Computational intelligence-based ocean characteristics forecasting applications, such as Significant Wave Height (SWH) prediction, are crucial for avoiding social and economic loss in coastal cities. Compared to the traditional empirical-based or numerical-based forecasting models, "soft computing" approaches, including machine learning and deep learning models, have shown numerous success in recent years. In this paper, we focus on enabling the deep learning model to learn both short-term and long-term spatial-temporal dependencies for SWH prediction. A Wavelet Graph Neural Network (WGNN) approach is proposed to integrate the advantages of wavelet transform and graph neural network. Several parallel graph neural networks are separately trained on wavelet decomposed data, and the reconstruction of each model's prediction forms the final SWH prediction. Experimental results show that the proposed WGNN approach outperforms other models, including the numerical models, the machine learning models, and several deep learning models.

First unveiled in 2018 at CES, LG is finally bringing its futuristic, rollable LG Signature OLED R 65-inch 4K TV to the US for the hefty sum of $100,000. According to LG's website, the television has an OLED screen, a Dolby Atmos and Sound Pro sound system and has both Google Assistant and Amazon's Alexa for built-in voice control. The 65-inch screen, which is described as a'revolutionary new experience,' gets tucked into aluminum housing unit when not in use, either for watching movies or playing video games. It has an OLED screen, a Dolby Atmos and Sound Pro sound system and both Google Assistant and Amazon's Alexa for built-in voice control The cabinet also has a Dolby Atmos sound system of its own. Manufactured in LG's Gumi facility, each TV is painstakingly assembled'with craftsman-like skill with attention to every detail', LG said last year.

As the Chemistry-Kayak (affectionately known as the ChemYak) swept over the Arctic estuary waters, Victoria Preston was glued to a monitor in a boat nearby, watching as the robot's sensors captured new data. She and her team had spent weeks preparing for this deployment. With only a week to work on-site, they were making use of the long summer days to collect thousands of observations of a hypothesized chemical anomaly associated with the annual ice-cover retreat. The robot moved up and down the stream, using its chemical sensors to detect the composition of the flowing water. Its many measurements revealed a short-lived but massive influx of greenhouse gases in the water during the annual "flushing" of the estuary as ice thawed and receded.

This story was originally published by Wired and is reproduced here as part of the Climate Desk collaboration. An actual space laser is cruising 300 miles above your head right now. Launched in 2018, NASA's ICESat-2 satellite packs a lidar instrument, the same kind of technology that allows self-driving cars to see in three dimensions by spraying lasers around themselves as they roll down the street and analyzing the light that bounces back. But instead of mapping a road, ICESat-2 measures the elevation of Earth's surface with extreme accuracy. Although this space laser means you no harm, it does portend catastrophe. Today in the journal Nature Communications, scientists describe how they used ICESat-2's new lidar data to map the planet's land that's less than 2 meters above sea level, which makes it vulnerable to the creep of sea level rise.

Understanding and representing traffic patterns are key to detecting anomalies in the maritime domain. To this end, we propose a novel graph-based traffic representation and association scheme to cluster trajectories of vessels using automatic identification system (AIS) data. We utilize the (un)clustered data to train a recurrent neural network (RNN)-based evidential regression model, which can predict a vessel's trajectory at future timesteps with its corresponding prediction uncertainty. This paper proposes the usage of a deep learning (DL)-based uncertainty estimation in detecting maritime anomalies, such as unusual vessel maneuvering. Furthermore, we utilize the evidential deep learning classifiers to detect unusual turns of vessels and the loss of AIS signal using predicted class probabilities with associated uncertainties. Our experimental results suggest that using graph-based clustered data improves the ability of the DL models to learn the temporal-spatial correlation of data and associated uncertainties. Using different AIS datasets and experiments, we demonstrate that the estimated prediction uncertainty yields fundamental information for the detection of traffic anomalies in the maritime and, possibly in other domains.

Anyone working in data management and data science can attest to the challenge and time-consuming nature of mapping a set of data from a new source into a platform where it can be cleaned, validated, and ultimately analyzed and used to train algorithms. After all, your algorithms are only as good as the data used to train them. Now imagine if these data sets are coming from hundreds of external users who have employed any number of systems to collect this data, from Excel files to actual shoeboxes full of photos. That is the challenge that non-profit wildlife conservation machine learning and artificial intelligence service provider Wild Me has faced over its more than a decade of operation. The organization builds open software and AI for the conservation research community.

Making predictions in a robust way is not easy for nonlinear systems. In this work, a neural network computing framework, i.e., a spatiotemporal convolutional network (STCN), was developed to efficiently and accurately render a multistep-ahead prediction of a time series by employing a spatial-temporal information (STI) transformation. The STCN combines the advantages of both the temporal convolutional network (TCN) and the STI equation, which maps the high-dimensional/spatial data to the future temporal values of a target variable, thus naturally providing the prediction of the target variable. From the observed variables, the STCN also infers the causal factors of the target variable in the sense of Granger causality, which are in turn selected as effective spatial information to improve the prediction robustness. The STCN was successfully applied to both benchmark systems and real-world datasets, all of which show 1 superior and robust performance in multistep-ahead prediction, even when the data were perturbed by noise. From both theoretical and computational viewpoints, the STCN has great potential in practical applications in artificial intelligence (AI) or machine learning fields as a model-free method based only on the observed data, and also opens a new way to explore the observed high-dimensional data in a dynamical manner for machine learning.

The internet is now our nervous system. We are constantly streaming and buying and watching and liking, our brains locked into the global information matrix as one universal and coruscating emanation of thought and emotion. What happens when the machine stops though? It's a question that E.M. Forster was intensely focused on more than a century ago in a short story called, rightly enough, "The Machine Stops," about a human civilization connected entirely through machines that one day just turn off. Those fears of downtime are not just science fiction anymore.

Atmospheric science is overwhelmingly white. These Black scientists ignited a change. Everything depended on finding the gigantic dust cloud. Seventeen years ago, a scientific crew set out on the Ron Brown , a gleaming U.S. research ship, in search of a plume of desert dust that had sheared off the Sahara and wafted over the Atlantic Ocean. Sailing from Barbados with day after day of clear sky, the crew was anxious about finding the dust storm. But that wasn't the only thing weighing on Vernon Morris, the atmospheric chemist who'd organized the cruise, the first of its kind run largely by Black and Hispanic scientists. Failure could make life complicated for the atmospheric sciences program Morris had recently co-founded at Howard University. And, he says, “They would have never entrusted the ship to a bunch of Puerto Ricans and Blacks again.” Finally, on the fifth morning, the crew awoke to an eclipse of dust. It settled on railings, instruments, and weather balloons. “We were just all giddy, the happiest scientists,” says Michelle Hawkins, a Howard graduate student at the time who now leads severe weather forecasts at the National Weather Service. The schedule was intense, as the crew launched weather balloons around the clock and took measurements in the ocean and at the surface to capture a picture of what turned out to be one of the largest Saharan plumes ever observed. And the cruise began a trend: The Aerosol and Ocean Science Expeditions (AEROSEs) have set out nearly every year since then, with the latest cruise defying the pandemic to sail in January. Although AEROSE cruises are still full of black and brown faces, most research cruises—indeed, most of the geosciences—are not. Nearly 90% of geoscience doctorate holders are white, and by Morris's count, there are no more than seven Black atmospheric scientists in tenured positions in the country's major academic departments. Many of the communities most at risk from climate-related extremes, such as heat waves or hurricanes, are those least represented in the science that explores those threats. “It's not only a Black man's challenge,” says Belay Demoz, an atmospheric physicist originally from Eritrea who is at the University of Maryland, Baltimore County. “It's the nation's problem.” Amid this dire portrait, however, the Howard University Graduate Program in Atmospheric Science has been a notable success. From 2006 to 2018, the Howard program, one of AEROSE's sponsors, produced 17 Black doctorate holders in atmospheric science—more than half the country's total—and 30% of its Latina doctorate holders. Seventy-five percent of graduates came from low-income backgrounds. Nearly all hold scientific jobs and some are now carving out prominent positions in the country's premier climate science agencies, especially the National Oceanic and Atmospheric Administration (NOAA). “I feel like ‘successful’ is not strong enough,” Hawkins says. “It's been such a guiding light for all of us.” With the Biden administration promising to increase its support for historically Black colleges and universities (HBCUs) like Howard, including a potential new climate research lab based at one, this should be a time of hope and expansion for the Howard program. But its future is in doubt. For years, school leadership neglected the program, according to former faculty, and most of its founders, including Morris himself, have left. “I don't think Howard ever appreciated what they had on their hands,” says Marshall Shepherd, a Black atmospheric scientist at the University of Georgia, Athens, and former president of the American Meteorological Society (AMS). “They had a game-changing program.” As the geosciences seek to improve their diversity, Howard's success holds lessons for leaders and institutions. How can it be replicated? And can it even be sustained at Howard itself? MORRIS “BACKED into college,” as he puts it, attending Morehouse College, an HBCU in Atlanta, after deciding not to follow his father into the Air Force. But he felt adrift, far from his family in Washington, spending above his means to keep up with the rich kids. Thinking about dropping out, Morris ran into Henry McBay, a legendary Black chemist who offered to buy him books as long as he majored in chemistry and math. That led to a mentorship with John Hall, the pioneering Black atmospheric chemist who worked on ozone depletion. “I started doing work on chlorine nitrate chemistry and matrices,” Morris says. “I loved it.” In 1990 he became the first Black person to earn a Ph.D. from the Georgia Institute of Technology's earth science program. As a postdoc, he became intrigued by cosmic chemistry and the atmosphere of Venus. He wanted to get back to an HBCU, and he noticed that Howard had recently launched a small, NASA-funded Center for the Study of Terrestrial and Extraterrestrial Atmospheres. Morris wrangled an invite and sold himself as someone who could help focus the center's research and ensure its continuation—at the time, external NASA reviewers were questioning its lack of relevant expertise and threatening to claw back the grant. He was hired as deputy director in 1994. At the time, Morris was one of a few people of color who regularly appeared at national atmospheric science meetings. He and a handful of others would meet at a nearby hotel lobby bar to unwind. “Those meetings used to be superstressful, not seeing anyone who looks like you,” says Gregory Jenkins, a climatologist who now works at Pennsylvania State University, University Park. “You wanted to give a paper, check out other papers, and go back to the hotel room.” The stress did not stop there. In an essay this year in AGU Advances , Morris wrote of being harassed by police. “I have been that figure sitting on the curb with my hands bound behind my back,” he wrote. “I have been struck so hard with the butt of a police flashlight that the manufacturer label could be deciphered from the imprint on my chest days later.” Morris and his peers decided to create a community of Black atmospheric scientists at Howard by founding a new graduate program. Sonya Smith, an atmospheric engineer, came the year after Morris. Jenkins came, too, for a time. Everette Joseph, a code-savvy atmospheric scientist, joined soon after, as did Anthony Reynolds, a white physicist now at Embry-Riddle Aeronautical University. They started with a single course in atmospheric chemistry and gradually added more to build a case for a degree-granting program, ironing out their talking points over drinks and wings at a local bar. They won approval for the program from the Board of Trustees in 1997. None of them realized what they were getting into. The board had allocated little funding, so they would have to support the program by winning external grants. “We had to worry about building a program and building our careers at the same time,” says Joseph, who in 2019 became the first Black director of the National Center for Atmospheric Research, one of the country's leading climate labs. “We were stupid and brash not to realize the monumental nature of the challenge.” They also needed to recruit students. Some they found at Howard, including DaNa Carlis, a first-generation college student who initially wanted to become a doctor. He ran into Morris, who pitched the program and offered him a scholarship. “I was like, ‘What, you're going to pay me to go to school!’” says Carlis, who is now deputy director at NOAA's Global Systems Laboratory. Soon enough, he was doing research on ozone chemistry at NASA's Goddard Space Flight Center. Casting a wider net, the Howard faculty began to lure chemistry, physics, and math undergraduates at five HBCUs to Howard for NASA-sponsored summer programs. They also scouted graduate programs where students often stopped at a master's degree. “We recruited those students hard,” Morris says, by touting their connections to NASA and NOAA. They cobbled together money for a conference that attracted nearly 200 students of color to Washington, D.C., a gambit that gave them enough recruits to fill the program for 5 years. In 2001, the Howard team scored a huge victory, winning a $2.5 million annual grant from NOAA to establish one of four new scientific centers at minority-serving institutions. The NOAA grant, which also supports research and students elsewhere, enabled Howard to bring on several new faculty, including Demoz, an atmospheric physicist. Demoz belonged to the majority ethnic group in his home country of Eritrea, and it wasn't until he worked at Goddard, where the only other Black scientist in his division was Shepherd, that he became truly aware of U.S. racial dynamics. Training minority scientists became a cause equal to his research. “I'm Eritrean and I have a guilty feeling that I didn't fight for independence,” he says. “This is my independence.” Meanwhile, the first generation of Howard atmospheric science students was advancing toward doctorates. It was a tight group. One day, Joseph hauled them all into his office, ready to breathe fire because they had all gotten the same test question wrong in the same way. Then it became clear what happened: They had spent days together studying the problem in the wrong way. The tests required your best, says Isha M. Renta López, now a program analyst at NOAA's Office of Oceanic and Atmospheric Research. Once, Morris asked students to imagine a pyramid-shaped planet that doesn't rotate, then describe the chemical reactions in its atmosphere. “He would put in the craziest stuff,” López says. The professors pushed the students to present their research at scientific meetings, paying their way if they couldn't get a scholarship. “I remember our very first meeting, Vernon giving us the talk,” Hawkins says. “This is what you wear. This is how you introduce yourself. This is how you give a presentation.” The students, in turn, helped recruit their own successors. The program let the students be themselves and focus on their research without facing the tension and microaggressions that could come with being the sole Black student in a program, like passing comments about how “intelligent” or “well spoken” they were, or a critique that seemed excessively harsh for no reason. At Howard, Jenkins says, “They knew that it wasn't going to be easy, but one thing they didn't have to worry about were questions about whether they were qualified.” KNOWING FIELD RESEARCH would be critical to the students' success, the Howard faculty began to build opportunities. Many revolved around a small wooded campus owned by Howard in Beltsville, Maryland. Its haphazard assortment of squat red-brick buildings had previously hosted an observatory, animal experiments, and an argon beamline for particle physics research. Joseph and others saw huge potential in the site. At the time, Joseph says, simulations of the lower atmosphere tended to rely heavily on data from simple environments, like “pristine homogeneous fields in Kansas.” The Beltsville campus was right at the urban-rural divide, with countryside to the north and the sprawl of Washington, D.C., to the south, and the overlying air pushed and pulled from continental and ocean sources. Students took a lead role in launching weather balloons to study this complex environment. In 2006, they won a NASA grant to use their balloons to validate water vapor and ozone measurements from its newly launched Aura satellite—work that might have traditionally gone to a NASA center. “I'm very proud of that,” Demoz says. “Somebody took a risk and said let's do this.” Today, the Beltsville site is one of the few U.S. locations certified to make measurements of the upper atmosphere to the exacting standards of the World Meteorological Organization. It hosts a 30-meter tower for measuring winds, carbon dioxide, and air pollution; instruments for studying dust, soot, and similar particles; and sensors for measuring the precise amount of sunlight reaching the surface. Data gathered by Howard students help feed the numerical models used in National Weather Service forecasts. Many students interned at NOAA and NASA branches around the country, and some opportunities took them even farther afield. In the late 2000s, Jenkins flew students to West Africa for NASA-sponsored research on the birth of Atlantic hurricanes and their interaction with Saharan dust. His students flew on a DC-8 into tropical storms, running the radar instruments to capture these rare data. Follow-up flights chased dust storms across the Atlantic and studied ozone variability in the tropics. “The most important thing was to send students way outside their comfort zone,” Jenkins says. Perhaps nothing was more uncomfortable for some Howard students than spending weeks at sea, as the AEROSE cruises have done now for nearly 2 decades. “Being a girl from the South Side of Chicago, that was really intimidating,” Hawkins says. Mayra Oyola-Merced, now an atmospheric physicist at NASA's Jet Propulsion Laboratory, remembers when they got a new lidar scanner on board for tracking dust in the air. Joseph asked whether she wanted to run it. “This was a $250,000 instrument,” she says, and she was just an undergraduate. But Joseph patiently explained the physics behind it, and that stuck with her. “Feeling someone trusted me and someone could see my potential to do things—it changed my complete perspective about going to graduate school.” FOR ALL ITS SUCCESS , the Howard program's future remains cloudy. For decades it was just one failed grant application away from collapse. The strain on faculty prompted many to leave, their vacant positions often going unfilled—an exodus that has many former faculty and alumni fearing for the program. Morris left early last year when Arizona State University offered him a chance to lead the school of science at its small liberal arts college. Jenkins, Joseph, and Demoz have also left, though Demoz still helps at Beltsville. “I'm the last one left,” Smith says. She and Terri Adams, a Howard sociologist who led the NOAA center on an interim basis, have been tasked with rebuilding the program, even though Smith's work has veered toward hypersonic weapons and Adams studies emergency management of climate disasters, not geoscience itself. For the university, Morris's departure served as a wake-up call. The university is now creating a department of earth, environment, and equity based on the program, giving it a lasting home that will include undergraduate students. (Previously the program was jointly administered by three departments, diluting its clout with the administration.) Charles Ichoku, a former senior NASA scientist originally from Nigeria, joined the faculty just before the pandemic and is pursuing grants for upgrades at Beltsville. Howard has hired a new director for its NOAA center and three new faculty in atmospheric sciences, two junior and one senior. Atmospheric sciences is essential to the university's future, says Bruce Jones, who joined Howard in 2018 as its first ever vice president for research and is charged with increasing its research ambitions. “While we acknowledge we lost some of the great minds in the field, the recent investment is just the beginning of the rebirth of the program,” he says. The recommitment is good to see, says Jack Kaye, associate director of NASA's earth science division, who is white. “Howard is special place in American education,” he says. “Having a program focused on atmospheric sciences is important to the community. It's important to the nation.” Whatever the future of the program, its mark will be lasting. Morris, his colleagues, and former students have a tradition of getting together at the AMS annual meeting. Their once-informal gathering—online during the pandemic but scheduled to resume next year—is now one of the meeting's primary social events, attended by a diverse crowd that includes agency leaders and senior scientists. Called the “Colour of Weather,” it regularly fills a ballroom. Many former Howard students now occupy leadership positions, especially at NOAA, which remains the primary sponsor of the Howard graduate program. “They're smart, pushing, building communities—that's a pay back, there's no dollar sign on that,” Jenkins says. And they continue to try to make atmospheric science more welcoming. In 2014, Hawkins and Carlis started a diversity working group at NOAA, which hosts monthly seminars and encourages minority scientists scattered across the agency's many divisions to connect and support each other. They have also advised the agency to implement steps like evaluating supervisors on their support for inclusion and increasing the diversity of hiring panels. “We can move the needle,” Hawkins says. “We can provide equity where we can.” One disappointment, though, is that few Howard graduates have ended up in academia. Universities hire faculty from the same few elite academic programs, which continue to churn out predominately white graduates—and when few faculty are people of color, potential students are put off, Marshall says. “Students need to see professors of color,” he says. “We just don't see enough people at the university level, teaching,” Jenkins adds. “That's still the struggle.” In the wake of the murder of George Floyd in May 2020, Morris and several peers published a letter online urging geoscientists to end their silence on the racism in their field. “In place of police brutality, careers are killed through forced attrition and under-investment,” they wrote. New Black professors are subject to biased reviews and limited mentorship. “The time has passed for predominantly white scientific organizations to post photos of happy, multiracial groups on their websites in place of actually diversifying their leadership and members,” they wrote. Since that letter, professional organizations have taken some real steps, Morris says. At the AMS meeting in January, the presidential forum focused on building a culture of antiracism. (Morris was among the speakers.) AMS and the American Geophysical Union have created new senior positions focused on improving diversity, featured talks on diversity more prominently at meetings, and gathered more data about the race and ethnicity of members. But academic programs have been much slower to react, Morris adds. Overall, he sees little evidence that the toxic environment often faced by students and faculty of color has changed. New hires still face an evaluation and tenure process that reinforces white privilege, he says. “Many of the current cluster hires are like experiments that introduce new fish into a polluted pond to see if they survive,” he says. So much more can be done, Morris says. Investing more federal research dollars in HBCUs and minority-serving institutions is an obvious start. “A lot of HBCU programs are funded at levels that aren't going to enable their success,” Morris says. But it's not just money that made the Howard program so successful. It had federal agencies invested in its success and benefited from their material support in the form of adjunct professors and lab space. It recruited students from places other programs hadn't looked. And most of all, it had a cohort of young Black professors hungry for the program to succeed—who saw its success as their own. Jamese Sims, an alumnus who's now NOAA's senior science adviser for artificial intelligence, recalls that passion. Howard's faculty asked how they could speak up for those without a voice, she says. They asked how their scientific expertise could make this a better country for all. “Because, if our goal is ultimately to save lives and property,” she says, “that includes everyone.”

Of all the perils he faced during World War II, Winston Churchill said German submarine wolfpacks were his greatest concern, because their attacks on merchant ship convoys threatened to choke Britain's economic lifelines. Today, it seems there is another emerging undersea threat, one that has the potential to disrupt the global economy by severing fiber-optic lines of communication that run along the world's various seabeds. There are nearly 400 undersea cables that stretch for almost three-quarters of a million miles, the densest concentrations of them being in the North Atlantic and the North Sea, the Mediterranean, and in Southeast Asia and around Japan. They carry virtually all (97%) international communications, and their exact locations are reasonably well-known. They are also increasingly vulnerable to being tapped or even cut by advanced submarine craft of a range of types, from manned mini-subs to remotely operated undersea drones, and even fully autonomous "U-bots."