Geology topics

Gretchen G. Moisen

Publications and source records attributed to Gretchen G. Moisen.

11 recordsLinked to original sources

USGS2018

Mapping forest change using stacked generalization: An ensemble approach

The ever-increasing volume and accessibility of remote sensing data has spawned many alternative approaches for mapping important environmental features and processes. For example, there are several viable but highly varied strategies for using time series of Landsat imagery to detect changes in forest cover. Performance among algorithms varies across complex natural systems, and it is reasonable to ask if aggregating the strengths of an ensemble of classifiers might result in increased overall accuracy. Relatively simple rules have been used in the past to aggregate classifications among remotely sensed maps (e.g. using majority predictions), and in other fields, empirical models have been used to create situationally specific algorithm weights. The latter process, called “stacked generalization” (or “stacking”), typically uses a parametric model for the fusion of algorithm outputs. We tested the performance of several leading forest disturbance detection algorithms against ensembles of the outputs of those same algorithms based upon stacking using both parametric and Random Forests-based fusion rules. Stacking using a Random Forests model cut omission and commission error rates in half in many cases in relation to individual change detection algorithms, and cut error rates by one quarter compared to more conventional parametric stacking. Stacking also offers two auxiliary benefits: alignment of outputs to the precise definitions built into a particular set of empirical calibration data; and, outputs which may be adjusted such that map class totals match independent estimates of change in each year. In general, ensemble predictions improve when new inputs are added that are both informative and uncorrelated with existing ensemble components. As increased use of cloud-based computing makes ensemble mapping methods more accessible, the most useful new algorithms may be those that specialize in providing spectral, temporal, or thematic information not already available through members of existing ensembles.

Remote Sensing of Environment↗

USGS2017

How similar are forest disturbance maps derived from different Landsat time series algorithms?

Disturbance is a critical ecological process in forested systems, and disturbance maps are important for understanding forest dynamics. Landsat data are a key remote sensing dataset for monitoring forest disturbance and there recently has been major growth in the development of disturbance mapping algorithms. Many of these algorithms take advantage of the high temporal data volume to mine subtle signals in Landsat time series, but as those signals become subtler, they are more likely to be mixed with noise in Landsat data. This study examines the similarity among seven different algorithms in their ability to map the full range of magnitudes of forest disturbance over six different Landsat scenes distributed across the conterminous US. The maps agreed very well in terms of the amount of undisturbed forest over time; however, for the ~30% of forest mapped as disturbed in a given year by at least one algorithm, there was little agreement about which pixels were affected. Algorithms that targeted higher-magnitude disturbances exhibited higher omission errors but lower commission errors than those targeting a broader range of disturbance magnitudes. These results suggest that a user of any given forest disturbance map should understand the map’s strengths and weaknesses (in terms of omission and commission error rates), with respect to the disturbance targets of interest.

Forests↗

USGS2007

Remote sensing-based predictors improve distribution models of rare, early successional and broadleaf tree species in Utah

1. Compared to bioclimatic variables, remote sensing predictors are rarely used for predictive species modelling. When used, the predictors represent typically habitat classifications or filters rather than gradual spectral, surface or biophysical properties. Consequently, the full potential of remotely sensed predictors for modelling the spatial distribution of species remains unexplored. Here we analysed the partial contributions of remotely sensed and climatic predictor sets to explain and predict the distribution of 19 tree species in Utah. We also tested how these partial contributions were related to characteristics such as successional types or species traits. 2. We developed two spatial predictor sets of remotely sensed and topo-climatic variables to explain the distribution of tree species. We used variation partitioning techniques applied to generalized linear models to explore the combined and partial predictive powers of the two predictor sets. Non-parametric tests were used to explore the relationships between the partial model contributions of both predictor sets and species characteristics. 3. More than 60% of the variation explained by the models represented contributions by one of the two partial predictor sets alone, with topo-climatic variables outperforming the remotely sensed predictors. However, the partial models derived from only remotely sensed predictors still provided high model accuracies, indicating a significant correlation between climate and remote sensing variables. The overall accuracy of the models was high, but small sample sizes had a strong effect on cross-validated accuracies for rare species. 4. Models of early successional and broadleaf species benefited significantly more from adding remotely sensed predictors than did late seral and needleleaf species. The core-satellite species types differed significantly with respect to overall model accuracies. Models of satellite and urban species, both with low prevalence, benefited more from use of remotely sensed predictors than did the more frequent core species. 5. Synthesis and applications. If carefully prepared, remotely sensed variables are useful additional predictors for the spatial distribution of trees. Major improvements resulted for deciduous, early successional, satellite and rare species. The ability to improve model accuracy for species having markedly different life history strategies is a crucial step for assessing effects of global change. ?? 2007 The Authors.

Journal of Applied Ecology↗

USGS2007

Habitat classification modeling with incomplete data: Pushing the habitat envelope

Habitat classification models (HCMs) are invaluable tools for species conservation, land-use planning, reserve design, and metapopulation assessments, particularly at broad spatial scales. However, species occurrence data are often lacking and typically limited to presence points at broad scales. This lack of absence data precludes the use of many statistical techniques for HCMs. One option is to generate pseudo-absence points so that the many available statistical modeling tools can be used. Traditional techniques generate pseudoabsence points at random across broadly defined species ranges, often failing to include biological knowledge concerning the species-habitat relationship. We incorporated biological knowledge of the species-habitat relationship into pseudo-absence points by creating habitat envelopes that constrain the region from which points were randomly selected. We define a habitat envelope as an ecological representation of a species, or species feature's (e.g., nest) observed distribution (i.e., realized niche) based on a single attribute, or the spatial intersection of multiple attributes. We created HCMs for Northern Goshawk (Accipiter gentilis atricapillus) nest habitat during the breeding season across Utah forests with extant nest presence points and ecologically based pseudo-absence points using logistic regression. Predictor variables were derived from 30-m USDA Landfire and 250-m Forest Inventory and Analysis (FIA) map products. These habitat-envelope-based models were then compared to null envelope models which use traditional practices for generating pseudo-absences. Models were assessed for fit and predictive capability using metrics such as kappa, thresholdindependent receiver operating characteristic (ROC) plots, adjusted deviance (Dadj2), and cross-validation, and were also assessed for ecological relevance. For all cases, habitat envelope-based models outperformed null envelope models and were more ecologically relevant, suggesting that incorporating biological knowledge into pseudo-absence point generation is a powerful tool for species habitat assessments. Furthermore, given some a priori knowledge of the species-habitat relationship, ecologically based pseudo-absence points can be applied to any species, ecosystem, data resolution, and spatial extent. ?? 2007 by the Ecological Society of America.

Ecological Applications↗

USGS2006

Effects of sample survey design on the accuracy of classification tree models in species distribution models

We evaluated the effects of probabilistic (hereafter DESIGN) and non-probabilistic (PURPOSIVE) sample surveys on resultant classification tree models for predicting the presence of four lichen species in the Pacific Northwest, USA. Models derived from both survey forms were assessed using an independent data set (EVALUATION). Measures of accuracy as gauged by resubstitution rates were similar for each lichen species irrespective of the underlying sample survey form. Cross-validation estimates of prediction accuracies were lower than resubstitution accuracies for all species and both design types, and in all cases were closer to the true prediction accuracies based on the EVALUATION data set. We argue that greater emphasis should be placed on calculating and reporting cross-validation accuracy rates rather than simple resubstitution accuracy rates. Evaluation of the DESIGN and PURPOSIVE tree models on the EVALUATION data set shows significantly lower prediction accuracy for the PURPOSIVE tree models relative to the DESIGN models, indicating that non-probabilistic sample surveys may generate models with limited predictive capability. These differences were consistent across all four lichen species, with 11 of the 12 possible species and sample survey type comparisons having significantly lower accuracy rates. Some differences in accuracy were as large as 50%. The classification tree structures also differed considerably both among and within the modelled species, depending on the sample survey form. Overlap in the predictor variables selected by the DESIGN and PURPOSIVE tree models ranged from only 20% to 38%, indicating the classification trees fit the two evaluated survey forms on different sets of predictor variables. The magnitude of these differences in predictor variables throws doubt on ecological interpretation derived from prediction models based on non-probabilistic sample surveys. ?? 2006 Elsevier B.V. All rights reserved.

Ecological Modelling↗

USGS2006

Predicting tree species presence and basal area in Utah: A comparison of stochastic gradient boosting, generalized additive models, and tree-based methods

Many efforts are underway to produce broad-scale forest attribute maps by modelling forest class and structure variables collected in forest inventories as functions of satellite-based and biophysical information. Typically, variants of classification and regression trees implemented in Rulequest's?? See5 and Cubist (for binary and continuous responses, respectively) are the tools of choice in many of these applications. These tools are widely used in large remote sensing applications, but are not easily interpretable, do not have ties with survey estimation methods, and use proprietary unpublished algorithms. Consequently, three alternative modelling techniques were compared for mapping presence and basal area of 13 species located in the mountain ranges of Utah, USA. The modelling techniques compared included the widely used See5/Cubist, generalized additive models (GAMs), and stochastic gradient boosting (SGB). Model performance was evaluated using independent test data sets. Evaluation criteria for mapping species presence included specificity, sensitivity, Kappa, and area under the curve (AUC). Evaluation criteria for the continuous basal area variables included correlation and relative mean squared error. For predicting species presence (setting thresholds to maximize Kappa), SGB had higher values for the majority of the species for specificity and Kappa, while GAMs had higher values for the majority of the species for sensitivity. In evaluating resultant AUC values, GAM and/or SGB models had significantly better results than the See5 models where significant differences could be detected between models. For nine out of 13 species, basal area prediction results for all modelling techniques were poor (correlations less than 0.5 and relative mean squared errors greater than 0.8), but SGB provided the most stable predictions in these instances. SGB and Cubist performed equally well for modelling basal area for three species with moderate prediction success, while all three modelling tools produced comparably good predictions (correlation of 0.68 and relative mean squared error of 0.56) for one species. ?? 2006 Elsevier B.V. All rights reserved.

Ecological Modelling↗

USGS2003

Predictive modeling of forest cover type and tree canopy height in the central Rocky Mountains of Utah

Maps of forest cover type and canopy height are needed for LANDFIRE, a multi-scale fire risk assessment project designed to generate intermediate-resolution data of vegetation and fire fuel characteristics for the U.S. Here we describe an evaluation study in the central Rockies of Utah, comparing tree-based methods, multivariate adaptive regression splines (MARS), and a hybrid method for mapping forest cover and canopy height on the basis of more than 2,000 forest inventory ground plots in the seven million ha mapping zone. The two forest attributes were modeled as functions of a variety of predictor variables, including: Landsat 7 Enhanced Thematic Mapper Plus (ETM+) images acquired at three different seasons; Tasseled-cap brightness, greenness, and wetness; a forest type group map; and topographic variables derived from Digital Elevation Models (DEMs); and other ancillary variables. The hybrid modeling approach showed a marked increase in overall and within forest cover type accuracies, outperforming the tree-based and MARS approaches. Little difference was seen in global performance measures of forest canopy height models, but patterns in residual plots resulting from different modeling approaches raise questions about utility of height predictions in different applications.

Idaho, Utah, Wyoming↗

USGS2003

Exploration of satellite-measured vegetation seasonality for Landfire land cover

The purpose of this study is to explore the use of satellite data and other sources of spatial data for large area classification in the western United States to support research on potential fire hazards. Extensive field information was made available to this project from two sources: Forest Inventory and Assessment (FIA) and Utah State University. Seasonal spectral patterns of reflectance generated for select vegetation communities indicated that substantial spectral changes occurred through the growing season for most land cover types. In many cases, pronounced spectral differences characterized different types of vegetation, indicating a high probability that classification will accurately separate these particular types of land cover. However, spectral similarities between other types of land cover, such as Douglas fir and white fir, indicate potential classification challenges. Results from this study also show that decision tree analysis is highly effective for assessing quality of input field data and for generating large area land cover classification data sets. It was found that a 5-7% improvement in classification results could be achieved simply by not using those field plots that appeared to be sub-optimal for classification purposes based on image interpretation.

Conference Paper↗

USGS2003

A strategy for mapping mid-scale existing vegetation in support of national fire fuel assessment

Geospatial distribution of natural vegetation is among the very important environmental parameters required for applications ranging from global climate change to monitoring of natural hazards, monitoring of ecosystem vitality, and fire management practices. Increasingly sophisticated applications require vegetation datasets to cover large areas at a suitable scale and provide sufficiently detailed information. In this paper, we describe a research effort to develop a remote sensing methodology capable of producing 30-meter resolution, wall-to-wall coverage of existing vegetation types and structure variables in support of a multi-agency fire fuels and fire risks assessment project. Success of this remote sensing research effort is dependent on improved sensor and data qualities, a thorough understanding of regional and local vegetation ecology, successful integration of remote sensing with a large amount of field plot data, and flexible mapping algorithms. Preliminary results produced in the Wasatch Range and Uinta Mountains of central Utah include 28 vegetation types with an overall accuracy of 60% (average by life forms), percent canopy density (sub-pixel density) of forest, shrub, and herbaceous cover (correlation coefficient of 89, 60, and 55% respectively), and average top canopy height of forest, shrub, and herbaceous cover (correlation coefficient of 73, 50, 20% respectively). Techniques to improve the first-round results are discussed, including refinements of mapping models and use of relevant environmental gradients and potential vegetation classification associated with actual vegetation types.

Conference Paper↗

USGS1999

Use of generalized linear models and digital data in a forest inventory of northern Utah

Forest inventories, like those conducted by the Forest Service's Forest Inventory and Analysis Program (FIA) in the Rocky Mountain Region, are under increased pressure to produce better information at reduced costs. Here we describe our efforts in Utah to merge satellite-based information with forest inventory data for the purposes of reducing the costs of estimates of forest population totals and providing spatial depiction of forest resources. We illustrate how generalized linear models can be used to construct approximately unbiased and efficient estimates of population totals while providing a mechanism for prediction in space for mapping of forest structure. We model forest type and timber volume of five tree species groups as functions of a variety of predictor variables in the northern Utah mountains. Predictor variables include elevation, aspect, slope, geographic coordinates, as well as vegetation cover types based on satellite data from both the Advanced Very High Resolution Radiometer (AVHRR) and Thematic Mapper (TM) platforms. We examine the relative precision of estimates of area by forest type and mean cubic-foot volumes under six different models, including the traditional double sampling for stratification strategy. Only very small gains in precision were realized through the use of expensive photointerpreted or TM-based data for stratification, while models based on topography and spatial coordinates alone were competitive. We also compare the predictive capability of the models through various map accuracy measures. The models including the TM-based vegetation performed best overall, while topography and spatial coordinates alone provided substantial information at very low cost.

Utah↗

USGS1998

Assessing map accuracy in a remotely sensed, ecoregion-scale cover map

Landscape- and ecoregion-based conservation efforts increasingly use a spatial component to organize data for analysis and interpretation. A challenge particular to remotely sensed cover maps generated from these efforts is how best to assess the accuracy of the cover maps, especially when they can exceed 1000 s/km2 in size. Here we develop and describe a methodological approach for assessing the accuracy of large-area cover maps, using as a test case the 21.9 million ha cover map developed for Utah Gap Analysis. As part of our design process, we first reviewed the effect of intracluster correlation and a simple cost function on the relative efficiency of cluster sample designs to simple random designs. Our design ultimately combined clustered and subsampled field data stratified by ecological modeling unit and accessibility (hereafter a mixed design). We next outline estimation formulas for simple map accuracy measures under our mixed design and report results for eight major cover types and the three ecoregions mapped as part of the Utah Gap Analysis. Overall accuracy of the map was 83.2% (SE=1.4). Within ecoregions, accuracy ranged from 78.9% to 85.0%. Accuracy by cover type varied, ranging from a low of 50.4% for barren to a high of 90.6% for man modified. In addition, we examined gains in efficiency of our mixed design compared with a simple random sample approach. In regard to precision, our mixed design was more precise than a simple random design, given fixed sample costs. We close with a discussion of the logistical constraints facing attempts to assess the accuracy of large-area, remotely sensed cover maps.

Remote Sensing of Environment↗