The k-nearest neighbor (k-NN) technique is a non-parametric technique that can be used to make predictions of discrete (class-type) as well as continuous variables. The k-NN technique and many of its derivatives belong to the group of .lazy learning algorithms.. It is lazy, as it passively stores the development data set until the time of application; all calculations are performed only when estimations need to be generated.
A hydrologic simulation model for studying the effects of management practices on movement of sediment and chemicals in response to rainfall or irrigation on small field areas. Includes models for plant growth and nutrient cycling, and operates on a continuous basis. Weather conditions and rainfall may be stochastically simulated.
RHEM is designed to provide sound, science-based technology to model and predict runoff and erosion rates on rangelands and to assist in assessing rangeland conservation practice effects. RHEM is a newly conceptualized, process-based erosion prediction tool specific for rangeland application, based on fundamentals of infiltration, hydrology, plant science, hydraulics and erosion mechanics.
The NorWeST webpage hosts stream temperature data and climate scenarios in a variety of user-friendly digital formats for streams and rivers across the western U.S. Temperature data and model outputs, registered to NHDPlus stream lines, are posted to the website after QA/QC procedures and development of the final temperature model within a river basin.
National Stream Internet (NSI) project was developed as a means of providing a consistent, flexible analytical infrastructure that can be applied with many types of stream data anywhere in the country. A key part of that infrastructure is the NSI network, a digital GIS layer which has a specific topological structure that was designed to work effectively with SSNMs. The NSI network was derived from the National Hydrography Dataset Plus, Version 2 (NHDPlusV2) following technical procedures that ensure compatibility with SSNMs.
Geomorphic Road Analysis and Inventory Package (GRAIP) is designed to help land managers learn about the impacts of road systems on erosion and sediment delivery to streams. GRAIP couples analytical tools with an inventory process to build an approach to roads analysis that can be locally calibrated in a repeatable fashion and with minimal effort. The full scope of GRAIP includes methods to inventory roads and analyze the inventory for surface erosion, gully risk, landslide risk and stream crossing failure risks. Methods to measure road surface erosion from sample sites are also included.
The eDNA samples in the eDNAtlas database describe species occurrence locations and were collected by the U.S. Forest Service and numerous agencies that have partnered with the National Genomics Center for Wildlife and Fish Conservation (NGC) throughout the United States. The eDNAtlas is accessed via an interactive ArcGIS Online (AGOL) map that allows users to view and download sample site information and lab results of species occurrence for the U.S. The results are primarily based on samples analyzed at the National Genomics Center for Wildlife and Fish Conservation (NGC) and associated with geospatial attributes created by the Boise Spatial Streams Group (BSSG).
Data from: Trends and sensitivities of low streamflow extremes to discharge timing and magnitude in Pacific Northwest mountain streams
The relative influences of total precipitation and air temperature on the annual low streamflow extremes are quantified from 42 Pacific Northwest stream gauges from 1948 to 2013 using mean annual streamflow as a proxy for precipitation amount effects and streamflow center of timing as a proxy for temperature effects on low flow metrics.