Rhodoliths may look like small rocks on the seafloor, but they're actually living algae that create habitats for marine life and contribute to long-term carbon storage.  A new study found that the deeper ‘low-light’ waters off Japan's Tanegashima Island harbor a surprisingly distinct and diverse community of these ‘living pink rocks,’ including four species completely new to science. Researchers identified at least 12 species in a small patch of seafloor 35–38 meters deep, but only three were also found in nearby shallow waters, suggesting the deeper habitat is not simply a continuation of the one near the surface.

Xiaowei Yue and colleagues propose a physical-mechanism-aided, transformer-based model capable of producing reliable predictions of wind shear. Wind shear, a sudden change in wind speed or direction, is a major cause of aviation incidents; it was responsible for 18% of aviation accidents in 2022. Predicting wind shear events is a priority for aviation safety, as it would allow pilots to avoid areas where wind shear is likely. 

Artificial intelligence increasingly helps providers achieve more robustness for their grids, provide better forecasts of electricity prices, and make energy use more efficient. In critical infrastructures, such as the energy system, AI should not be a black box – its decisions need to be understandable at any time. Researchers at the Karlsruhe Institute of Technology (KIT) have developed a new method for a more transparent analysis of AI-based predictions for energy systems. The results of their study have been published in Nature Communications.  (DOI: 10.1038/s41467-026-73243-5)

Penn Engineers have developed FireANTs, an open-source algorithm that compares complex medical images quickly and accurately by combining optimization techniques from modern AI with the precision of geometry. The method could help clinicians and researchers detect subtle changes in tissue over time, while making large-scale image analysis far more practical.

A team of researchers, co-led by an engineer at Penn State, are developing artificial vision technology that could help self-driving cars and robots see more clearly in changing light. Inspired by the way human eyes adjust from bright to dark settings, the new system is able to recognize visual patterns with high accuracy in mixed lighting in a test reminiscent of an eye doctor exam.