Data Release

This proposal would fund the development of Seg2Map, a new open-source, browser-accessible software deployed on the cloud that will apply Machine Learning to imagery and image time-series, to make highly customizable to study Earth’s changing surface for a range of scientific purposes.

We synthesize local high-resolution urban landcover imagery with microclimate data and regional meteorology to determine landcover drivers of extreme urban heat. Resulting outputs are mappable items spatially describing urban temperatures at fine scales, and a web application to analyze changes in urban heat under different climate scenarios.

Effectively documenting and distributing information about restoration projects is essential for measuring progress towards national conservation goals. We will improve the National Fish Habitat Partnership Project Tracking database by creating a data pipeline to compile project information and link data with other decision support tools.

This proposal would fund the testing of quantitative methods for extracting total water level from imagery, with add-on applications including satellite shoreline detection, digital stream gauges, and flood detection. This project supports national scale USGS coastal hazards products.

Scientists who study coastal ecosystems and hazards such as hurricanes, flooding, and cliff failure collect lots of photographs of coastal environments from airplanes and drones. A large area can be surveyed at high resolution and low cost. Additionally, satellites such as Landsat have provided imagery of the Nation’s coastlines every few days for decades. Scientist’s ability to understand coastal...

To make informed decisions, land managers require knowledge about the state of the ecosystems present. Vegetation structure is a key indicator of the state of forested systems; it influences habitat suitability, water quality and runoff, microclimate, and informs wildfire-related characteristics such as fuel loads, burn severity, and post-fire regeneration. Field data used to derive vegetation st

Fire has increased dramatically across the western U.S. and these increases are expected to continue. With this reality, it is critical that we improve our ability to forecast the timing, extent, and intensity of fire to provide resource managers and policy makers the information needed for effective decisions. For example, an advanced, spatially-explicit prediction of the upcoming fire season wou

Wildfires are increasing across the western U.S., causing damage to ecosystems and communities. Addressing the fire problem requires understanding the trends and drivers of fire, yet most fire data is limited only to recent decades. Tree-ring fire scars provide fire records spanning 300-500 years, yet these data are largely inaccessible to potential users. Our project will deliver the newly compil

Detailed information about past fire history is critical for understanding fire impacts and risk, as well as prioritizing conservation and fire management actions. Yet, fire history information is neither consistently nor routinely tracked by many agencies and states, especially on private lands in the Southeast. Remote sensing data products offer opportunities to do so but require additional pr

The USGS maintains an extensive monitoring network throughout the United States in order to protect the public and help manage natural resources. This network generates millions of data points each year, all of which must be evaluated and reviewed manually for quality assurance and control. Sensor malfunctions and issues can result in data losses and unexpected costs, and are typically only notice

Understanding and anticipating change in dynamic Earth systems is vital for societal adaptation and welfare. USGS possesses the multidisciplinary capabilities to anticipate Earth systems change, yet our work is often bound within a single discipline and/or Mission Area. The proposed work breaks new ground in moving USGS towards an interdisciplinary predictive modeling framework. We are initially l

The proposed work will create a seamless pilot dataset of continuous basin characteristics (for example upstream average precipitation, elevation, or dominant land cover type) for the conterminous United States. Basin characteristic data are necessary for training or parameterizing statistical, machine learning, and physical models, and for making predictions across the landscape, particularly in