Filters: Tags: Machine learning (X)
178 results (50ms)|
Filters
|
The cascade correlation neural network was used to predict the two-year peak discharge (Q2) for major regional river basins of the continental United States (US). Watersheds ranged in size by four orders of magnitude. Results of the neural network predictions ranged from correlations of 0.73 for 104 test data in the Souris-Red Rainy river basin to 0.95 for 141 test data in California. These results are improvements over previous multilinear regressions involving more variables that showed correlations ranging from 0.26 to 0.94. Results are presented for neural networks trained and tested on drainage area, average annual precipitation, and mean basin elevation. A neural network trained on regional scale data in the...
Categories: Publication;
Types: Citation,
Journal Citation;
Tags: Journal of the American Water Resources Association,
local scale predictions,
machine learning,
neural networks,
regional scale,
Groundwater from the Mississippi River Valley alluvial aquifer (MRVA) is a vital resource for agriculture and drinking-water supplies in the central United States. Water availability can be limited in some areas of the aquifer by high concentrations of trace elements, including manganese and arsenic. Boosted regression trees, a type of ensemble-tree machine-learning method, were used to predict manganese concentration and the probability of arsenic concentration exceeding a 10 µg/L threshold throughout the MRVA. Explanatory variables for the BRT models included attributes associated with well location and construction, surficial variables (such as hydrologic position and recharge), variables extracted from a MODFLOW-2005...
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...
This model archive contains the input data, model code, and model outputs for machine learning models that predict daily non-tidal stream salinity (specific conductance) for a network of 459 modeled stream segements across the Delaware River Basin (DRB). Results are provided for two time periods: the historical drought-of-record from 1965-10-02 to 1969-12-30, and that same drought evaluated in climatic conditions that are consistent with a LENS2 enseble climate projection from 2057-10-02 to 2061-12-30. Results are provided for a total of three Random Forest models, corresponding to three input attribute sets (dynamic attributes, dynamic and static attributes, and dynamic attributes and a minimum set of static attributes)....
Categories: Data,
Data Release - In Progress;
Types: Map Service,
OGC WFS Layer,
OGC WMS Layer,
OGC WMS Service;
Tags: Delaware (DE),
Delaware River Basin,
Environment,
Machine Learning,
Maryland (MD),
This data release component contains model inputs including river basin attributes, weather forcing data, and simulated and observed river discharge.
Observed water temperatures from 1980-2019 were compiled for 2,332 lakes in the US. These data were used as training, test, and error-estimation data for process-guided deep learning models and the evaluation of process-based models. The data are formatted as a single csv (comma separated values) file with attributes corresponding to the unique combination of lake identifier, time, and depth. Data came from a variety of sources, including the Water Quality Portal, the North Temperate Lakes Long-Term Ecological Research Project, and digitized temperature records from the MN Department of Natural Resources. This dataset is part of a larger data release of lake temperature model inputs and outputs for these same lakes...
Daily lake surface temperatures estimates for 185,549 lakes across the contiguous United States from 1980 to 2020 generated using an entity-aware long short-term memory deep learning model. In-situ measurements used for model training and evaluation are from 12,227 lakes and are included as well as daily meteorological conditions and lake properties. Median per-lake estimated error found through cross validation on lakes with in-situ surface temperature observations was 1.24 °C. The generated dataset will be beneficial for a wide range of applications including estimations of thermal habitats and the impacts of climate change on inland lakes.
Using predicted lake temperatures from uncalibrated, process-based models (PB0) and process-guided deep learning models (PGDL), this dataset summarized a collection of thermal metrics to characterize lake temperature impacts on fish habitat for 881 lakes. Included in the metrics are daily thermal optical habitat areas and a set of over 172 annual thermal metrics.
This section provides code for reproducing the figures in Rahmani et al. (2023b). The full model archive is organized into these four child items: 1. Model code - Python files and README for reproducing model training and evaluation 2. Inputs - Basin attributes and shapefiles, forcing data, and stream temperature observations 3. Simulations - Simulation descriptions, configurations, and outputs [THIS ITEM] 4. Figure code - Jupyter notebook to recreate the figures in Rahmani et al. (2023b) The publication associated with this model archive is: Rahmani, F., Appling, A.P., Feng, D., Lawson, K., and Shen, C. 2023b. Identifying structural priors in a hybrid differentiable model for stream water temperature modeling....
This dataset is support materials for the publication "Crop type classification, trends, and patterns of central California agricultural fields from 2005 – 2020". This data release is comprised of two child datasets. The first dataset, 'Labeled_CropType_Points', is a shapefile that consists of randomly selected point locations in which crop types were verified using high resolution imagery for each examined year across the study period (2005 - 2020). The second dataset, 'Central_CA_Classified_Croplands', is also a shapefile, but contains polygons of 9 classified crop types derived from a random forest machine learning classifier for central California for each examined year across the study period (2005 - 2020).
Groundwater is a vital resource to the Mississippi embayment region of the central United States. Regional and integrated assessments of water availability that link physical flow models and water quality in principal aquifer systems provide context for the long-term availability of these water resources. An innovative approach using machine learning was employed to predict groundwater pH across drinking water aquifers of the Mississippi embayment. The region includes two principal regional aquifer systems; the Mississippi River Valley alluvial (MRVA) aquifer and the Mississippi embayment aquifer system that includes several regional aquifers and confining units. Based on the distribution of groundwater use for...
Groundwater is a vital resource in the Mississippi embayment of the central United States. An innovative approach using machine learning (ML) was employed to predict groundwater salinity—including specific conductance (SC), total dissolved solids (TDS), and chloride (Cl) concentrations—across three drinking-water aquifers of the Mississippi embayment. A ML approach was used because it accommodates a large and diverse set of explanatory variables, does not assume monotonic relations between predictors and response data, and results can be extrapolated to areas of the aquifer not sampled. These aspects of ML allowed potential drivers and sources of high salinity water that have been hypothesized in other studies to...
Observed water temperatures from 1980-2018 were compiled for 877 lakes in Minnesota (USA). There were four lakes included in this data release that did not have temperature observations available at the time of compilation or these data existed elsewhere and were unknown to the compilation team. These data were used as training, test, and error-estimation data for process-guided deep learning models and the evaluation of process-based models. The data are formatted as a single csv (comma separated values) file with attributes corresponding to the unique combination of lake identifier, time, and depth. Data came from a variety of sources, including the Water Quality Portal, the North Temperate Lakes Long-Term Ecological...
Coastal resources are increasingly impacted by erosion, extreme weather events, sea-level rise, tidal flooding, and other potential hazards related to climate change. These hazards have varying impacts on coastal landscapes due to the numerous geologic, oceanographic, ecological, and socioeconomic factors that exist at a given location. Here, an assessment framework is introduced that synthesizes existing datasets describing the variability of the landscape and hazards that may act on it to evaluate the likelihood of coastal change along the U.S coastline within the coming decade. The pilot study, conducted in the Northeastern U.S. (Maine to Virginia), is comprised of datasets derived from a variety of federal,...
Categories: Data;
Types: Downloadable,
GeoTIFF,
Map Service,
Raster;
Tags: Acadia National Park,
ArcGIS Pro,
Arcpy,
Autoclassification,
Automation,
These data include down-looking images of round goby (Neogobius melanostomus) in either cobble or sand substrates within clear acrylic enclosures (0.86-meters (m) long, by 0.56-m wide, by 1.07-m high). Ten individual round goby were added to enclosures for imaging to ensure known abundances in each tank. Images were collected to evaluate the efficiency of image-based methodologies for estimating round goby abundance. All data were collected with Sony a6100 cameras in the wet lab at the USGS Great Lakes Science Center in Ann Arbor, Michigan.
Coastal resources are increasingly impacted by erosion, extreme weather events, sea-level rise, tidal flooding, and other potential hazards related to climate change. These hazards have varying impacts on coastal landscapes due to the numerous geologic, oceanographic, ecological, and socioeconomic factors that exist at a given location. Here, an assessment framework is introduced that synthesizes existing datasets describing the variability of the landscape and hazards that may act on it to evaluate the likelihood of coastal change along the U.S coastline within the coming decade. The pilot study, conducted in the Northeastern U.S. (Maine to Virginia), is comprised of datasets derived from a variety of federal,...
Categories: Data;
Types: Downloadable,
GeoTIFF,
Map Service,
Raster;
Tags: Acadia National Park,
ArcGIS Pro,
Arcpy,
Autoclassification,
Automation,
Daily maximum water temperature predictions in the Delaware River Basin (DRB) can inform decision makers who can use cold-water reservoir releases to maintain thermal habitat for sensitive fish species. This data release contains the forcings and outputs of 7-day ahead maximum water temperature forecasting models that makes predictions at 70 river reaches in the upper DRB. The modeling approach includes process-guided deep learning and data assimilation (Zwart et al., 2023). The model is driven by weather forecasts and observed reservoir releases and produces maximum water temperature forecasts for the issue day (day 0) and 7 days into the future (days 1-7). In combination with data provided in Oliver et al. (2022),...
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...
The datasets are to accompany a manuscript describing the prediction of submersed aquatic vegetation presence and its potential vulnerability and recovery potential. The data and accompanying analysis scripts allow users to run the final random forests predictive model and reproduce the figures reported in the manuscript. Files from several data sources (aqa_2010_lvl3_pct_oute_joined_VEG_BARCODE.csv, eco_states_near_SAV.csv, ltrm_vegsrs_thru2019_GEOMORPHIC_METRICS_final.csv, vegetation_data.csv, and water_full.csv) were combined into a single .csv file (analysis_data_for_SAV_RandomForest.csv) used as the input for the random forest model. When intersecting points with geomorphic metrics some sites were moved slightly...
|
|
