Work by AI for Earth researchers at Columbia University sheds even more light on why accurate, detailed, and up-to-date information is important. Dr Maria Uriarte, an ecologist, and Dr Tian Zheng, a statistician, have been studying the impact of extreme weather on forests and their regrowth patterns, with an eye towards the impact this has on carbon sequestration abilities – shorter, younger and less dense forests are less effective than older, denser areas. She recently took a team to Puerto Rico to assess the damage to the forests following Hurricane Maria. Uriarte and Zheng, both affiliated with the Data Science Institute at Columbia, will eventually use the collected data, with the remote-sensing images and measurements, to come up with a detailed estimate of the loss from the storm. Without current baseline data and a forward-leaning view of what the forest inventory may be in the future, planners may undervalue forests, or countries may over-value sequestration abilities.

Climate change is killing our planet. The excess production of carbon dioxide and other greenhouse gasses are filling the atmosphere and warming the Earth faster than natural processes can effectively negate them. Since 1951, the surface temperature has risen by 0.8 degrees C, with no sign of slowing. So now it's time for humans to step in and rectify the problem they created -- by using technology to suck excess CO2 straight from the air. Direct Air Capture (DAC), is one of a number of (still largely theoretical) methods of collecting and sequestering atmospheric carbon currently being looked at.

Dubai Electricity and Water Authority (DEWA) is organising the AI Leadership Programme in cooperation with experts from the University of California, Berkeley. The programme is attended by DEWA's leadership and staff who specialise in Artificial Intelligence (AI). The programme supports DEWA's efforts to achieve the directives of the wise leadership to anticipate the future and keep pace with the Fourth Industrial Revolution. The 3-day programme covers the latest developments in AI application in energy, water, machine learning, data science and applications, and other related topics. Participants will also learn about virtual implementation of AI applications in the work environment.

Forecasting multivariate time series data, such as prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. However, complex and non-linear interdependencies between time steps and series complicate the task. To obtain accurate prediction, it is crucial to model long-term dependency in time series data, which can be achieved to some good extent by recurrent neural network (RNN) with attention mechanism. Typical attention mechanism reviews the information at each previous time step and selects the relevant information to help generate the outputs, but it fails to capture the temporal patterns across multiple time steps. In this paper, we propose to use a set of filters to extract time-invariant temporal patterns, which is similar to transforming time series data into its "frequency domain". Then we proposed a novel attention mechanism to select relevant time series, and use its "frequency domain" information for forecasting. We applied the proposed model on several real-world tasks and achieved the state-of-the-art performance in all of them with only one exception. We also show that to some degree the learned filters play the role of bases in discrete Fourier transform.

In many real-world applications (e.g., planetary exploration, robot navigation), an autonomous agent must be able to explore a space with guaranteed safety. Most safe exploration algorithms in the field of reinforcement learning and robotics have been based on the assumption that the safety features are a priori known and time-invariant. This paper presents a learning algorithm called ST-SafeMDP for exploring Markov decision processes (MDPs) that is based on the assumption that the safety features are a priori unknown and time-variant. In this setting, the agent explores MDPs while constraining the probability of entering unsafe states defined by a safety function being below a threshold. The unknown and time-variant safety values are modeled using a spatio-temporal Gaussian process. However, there remains an issue that an agent may have no viable action in a shrinking true safe space. To address this issue, we formulate a problem maximizing the cumulative number of safe states in the worst case scenario with respect to future observations. The effectiveness of this approach was demonstrated in two simulation settings, including one using real lunar terrain data.

Vulnerable road users (VRUs, i.e. cyclists and pedestrians) will play an important role in future traffic. To avoid accidents and achieve a highly efficient traffic flow, it is important to detect VRUs and to predict their intentions. In this article a holistic approach for detecting intentions of VRUs by cooperative methods is presented. The intention detection consists of basic movement primitive prediction, e.g. standing, moving, turning, and a forecast of the future trajectory. Vehicles equipped with sensors, data processing systems and communication abilities, referred to as intelligent vehicles, acquire and maintain a local model of their surrounding traffic environment, e.g. crossing cyclists. Heterogeneous, open sets of agents (cooperating and interacting vehicles, infrastructure, e.g. cameras and laser scanners, and VRUs equipped with smart devices and body-worn sensors) exchange information forming a multi-modal sensor system with the goal to reliably and robustly detect VRUs and their intentions under consideration of real time requirements and uncertainties. The resulting model allows to extend the perceptual horizon of the individual agent beyond their own sensory capabilities, enabling a longer forecast horizon. Concealments, implausibilities and inconsistencies are resolved by the collective intelligence of cooperating agents. Novel techniques of signal processing and modelling in combination with analytical and learning based approaches of pattern and activity recognition are used for detection, as well as intention prediction of VRUs. Cooperation, by means of probabilistic sensor and knowledge fusion, takes place on the level of perception and intention recognition. Based on the requirements of the cooperative approach for the communication a new strategy for an ad hoc network is proposed.

Scuba diving archaeologists are scouring the seabed where a gas pipeline is being built off Israel's coast in a bid to preserve ancient relics. The area lies near a 5,000-year-old port which once was a key trade hub for the Mediterranean's ancient civilisations. Scientists say the vestiges of marine traders throughout the ages - from the Phoenicians to the Romans - lie hidden beneath the seabed at the port of Dor. They have already found earthenware jugs, anchors and the remains of wrecked ships, setting new guidelines for similar future projects. Underwater robots are scouring the seabed where a gas pipeline is being built off Israel's coast in a bid to preserve ancient relics.

Nintendo has delayed a crucial video presentation around its Nintendo Switch and 3DS games consoles after a powerful earthquake hit Hokkaido, Japan. The major quake, which struck shortly before 3am local time this morning (7pm BST/ 2pm ET yesterday), left 5.3 million without electricity and at least eight people dead. More than 150 people have been injured in the natural disaster, which measured around 6.7 on the Richter magnitude scale. Nintendo had planned to reveal details around a slew of new video game titles coming to its Nintendo Switch and 3DS consoles in time for the holiday season. However, the video presentation, which is streamed live on the Japanese firm's website as well as YouTube, will be rescheduled.

Elon Musk has reiterated his controversial belief we are living in a simulation. During his controversial appearance on comedian Joe Rogan's popular podcast, 'The Joe Rogan Experience,' where he smoked a joint, he also explained why he still believes we are living in the Matrix. He said that the sheer age of the universe - 13.8 billion years, means alien civilizations have had time to develop the complex systems needed. 'If you assume any rate of improvement at all, then games will be indistinguishable from reality, or civilization will end. One of those two things will occur,' Musk said.

Skydio blew our minds when they announced the R1 back in February--it's by far the smartest, most autonomous consumer camera drone we've ever seen. The company promised that they'd keep on making the R1 even more capable, and today they're announcing a slew of upgrades, including a new software development kit (SDK) that lets you leverage the R1's obstacle-dodging cleverness in any custom application you can dream up. The Skydio R1 is amazing, and you should read our February article about it, but in a nutshell, it's a drone that uses an array of 12 cameras to dynamically detect and avoid obstacles while it tracks you and films what you're doing. This means that it can follow someone riding a mountain bike through a forest, dodging trees and branches and keeping them in frame the whole time. It's basically the kind of capability that every single company working on drone delivery has implicitly promised and so far failed to deliver, and now you can spend some cash (okay, kind of a lot of cash) and play with it yourself.