The expedition to find the wreck of Sir Ernest Shackleton's Endurance is set to sail next month, it was announced today on the centenary of the polar explorer's death. Endurance was one of two ships used by the Imperial Trans-Antarctic expedition of 1914–1917, which hoped to make the first land crossing of the Antarctic. Carrying an expedition crew of 28 men, the 144-foot-long Endurance was a three-masted schooner barque sturdily built for operations in polar waters. Aiming to land at Vahsel Bay, the vessel became stuck in pack ice on the Weddell Sea on January 18, 1915 -- where she and her crew would remain for many months. In late October, however, a drop in temperature from 42 F to -14 F saw the ice pack begin to steadily crush the Endurance, which finally sank on November 21, 1915.

Fully automatic semantic segmentation of highly specific semantic classes and complex shapes may not meet the accuracy standards demanded by scientists. In such cases, human-centered AI solutions, able to assist operators while preserving human control over complex tasks, are a good trade-off to speed up image labeling while maintaining high accuracy levels. TagLab is an open-source AI-assisted software for annotating large orthoimages which takes advantage of different degrees of automation; it speeds up image annotation from scratch through assisted tools, creates custom fully automatic semantic segmentation models, and, finally, allows the quick edits of automatic predictions. Since the orthoimages analysis applies to several scientific disciplines, TagLab has been designed with a flexible labeling pipeline. We report our results in two different scenarios, marine ecology, and architectural heritage.

There is an increasing demand for piloted autonomous underwater vehicles (AUVs) to operate in polar ice conditions. At present, AUVs are deployed from ships and directly human-piloted in these regions, entailing a high carbon cost and limiting the scope of operations. A key requirement for long-term autonomous missions is a long-range route planning capability that is aware of the changing ice conditions. In this paper we address the problem of automating long-range route-planning for AUVs operating in the Southern Ocean. We present the route-planning method and results showing that efficient, ice-avoiding, long-distance traverses can be planned.

We study adaptive sensing of Cox point processes, a widely used model from spatial statistics. We introduce three tasks: maximization of captured events, search for the maximum of the intensity function and learning level sets of the intensity function. We model the intensity function as a sample from a truncated Gaussian process, represented in a specially constructed positive basis. In this basis, the positivity constraint on the intensity function has a simple form. We show how an minimal description positive basis can be adapted to the covariance kernel, non-stationarity and make connections to common positive bases from prior works. Our adaptive sensing algorithms use Langevin dynamics and are based on posterior sampling (\textsc{Cox-Thompson}) and top-two posterior sampling (\textsc{Top2}) principles. With latter, the difference between samples serves as a surrogate to the uncertainty. We demonstrate the approach using examples from environmental monitoring and crime rate modeling, and compare it to the classical Bayesian experimental design approach.

NOAA and Saildrone Inc. are piloting five specially designed surface drones in the Atlantic Ocean to gather data around the clock to help understand the physical processes of hurricanes. NOAA and Saildrone Inc. are piloting five specially designed surface drones in the Atlantic Ocean to gather data around the clock to help understand the physical processes of hurricanes. Researchers for the National Oceanic and Atmospheric Administration have dispatched a surface drone inside Hurricane Sam as it barrels toward the Caribbean, giving scientists a new perspective of what it's like inside such a storm. The video and images shared were the first of their kind gathered by an "uncrewed surface vehicle" from inside a major hurricane as it moved across the Atlantic Ocean. The onboard camera shows eerily gray skies and turbulent ocean waters.

In estimations of ocean heat content – important when assessing and predicting the effects of climate change – calculations have often presented the rate of warming as a gradual rise from the mid 20th century to today. However, new research from UC Santa Barbara scientists Timothy DeVries and Aaron Bagnell could overturn that assumption, suggesting the ocean maintained a relatively steady temperature throughout most of the 20th century, before embarking on a steep rise. The newly discovered dynamics may have significant implications for what we might expect in the future. "There wasn't an onset of an imbalance until about 1990, which is later than most estimates," said DeVries, an associate professor in the Department of Geography, and a co-author on a paper that appears in the journal Nature Communications. According to the study, the period from 1950 to1990 saw temperature fluctuations in the water column but no net warming.

In this work, we propose a method to learn probability distributions using sample path data from stochastic differential equations. Specifically, we consider temporally evolving probability distributions (e.g., those produced by integrating local or nonlocal Fokker-Planck equations). We analyze this evolution through machine learning assisted construction of a time-dependent mapping that takes a reference distribution (say, a Gaussian) to each and every instance of our evolving distribution. If the reference distribution is the initial condition of a Fokker-Planck equation, what we learn is the time-T map of the corresponding solution. Specifically, the learned map is a normalizing flow that deforms the support of the reference density to the support of each and every density snapshot in time. We demonstrate that this approach can learn solutions to non-local Fokker-Planck equations, such as those arising in systems driven by both Brownian and L\'evy noise. We present examples with two- and three-dimensional, uni- and multimodal distributions to validate the method.

The neural ordinary differential equation (neural ODE) model has attracted increasing attention in time series analysis for its capability to process irregular time steps, i.e., data are not observed over equally-spaced time intervals. In multi-dimensional time series analysis, a task is to conduct evolutionary subspace clustering, aiming at clustering temporal data according to their evolving low-dimensional subspace structures. Many existing methods can only process time series with regular time steps while time series are unevenly sampled in many situations such as missing data. In this paper, we propose a neural ODE model for evolutionary subspace clustering to overcome this limitation and a new objective function with subspace self-expressiveness constraint is introduced. We demonstrate that this method can not only interpolate data at any time step for the evolutionary subspace clustering task, but also achieve higher accuracy than other state-of-the-art evolutionary subspace clustering methods. Both synthetic and real-world data are used to illustrate the efficacy of our proposed method.

From the bottom of the oceans to the skies above us, natural evolution has filled our planet with a vast and diverse array of lifeforms, with approximately 8 million species adapted to their surroundings in a myriad of ways. Yet 100 years after Karel Čapek coined the term robot, the functional abilities of many species still surpass the capabilities of current human engineering, which has yet to convincingly develop methods of producing robots that demonstrate human-level intelligence, move and operate seamlessly in challenging environments, and are capable of robust self-reproduction. But could robots ever reproduce? This, undoubtedly, forms a pillar of "life" as shared by all natural organisms. A team of researchers from the UK and the Netherlands have recently demonstrated a fully automated technology to allow physical robots to repeatedly breed, evolving their artificial genetic code over time to better adapt to their environment.

Climate models are critical tools for developing strategies to manage the risks posed by sea-level rise to coastal communities. While these models are necessary for understanding climate risks, there is a level of uncertainty inherent in each parameter in the models. This model parametric uncertainty leads to uncertainty in future climate risks. Consequently, there is a need to understand how those parameter uncertainties impact our assessment of future climate risks and the efficacy of strategies to manage them. Here, we use random forests to examine the parametric drivers of future climate risk and how the relative importances of those drivers change over time. We find that the equilibrium climate sensitivity and a factor that scales the effect of aerosols on radiative forcing are consistently the most important climate model parametric uncertainties throughout the 2020 to 2150 interval for both low and high radiative forcing scenarios. The near-term hazards of high-end sea-level rise are driven primarily by thermal expansion, while the longer-term hazards are associated with mass loss from the Antarctic and Greenland ice sheets. Our results highlight the practical importance of considering time-evolving parametric uncertainties when developing strategies to manage future climate risks.