Filters: Tags: regression model (X)
3 results (8ms)|
Filters
Date Range
Contacts
Categories Tag Types Tag Schemes |
Ensemble-tree machine learning (ML) regression models can be prone to systematic bias: small values are overestimated and large values are underestimated. Additional bias can be introduced if the dependent variable is a transform of the original data. Six methods were evaluated for their ability to correct systematic and introduced bias: (1) empirical distribution matching (EDM); (2) regression of observed on estimated values (ROE); (3) linear transfer function (LTF); (4) linear equation based on Z-score transform (ZZ); (5) second machine learning model used to estimate residuals (ML2-RES); and (6) Duan smearing estimate applied after ROE is implemented (ROE-Duan). The performance of the methods was evaluated using...
Categories: Data;
Tags: Central Valley, California,
Glacial aquifer system,
Mississippi Embayment,
NAWQA,
North Atlantic Coastal Plain,
These data were released prior to the October 1, 2016 effective date for the USGS’s policy dictating the review, approval, and release of scientific data as referenced in USGS Survey Manual Chapter 502.8 Fundamental Science Practices: Review and Approval of Scientific Data for Release. This data set consists of 204 drainage basin boundaries for U.S. Geological Survey's (USGS) stream sites sampled in the National Water Quality Assessment (NAWQA) Program and the National Stream Quality Accounting Network (NASQAN). These drainage basin boundaries are used to generate watershed characteristics for the development of water-quality models. The basin boundaries were collected from USGS hydrologists and geographers from...
Categories: pre-SM502.8;
Tags: Conterminous United States,
NASQAN,
NAWQA,
NSDI,
National Stream Quality Accounting Network,
These data were released prior to the October 1, 2016 effective date for the USGS’s policy dictating the review, approval, and release of scientific data as referenced in USGS Survey Manual Chapter 502.8 Fundamental Science Practices: Review and Approval of Scientific Data for Release. This data set contains 204 drainage basin boundaries for U.S. Geological Survey (USGS) stream sites analyzed in the Watershed Regressions for Pesticides (WARP) model. This dataset supercedes version 1.0 released in April 2010, and consists of revisions to 26 basin boundaries.
Categories: pre-SM502.8;
Tags: Conterminous United States,
NAWQA,
NSDI,
National Water Quality Assessment,
USGS Science Data Catalog (SDC),
|
|
