Researchers combined forest inventory data, satellite observations, and machine learning to estimate tree density across North America and evaluate the uncertainty of those estimates. The study suggests the continent contains between 339 billion and 514 billion trees with DBH＞10 cm and shows that estimates can vary substantially depending on forest definitions and tree size thresholds. The framework provides a consistent approach for large-scale forest monitoring, biodiversity assessment, and carbon accounting.

What if a prosthetic hand could adapt to the person instead of the other way around? Researchers have developed a personalized AI-powered prosthetic system that combines custom 3D-printed wearable sleeves with soft magnetic sensors to decode each user’s unique muscle movements in real time. Designed for every individual’s anatomy, the technology delivers more natural, reliable control and remained highly accurate during repeated testing, offering a promising step toward prosthetic devices that feel more intuitive, comfortable and responsive.

China's massive reforestation effort has transformed more than 77 million hectares of land, but new research shows that planted forests face different drought risks from natural forests. Using satellite observations from 1990 to 2024 and machine learning analysis, researchers found that planted forests are more vulnerable to rapid-onset flash droughts but less prone to prolonged slow droughts. The differences are linked to forest structure: natural forests have greater species diversity, more complex canopies, and deeper root systems that help buffer sudden water shortages, while planted forests are typically younger and less diverse. The findings highlight a trade-off in drought resilience and suggest that future forest management should prioritize mixed-species, structurally diverse forests to better withstand increasing climate extremes.

In recent years, domain generalization (DG) has garnered significant attention for its goal of learning models from multiple source domains to mitigate domain shift and enable generalization to unseen target domains. Most existing methods e.g., domain-invariant representation, focus on learning a universal sample-to-label mapping (function) across domains, overlooking semantically intrinsic domain-specific information and failing to maintain invariance across diverse unseen target domains.