Speakers
Description
Earth observation (EO) data delivered by remote sensing satellites provides a basic service to society, with great benefits to the civilian. The data is nowadays ubiquitously used throughout society for a range of diverse applications, such as environment and resource monitoring, emergency management and civilian security. Over the past 50 years, the EO data chain that has been mastered involves acquisition process of sensor data on-board the satellite, its compression and storage on-board, and its transfer to ground by a variety of communication means, for later processing on ground and the generation of the downstream EO image products. While the market is growing, the classical EO data chain generates a severe bottleneck problem, given the very large amount of EO raw data generated on-board the satellite that must be transferred to ground, slowing down the EO product availability, increasing latency, and hampering applications to grow in accordance with the increased User Demand for EO products.
Increasing transmission throughput is one possible solution to the bottleneck problem. A different approach, which is establishing itself as a new trend for several space missions, is the implementation of processing capabilities on-board the satellite, with the goal of producing EO image products on-board that can be quickly and reliably transferred to ground given their relatively low data volume. They can also be used on-board to support increased autonomy. In recent years, several solutions have been proposed for the on-board processing of optical images, multispectral data and even SAR data, to be implemented on micro- and nano-satellites, LEO satellites and GEO satellites.
In this context, Artificial Intelligence is playing an increasing role in many aspects of space missions, and intelligent space agents, able to autonomously perform several operations, such as data processing and command and control of the space system, have been proposed, designed and in some cases successfully used. The potential for space missions to use on-board decision-making have been proposed and in some bases demonstrated by, for example, several operations of the Autonomous Sciencecraft on EO-1 [Sherwood et al.] [Tran et al.], and Sensorweb [Davies et al.] tracking volcanoes, flooding and wildfires, Machine Learning to triage enormous data streams in radio (V-FASTR) [Burke et al.] and visual (i-PTF) astronomy, Automated Targeting onboard the MER and MSL rovers (AEGIS) [Estlin et al.], automatic semantic indexing of science features (Mars Target Encyclopedia), and automation of data management for Rosetta Orbiter operations [Ferri&Sørensen].
In this paper, we provide an overview of the H2020 EU project EO-ALERT (see, EO-ALERT project website) and specify the preliminary on-board (OB) image generation and processing solution that is being developed within the project, that makes use of a combination of classical and AI solution concepts. The aim of the EO-ALERT project is to propose the definition and development of the next-generation Earth observation (EO) data and processing chain, based on a novel flight segment architecture moving optimised key EO data processing elements from the ground segment to on-board the satellite. In particular, we will focus in this paper on the on-board image generation and processing algorithms, showing the capability of the system of producing EO image products on-board and with very low latency (minutes), in two main scenarios defined for testing the potential of the proposed high-speed data chain: ship detection and extreme weather monitoring.
The first step of the processing chain, identified as Image Generation (IG), is responsible for the conversion of the raw data captured by the optical sensor into a radiance calibrated and artefact-free image, which could optionally be sent to the ground as an intermediate EO product. The second step, identified as Image Processing (IP), is responsible for extracting the product information from the images, and producing a scenario related alert that will be transferred to the ground; since the size of the final alert will be considerably smaller than the acquired raw data, the EO product and alert will be available to the final user with very low latency, much lower than in the classical EO data chain.
The paper will describe the functional blocks of the proposed IG/IP chain, as part of the overall avionics architecture. It is based on a combination of computer vision algorithms for efficient image generation and extraction of visual features from optical images, tailored to the specific scenario of interest and optimized to the lower computational capabilities of on-board hardware, in conjunction with machine learning algorithms for visual feature classification and discrimination of events of interest. In particular, a pre-trained Support Vector Machine (SVM), a popular classification tool that uses supervised machine learning theory to maximize the predictive accuracy and whose efficient implementation in field programmable gate arrays (FPGAs) has been proven by several studies, will be used as the final classifier.
The paper will provide examples of the performance of the on-board IG/IP algorithms using acquired raw data from the DEIMOS-2 payload (sub-meter) and Meteosat Second Generation (MSG) payloads from these satellite missions, showing the performance of on-board solution against the ground-based classical solution. The examples are presented to show the detection capabilities of the system in the two proposed scenarios. The paper will also present an analysis of the avionics needs for the implementation of the proposed solution, showing its feasibility in an FPGA-based on-board avionics architecture.
[Sherwood et al.] “Autonomous Science Agents and Sensor Webs: EO-1 and Beyond” Rob Sherwood, Steve Chien, Daniel Tran, Benjamin Cichy, Rebecca Castano, Ashley Davies, Gregg Rabideau
[Tran et al.] “The Autonomous Sciencecraft Experiment Onboard the EO-1 Spacecraft” Daniel Tran, Steve Chien, Rob Sherwood, Rebecca Castano, Benjamin Cichy, Ashley Davies, Gregg Rabideau
[Davies et al.] “Artificial Intelligence in the NASA Volcano Sensorweb: Over a Decade in Operations” Ashley G. Davies, Steve Chien, Joshua Doubleday, Daniel Tran, David Mclaren
[Burke et al.] “Limits on Fast Radio Bursts from Four Years of the V-FASTR Experiment” S. Burke-Spolaor, Cathryn M. Trott, Walter F. Brisken, Adam T. Deller, Walid A. Majid, Divya Palaniswamy, David R. Thompson, Steven J. Tingay, Kiri L. Wagstaff, and Randall B. Wayth
[Estlin et al.] “Automated Targeting for the MER Rovers” Tara Estlin, Rebecca Castano, Benjamin Bornstein, Daniel Gaines, Robert C. Anderson, Charles de Granville, David Thompson, Michael Burl, Michele Judd and Steve Chien
[Ferri&Sørensen] “Automated Mission Operations for Rosetta” Paolo Ferri and Erik M. Sørensen
| Paper submission | Yes |
|---|
