Axios

In a significant advance for improving weather forecast accuracy, Google DeepMind scientists have developed a weather model that largely beats the world's most accurate modeling system.

Why it matters: The new model provides — for the first time — a machine learning-driven method of conducting ensemble-based forecasting, in which the same model is run with many different initial conditions, to generate probability-based projections.

Even if Thursday's expected OPEC+ decision to delay adding barrels lasts only a few months, it's a sign of longer-term hurdles facing the cartel.

Why it matters: Tepid demand growth and rising output outside OPEC+, including U.S. shale, is forcing tradeoffs between trying to prop up prices and regain market share.

Facebook parent Meta is seeking developers that can bring nuclear reactors online starting in the early 2030s to support data centers and communities around them.

Why it matters: Meta is joining Amazon, Google and other tech giants in turning to nuclear generation to fuel energy-thirsty AI data centers with zero-carbon electrons.

The first day of International Court of Justice hearings on countries' obligations to combat climate change revealed deep dissatisfaction with the climate finance agreement struck at COP29 last month.

Why it matters: The court's advisory opinion will be nonbinding. But vulnerable nations — led by Vanuatu — see it as a potential boost to efforts to hold big greenhouse gas emitters accountable, compared to the COP process.

Environmental intelligence firm Kayrros is rolling out a large language model (LLM) to allow the public to pinpoint methane-emitting facilities, the company first told Axios.

Why it matters: The new "methane GPT" allows users to ask plain-language questions and get answers from the company's Methane Watch map for free.