Knowing where fire retardant lands once it’s dropped from a plane is hard to pin down. A new remote sensing approach offers clues.
machine learning & AI
Mapping Beaver Dams with Machine Learning
A new model deploys a neural network to spot beavers’ engineering exploits in aerial and satellite imagery, an approach that should aid studies of ecosystem and landscape change.
Machine Learning Helps Constrain the Thickness of Ancient Crust
A machine learning model trained using data on the chemical composition of magmatic rocks yields comparable, if not better, results to previously developed geochemical proxies.
New Forecasting Tool Could Help Indian Farmers Plan Irrigation
Tropical weather is unpredictable, but a new tool could help farmers get a better grasp on it.
Inductive Approach Reveals Controls on Dissolved Organic Carbon
Machine learning leverages large data sets to reveal hidden patterns explaining when, where, and why dissolved organic carbon moves from hillslopes to streams.
New Machine Learning Parameterization Tested on Atmospheric Model
For the first time, a neural network parameterization of subgrid momentum transport is developed by training on a coarse-grained high-resolution atmospheric simulation.
Neural Networks Map the Ebb and Flow of Tiny Ponds
Ponds play an outsized role in carbon emissions, but their size makes them hard to track. Enter machine learning.
Analyzing Sources of Pollution in the Great Lakes
Understanding how agriculture and land use affect nutrient flows and concentrations in the vast area of the Great Lakes is an essential step to developing sustainable management strategies.
How Big Data is Helping Environmental and Climate Research
A new special collection invites papers focusing on the processing, modeling, and analysis of all types of big datasets in the Earth and space sciences, including the influence of solar forcing on Earth’s climate.