AI Transforming Space and Global Industries

AI Transforming Space and Global Industries

In recent years, a big increase in private investments and robust government support in space are fueling rapid innovations and expansion of the ecosystem. Looking ahead, we believe the convergence of AI (AI) and machine learning (ML) with other innovations is one of the foremost disruptive technology trends. AI is transforming the whole space ecosystem, from manufacturing to in-orbit operations like collision avoidance and optimization of spectral efficiency. AI on-board converting would allow more timely delivery of insights from space. This is often transforming not just the space industry but is additionally revolutionizing global enterprises and government operations. Even the Pentagon has announced AI national importance and is seeking partnerships with tech giants and startups to accelerate AI adoption across all operations.

Drowning in Data, But this is often Just the Tip of the Iceberg

Until recently, space was controlled by governments using large and expensive charming satellites. But now the satellite industry has significantly lower barriers to entry with the onset of the smallsat revolution which is driving an explosion of latest data with higher resolution and revisit. Additionally, growing drone fleets, Internet of Things (IoT) and new sensors are collecting ever more data of the world that it's become humanly impossible to manage, including analysis. With on the brink of 1,500 new earth observation (EO) small satellites expected to be launched within the coming years, the explosion of knowledge we are currently experiencing is simply the start. This is often added to the 400 plus small sats already launched by startups like Planet and Spire over the last five years.

New Sensors are forcing Even More Data and New Applications

New sensors like Synthetic Aperture Radar (SAR), Hyperspectral, Infrared, Automated Identification System and frequency (RF) Sensing are delivering new data sets to enrich traditional optical imagery, enabling new commercial applications through advanced analytics. SAR, unlike optical, can capture imagery altogether weather, in the dark and thru clouds. SAR startups include ICEYE, Capella, and Umbra Lab, etc. Hyperspectral imaging is often wont to find objects and identify materials with applications in oil and gas, mining, and agriculture. Startups building appearance constellations are Satellogic, NorthStar Earth & Space and HyperSat. Infrared or thermal imaging is complementary to other sensors; SatelliteVU, ConstelIR, and Koolock are building IR constellations for meteorology, environmental monitoring, and defense applications.

Next, the automated identification system, one among the payloads on Spire, which also provides weather and aircraft tracking data, allows maritime tracking and monitoring of vessels. RF Sensing startups HawkEye 360 and Kleos identify and geo-locate specific radio signals, which give valuable insights on maritime awareness when ships have turned off their AIS tracking device.

“With on the brink of 1,500 small satellites expected to be launched for earth observation, the explosion of knowledge we are currently experiencing is simply the beginning”

Technology approaches in computing power; cloud and AI/ML have allowed automated extraction of insights from massive data at scale. This is often done by training the machines to mimic humans to perform repetitive tasks like data collection, processing, object and alter detection from satellite imagery. More importantly, AI enables the fusion of remote sensing data with other ground data sets (news and social media feed, terrain data, etc.), creating big data analytics to unravel large and sophisticated problems from environmental monitoring, disaster response to enabling self-driving cars.

Customer Want More Insights and fewer Pixels

Traditional Earth Observation players like Maxar Technologies and Airbus, joined by EO startups like Planet and Spire have all developed beyond selling mere imagery to valued-added services backed AI. At an equivalent time, a good range of VC-backed geospatial analytics startups is leveraging lower cost and growing data sources to deliver geospatial intelligence or insights to enterprise and government customers. Customers are not any longer curious about pixels only an appearance for providers to assist them to extract insights to support better decisions.

Leading geospatial analytics startups pivot to specialize in Defense/Intel. These organizations offer data-agnostic platforms and deliver geospatial data as a subscription service. Orbital Insights uses Machine Learning and Computer Vision to spot economic trends at scale. For instance, it administers automated trends analysis of cars in retailer parking lots, tracks global energy supply and predicts crop yields for financial traders. Descartes and Ursa offer horizontal data platforms for patrons to access and run analytics on pre-processed multi-sourced imagery. Ursa is concentrated on providing access to analytics-ready SAR data.

Highlighting Three Startups Gaining Traction with Vertical Market Focus

First, Kayrros may be a data analytics startup with deep domain expertise within the Energy market. Like Orbital Insights and Ursa, they sell energy indicators to traders, but they also deliver insights to the Oil and Gas industry by tracking global storage, transportation, and production. Second, PlanetWatchers delivers all-weather data analytics for giant-scale natural resources and infrastructure monitoring by fusing high-resolution SAR with optical imagery. User cases include oil and gas pipeline monitoring, forestry drought and early disease detection. Lastly, Delair began in drone inspection but has expanded into Big Data Analytics targeting mining and construction. it's working with large global companies to accelerate their digital transformation by developing digital twins of their assets and activities using drone collected aerial imagery combined with satellite, sensor, and other data sources 

In summary, AI/ML is critical in unlocking the worth of remote sensing data. Geospatial AI analytics remains a nascent market and continues to face the challenge of inadequate training data and a shortage of talent. Lastly, AI will always require a person's within the loop because it is the maximum amount of an art as science. Domain expert/user is vital in working with knowledge scientists to create the proper models with the proper data input, also on the test and evaluates the algorithms and models to enhance accuracy. Digital transformation occurs when an enterprise can incorporate geospatial data/location intelligence in their workflow to trace, monitor, and manage their assets and activities.

Weekly Brief

Read Also

Unlocking the Third Dimension in Transportation

Unlocking the Third Dimension in Transportation

Andrew Munday, Practice Director for Advanced Engineering, Atkins
Drone Air Traffic Control

Drone Air Traffic Control

Lee Priest, CEO, ETAK
Military UAVs - How Interoperable SATCOM Keeps the Hunters from Becoming the Hunted

Military UAVs - How Interoperable SATCOM Keeps the Hunters from Becoming the Hunted

Rick Lober, VP and General Manager, Hughes Defense, and Intelligence Systems Division
Agile Manufacturing and Robotics: An Inside Look to the Future of Aerospace Assembly

Agile Manufacturing and Robotics: An Inside Look to the Future of Aerospace Assembly

Ted Freeman, Director of Manufacturing, Vertex Aerospace
Our Future in Space Depends on NUCLEAR FISSION

Our Future in Space Depends on NUCLEAR FISSION

Dr Christopher Boshuizen, Operating Partner, DCVC (Data Collective)
Space Technology is a $400b Workforce Development Opportunity

Space Technology is a $400b Workforce Development Opportunity

Shelli Brunswick, Chief Operating Officer, Space Foundation