Deep learning weather models now match numerical weather prediction accuracy while running orders of magnitude faster, but produce deterministic forecasts without uncertainty estimates, a critical gap for high-stakes decisions during extreme weather events. This paper proposes Neural Tangent Kernel-based uncertainty quantification (NTK-UQ) using last-layer empirical features. Theoretical analysis predicts that UQ quality is architecture-dependent through two mechanisms. First, a variance collapse mechanism explains when UQ fails: when the eigenvalue truncation rank approaches the effective rank of the feature space, the GP correction term consumes nearly all prior variance, destroying discrimination between tropical cyclones and routine conditions; architectures with concentrated spectra (spectral operators) require aggressive truncation ($k \leq 10$), while attention-based models tolerate full-rank computation. Second, decomposition performance depends on the non-Gaussian, heavy-tailed structure of extreme weather: Independent Component Analysis exploits higher-order statistics (kurtosis, negentropy) to isolate heavy-tailed extreme-event features, achieving higher discrimination t
Machine learning inference occurs at a massive scale, yet its environmental impact remains poorly quantified, especially on low-resource hardware. We present ML-EcoLyzer, a cross-framework tool for measuring the carbon, energy, thermal, and water costs of inference across CPUs, consumer GPUs, and datacenter accelerators. The tool supports both classical and modern models, applying adaptive monitoring and hardware-aware evaluation. We introduce the Environmental Sustainability Score (ESS), which quantifies the number of effective parameters served per gram of CO$_2$ emitted. Our evaluation covers over 1,900 inference configurations, spanning diverse model architectures, task modalities (text, vision, audio, tabular), hardware types, and precision levels. These rigorous and reliable measurements demonstrate that quantization enhances ESS, huge accelerators can be inefficient for lightweight applications, and even small models may incur significant costs when implemented suboptimally. ML-EcoLyzer sets a standard for sustainability-conscious model selection and offers an extensive empirical evaluation of environmental costs during inference.
Scientists have uncovered new evidence that fireworks can pollute both the air and water in ways that extend beyond the visible smoke。 The findings show that leftover debris, fine particles, and airborne chemicals may affect ecosystems and increase people's exposure to air pollution during major celebrations
Water’s odd behavior becomes even more dramatic when it is supercooled, but scientists have struggled to compare the many different ways of describing its microscopic structure。 Researchers at the University of Osaka used an AI model trained on computer simulations to evaluate 16 different structural descriptors。 The system identified the most effe
What if consciousness isn’t limited to brains like ours。 Philosophers Eric Schwitzgebel and Jeremy Pober argue that consciousness could arise in many different forms of life, even in beings built from radically different materials than those found on Earth。 Drawing on the vastness of the universe and the likely existence of countless alien civiliza
AI cheating leads to "a failed society," professor says
Scientists have identified new clues that could help astronomers spot one of the most famous hypothetical alien megastructures: a Dyson sphere。 The study finds that red dwarfs and white dwarfs are the most promising stars to examine, since advanced civilizations could potentially build energy-harvesting swarms around them more easily。 These objects
Scientists are calling for a lunar quarantine facility where samples from Mars, the Moon, and beyond would be examined before being brought to Earth。 They warn that even a tiny alien microorganism could have unpredictable effects on Earth's ecosystems。 By using robotic handling systems on the Moon, researchers hope to eliminate the risk of accident
A centimeter-sized crystal has revealed clear signs of quantum entanglement, showing that large, everyday objects can display surprisingly deep quantum behavior。 The discovery could help solve the mystery of strange metals while opening new possibilities for ultra-precise quantum sensors and other advanced technologies
Ancient asteroid impacts may have done more than reshape Earth's surface—they could have helped spark life itself。 New computer models show the collisions created enormous underground hydrothermal systems by cracking the planet's crust and allowing hot water to flow through it。 These long-lasting, life-friendly environments may have covered much of
Quantum mechanics has journeyed from a strange and controversial idea to the foundation of some of humanity’s most advanced technologies。 Now researchers are pushing its boundaries even further, with potential breakthroughs in energy, medicine, computing, and our understanding of the universe
8 L eight-cylinder generates more than 1,000 hp and 1,000 Nm, Ruf says
A planet with one side permanently roasting and the other frozen in endless darkness might still have a chance of supporting life。 Researchers found that heat inside a tidally locked exoplanet could circulate in a stable, continuous loop, helping moderate temperatures in certain regions。 Their laboratory model suggests these worlds may be more hosp
The hunt for ancient life on Mars just got an important test run。 Scientists confirmed that the Rosalind Franklin rover's sophisticated instrument can detect subtle differences in two stable molecules that could preserve evidence of past life for billions of years。 But the team also uncovered a surprise: organic molecules in the Murchison meteorite