Air pollution remains a leading global health and environmental risk, particularly in regions vulnerable to episodic air pollution spikes due to wildfires, urban haze and dust storms. Accurate forecasting of particulate matter (PM) concentrations is essential to enable timely public health warnings and interventions, yet existing models often underestimate rare but hazardous pollution events. Here, we present SynCast, a high-resolution neural forecasting model that integrates meteorological and air composition data to improve predictions of both average and extreme pollution levels. Built on a regionally adapted transformer backbone and enhanced with a diffusion-based stochastic refinement module, SynCast captures the nonlinear dynamics driving PM spikes more accurately than existing approaches. Leveraging on harmonized ERA5 and CAMS datasets, our model shows substantial gains in forecasting fidelity across multiple PM variables (PM$_1$, PM$_{2.5}$, PM$_{10}$), especially under extreme conditions. We demonstrate that conventional loss functions underrepresent distributional tails (rare pollution events) and show that SynCast, guided by domain-aware objectives and extreme value theory, significantly enhances performance in highly impacted regions without compromising global accuracy. This approach provides a scalable foundation for next-generation air quality early warning systems and supports climate-health risk mitigation in vulnerable regions.

Experts can make crucial decisions about future biodiversity management by using artificial intelligence to learn from past environmental change, according to research at the University of Birmingham. A team, led by the University's School of Biosciences, has proposed a'time machine framework' that will help decision-makers effectively go back in time to observe the links between biodiversity, pollution events and environmental changes such as climate change as they occurred and examine the impacts they had on ecosystems. In a new paper, published in Trends in Ecology and Evolution, the team sets out how these insights can be used to forecast the future of ecosystem services such as climate change mitigation, food provisioning and clean water. Using this information, stakeholders can prioritise actions which will provide the greatest impact. Principal investigator, Dr Luisa Orsini, is an Associate Professor at the University of Birmingham and Fellow of The Alan Turing Institute.

As air quality plummets across the U.S. this summer, researchers have a glimmer of good news. Artificial intelligence may soon provide advanced warning of future pollution events, which could help hospitals prepare for the uptick in pollution-related illnesses, or even reduce people's exposure entirely. A spike in air pollution often leads to a spike in hospital admissions, as it can exacerbate asthma and other pre-existing respiratory conditions, cause upper respiratory tract infections, or increase the likelihood of stroke. But it's currently impossible to prepare for these spikes due to the constraints of existing air quality forecasts, which are only accurate up to three days in advance, Yunsoo Choi, associate professor of atmospheric chemistry from the University of Houston, told EHN. In that short amount of time, one of the only things we can do to protect ourselves is to limit time spent outdoors. But now, through the use of artificial intelligence (AI) technology, Choi and the University of Houston's Air Quality Forecasting and Modeling Lab created a new model that can predict ozone pollution up to 14 days ahead of time.

A team of University of Illinois researchers estimated the mortality costs associated with air pollution in the U.S. by developing and applying a novel machine learning-based method to estimate the life-years lost and cost associated with air pollution exposure. Scholars from the Gies College of Business at Illinois studied the causal effects of acute fine particulate matter exposure on mortality, health care use and medical costs among older Americans through Medicare data and a unique way of measuring air pollution via changes in local wind direction. The researchers--Tatyana Deryugina, Nolan Miller, David Molitor and Julian Reif--calculated that the reduction in particulate matter experienced between 1999-2013 resulted in elderly mortality reductions worth $24 billion annually by the end of that period. Garth Heutel of Georgia State University and the National Bureau of Economic Research was a co-author of the paper. "Our goal with this paper was to quantify the costs of air pollution on mortality in a particularly vulnerable population: the elderly," said Deryugina, a professor of finance who studies the health effects and distributional impact of air pollution.

A team of University of Illinois researchers estimated the mortality costs associated with air pollution in the U.S. by developing and applying a novel machine learning-based method to estimate the life-years lost and cost associated with air pollution exposure. Scholars from the Gies College of Business at Illinois studied the causal effects of acute fine particulate matter exposure on mortality, health care use and medical costs among older Americans through Medicare data and a unique way of measuring air pollution via changes in local wind direction. The researchers - Tatyana Deryugina, Nolan Miller, David Molitor and Julian Reif - calculated that the reduction in particulate matter experienced between 1999-2013 resulted in elderly mortality reductions worth $24 billion annually by the end of that period. Garth Heutel of Georgia State University and the National Bureau of Economic Research was a co-author of the paper. "Our goal with this paper was to quantify the costs of air pollution on mortality in a particularly vulnerable population: the elderly," said Deryugina, a professor of finance who studies the health effects and distributional impact of air pollution.