Lake classification to enhance prediction of eutrophication endpoints in Finnish lakes

We used the Bayesian TREED procedure to determine the efficacy of using an existing trophic status classification scheme for prediction of chlorophyll a in 150 Finnish lakes. Growing season data were log (base e) transformed and averaged by lake and year. We compared regressions of lnTP and lnTN on lnChla based on aggregations of the 9 levels of ''Lake Type'', the classification scheme of the Finnish Environment Institute (SYKE), to a new classification scheme identified by the Bayesian TREED regression algorithm that partitioned the data based on geographic, morphometric and chemical properties of the lakes. The classifier identified with the BTREED algorithm had the best resulting model fit as measured by several different metrics. The model identified by the BTREED procedure that was allowed to use the suite of geographic, morphometric and chemical classifiers selected only the morphometric variable mean lake depth as the basis of the classification scheme. This model resulted in separate classes for shallow (<2.6m), medium (2.6m16.3m) lakes corresponding to co-control by N and P (shallow and medium depths) and N-control (deep lakes) of algal productivity as measured by chlorophyll a, as indicated by the regression coefficients for each partition on depth. However, TN:TP ratios indicate clear P limitation in each depth class.

[1]  R. Bissoli,et al.  Water Framework Directive 2000/60/EC. , 2008 .

[2]  A. Raftery.  Bayesian Model Selection in Social Research , 1995 .

[3]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[4]  Craig A Stow,et al.  Bayesian methods for regional-scale eutrophication models. , 2004, Water research.

[5]  Adrian F. M. Smith,et al.  A Bayesian CART algorithm , 1998 .

[6]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[7]  S. Weisberg.  Applied Linear Regression , 1981 .

[8]  Edward I. George,et al.  Bayesian Treed Models , 2002, Machine Learning.

[9]  Summer total phosphorus in lakes: A map of Minnesota, Wisconsin, and Michigan, USA , 1988 .

[10]  O. Malve.  Water quality prediction for river basin management , 2007 .

[11]  Daryl Pregibon,et al.  Tree-based models , 1992 .

[12]  Lawrence B. Slobodkin,et al.  A Critique for Ecology , 1991 .

[13]  H. Chipman,et al.  Bayesian CART Model Search , 1998 .

[14]  R. Tibshirani,et al.  Model Search by Bootstrap “Bumping” , 1999 .

[15]  C. Stow,et al.  Nutrient criteria for lakes, ponds, and reservoirs: a Bayesian TREED model approach. , 2009 .

[16]  O. Pietiläinen,et al.  The Finnish Eurowaternet with information about Finnish water resources and monitoring strategies , 2001 .

[17]  Heikki Haario,et al.  Bayesian modelling of algal mass occurrences - using adaptive MCMC methods with a lake water quality model , 2007, Environ. Model. Softw..

[18]  L. M. M.-T..  Theory of Probability , 1929, Nature.

[19]  T. Hassard,et al.  Applied Linear Regression , 2005 .

[20]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[21]  J. Omernik.  Ecoregions of the Conterminous United States , 1987 .

[22]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[23]  Trevor Hastie,et al.  Statistical Models in S , 1991 .