We introduce EarthPT -- an Earth Observation (EO) pretrained transformer. EarthPT is a 700 million parameter decoding transformer foundation model trained in an autoregressive self-supervised manner and developed specifically with EO use-cases in mind. We demonstrate that EarthPT is an effective forecaster that can accurately predict future pixel-level surface reflectances across the 400-2300 nm range well into the future. For example, forecasts of the evolution of the Normalised Difference Vegetation Index (NDVI) have a typical error of approximately 0.05 (over a natural range of -1 -> 1) at the pixel level over a five month test set horizon, out-performing simple phase-folded models based on historical averaging. We also demonstrate that embeddings learnt by EarthPT hold semantically meaningful information and could be exploited for downstream tasks such as highly granular, dynamic land use classification. Excitingly, we note that the abundance of EO data provides us with -- in theory -- quadrillions of training tokens. Therefore, if we assume that EarthPT follows neural scaling laws akin to those derived for Large Language Models (LLMs), there is currently no data-imposed limit to scaling EarthPT and other similar `Large Observation Models.'

England's BBC Channel 4 is going have an AI robot named Ameca provide the alternative Christmas message to King Charles' official royal remarks. A dystopian humanoid cyborg is set to give us the seasons' greetings this year on Channel 4. According to a report from Deadline, the AI robot, whose name is Ameca will be delivering alternate remarks to King Charles III's annual Royal Christmas message which will broadcast on its usual home on Channel 1. The robot was developed by Engineered Arts, a developing firm in Cornwall, England. The AI for Ameca is apparently set to deliver remarks which seek to calm the nation and the world at large, by reassuring us that 2022 was a "learning opportunity, a chance to change the way we think about the world and a reminder to help those in need whenever we can." This sounds suspiciously like some kind of terrifying cyborg threat, especially without hearing the accompanying Apple Maps voice delivering the statement, but Channel 4 assures us the robot supports the human race and loves a good laugh when times get tough.

The UK's Royal Mail wants to set up as many as 50 drone routes over the next three years to make deliveries to remote communities. The plan, which requires approval from the Civil Aviation Authority, would see the service secure up to 200 of the autonomous devices from logistics drone company Windracers. The Royal Mail said the first communities to benefit would be the Isles of Scilly (off the coast of Cornwall in south-west England) and the Scottish islands of Shetland, Orkney and the Hebrides. Test flights started last year. In the most recent one, held in April, the service was able to use a UAV to deliver mail to Unst, Britain's most northerly inhabited island, from Tingwall Airport on Shetland's largest island.

Royal Mail is building a fleet of 500 drones to carry mail to remote communities all over the UK, including the Isles of Scilly and the Hebrides. The postal service, which has already conducted successful trials over Scotland and Cornwall, will create more than 50 new postal drone routes over the next three years as part of a new partnership with London company Windracers. Drones, or UAVs (uncrewed aerial vehicles), can help reduce carbon emissions and improve the reliability of island mail services, Royal Mail claims. They offer an alternative to currently-used delivery methods that can be affected by bad weather – ferries, conventional aircraft and land-based deliveries. They can also take off from any flat surface (sand, grass or tarmac) providing it is long enough.

PENRYN, ENGLAND - MAY 09: Engineered Arts prosthetic expert Mike Humphrey checks on Fred a recently ... [ ] completed Mesmer robot that was built at the company's headquarters in Penryn on May 9, 2018 in Cornwall, England. Founded in 2004, the Cornish company operating from an industrial unit near Falmouth, is a world leader in life sized commercial available humanoid robots for entertainment, information, education and research. The company has successfully sold its the fully interactive and multilingual RoboThespian robot around the world to science centres, theme parks and visitor attractions, and also to academic and commercial research groups where they are used as research and development platforms. However, more recently the company has been building a range of lifelike bio-mechanical Mesmer robots. Built on the sensors and the extensive software framework already developed for RoboThespian, the Mesmer robots can offer some of the smartest animatronics on the market, giving extensive interaction but can also move very smoothly, quietly and naturally too.

Another ship called the Mayflower is set to make its way across the Atlantic Ocean this week, but it won't be carrying English pilgrims -- or any people -- at all. When the Mayflower Autonomous Ship leaves its home port in Plymouth, England to attempt the world's first fully autonomous transatlantic voyage, it will have a highly trained "captain" and a "navigator" versed in the rules of avoiding collisions at sea on board, both controlled by artificial intelligence (AI). The ship's AI captain was developed by Marine AI and is guided by an expert system based on IBM technologies, including automation software widely used by the financial sector. The technology could someday help crewed vessels navigate difficult situations and facilitate low-cost exploration of the oceans that cover 70 percent of the Earth's surface. Over its roughly three-week trip, the Mayflower sea drone will sail through the Isles of Scilly and over the site of the lost Titanic to land in Plymouth, Massachusetts, as the colonists on the first Mayflower did more than 400 years ago.

Sue Hodge lost seven hours and has no memory of going in the sea or even driving to Newquay.

A central problem in hyperspectral image classification is obtaining high classification accuracy when using a limited amount of labelled data. In this paper we present a novel graph-based framework, which aims to tackle this problem in the presence of large scale data input. Our approach utilises a novel superpixel method, specifically designed for hyperspectral data, to define meaningful local regions in an image, which with high probability share the same classification label. We then extract spectral and spatial features from these regions and use these to produce a contracted weighted graph-representation, where each node represents a region rather than a pixel. Our graph is then fed into a graph-based semi-supervised classifier which gives the final classification. We show that using superpixels in a graph representation is an effective tool for speeding up graphical classifiers applied to hyperspectral images. We demonstrate through exhaustive quantitative and qualitative results that our proposed method produces accurate classifications when an incredibly small amount of labelled data is used. We show that our approach mitigates the major drawbacks of existing approaches, resulting in our approach outperforming several comparative state-of-the-art techniques.

FALMOUTH, England (Reuters) - Can robots be creative? British gallery owner Aidan Meller hopes to go some way towards answering that question with Ai-Da, who her makers say will be able to draw people from sight with a pencil in her bionic hand.

We generalize the log Gaussian Cox process (LGCP) framework to model multiple correlated point data jointly. The resulting log Gaussian Cox process network (LGCPN) considers the observations as realizations of multiple LGCPs, whose log intensities are given by linear combinations of latent functions drawn from Gaussian process priors. The coefficients of these linear combinations are also drawn from Gaussian processes and can incorporate additional dependencies a priori. We derive closed-form expressions for the moments of the intensity functions in our model and use them to develop an efficient variational inference algorithm that is orders of magnitude faster than competing deterministic and stochastic approximations of multivariate LGCP and coregionalization models. Our approach outperforms the state of the art in jointly estimating multiple bovine tuberculosis incidents in Cornwall, UK, and multiple crime type intensities across New York city.