Advanced Information Systems Technology
Pioneering the Next-Generation of Intelligent Systems for Earth Science
NASA’s Advanced Information Systems Technology (AIST) Program identifies, develops, and supports adoption of software and information systems, as well as novel computer science technologies expected to be needed by the Earth Science Division in the 5-10-year timeframe.
AIST’s previous thrusts have been New Observing Strategies (NOS) and Analytic Collaborative Frameworks (ACF). The current vision is to connect these two thrusts and integrate them into the larger concept of Earth System Digital Twins (ESDT).
To implement this new vision, the AIST Program is focusing on technologies and innovative concepts with three main objectives:
- O1. Enable new observation measurements and new observing systems design and operations through intelligent, timely, dynamic, and coordinated distributed sensing;
- O2. Enable agile science investigations that fully utilize the large amount of diverse observations using advanced analytic tools, visualizations, and computing environments, and that interact seamlessly with relevant observing systems;
- O3. Enable the development of integrated Earth Science frameworks that mirror the Earth with state-of-the-art models (Earth system models and others), timely and relevant observations, and analytic tools. This thrust will provide technology for enabling near- and long-term science and policy decisions (“science decisions” including planning for the acquisition of new measurements; the development of new models or science analysis; the integration of Earth observations in novel ways; applications to inform choices, support decisions, and guide actions for societal benefit; etc.).
The three thrusts are described below.
NOS Technologies, which respond to Objective O1, concentrate on optimizing measurement acquisitions by using diverse observing and modeling capabilities, representing various resolutions, dynamically coordinated and collaborating to provide complete representations of Earth Science phenomena. The observing assets can be in space, in the air, or in situ, and the observed phenomena may exist on a variety of spatial or temporal scales (e.g., real-time tracking of hazards and disasters or long-term asset coordination for continuous ecosystem monitoring). NOS can be described as a federated Observing System, a generalized SensorWeb, or more generally as an “Internet-of-Space (IoS)” concept in which each node can be a sensor, a group of sensors, a constellation of satellites (e.g., Earth System Observatory concept), a model or integrated models, or even database(s) or any other source of relevant information, that have varying degrees of coordination to achieve a common science objective. The two main NOS goals are to:
- Design and develop future observation concepts at the request of a new measurement, for example as identified in the latest Decadal Survey or as the result of a model or other science data analysis; and
- Dynamically respond to science and applied science events of interest, not only focusing on rapid disaster-like events, but also considering mid- and long-term events and various area coverages, from global to regional to local-impact events, (e.g., distressed vegetation, potential landslides due to runoff, etc.).
More details about NOS are available in the 2020 NOS Workshop Report. A prototyped use case using a flood scenario and the NOS Testbed is presented in the first NOS-Testbed (NOS-T) demonstration (May 28, 2021).
For more information on AIST NOS projects, please download our 2021 NOS Annual Reviews (PDF / 184MB).
Once an Earth observing mission is in operation, we can expect a lot of data back on land. Data from different missions often arrive in different formats, and when combined with ground-based and airborne-derived data, things get tricky. Scientists can look to this framework, which incorporates software tools like machine learning, to help them more easily use and visualize the data in their research.
ACF technologies respond to AIST Objective O2 and address the challenges associated to observing systems such as NOS systems which will acquire an increased variety and volume of data over various geographical scales, latencies, and frequencies. The ACF thrust is designed to facilitate access, integration, and understanding of large amounts of disparate datasets. Its purpose is to harmonize analytics tools, data, visualization and computing environments to meet the needs of Earth science investigations and applications. The ACF thrust integrates new or previously unlinked datasets, tools, models, and a variety of computing resources together into a common platform to address previously intractable scientific and science-informed application questions. Additionally, this activity seeks to generalize custom or unique tools that are currently used by a limited community of experts or practitioners, to make them accessible and useful to a broader community. ACF focuses on reducing the amount of time a science user spends on data preparation and enables the tailoring of configurations of datasets and reusable tools to avoid repetitive work (e.g., by developing reusable components).
Both NOS and ACF aim at optimizing Earth Science mission return – NOS from an observation point of view and ACF from an analysis point of view. The assets and data accessed and utilized in these investigations may come from NASA and non-NASA sources, as described in the National Academy of Sciences (NAS) 2017 Earth Science Decadal Survey.
For more information on AIST ACF projects, please download our 2021 ACF Project Reviews from January (PDF / 111MB) and February (PDF / 116MB). For more information about how autonomy can impact future NASA missions, please explore the 2018 Workshop on Autonomy for Future NASA Science Missions.
Earth System Digital Twins
AIST defines an Earth System Digital Twin (ESDT) as an interactive and integrated multidomain, multiscale, digital replica of the state and temporal evolution of Earth systems. It dynamically integrates: relevant Earth system models and simulations; other relevant models (e.g., related to the world’s infrastructure); continuous and timely (including near real time and direct readout) observations (e.g., space, air, ground, over/underwater, Internet of Things (IoT), socioeconomic); long-time records; as well as analytics and artificial intelligence tools. Effective ESDTs enable users to run hypothetical scenarios to improve the understanding, prediction of and mitigation/response to Earth system processes, natural phenomena and human activities as well as their many interactions.
An ESDT is a type of integrated information system that, for example, enables continuous assessment of impact from naturally occurring and/or human activities on physical and natural environments. ESDT technologies respond to Objective O3.
AIST ESDT strategic goals are to:
- Develop information system frameworks to provide continuous and accurate representations of systems as they change over time;
- Mirror various Earth science systems and utilize the combination of Data Analytics, Artificial Intelligence, Digital Thread , and state-of-the-art models to help predict the Earth’s response to various phenomena;
- Provide the tools to conduct “what if” investigations that can result in actionable predictions.
The AIST ESDT thrust will develop capabilities toward the development of future digital twins of the Earth or of subcomponents of the Earth, as well as toward the development of an overarching framework that will continuously evolve and connect the various components developed by Research and Analysis, Applied Sciences, Data Systems, and Computational Capabilities from other Earth Science Programs. From an AIST point of view, ESDT capabilities will integrate Earth observations analysis and understanding capabilities provided by ACF-type systems and on-demand and timely IoT and IoS data using NOS capabilities, while taking advantage of advanced Machine Learning, Big Data Analytics, and powerful computational and visualization capabilities.
For more background information about Digital Twins and related technologies, please download this list of references (PDF / 133 KB).
AIST Project Highlights
Novel Algorithms Merge Ground- and Space-based Data to Forecast Air Pollution Events
A NASA-sponsored research team is developing new machine-learning software that uses data from satellites and ground-based sensors to forecast air pollution events in Los Angeles.
A Coordinated Dance in Outer Space
A new tool simulates how future sensors on satellites will communicate with each other to coordinate how best to image Earth.
Mapping Biodiversity as the Climate Changes
A new interactive map helps predict where species will move in a warmer climate.
AIST uses the NASA Research Announcement as its investment vehicle. Links to the full solicitations and awards are listed below.
As of July 2, 2021, the 2021 solicitation for the Advanced Information Systems Technology (AIST) Program is open as element A.46 of the ROSES-21 omnibus announcement.
Step-1 proposals are due August 25, 2021, and Step-2 proposals are due November 30, 2021.