Total phosphorus (TP) is commonly used to assess water quality in shallow lakes and other surface waters. Shallow lakes require special consideration because they can transition between two alternative stable states: (1) a clear-water state that typically supports abundant submerged vegetation and provides high quality wildlife habitat, and (2) a turbid-water state with frequent algal blooms and poor habitat quality. A shallow lake's TP level in relation to critical TP tipping points determines whether the lake is in a highly resilient clear state, a highly resilient turbid state, or whether the lake is in a dynamic region where either state is possible. Further, management options differ for highly resilient clear lakes versus lakes that may be in the turbid state. For example, resilient clear lakes may be assigned special watershed and shoreline protection to preserve their healthy conditions. On the other hand, managers may plan to allocate resources for assessment and possible in-lake management for lakes that have TP levels where the turbid state is possible. Managers would benefit from models that can predict whether a lake is in a resilient clear state or may be in the turbid state without physically visiting a lake to collect water samples or other in-lake data. We used TP data from 118 shallow lakes in Minnesota and previously estimated TP tipping points to classify lakes as either highly resilient clear lakes (“stable-clear”) or possibly turbid (“bistable-turbid”). We used random forest methodology to build models for predicting these two TP classes using both remotely sensed watershed-scale predictors and in-lake variables, and we performed recursive feature elimination to find the most parsimonious model. We demonstrate that TP class can be predicted using only watershed-scale remotely sensed variables and that land cover and use, soil texture, and ecoregion are key predictor variables for TP class. We highlight how our model predictions can be used as indicators to help make management decisions for a set of shallow lakes.
Bibliographical noteFunding Information:
Research funding was provided by the Minnesota Environment and Natural Resources Trust Fund (Award M.L. 2010, Chap. 362, Sec. 2, Subd. 5g), the Minnesota Department of Natural Resources , and the University of St. Thomas Department of Biology . KV received partial support from the Natural Resources Science and Management graduate program at the University of Minnesota. JF received partial support from the Minnesota Agricultural Experimental Station and the McKnight Foundation . KV thanks Nic Jelinski, Brent Dalzell, Jacques Finlay, and Althea ArchMiller for help identifying and navigating soils data. We thank all of the collaborators who helped develop the in-lake and GIS data.
- Alternative stable states
- Land use
- Random forest
- Variable selection