A WEB-BASED PLATFORM FOR VISUALIZING SPATIOTEMPORAL DYNAMICS OF BIG TAXI DATA

Mesoscale eddies are ubiquitous in the ocean and account for 90 % of its kinetic energy, but their generation and dissipation are difficult to observe using current remote sensing technology. Our submesoscale eddy dataset, formed by suppressing large-scale circulation signals and enhancing small-scale chlorophyll structures, has important implications for understanding marine environments and ecosystems, as well as improving climate model predictions.

We developed an interpretable machine learning model to predict sub-seasonal and near-future wildfire-burned area over African and South American regions. We found strong time-lagged controls (up to 6–8 months) of local climate wetness on burned areas. A skillful use of such time-lagged controls in machine learning models results in highly accurate predictions of wildfire-burned areas; this will also help develop relevant early-warning and management systems for tropical wildfires.