Ernest Shackleton knew'Endurance' had shortcomings, new study says Issues with the ship's hull, deck beams, and more show the ship was no match for Antarctic sea ice. The'Endurance' leaning to one side, during the Imperial Trans-Antarctic Expedition, 1914-17, led by Sir Ernest Shackleton. Breakthroughs, discoveries, and DIY tips sent every weekday. For almost 110 years, the has rested at the bottom of the icy waters of the Antarctic's Weddell Sea . Long held as the poster ship for Antarctic exploration, Sir Ernest Shackleton's ill-fated ship was no match for the crushing sea ice that sank it in November 1915 .

Scientists have a lot of questions about our planet's most important carbon sink--and a new project could help answer them. NEW YORK, NEW YORK - APRIL 16: Eric Schmidt, former chairman and CEO at GOOGLE visits Fox Business Network Studios on April 16, 2019 in New York City. A foundation created by Eric Schmidt, the former CEO of Google, will fund a project to send drone boats out into the rough ocean around Antarctica to collect data that could help solve a crucial climate puzzle. The project is part of a suite of funding announced today from Schmidt Sciences, which Schmidt and his wife Wendy created to focus on projects tackling research into the global carbon cycle. It will spend $45 million over the next five years to fund these projects, which includes the Antarctic research.

A concert is raging underneath the sea ice. But will we drown it out? Breakthroughs, discoveries, and DIY tips sent every weekday. Earth's oceans have always been a wild world of sound . A symphony of chatter between creatures, rain hitting the surface, the boom of calving ice, the thunders of waves and fizz of bubbles, the rumble of undersea earthquakes, and even mysterious quacking sounds .

Breakthroughs, discoveries, and DIY tips sent every weekday. It is in these waters that marine mammal ecologist Ari Friedlaender shuts off the inflatable boat's engine and waits. This is the edge of the world--remote, hostile, and stunningly alive. Beneath the hull, the dark sea churns with wonder abound. A humpback whale (Megaptera novaeangliae) emerges, slow, deliberate, and gentle in its curious demeanor, casting a ripple across the surface.

Breakthroughs, discoveries, and DIY tips sent every weekday. Oceanographers on an excursion in the Southern Ocean captured a chance, unprecedented encounter with a sizable deep-sea squid. While piloting a remotely operated submersible 7,000 feet below the ocean surface from aboard the Schmidt Ocean Institute's research vessel Falkor (too), experts glimpsed a three-foot-long Gonatus antarcticus specimen. But according to National Geographic's announcement, the team wasn't even supposed to be in that location when they stumbled across the elusive cephalopod. "The ice blocks were moving so fast, it would put all the ships in danger, so we had to rearrange everything," said Manuel Novillo, a researcher at the Instituto de Diversidad y Ecología Animal.

Accurate segmentation of sea ice types is essential for mapping and operational forecasting of sea ice conditions for safe navigation and resource extraction in ice-covered waters, as well as for understanding polar climate processes. While deep learning methods have shown promise in automating sea ice segmentation, they often rely on extensive labeled datasets which require expert knowledge and are time-consuming to create. Recently, foundation models (FMs) have shown excellent results for segmenting remote sensing images by utilizing pre-training on large datasets using self-supervised techniques. However, their effectiveness for sea ice segmentation remains unexplored, especially given sea ice's complex structures, seasonal changes, and unique spectral signatures, as well as peculiar Synthetic Aperture Radar (SAR) imagery characteristics including banding and scalloping noise, and varying ice backscatter characteristics, which are often missing in standard remote sensing pre-training datasets. In particular, SAR images over polar regions are acquired using different modes than used to capture the images at lower latitudes by the same sensors that form training datasets for FMs. This study evaluates ten remote sensing FMs for sea ice type segmentation using Sentinel-1 SAR imagery, focusing on their seasonal and spatial generalization. Among the selected models, Prithvi-600M outperforms the baseline models, while CROMA achieves a very similar performance in F1-score. Our contributions include offering a systematic methodology for selecting FMs for sea ice data analysis, a comprehensive benchmarking study on performances of FMs for sea ice segmentation with tailored performance metrics, and insights into existing gaps and future directions for improving domain-specific models in polar applications using SAR data.

Oceanic processes at fine scales are crucial yet difficult to observe accurately due to limitations in satellite and in-situ measurements. The Surface Water and Ocean Topography (SWOT) mission provides high-resolution Sea Surface Height (SSH) data, though noise patterns often obscure fine scale structures. Current methods struggle with noisy data or require extensive supervised training, limiting their effectiveness on real-world observations. We introduce SIMPGEN (Simulation-Informed Metric and Prior for Generative Ensemble Networks), an unsupervised adversarial learning framework combining real SWOT observations with simulated reference data. SIMPGEN leverages wavelet-informed neural metrics to distinguish noisy from clean fields, guiding realistic SSH reconstructions. Applied to SWOT data, SIMPGEN effectively removes noise, preserving fine-scale features better than existing neural methods. This robust, unsupervised approach not only improves SWOT SSH data interpretation but also demonstrates strong potential for broader oceanographic applications, including data assimilation and super-resolution.

Accurately quantifying air-sea fluxes is important for understanding air-sea interactions and improving coupled weather and climate systems. This study introduces a probabilistic framework to represent the highly variable nature of air-sea fluxes, which is missing in deterministic bulk algorithms. Assuming Gaussian distributions conditioned on the input variables, we use artificial neural networks and eddy-covariance measurement data to estimate the mean and variance by minimizing negative log-likelihood loss. The trained neural networks provide alternative mean flux estimates to existing bulk algorithms, and quantify the uncertainty around the mean estimates. Stochastic parameterization of air-sea turbulent fluxes can be constructed by sampling from the predicted distributions. Tests in a single-column forced upper-ocean model suggest that changes in flux algorithms influence sea surface temperature and mixed layer depth seasonally. The ensemble spread in stochastic runs is most pronounced during spring restratification.

Marine ecosystem monitoring via Passive Acoustic Monitoring (PAM) generates vast data, but deep learning often requires precise annotations and short segments. We introduce DSMIL-LocNet, a Multiple Instance Learning framework for whale call detection and localization using only bag-level labels. Our dual-stream model processes 2-30 minute audio segments, leveraging spectral and temporal features with attention-based instance selection. Tests on Antarctic whale data show longer contexts improve classification (F1: 0.8-0.9) while medium instances ensure localization precision (0.65-0.70). This suggests MIL can enhance scalable marine monitoring. Code: https://github.com/Ragib-Amin-Nihal/DSMIL-Loc

Retrieval-Augmented Generation (RAG) enhances the performance of Large Language Models (LLMs) by incorporating external knowledge. However, LLMs still encounter challenges in effectively utilizing the knowledge from retrieved documents, often being misled by irrelevant or noisy information. To address this issue, we introduce RankCoT, a knowledge refinement method that incorporates reranking signals in generating CoT-based summarization for knowledge refinement based on given query and all retrieval documents. During training, RankCoT prompts the LLM to generate Chain-of-Thought (CoT) candidates based on the query and individual documents. It then fine-tunes the LLM to directly reproduce the best CoT from these candidate outputs based on all retrieved documents, which requires LLM to filter out irrelevant documents during generating CoT-style summarization. Additionally, RankCoT incorporates a self-reflection mechanism that further refines the CoT outputs, resulting in higher-quality training data. Our experiments demonstrate the effectiveness of RankCoT, showing its superior performance over other knowledge refinement models. Further analysis reveals that RankCoT can provide shorter but effective refinement results, enabling the generator to produce more accurate answers. All code and data are available at https://github.com/NEUIR/RankCoT.