Elon Musk has made light of the latest SpaceX test, which ended with the enormous rocket exploding on the launch pad. While footage showed Starship bursting into a gigantic ball of fire, Musk claimed that this was'just a scratch.' The Starship 36 rocket was undergoing a static fire test at SpaceX's Starbase test site at around 11pm last night, when its nose suddenly burst open. Within seconds, a giant ball of fire could be seen spreading on the ground as black clouds of smoke reached up to the night sky. The static fire test is a pre-flight procedure in which a rocket engine or a set of engines are ignited while the vehicle is firmly bolted to the launch mount, meaning the rocket was not set to launch Wednesday night when the explosion occurred. In a statement, SpaceX said the rocket suffered'a major anomaly while on a test stand at Starbase.

Distribution shifts between sites can seriously degrade model performance since models are prone to exploiting unstable correlations. Thus, many methods try to find features that are stable across sites and discard unstable features. However, unstable features might have complementary information that, if used appropriately, could increase accuracy. More recent methods try to adapt to unstable features at the new sites to achieve higher accuracy. However, they make unrealistic assumptions or fail to scale to multiple confounding features. We propose Generalized Prevalence Adjustment (GPA for short), a flexible method that adjusts model predictions to the shifting correlations between prediction target and confounders to safely exploit unstable features. GPA can infer the interaction between target and confounders in new sites using unlabeled samples from those sites. We evaluate GPA on several real and synthetic datasets, and show that it outperforms competitive baselines.

Healthcare data often come from multiple sites in which the correlations between confounding variables can vary widely. If deep learning models exploit these unstable correlations, they might fail catastrophically in unseen sites. Although many methods have been proposed to tackle unstable correlations, each has its limitations. For example, adversarial training forces models to completely ignore unstable correlations, but doing so may lead to poor predictive performance. Other methods (e.g. Invariant risk minimization [4]) try to learn domain-invariant representations that rely only on stable associations by assuming a causal data-generating process (input X causes class label Y ). Thus, they may be ineffective for anti-causal tasks (Y causes X), which are common in computer vision. We propose a method called CoPA (Conditional Prevalence-Adjustment) for anti-causal tasks. CoPA assumes that (1) generation mechanism is stable, i.e. label Y and confounding variable(s) Z generate X, and (2) the unstable conditional prevalence in each site E fully accounts for the unstable correlations between X and Y . Our crucial observation is that confounding variables are routinely recorded in healthcare settings and the prevalence can be readily estimated, for example, from a set of (Y, Z) samples (no need for corresponding samples of X). CoPA can work even if there is a single training site, a scenario which is often overlooked by existing methods. Our experiments on synthetic and real data show CoPA beating competitive baselines.

Researchers have developed arrays of AI-controlled cameras and microphones to identify animals and birds and to monitor their movements in the wild – technology, they say, that should help tackle Britain's growing biodiversity problem. The robot monitors have been tested at three sites and have captured sounds and images from which computers were able to identify specific species and map their locations. Dozens of different birds were recognised from their songs while foxes, deer, hedgehogs and bats were pinpointed and identified by AI analysis. No human observers are involved. "The crucial point is the scale of the operation," said Anthony Dancer, a conservation specialist at the Zoological Society of London (ZSL).

Biofouling is a major challenge for sustainable shipping, filter membranes, heat exchangers, and medical devices. The development of fouling-resistant coatings requires the evaluation of their effectiveness. Such an evaluation is usually based on the assessment of fouling progression after different exposure times to the target medium (e.g., salt water). The manual assessment of macrofouling requires expert knowledge about local fouling communities due to high variances in phenotypical appearance, has single-image sampling inaccuracies for certain species, and lacks spatial information. Here we present an approach for automatic image-based macrofouling analysis. We created a dataset with dense labels prepared from field panel images and propose a convolutional network (adapted U-Net) for the semantic segmentation of different macrofouling classes. The establishment of macrofouling localization allows for the generation of a successional model which enables the determination of direct surface attachment and in-depth epibiotic studies.

Amazon is continuing to'secretly' test the capability of its Air Prime delivery drones at their proving ground in the UK countryside. Engineers in high vis jackets were spotted yesterday flying drones on wires from a giant metal gantry in a field near Cambridge, England. It is unclear why the drones are being flown attached to cables -- but could perhaps help to determine the drone's positions relative to the crane as they land. Cameras and sensors have also been added to the metal frame to carry out tests on the drones and check they can navigate and land correctly. The company first began secretly flying its drones in a field near Cambridge three years ago, in July 2016, after the UK's Civil Aviation Authority lifted the previous strict drone flying restrictions.

Elon Musk's Starhopper has taken another major step toward reality. The prototype ship blasted off from the Boca Chica, Texas test site on Tuesday evening just after 5 p.m. local time (6 p.m. ET) for its 150-meter untethered flight test. While it was at first enshrouded in smoke and flames, the water tower-shaped vehicle emerged moments later to be seen rising high above the ground without any obstructions to the view. The successful test comes after SpaceX was forced to abandon its attempt on Monday to allow for a last-minute inspection of the craft's igniters. Musk tweeted his congratulations to the SpaceX team not long after Tuesday's achievement wrapped up.

Wide-band Electromagnetic Induction Sensors (WEMI) have been used for a number of years in subsurface detection of explosive hazards. While WEMI sensors have proven effective at localizing objects exhibiting large magnetic responses, detecting objects lacking or containing very low amounts of conductive materials can be challenging. In this paper, we compare a number of target detection algorithms in the literature in terms of detection performance. In the comparison, methods are tested on two real-world data sets: one containing relatively low amounts of ground noise pollution, and the other demonstrating highly-magnetic soil interference. Results are quantitatively evaluated through receiver-operator characteristic (ROC) curves and are used to highlight the strengths and weaknesses of the compared approaches in hand-held explosive hazard detection.

Future Tense is a partnership of Slate, New America, and Arizona State University that examines emerging technologies, public policy, and society. The drone future that we all know is coming--more drones, everywhere, ferrying our stuff to wherever we want it sent--isn't coming just yet. Before flying robots can speckle the sky from coast to coast, the government needs to pass regulations that allow drones to fly beyond the line of sight of the operator, over densely populated areas, and at night--all things currently prohibited unless the drone operator gets a special waiver from the Federal Aviation Administration. Drones also have to be integrated into the national air traffic control system, which will have to help coordinate their movement and ensure the autonomous flyers don't collide in the sky. But before any of that gets off the ground, the U.S. Department of Transportation is giving the green light to 10 areas across the country to set up test sites for drones to do things like delivery, mosquito-killing, and security.

BEIJING – China has started building the world's largest test site for unmanned ships -- a technology with both civilian and military applications -- off a port in the disputed South China Sea, state media has reported. The test area is being constructed off the southern port city of Zhuhai bordering Macau, China's official Xinhua News Agency said Tuesday. China asserts sovereignty over almost all the South China Sea despite competing partial claims from the Philippines, Vietnam, Malaysia and Brunei, and has reclaimed several islands which it controls to bolster its claims. Unmanned or "autonomous" ship technology, still in its infancy, would allow both civilian and military craft to be remotely controlled. It could revolutionize the shipping industry by creating more cargo space on unmanned ships, which would also save huge sums in labor costs.