A customized framework for regional classification of conifers using automated feature extraction

Cali L. Roth; Peter S. Coates; K. Benjamin Gustafson; Michael P. Chenaille; Mark A. Ricca; Erika Sanchez-Chopitea; Michael L. Casazza

doi:10.1016/j.mex.2021.101379

USGS · 70221273

A customized framework for regional classification of conifers using automated feature extraction

Cali L. Roth·Peter S. Coates·K. Benjamin Gustafson·Michael P. Chenaille·Mark A. Ricca·Erika Sanchez-Chopitea·Michael L. Casazza

View original source ↗Export metadata ↓

Abstract

Pinyon and juniper expansion into sagebrush ecosystems is one of the major challenges facing land managers in the Great Basin. Effective pinyon and juniper treatment requires maps that accurately and precisely depict tree location and degree of woodland development so managers can target restoration efforts for early stages of pinyon and juniper expansion. However, available remotely sensed layers that cover a regional spatial extent lack the spatial resolution or accuracy to meet this need. Accuracy can be improved using object-based image analysis methods such as automated feature extraction, which has proven successful in accurately classifying land cover at the site-level but to date has yet to be applied to regional extents due to time and computational limitations. Using Feature Analyst™, we implement our framework with 1-m 2 reference imagery provided by National Agricultural Imagery Program to classify conifers across Nevada and northeastern California. Our resulting binary conifer map has an overall accuracy of 86%. We discuss the advantages to accuracy and precision our framework provides compared to other classification methods

Explore related subjects

MethodsX Article

Source-reported bounding extent: 35.42486791930558° to 44.5278427984555° latitude; -122.34374999999999° to -111.09374999999999° longitude. This indicates report coverage, not an exact sampling location. View area on OpenStreetMap.

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Cali L. Roth, Peter S. Coates, K. Benjamin Gustafson, Michael P. Chenaille, Mark A. Ricca, Erika Sanchez-Chopitea, Michael L. Casazza. 2021. A customized framework for regional classification of conifers using automated feature extraction. https://doi.org/10.1016/j.mex.2021.101379

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related USGS reports

USGS2026

Statewide agent-based model for management of chronic wasting disease in white-tailed deer: PAOvCWD

Chronic wasting disease (CWD) is an always-fatal disease infecting wild cervids globally. Ecologically and economically important, CWD presents a challenge for managing white-tailed deer ( Odocoileus virginianus ). We built an agent-based model to simulate CWD transmission and assess potential management actions that could slow disease spread: PAOvCWD . We developed PAOvCWD using contact rates and other behavioral and ecological metrics estimated from deer monitored in Pennsylvania, USA. We programmed potential management responses (e.g., culling, altered hunter harvest) for all 22 Pennsylvania wildlife management units and validated the efficacy of PAOvCWD using a deer population in south-central Pennsylvania infected with CWD for > 10 years. To support applications of our model, we developed a user-friendly R pipeline that allows implementation with relatively minor modifications. Our pipeline includes four steps: • Steps 1 and 2 generate regional percent forest cover rasters and curate population-level demographics. • Step 3 initializes landscapes and agents using our PAOvPOP model. • Step 4 assesses CWD transmission and management responses using our PAOvCWD model.

Pennsylvania↗

USGS2026

Generating geochemical and mineralogy distributions of soil in the conterminous United States using Bayesian hierarchical spatial models

Characterizing geochemical and mineralogical soil distributions across large spatial extents is essential for understanding mineral resources, ecosystem processes, and environmental risks. Rasters of soil geochemical distributions for the conterminous United States, however, are limited. We present a Bayesian modeling workflow and tool for generating predictive geochemical and mineralogy distribution maps for the conterminous United States using integrated nested Laplace approximation (INLA) with the stochastic partial differential equation approach. By modeling soil geostatistical data with environmental covariates (soil properties, topography, climate, and land cover), we generate predictive distributions of soil geochemistry that can be mapped or extracted for further analyses. As an example, we model the spatial distribution of trace elements in soil relevant to vertebrate health (cobalt, copper, iron, manganese, selenium, and zinc) and provide a workflow that can be used to generate and visualize predictive distributions of 39 other major and trace elements and 21 minerals of the soil survey, supporting a variety of ecological, environmental, and agricultural applications.

MethodsX↗

USGS2023

A Bayesian multi-stage modelling framework to evaluate impacts of energy development on wildlife populations: An application to Greater Sage-Grouse (Centrocercus urophasianus)

Increased demand for domestic production of renewable energy has led to expansion of energy infrastructure across western North America. Much of the western U.S. comprises remote landscapes that are home to a variety of vegetation communities and wildlife species, including the imperiled sagebrush ecosystem and indicator species such as greater sage-grouse ( Centrocercus urophasianus ). Geothermal sources in particular have potential for continued development across the western U.S. but impacts to greater sage-grouse and other species are unknown. To address this information gap, we describe a novel two-pronged methodology that analyzes impacts of geothermal energy production on pattern and process of greater sage-grouse populations using (a) before-after control-impact (BACI) measures of population growth and lek absence rates and (b) concurrent-to-operation evaluations of demographic rates. Growth and absence rate analyses utilized 14 years of lek survey data collected prior (2005–2011) and concurrent (2012–2018) to geothermal operations at two sites in Nevada, USA. Demographic analyses utilized relocation data, restricted inference to concurrent years, and incorporated 17 additional control sites. Demographic results were applied to >100 potential geothermal sites distributed across the study region to generate spatially explicit predictions of unrealized population-level impacts.

MethodsX↗