Resource Data

Cornwall companies use AI to commercialize spatial data

In the coming decades, artificial intelligence (AI) will be the biggest business opportunity in the world. As we access an ever-richer tapestry of data and insights, improving deep learning through AI is intrinsically linked to increasing commercial space and satellite activity.

As the space and satellite industry in Cornwall County, UK keeps pace, so does the region’s AI capabilities. From cutting-edge AI for manufacturing to AI algorithms being developed to remove cloud cover and unlock satellite data for business transformation – Cornwall is home to a hugely unique mix of businesses leveraging the mutually beneficial relationship between the two technologies, in turn becoming a hub for innovation in AI applications.

The team at Goonhilly Earth Station Ltd, home to Britain’s Space AI institute, are spearheading Cornwall’s acceleration to become the UK’s first site for manipulated AI in space and the deep learning. The institute provides a melting pot for technology providers, industry, end users and academia to collaborate and create extraordinarily forward-thinking business opportunities. Underpinning the organization, Goonhilly has also built a state-of-the-art, GPU-enabled data center with the latest high-performance, Tier 3-4 equivalent GPU solutions.

In today’s digital world, businesses need on-demand access to real-time data, as well as AI/machine learning analytics, tools and techniques to create new business value from of their data. Goonhilly’s data infrastructure readiness has allowed many companies to test and accelerate their offerings in this area.

Meet the maverick companies taking data-driven transformations to the next level:

Aspia area

Startup Aspia Space is at the forefront of AI for Earth Observation – having developed a state-of-the-art AI algorithm that delivers unprecedented intelligence of cloud-free Earth Observation data in a near time.

Earth observation data is increasingly used for critical intelligence in multiple industrial sectors – from agriculture to environmental monitoring to land management and many more – but Earth observation satellite imagery is currently hampered by clouds, which means that intelligence is lost with each period of cloud cover.

With funding from AeroSpace Cornwall, Aspia Space has launched a cutting-edge solution that sees through the clouds. Its unique patented algorithm combines AI and Earth Observation data from cloud-penetrating Synthetic Aperture Radar (SAR) to predict detailed multi-spectral satellite images of the ground, from farmland to floodplains in passing through mountain ranges, even in the presence of 100% cloud cover.

This will allow organizations to see the big picture and finer details with precision, identify and understand trends, spot problems and predict risks, and make faster, more informed decisions.

4 Earth Intelligence

4 Earth Intelligence (4EI) also maximizes the potential of space-based data – helping to drive environmental intelligence through the unique application of AI and Earth observation. At the forefront of their field, they use space data for the good of people and the planet.

Their innovative practices stem from a diverse body of knowledge and expertise, providing solution-focused capabilities including artificial intelligence, software development, geospatial mapping and environmental analysis. The company has worked with leading public and private organizations around the world, enabling them to harness space data to deepen their knowledge and, in turn, become more environmentally conscious.

Their innovative use of space technology and AI allows them to create large-scale environmental benchmarks through the mapping of entire landscapes which can then be turned into an audit of environmental assets. This data can be translated into actionable information for a range of applications – small and large scale.

4EI’s Cornwall team focuses on the application of satellite Earth observation in the offshore renewable energy sector, in particular offshore floating wind. With the growing focus on the energy transition, space data can provide a powerful tool to increase efficiency throughout the supply chain.

Bluefruit software

Ready to revolutionize

In heavily regulated industries such as medical, aerospace, and space beyond reconnaissance, cutting-edge AI works by helping machines make smart decisions and provide critical feedback while curating data on board a local device.

Embedded software company Bluefruit has pioneered cutting-edge AI, producing a machine learning solution that achieves high levels of accuracy with small amounts of data samples – one of the main obstacles to Applied AI. Their first prototype, the Audio Classification Equipment (ACE) project is an integrated software application that can take pre-recorded audio or live audio and classify the sample into pre-trained categories. Enable machines to “listen” – diagnose internal faults through sound recognition using real-time AI solutions.

The initial training of any AI algorithm is an essential part of the R&D process, but it is so computationally intensive that each iteration can take hours, days, or even weeks on standard hardware. A key factor in the success of this project was the ability to use the supercomputing facilities of the Space AI Institute at Goonhilly Earth Station. With the added help of Goonhilly workstations, each training iteration is reduced to minutes, meaning Bluefruit was able to complete all R&D and neural network training in eight weeks.

Sechoia

Sechoia Ltd is a UK-based, self-funded, disruptive tech start-up. They recently delivered proof-of-concept software that combines deep imaging, edge computing, and machine learning to create real-time data analytics.

Sechoia’s unique combination of 3D mapping and object tracking enables spatial localization, creating intuitive datasets that highlight how objects interact with their surroundings. Using AI in this way opens up a whole new world of intelligent planning where companies are able to predict spatial outcomes and future-proof them based on data. The construction of a new office, for example, can be influenced by algorithms that map and detect spatial patterns in previous office spaces, unlocking the full potential of the project.

By developing lightweight algorithms, Sechoia has achieved results compatible with techniques that rely on larger, centralized computing resources, while running on low-power, cost-effective edge devices. This allows real-time vision processing, deep imaging and data analysis to be performed in the field, eliminating the need to send large volumes of data to the cloud for processing.

This technology has enormous potential across a range of industries, particularly space and aerospace. AeroSpace Cornwall is funding Sechoia’s next round of technology upgrades and environmental testing.

With the aim of expanding its customer base, Sechoia also uses its skills to develop efficient, integrated and edge-based AI software to provide tailor-made software solutions to companies in the defense sector.

Asentech

Cornwall-based Assentech is at the forefront of AI to reduce fugitive emissions – a huge problem that results from farm storage tanks and biogas digesters. In the UK alone, there are around 900 COMAH* registered sites.

Ewart Cox, Managing Director, has been on a mission for 25 years in the tank storage industry, he was so committed to reducing fugitive emissions that he formed Assentech in 2009 to focus entirely on helping the tank storage industry to take control and reduce its emissions.

Bypassing the problems of manual testing, Assentech has developed a software architecture that takes pressure readings every 200 milliseconds referring to complex algorithms to make decisions on whether to change the airflow to the valve during a test cycle. Through the use of machine learning, the program will observe and analyze the behavior of the valve in response to the change in flow, and create a performance report which will be used by another complex algorithm to determine the best method to measure the valve leakage rate and use it. to test the valve automatically.

Their system, Vent-Less, confirms the functionality of the vent – demonstrating that it is safe to use and specified to scope and requirements. This functionality check is important because the operator has confirmation that the installation is safe.

This technology is not only extremely beneficial to the environment – one example demonstrated a reduction in global warming potential of 160 tonnes per year to 158 kg – but it brings immense benefits to all stakeholders, namely, a reduction greenhouse gas leaks into the environment, less evaporative loss costs for operators, safer environment for staff and neighbors, better ESG monitoring and reduced manufacturing time for producers.

With innovation aimed at maximizing the potential of technology capabilities within Cornwall, through cross-industry collaboration and leveraging existing assets, these companies are a small glimpse into how the industries of space, AI and deep learning in Cornwall are progressing hand in hand.

Sign up for the free insideBIGDATA newsletter.

Join us on Twitter: @InsideBigData1 – https://twitter.com/InsideBigData1