Urban transportation systems face increasing resilience challenges from extreme weather events, but current assessment methods rely on surface-level recovery indicators that miss hidden structural damage. Existing approaches cannot distinguish between true recovery and "false recovery," where traffic metrics normalize, but the underlying system dynamics permanently degrade. To address this, a new physics-constrained Hamiltonian learning algorithm combining "structural irreversibility detection" and "energy landscape reconstruction" has been developed. Our approach extracts low-dimensional state representations, identifies quasi-Hamiltonian structures through physics-constrained optimization, and quantifies structural changes via energy landscape comparison. Analysis of London's extreme rainfall in 2021 demonstrates that while surface indicators were fully recovered, our algorithm detected 64.8\% structural damage missed by traditional monitoring. Our framework provides tools for proactive structural risk assessment, enabling infrastructure investments based on true system health rather than misleading surface metrics.

Feedback was amazed to hear that dog ownership could cause a hurricane across the other side of the world. Or are we barking up the wrong tree? Kristian Steensen Nielsen seems like a sensible type. A researcher at the Copenhagen Business School in Denmark, he studies "the role of behavior change in mitigating climate change and conserving biodiversity". In other words, how can we make our lives more environmentally friendly, and how and when do those changes scale up to become truly effective?

Sign up for the Slatest to get the most insightful analysis, criticism, and advice out there, delivered to your inbox daily. Chris Heinrich will never forget the winter day he and his family evacuated their home in Altadena, California, as a vertical wall of flame was slowly bearing down on their neighborhood from the mountains. "It was dark," he told Slate. "There was no internet, my daughter was crying, the wind was blowing." Even as the fires approached, he said, he didn't really believe that their house would burn.

Many tasks related to Computational Social Science and Web Content Analysis involve classifying pieces of text based on the claims they contain. State-of-the-art approaches usually involve fine-tuning models on large annotated datasets, which are costly to produce. In light of this, we propose and release a qualitative and versatile few-shot learning methodology as a common paradigm for any claim-based textual classification task. This methodology involves defining the classes as arbitrarily sophisticated taxonomies of claims, and using Natural Language Inference models to obtain the textual entailment between these and a corpus of interest. The performance of these models is then boosted by annotating a minimal sample of data points, dynamically sampled using the well-established statistical heuristic of Probabilistic Bisection. We illustrate this methodology in the context of three tasks: climate change contrarianism detection, topic/stance classification and depression-relates symptoms detection.

Data-driven weather forecast based on machine learning (ML) has experienced rapid development and demonstrated superior performance in the global medium-range forecast compared to traditional physics-based dynamical models. However, most of these ML models struggle with accurately predicting extreme weather, which is closely related to the extreme value prediction. Through mathematical analysis, we prove that the use of symmetric losses, such as the Mean Squared Error (MSE), leads to biased predictions and underestimation of extreme values. To address this issue, we introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. Furthermore, we introduce a training-free extreme value enhancement strategy named ExEnsemble, which increases the variance of pixel values and improves the forecast robustness. Combined with an advanced global weather forecast model, extensive experiments show that our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.

Recent years have heralded a particularly disruptive period in human history. Against the backdrop of a warming planet and the spillover effects of the COVID-19 pandemic, we face some of the most challenging economic and geopolitical conditions in decades. And things may only deteriorate from here. These challenges are detailed at length in the World Economic Forum's Global Risks Report 2024, released this week. The report, based on the views of nearly 1,500 global risks experts, policy-makers, and industry leaders, finds that the world's top three risks over the next two years are false information, extreme weather, and societal polarization.

False and misleading information supercharged with cutting-edge artificial intelligence that threatens to erode democracy and polarize society is the top immediate risk to the global economy, the World Economic Forum said in a report Wednesday. In its latest Global Risks Report, the organization also said an array of environmental risks pose the biggest threats in the longer term. The report was released ahead of the annual elite gathering of CEOs and world leaders in the Swiss ski resort town of Davos and is based on a survey of nearly 1,500 experts, industry leaders and policymakers. The report listed misinformation and disinformation as the most severe risk over the next two years, highlighting how rapid advances in technology also are creating new problems or making existing ones worse. The authors worry that the boom in generative AI chatbots like ChatGPT means that creating sophisticated synthetic content that can be used to manipulate groups of people won't be limited any longer to those with specialized skills. AI is set to be a hot topic next week at the Davos meetings, which are expected to be attended by tech company bosses including OpenAI CEO Sam Altman, Microsoft CEO Satya Nadella and AI industry players like Meta's chief AI scientist, Yann LeCun.

Most of us don't have a favorite TV meteorologist anymore. Instead, we roll out of bed and check a weather app on our phones. When they fail--and they often do--we feel confused and almost betrayed. After all, we chose this weather app, checked it days in advance, trusted it with our plans … and the prediction it made led us astray, maybe left us soaking wet. Many professional meteorologists call weather apps "crap apps."

High above the valley in California's wine country, Joanna Wells' vineyard is a challenging place to grow grapes. It's nearly 3,000 feet above sea level, atop a mountain ridge, "Forty minutes off a main road just to get there," Wells says. But it's these rocky hilltop terrains, with plenty of sunshine and maritime breezes, that Wells says, are perfect for the job. What's not idyllic, though, is California's extreme weather. "Every year tends to be climatically extreme now."

These risk estimates are from the World Economic Forum, the Intergovernmental Panel on Climate Change, the Chicago Actuarial Association, the Global Challenges Foundation, Bethan Harris at the University of Reading, and David Morrison at NASA, with advice from Phil Torres at the Institute for Ethics and Emerging Technologies, author of Human Extinction: A Short History. Fully autonomous weapons don't exist yet, but advances in drone technology and AI make them likely. Rogue code and irresponsible use could lead to mass violence on a scale and speed we don't understand today. Hacking the transport system or a central bank would wreak havoc and threaten public safety. Prevention relies on educating people about cybersecurity.