Filters: Tags: random forests (X)
50 results (13ms)|
Filters
Date Range
Extensions Types
Contacts
Categories Tag Types
|
These data were compiled to demonstrate new predictive mapping approaches and provide comprehensive gridded 30-meter resolution soil property maps for the Colorado River Basin above Hoover Dam. Random forest models related environmental raster layers representing soil forming factors with field samples to render predictive maps that interpolate between sample locations. Maps represented soil pH, texture fractions (sand, silt clay, fine sand, very fine sand), rock, electrical conductivity (ec), gypsum, CaCO3, sodium adsorption ratio (sar), available water capacity (awc), bulk density (dbovendry), erodibility (kwfact), and organic matter (om) at 7 depths (0, 5, 15, 30, 60, 100, and 200 cm) as well as depth to restrictive...
These data were compiled to demonstrate new predictive mapping approaches and provide comprehensive gridded 30-meter resolution soil property maps for the Colorado River Basin above Hoover Dam. Random forest models related environmental raster layers representing soil forming factors with field samples to render predictive maps that interpolate between sample locations. Maps represented soil pH, texture fractions (sand, silt clay, fine sand, very fine sand), rock, electrical conductivity (ec), gypsum, CaCO3, sodium adsorption ratio (sar), available water capacity (awc), bulk density (dbovendry), erodibility (kwfact), and organic matter (om) at 7 depths (0, 5, 15, 30, 60, 100, and 200 cm) as well as depth to restrictive...
Our objective was to model specific minimum flow (mean of the annual minimum flows divided by drainage area [cubic feet per second per square mile]) on small, ungaged streams in the Upper Colorado River Basin. Modeling streamflows is an important tool for understanding landscape-scale drivers of flow and estimating flows where there are no gaged records. We focused our study in the Upper Colorado River Basin, a region that is not only critical for water resources but also projected to experience large future climate shifts toward a drier climate. We used a random forest modeling approach to model the relation between specific minimum flow on gaged streams (115 gages) and environmental variables. We then projected...
Our objective was to model specific mean daily flow (mean daily flow divided by drainage area [cubic feet per second per square mile]) on small, ungaged streams in the Upper Colorado River Basin. Modeling streamflows is an important tool for understanding landscape-scale drivers of flow and estimating flows where there are no gaged records. We focused our study in the Upper Colorado River Basin, a region that is not only critical for water resources but also projected to experience large future climate shifts toward a drier climate.We used a random forest modeling approach to model the relation between specific mean daily flow on gaged streams (115 gages) and environmental variables. We then projected specific mean...
This dataset shows modelled habitat suitability for the Pacific-slope Flycatcher (Empidonax difficilis) under current and projected future conditions. We built habitat suitability models for 237 bird, 117 mammal, and 12 amphibian species. Species were chosen for inclusion in the study based on a simple set of criteria. For a species to be included in the study, it had to be primarily associated with terrestrial habitats, have a digital map of its current range, and have some portion of its current distribution intersect with the study area extent. In addition, we restricted the list of species used in the study to those for which a well-performing continental-scale model could be built. Digital species range maps...
Categories: Data;
Types: ArcGIS REST Map Service,
ArcGIS Service Definition,
Downloadable,
Map Service;
Tags: biota,
climate change,
environment,
habitat,
modeling,
Our objective was to model the risk of becoming intermittent under drier climate conditions on small, ungaged streams in the Upper Colorado River Basin. Modeling streamflows is an important tool for understanding landscape-scale drivers of flow and estimating flows where there are no gaged records. We focused our study in the Upper Colorado River Basin, a region that is not only critical for water resources but also projected to experience large future climate shifts toward a drier climate. We used a conditional inference modeling approach to model the relation between intermittency status on gaged streams (115 gages) and selected mean and minimum flow metrics. We then projected intermittency status and if a stream...
Our objective was to model minimum flow coefficient of variation (CV) on small, ungaged streams in the Upper Colorado River Basin. Modeling streamflows is an important tool for understanding landscape-scale drivers of flow and estimating flows where there are no gaged records. We focused our study in the Upper Colorado River Basin, a region that is not only critical for water resources but also projected to experience large future climate shifts toward a drier climate. We used a random forest modeling approach to model the relation between minimum flow CV (the standard deviation of annual minimum flows times 100 divided by the mean of annual minimum flows) on gaged streams (115 gages) and environmental variables....
Types: Citation;
Tags: Random forests,
Streamflow,
Streamflow modeling,
Ungaged streams,
Upper Colorado River Basin,
These data were compiled to demonstrate new predictive mapping approaches and provide comprehensive gridded 30-meter resolution soil property maps for the Colorado River Basin above Hoover Dam. Random forest models related environmental raster layers representing soil forming factors with field samples to render predictive maps that interpolate between sample locations. Maps represented soil pH, texture fractions (sand, silt clay, fine sand, very fine sand), rock, electrical conductivity (ec), gypsum, CaCO3, sodium adsorption ratio (sar), available water capacity (awc), bulk density (dbovendry), erodibility (kwfact), and organic matter (om) at 7 depths (0, 5, 15, 30, 60, 100, and 200 cm) as well as depth to restrictive...
Our objective was to model mean annual number of zero-flow days (days per year) for small streams in the Upper Colorado River Basin under historic hydrologic conditions on small, ungaged streams in the Upper Colorado River Basin. Modeling streamflows is an important tool for understanding landscape-scale drivers of flow and estimating flows where there are no gaged records. We focused our study in the Upper Colorado River Basin, a region that is not only critical for water resources but also projected to experience large future climate shifts toward a drier climate. We used a random forest modeling approach to model the relation between zero-flow days per year on gaged streams (115 gages) and environmental variables....
Types: Citation;
Tags: Random forests,
Streamflow,
Streamflow modeling,
Ungaged streams,
Upper Colorado River Basin,
This dataset shows modelled habitat suitability for the American Beaver (Castor canadensis) under current and projected future conditions. We built habitat suitability models for 237 bird, 117 mammal, and 12 amphibian species. Species were chosen for inclusion in the study based on a simple set of criteria. For a species to be included in the study, it had to be primarily associated with terrestrial habitats, have a digital map of its current range, and have some portion of its current distribution intersect with the study area extent. In addition, we restricted the list of species used in the study to those for which a well-performing continental-scale model could be built. Digital species range maps were converted...
Categories: Data;
Types: ArcGIS REST Map Service,
ArcGIS Service Definition,
Downloadable,
Map Service;
Tags: biota,
climate change,
environment,
habitat,
modeling,
These data were compiled to demonstrate new predictive mapping approaches and provide comprehensive gridded 30-meter resolution soil property maps for the Colorado River Basin above Hoover Dam. Random forest models related environmental raster layers representing soil forming factors with field samples to render predictive maps that interpolate between sample locations. Maps represented soil pH, texture fractions (sand, silt clay, fine sand, very fine sand), rock, electrical conductivity (ec), gypsum, CaCO3, sodium adsorption ratio (sar), available water capacity (awc), bulk density (dbovendry), erodibility (kwfact), and organic matter (om) at 7 depths (0, 5, 15, 30, 60, 100, and 200 cm) as well as depth to restrictive...
This dataset shows modelled habitat suitability for the Collared Pika (Ochotona collaris) under current and projected future conditions. We built habitat suitability models for 237 bird, 117 mammal, and 12 amphibian species. Species were chosen for inclusion in the study based on a simple set of criteria. For a species to be included in the study, it had to be primarily associated with terrestrial habitats, have a digital map of its current range, and have some portion of its current distribution intersect with the study area extent. In addition, we restricted the list of species used in the study to those for which a well-performing continental-scale model could be built. Digital species range maps were converted...
Categories: Data;
Types: ArcGIS REST Map Service,
ArcGIS Service Definition,
Downloadable,
Map Service;
Tags: biota,
climate change,
environment,
habitat,
modeling,
This metadata record describes monthly estimates of natural baseflow for 15,866 stream reaches, defined by the National Hydrography Dataset Plus Version 2.0 (NHDPlusV2), in the Delaware River Basin for the period 1950-2015. A statistical machine learning technique - random forest modeling (Liaw and Wiener, 2018; R Core Team, 2020) - was applied to estimate natural flows using about 150 potential predictor variables (Miller and others, 2018). Calibration data used for the random forest model are available from (Foks and others, 2020). Each model was run twice, first using all potential predictor variables, which represents a "full" model run, and a second time using the top 20 predictors from the original run, which...
Categories: Data;
Tags: Delaware,
Delaware River Basin,
Hydrology,
National Hydrography Dataset Plus Version 2.0,
New Jersey,
These data were compiled to demonstrate new predictive mapping approaches and provide comprehensive gridded 30-meter resolution soil property maps for the Colorado River Basin above Hoover Dam. Random forest models related environmental raster layers representing soil forming factors with field samples to render predictive maps that interpolate between sample locations. Maps represented soil pH, texture fractions (sand, silt clay, fine sand, very fine sand), rock, electrical conductivity (ec), gypsum, CaCO3, sodium adsorption ratio (sar), available water capacity (awc), bulk density (dbovendry), erodibility (kwfact), and organic matter (om) at 7 depths (0, 5, 15, 30, 60, 100, and 200 cm) as well as depth to restrictive...
These data were compiled to demonstrate new predictive mapping approaches and provide comprehensive gridded 30-meter resolution soil property maps for the Colorado River Basin above Hoover Dam. Random forest models related environmental raster layers representing soil forming factors with field samples to render predictive maps that interpolate between sample locations. Maps represented soil pH, texture fractions (sand, silt clay, fine sand, very fine sand), rock, electrical conductivity (ec), gypsum, CaCO3, sodium adsorption ratio (sar), available water capacity (awc), bulk density (dbovendry), erodibility (kwfact), and organic matter (om) at 7 depths (0, 5, 15, 30, 60, 100, and 200 cm) as well as depth to restrictive...
Big sagebrush (Artemisia tridentata) is one of the most widespread and abundant plant species in the intermountain regions of western North America. This species occupies an extremely wide ecological niche ranging from the semi-arid basins to the subalpine. Within this large niche, three widespread subspecies are recognized. Montane ecoregions are occupied by subspecies vaseyana, while subspecies wyomingensis and tridentata occupy basin ecoregions. In cases of wide-ranging species with multiple subspecies, it can be more practical from the scientific and management perspective to assess the climate profiles at the subspecies level. We focus bioclimatic model efforts on subspecies wyomingensis, which is the most...
Categories: Data,
Publication;
Types: Citation;
Tags: Academics & scientific researchers,
California,
Completed,
EARTH SCIENCE > LAND SURFACE > LANDSCAPE,
Federal resource managers,
Longer, drier summers projected for arid and semi-arid regions of western North America under climate change are likely to have enormous consequences for water resources and river-dependent ecosystems. Many climate change scenarios for this region involve decreases in mean annual streamflow, latesummer precipitation and late-summer streamflow in the coming decades. Intermittent streams are already common in this region, and it is likely that minimum flows will decrease and some perennial streams will shift to intermittent flow under climate-driven changes in timing and magnitude of precipitation and runoff, combined with increases in temperature. To understand current intermittency among streams and analyze the...
Categories: Data;
Types: Map Service,
OGC WFS Layer,
OGC WMS Layer,
OGC WMS Service;
Tags: EARTH SCIENCE > LAND SURFACE > LANDSCAPE,
LCC Network Science Catalog,
LCC Network Science Catalog,
Random forests,
Report,
To determine the current spatial distribution of waterfowl nesting areas and understand the importance of environmental variables in the selection of nest locations, we modeled nest densities for six species of geese and eiders that commonly breed on the Yukon-Kuskokwim Delta, including cackling goose ( Branta hutchinsii minima), emperor goose ( Chen canagica), black brant ( B. bernicla nigricans), greater white-fronted goose ( Anser albifrons frontalis), spectacled eider ( Somateria fischeri), and common eider ( S. mollissima). The data used were from U.S. Fish and Wildlife Service's long-term waterbird monitoring program in which single-visit nest searches were conducted during incubation (typically from early...
This raster dataset represents spatially explicit predictions of burn severity (dNBRPredict.tif) in the Mojave Desert based on models developed from data on the difference normalized burn ratio (dNBR) within perimeters of fires greater than 405 hectares that burned between 1984 to 2010. Raster resolution equals 30 meters, projection equals UTM Zone 11N.
Categories: Data;
Types: Downloadable,
GeoTIFF,
Map Service,
Raster;
Tags: Grass-fire cycle,
Mojave Desert,
Mojave Desert,
Predictive models,
Random forests,
This U.S. Geological Survey data release consists of 3 raster datasets representing estimates of probability of ignition (ProbIgnitPredict.tif), fire frequency (FrequencyPredictRF.tif), and burn severity (dNBRPredictRF.tif) in the Mojave Desert from 1984 to 2010. The data include: (1) A shapefile of the Mojave Desert that was used as our study area boundary (MojaveEcoregion_TNS_UTM83.shp). The original shapefile was obtained from NatureServe in 2009; (2) Three Tagged-Interchange Format (TIF) raster datasets representing probability of ignition, fire frequency, and burn severity. Resolution equals 30 meters, projection equals UTM Zone 11N. These data support the following publication: Klinger, R., Underwood, E.C.,...
|
|
