YellowScan's Navigator system is designed to map underwater topography in rivers, ponds and coastal areas. Below, its lidar system scans the landscape, mapping both the land and the shallow waters with pinpoint accuracy. This is precisely what YellowScan's new Navigator system is designed to do. Built specifically for mapping underwater topography in rivers, ponds and coastal areas, the Navigator is changing the game for environmental monitoring. With precision where traditional methods struggle, it's giving researchers and conservationists a whole new way to understand our planet's changing waterways.

As artificial intelligence and machine learning tools become more accessible, and scientists face new obstacles to data collection (e.g. rising costs, declining survey response rates), researchers increasingly use predictions from pre-trained algorithms as outcome variables. Though appealing for financial and logistical reasons, using standard tools for inference can misrepresent the association between independent variables and the outcome of interest when the true, unobserved outcome is replaced by a predicted value. In this paper, we characterize the statistical challenges inherent to this so-called ``inference with predicted data'' problem and elucidate three potential sources of error: (i) the relationship between predicted outcomes and their true, unobserved counterparts, (ii) robustness of the machine learning model to resampling or uncertainty about the training data, and (iii) appropriately propagating not just bias but also uncertainty from predictions into the ultimate inference procedure.

A new 30-foot tower has sprouted on the edge of The Ohio State University Airport, but it has nothing to do with directing the thousands of planes that take off and land there each year. Instead, this tower is the focal point of an Ohio State research project that will explore using artificial intelligence and a variety of sensors to monitor environmental conditions on a minute-to-minute basis. A key part of the project is the use of machine learning to interpret the data as it is collected, said Tanya Berger-Wolf, director of Ohio State's Translational Data Analytics Institute (TDAI) and the leader of the project. "This is a unique opportunity for our researchers to help understand environmental conditions in urban areas, such as carbon emissions, noise and air pollution, and how it changes in real time," Berger-Wolf said. "We will use artificial intelligence and machine learning models to take all the complex information we collect and get insight out of the data, such as the impact of emissions from the airplanes on the local environment."

"We will use artificial intelligence and machine learning models to take all the complex information we collect and get insight out of the data, such as the …