From the highest mountains to the deepest ocean, the driest desert to the lushest jungle, Earth displays a dazzling array of lifeforms. And eukaryotes account for many of these lifeforms, including nearly all of the multicellular life we can see in the landscape. But scientists are still piecing together exactly how this domain of life evolved from simpler predecessors.

A new study published in Big Earth Data systematically evaluates popular Uncertainty Quantification (UQ) methods and metrics for AI/ML-based geospatial applications, addressing challenges of predictive uncertainty, trustworthiness, and real-time integration in complex Earth system modelling. Using a PM2.5 calibration case study, it demonstrates that Deep Ensembles and Bayesian Neural Networks implemented in TensorFlow achieved the best reliability and calibration performance, while also highlighting framework-specific differences between TensorFlow and PyTorch in geospatial UQ applications.

Scientists have uncovered new evidence that Earth’s continents are continuously reworked deep beneath the surface, offering fresh insight into how continents have evolved over billions of years. 

In a new study, researchers observed red auroras over Japan that stretched to unexpectedly high altitudes, about 500 to 800 kilometers above Earth.