Geology topics

Inga P. La Puma

Publications and source records attributed to Inga P. La Puma.

5 recordsLinked to original sources

USGS2025

An interagency perspective on improving consistency and transparency of land use and land cover mapping

Executive Summary Geospatial products of land use and land cover are broadly used in many applications. For example, the annual national greenhouse gas inventory uses the National Land Cover Database, the Coastal Change Analysis Program, Landscape Fire and Resource Management Planning Tools, the Forest Inventory and Analysis, and the National Resources Inventory to represent the land use and management base of the United States and attribute sources and sinks of greenhouse gas emissions. Federally produced land use and land cover datasets for the United States, including those from the Multi-Resolution Land Characteristics Consortium, set the foundation for developing and informing applications such as land change, conservation, greenhouse gas monitoring, urban planning, agricultural production, ecosystem functions, and water quantity and use. No single land use and land cover product is optimal for all land use and land cover applications. Approaches for defining and mapping land use and land cover classes differ across Federal map products, reflecting the tailoring of product specifications to match specific agency needs. These differing approaches present a challenge when attempting to integrate and harmonize multiple land use and land cover products into single analysis or application frameworks. Nuanced understanding of how these products are designed and produced may not be immediately evident to users; however, the availability of a diverse suite of products also represents an opportunity, providing multiple approaches for observing landscape change. In response to the National Strategy to Advance an Integrated U.S. Greenhouse Gas Measurement, Monitoring, and Information System, this Multi-Resolution Land Characteristics Consortium-led interagency report presents (1) the current status of U.S. Federal land use and land cover products (as of May 2024), (2) existing synergies and integration among these federally produced land use and land cover products, (3) inherent challenges of creating a single consistent framework, and (4) strategies for collectively tackling these challenges to improve coordination and collaboration among data producers and facilitate the adoption of land use and land cover products for greenhouse gas monitoring and a variety of other applications.

Circular↗

USGS2024

The spatially adaptable filter for error reduction (SAFER) process: Remote sensing-based LANDFIRE disturbance mapping updates

LANDFIRE (LF) has been producing periodic spatially explicit vegetation change maps (i.e., LF disturbance products) across the entire United States since 1999 at a 30 m spatial resolution. These disturbance products include data products produced by various fire programs, field-mapped vegetation and fuel treatment activity (i.e., events) submissions from various agencies, and disturbances detected by the U.S. Geological Survey Earth Resources Observation and Science (EROS)-based Remote Sensing of Landscape Change (RSLC) process. The RSLC process applies a bi-temporal change detection algorithm to Landsat satellite-based seasonal composites to generate the interim disturbances that are subsequently reviewed by analysts to reduce omission and commission errors before ingestion them into LF’s disturbance products. The latency of the disturbance product is contingent on timely data availability and analyst review. This work describes the development and integration of the Spatially Adaptable Filter for Error Reduction (SAFER) process and other error and latency reduction improvements to the RSLC process. SAFER is a random forest-based supervised classifier and uses predictor variables that are derived from multiple years of pre- and post-disturbance Landsat band observations. Predictor variables include reflectance, indices, and spatial contextual information. Spatial contextual information that is unique to each contiguous disturbance region is parameterized as Z scores using differential observations of the disturbed regions with its undisturbed neighbors. The SAFER process was prototyped for inclusion in the RSLC process over five regions within the conterminous United States (CONUS) and regional model performance, evaluated using 2016 data. Results show that the inclusion of the SAFER process increased the accuracies of the interim disturbance detections and thus has potential to reduce the time needed for analyst review. LF does not track the time taken by each analyst for each tile, and hence, the relative effort saved was parameterized as the percentage of 30 m pixels that are correctly classified in the SAFER outputs to the total number of pixels that are incorrectly classified in the interim disturbance and are presented. The SAFER prototype outputs showed that the relative analysts’ effort saved could be over 95%. The regional model performance evaluation showed that SAFER’s performance depended on the nature of disturbances and availability of cloud-free images relative to the time of disturbances. The accuracy estimates for CONUS were inferred by comparing the 2017 SAFER outputs to the 2017 analyst-reviewed data. As expected, the SAFER outputs had higher accuracies compared to the interim disturbances, and CONUS-wide relative effort saved was over 92%. The regional variation in the accuracies and effort saved are discussed in relation to the vegetation and disturbance type in each region. SAFER is now operationally integrated into the RSLC process, and LANDFIRE is well poised for annual updates, contingent on the availability of data.

Fire↗

USGS2023

A multimodal data fusion and deep learning framework for large-scale wildfire surface fuel mapping

Accurate estimation of fuels is essential for wildland fire simulations as well as decision-making related to land management. Numerous research efforts have leveraged remote sensing and machine learning for classifying land cover and mapping forest vegetation species. In most cases that focused on surface fuel mapping, the spatial scale of interest was smaller than a few hundred square kilometers; thus, many small-scale site-specific models had to be created to cover the landscape at the national scale. The present work aims to develop a large-scale surface fuel identification model using a custom deep learning framework that can ingest multimodal data. Specifically, we use deep learning to extract information from multispectral signatures, high-resolution imagery, and biophysical climate and terrain data in a way that facilitates their end-to-end training on labeled data. A multi-layer neural network is used with spectral and biophysical data, and a convolutional neural network backbone is used to extract the visual features from high-resolution imagery. A Monte Carlo dropout mechanism was also devised to create a stochastic ensemble of models that can capture classification uncertainties while boosting the prediction performance. To train the system as a proof-of-concept, fuel pseudo-labels were created by a random geospatial sampling of existing fuel maps across California. Application results on independent test sets showed promising fuel identification performance with an overall accuracy ranging from 55% to 75%, depending on the level of granularity of the included fuel types. As expected, including the rare—and possibly less consequential—fuel types reduced the accuracy. On the other hand, the addition of high-resolution imagery improved classification performance at all levels.

California↗

USGS2022

LANDFIRE data and applications

LANDFIRE is a Federal program that provides a suite of spatial datasets indicating areas of disturbance, vegetation and fuels distributions and structure, and historical conditions. The level of detail presented in LANDFIRE’s classifications of disturbance, vegetation, and fuels is unparalleled and can be used in a variety of applications, including (1) modeling wildfire risk and fire behavior, (2) modeling habitat and species ranges, (3) understanding how disturbances affect the landscape, and (4) researching departure from precolonial conditions. Additionally, the all-lands paradigm of LANDFIRE mapping creates spatial data that do not stop at jurisdictional boundaries. The primary research and management applications of LANDFIRE data are detailed in this fact sheet, providing users with a well-rounded understanding of the potential of LANDFIRE’s spatial data layers.

Fact Sheet↗

USGS2018

Climate change science and modeling

This chapter provides a brief background on climate change science, climate simulation models, and models that project the impacts of changes in climate on tree species and ecosystems. Throughout the chapter, boxes list resources for more information on each topic. A more detailed scientific review of climate change science, trends, and modeling can be found in the Intergovernmental Panel on Climate Change (IPCC) Fifth Assessment Report (IPCC 2014), and the Fourth National Climate Assessment (U.S. Global Climate Research Program [USGCRP] 2017).

Delaware, Maryland, New Jersey, New York, Pennsylv↗