Premium
Boosted Regression Tree Models to Explain Watershed Nutrient Concentrations and Biological Condition
Author(s) -
Golden Heather E.,
Lane Charles R.,
Prues Amy G.,
D'Amico Ellen
Publication year - 2016
Publication title -
jawra journal of the american water resources association
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.957
H-Index - 105
eISSN - 1752-1688
pISSN - 1093-474X
DOI - 10.1111/1752-1688.12447
Subject(s) - environmental science , watershed , surface runoff , hydrology (agriculture) , land cover , index of biological integrity , base flow , riparian zone , land use , drainage basin , water quality , ecology , geography , habitat , geotechnical engineering , cartography , machine learning , computer science , engineering , biology
Boosted regression tree ( BRT ) models were developed to quantify the nonlinear relationships between landscape variables and nutrient concentrations in a mesoscale mixed land cover watershed during base‐flow conditions. Factors that affect instream biological components, based on the Index of Biotic Integrity ( IBI ), were also analyzed. Seasonal BRT models at two spatial scales (watershed and riparian buffered area [RBA]) for nitrite‐nitrate ( NO 2 ‐ NO 3 ), total Kjeldahl nitrogen, and total phosphorus ( TP ) and annual models for the IBI score were developed. Two primary factors — location within the watershed (i.e., geographic position, stream order, and distance to a downstream confluence) and percentage of urban land cover (both scales) — emerged as important predictor variables. Latitude and longitude interacted with other factors to explain the variability in summer NO 2 ‐ NO 3 concentrations and IBI scores. BRT results also suggested that location might be associated with indicators of sources (e.g., land cover), runoff potential (e.g., soil and topographic factors), and processes not easily represented by spatial data indicators. Runoff indicators (e.g., Hydrological Soil Group D and Topographic Wetness Indices) explained a substantial portion of the variability in nutrient concentrations as did point sources for TP in the summer months. The results from our BRT approach can help prioritize areas for nutrient management in mixed‐use and heavily impacted watersheds.