Small satellite technologies have enhanced the potential and feasibility of geodesic missions, through simplification of design and decreased costs allowing for more frequent launches. On-satellite data acquisition systems can benefit from the implementation of machine learning (ML), for better performance and greater efficiency on tasks such as image processing or feature extraction. This work presents convolutional autoencoders for implementation on the payload of small satellites, designed to achieve dual functionality of data compression for more efficient off-satellite transmission, and at-source anomaly detection to inform satellite data-taking. This capability is demonstrated for a use case of disaster monitoring using aerial image datasets of the African continent, offering avenues for both novel ML-based approaches in small satellite applications along with the expansion of space technology and artificial intelligence in Africa.

Car and motorbike maker Honda Motor Co. is positioning itself for a vertical takeoff. The Tokyo-based company is embarking on efforts to field a new electric-hybrid air taxi, a robot with human-like hands that may one day toil on the moon and a reusable rocket to carry small satellites into space more economically. Honda's vision of how people will work, travel and spend leisure time in the future will help expand its business beyond cars, lawn mowers and motorcycles. The efforts are a key component of Honda's "2030 Vision" to broaden the definition of mobility and to improve peoples' daily lives. The automaker, which also has a niche business in small planes, is a newcomer to the space industry, dominated today by established defense contractors such as Boeing Co. and well-funded upstarts such as Elon Musk's SpaceX and Jeff Bezos's Blue Origin.

Building a satellite with artificial intelligence onboard that is trained in space: For this project, Professor Hakan Kayal from Würzburg is receiving 2.6 million euros from the German Federal Ministry for Economic Affairs and Energy. Suddenly, circular holes were visible on the surface of Mars that were not there before. On photos of Saturn's moon Enceladus, geysers were discovered that hurl powerful fountains of steam towards space. And on the images sent to Earth by the Mars rover Curiosity, structures were found that look like fossilized worms. All these phenomena, some of which appear to be temporary, were discovered by chance.

Suddenly, circular holes were visible on the surface of Mars that were not there before. On photos of Saturn's moon Enceladus, geysers were discovered that hurl powerful fountains of steam towards space. And on the images sent to Earth by the Mars rover Curiosity, structures were found that look like fossilised worms. All these phenomena, some of which appear to be temporary, were discovered by chance. Or because humans took a lot of time to sift through the images from Earth's neighbouring planets.

Artificial intelligence (AI) is certainly the'flavor of the month' and has become a part of our daily lives. However, there is one area that, until now, hasn't been involved in AI… As ubiquitous as artificial intelligence has become in modern life -- from boosting the understanding of the cosmos to surfacing entertaining videos on a phone -- AI hasn't yet found its way into orbit. That is until September 2, when an experimental satellite about the size of a cereal box was ejected from a rocket's dispenser along with 45 other similarly small satellites. The satellite, named PhiSat-1, is now soaring at over 17,000 mph (27,500 kmh) in sun-synchronous orbit about 329 miles (530 km) overhead. PhiSat-1 contains a new hyperspectral-thermal camera and onboard AI processing from an Intel Movidius Myriad 2 Vision Processing Unit (VPU) -- the same chip inside many smart cameras and even a $99 selfie taken by a drone on Earth.

Machine learning, particularly deep learning, is being increasing utilised in space applications, mirroring the groundbreaking success in many earthbound problems. Deploying a space device, e.g. a satellite, is becoming more accessible to small actors due to the development of modular satellites and commercial space launches, which fuels further growth of this area. Deep learning's ability to deliver sophisticated computational intelligence makes it an attractive option to facilitate various tasks on space devices and reduce operational costs. In this work, we identify deep learning in space as one of development directions for mobile and embedded machine learning. We collate various applications of machine learning to space data, such as satellite imaging, and describe how on-device deep learning can meaningfully improve the operation of a spacecraft, such as by reducing communication costs or facilitating navigation. We detail and contextualise compute platform of satellites and draw parallels with embedded systems and current research in deep learning for resource-constrained environments.

Researchers at the National Security Agency are using artificial intelligence to characterize strange behaviors in small satellites to understand if they've secretly been brought under adversarial control. "We're looking at a way to characterize telemetry data so that as we deploy new satellites, we can make adjustments," said Aaron Ferguson, the technical director of the encryption solutions office of NSA's Capabilities Directorate, said at a Defense One event on Tuesday. "Now, if you talk to a variety of analysts, and I have at NASA, they'll say, 'Oh, we've got this under control. We checked the data twice, three times,' Ferguson said. "But we really don't know, because there is so much data that they really don't know if something is going wrong. They'll say, 'It's just orbital debris that bumped into the satellite and knocked it off its trajectory."

Geospatial technology is ubiquitous and the expanse of its reach in multiple fields is growing rapidly. Most technologies require a spatial component and it is one of the pillars of emerging technologies. Be it our day-to-day activities or cutting edge futuristic research, none can be visualized without geospatial information. In 2019, new trends in geospatial technology would have an impact on multiple sectors. Let's have a look at the major geospatial trends for 2019.

FARNBOROUGH, London--The head of Airbus SE's EADSY -1.10% defense and space business anticipates major long-term benefits, including possibly Pentagon contracts, as a result of implementing a high-volume automated production system for small satellites. Dirk Hoke said the production and quality-control changes--under way as part of a joint venture with Internet services provider OneWeb--will position Airbus to churn out less-expensive spacecraft using fewer workers and less testing than with traditional factory practices. Airbus officials previously highlighted expected financial gains stemming from assembling up to two satellites a day at the comparatively low cost of $1 million each. But Mr. Hoke's comments at the international air show here Monday were the most specific yet about the project's positive effect on internal industrial processes, as well as on the general approach of Airbus engineers. Committing to assemble a new generation of lightweight satellites primarily using robots "was a game-changer for us," Mr. Hoke said.

A UK-led experiment to tackle space junk has been sent into orbit. It takes the form of a small satellite that will practise techniques for tracking debris and capturing it. The RemoveDebris system is heading to the International Space Station where astronauts are expected to set the experiment running in late May. Space junk is an ever-growing problem with more than 7,500 tonnes of redundant hardware now thought to be circling the Earth. Ranging from old rocket bodies and defunct spacecraft through to screws and even flecks of paint - this material poses a collision hazard to operational missions.