault	nicolas.girault@esa.int