Publications

The advent of generative AI exemplified by large language models (LLMs) opens new ways to represent and compute geographic information and transcends the process of geographic knowledge production, driving geographic information systems (GIS) towards autonomous GIS. Leveraging LLMs as the decision core, autonomous GIS can independently generate and execute geoprocessing workflows to...

Data annotation is the process of labeling data to show the outcome that a related data model should predict. In this study, annotation data were transformed into semantic graph triples, mainly for use with the Resource Description Framework (RDF), a type of entity-relationship-attribute data model for graph databases. The transformation of annotation data to semantic graph triples...

A geometric accuracy assessment of lidar data collected in eastern Iowa in 2019 as part of the 3D Elevation Program (3DEP) was conducted. The assessment involved evaluating interswath accuracy, same surface precision, point density, absolute accuracy, and consistency with adjacent 3DEP datasets. The results demonstrate that the data meet or exceed the quality level 2 specifications...

Before implementing nontoxic shot requirements for hunting waterfowl and American coots Fulica americana in the United States in 1991, the U.S. Fish and Wildlife Service monitored lead poisoning in waterfowl on federal and state wildlife hunting areas during 1983-1986. Federal and state collaborators collected gizzards and livers from 9,029 hunter-killed waterfowl (10 species of dabbling...

The urgency to address ecosystem loss is paramount, as both land use change and climate change will continue to rapidly alter and degrade natural ecosystems and reduce the many services they provide. To support conservation actions that mitigate impacts from these dual threats, we have developed potential World Terrestrial Ecosystem (WTE) distributions for 2050 following IPCC best...

Executive Summary The U.S. Geological Survey Earth Resources Observation and Science Calibration and Validation (Cal/Val) Center of Excellence (ECCOE) focuses on improving the accuracy, precision, calibration, and product quality of remote-sensing data, leveraging years of multiscale optical system geometric and radiometric calibration and characterization experience. The ECCOE Landsat...

Hydrological streamline delineation is critical for effective environmental management, influencing agriculture sustainability, river dynamics, watershed planning, and more. This study develops a novel approach to combining transfer learning with convolutional neural networks that capitalize on image-based pre-trained models to improve the accuracy and transferability of streamline...

With the ever-increasing number of civil and commercial remote-sensing satellite launches in recent years, the Earth Observation community needs to better understand the quality of new data products as they become available for scientific research purposes.

The Joint Agency Commercial Imagery Evaluation (JACIE) was formed to leverage resources from several Federal agencies for the characterization of remote sensing data and to share those results across the remote sensing community (U.S. Geological Survey, 2024).Remote sensing data and the quality of that data are vital to (1) understanding the physical world and (2) supporting the science...

This paper reviews trends in GeoAI research and discusses cutting-edge ad- vances in GeoAI and its roles in accelerating environmental and social sciences. It ad- dresses ongoing attempts to improve the predictability of GeoAI models and recent re- search aimed at increasing model explainability and reproducibility to ensure trustworthy geospatial findings. The paper also provides...

Linguistic representation of geographic knowledge is semantically complex and particularly challenging when employing geographic information technology to automate interpreted analysis dealing with unstructured knowledge. This study describes an approach called GrammarToGraph (G2G) that applies dependency grammar rules through natural language processing to transform annotation data into...

The goal of the U.S. Geological Survey’s (USGS) 3D Elevation Program (3DEP) is to facilitate the acquisition of nationwide lidar data. Although data meet USGS lidar specifications, some point cloud tiles include noisy and incorrectly classified points. The enhanced accuracy of classified point clouds can improve support for many downstream applications such as hydrologic analysis, urban...