IceCloudNet is a novel method based on machine learning able to predict high-quality vertically resolved cloud ice water contents (IWC) and ice crystal number concentrations (N$_\textrm{ice}$). The predictions come at the spatio-temporal coverage and resolution of geostationary satellite observations (SEVIRI) and the vertical resolution of active satellite retrievals (DARDAR). IceCloudNet consists of a ConvNeXt-based U-Net and a 3D PatchGAN discriminator model and is trained by predicting DARDAR profiles from co-located SEVIRI images. Despite the sparse availability of DARDAR data due to its narrow overpass, IceCloudNet is able to predict cloud occurrence, spatial structure, and microphysical properties with high precision. The model has been applied to ten years of SEVIRI data, producing a dataset of vertically resolved IWC and N$_\textrm{ice}$ of clouds containing ice with a 3 kmx3 kmx240 mx15 minute resolution in a spatial domain of 30{\deg}W to 30{\deg}E and 30{\deg}S to 30{\deg}N. The produced dataset increases the availability of vertical cloud profiles, for the period when DARDAR is available, by more than six orders of magnitude and moreover, IceCloudNet is able to produce vertical cloud profiles beyond the lifetime of the recently ended satellite missions underlying DARDAR.

While artificial intelligence (AI) technology has the potential to transform society, the legal issues it raises touch upon diverse areas of law. These areas include privacy and data security, commercial contracts, intellectual property, antitrust, employee benefits, and products liability. AI is broadly defined as computer technology that can simulate human intelligence. Through algorithms, this software can aggregate data, detect patterns, optimize behaviors, and make future predictions. Some examples of AI applications include machine learning, natural language processing, artificial neural networks, machine perception, and motion manipulation.

If you live in Boston, you are likely familiar with the notion of getting "storrowed" (there's even a hashtag for it). On Storrow Drive, there are numerous warning signs and blinking lights that forewarn you about a bridge that has only an 11-foot clearance, and yet somehow drivers ram into it anyway. This can be somewhat explained, according to local lore, the confusion about ramming it is due to the aspect that when new students show-up for college in Boston, they often rent a vehicle that either is higher than 11 feet, or pile stuff on top of vehicles that end-up being higher than 11 feet. They then use Storrow Drive to get to their university and sadly either ignore, disbelieve, or don't notice the warning signs about the low bridge height. As an old saying goes, when a movable object strikes an immovable one, the moving object is going to likely lose out. Though the Bostonian bridge story gets some occasional attention, perhaps the big winner for offending low bridges goes to the 11 foot 8 inch bridge nicknamed The Can-Opener.

Self-driving cars have been given the green light to traverse well-trafficked roads in the Seaport and Fort Point areas of South Boston, according to a letter sent by the city last night. NuTonomy, which has driven more than 230 miles on public roads in Boston since the beginning of the year, will be allowed to drive its autonomous vehicles as far south as West First Street and to cross the Fort Point Channel to Dorchester Avenue. The company asked for and was granted approval to expand by Boston officials, under the terms of a testing agreement signed last year. "For autonomous vehicles to be able to deliver on the crash-reduction and network efficiency promises, we know that testing must gradually increase in complexity, while still maintaining safety as our paramount focus," Boston Transportation Commissioner Gina Fiandaca wrote in the approval letter. NuTonomy previously had been restricted to the Raymond L. Flynn Marine Park, a relatively quiet industrial and business area with no stoplights.

Among all of the self-driving startups working toward Level 4 autonomy (a self-driving system that doesn't require human intervention in most scenarios), Mountain View, Calif.-based Drive.ai's Drive sees deep learning as the only viable way to make a truly useful autonomous car in the near term, says Sameep Tandon, cofounder and CEO. "If you look at the long-term possibilities of these algorithms and how people are going to build [self-driving cars] in the future, having a learning system just makes the most sense. There's so much complication in driving, there are so many things that are nuanced and hard, that if you have to do this in ways that aren't learned, then you're never going to get these cars out there." It's only been about a year since Drive went public, but already, the company has a fleet of four vehicles navigating (mostly) autonomously around the San Francisco Bay Area--even in situations (such as darkness, rain, or hail) that are notoriously difficult for self-driving cars. Last month, we went out to California to take a ride in one of Drive's cars, and to find out how it's using deep learning to master autonomous driving.