Classification Of Nitrate Polluting Activities Through Clustering Of Isotope Mixing Model Outputs

Apportionment of nitrate (NO3-) sources in surface water and classification of monitoring locations according to NO3- polluting activities may help implementation of water quality control measures. In this study, we (i) evaluated a Bayesian isotopic mixing model (stable isotope analysis in R [SIAR]) for NO3- source apportionment using 2 yr of delta N-15-NO3- and delta O-18-NO3 data from 29 locations within river basins in Flanders (Belgium) and five expert-defined NO3- polluting activities, (ii) used the NO3- source contributions as input to an unsupervised learning algorithm (k-means clustering) to reclassify sampling locations into NO3- polluting activities, and (iii) assessed if a decision tree model of physicochemical data could retrieve the isotope-based and expert-defined classifications. Based on the SIAR and delta B-11 results, manure/sewage was identified as a major NO3- source, whereas soil N, fertilizer NO3-, and NH4+ in fertilizer and rain were intermediate sources and NO3- in precipitation was a minor source. The k-means clustering algorithm allowed classification of NO3 polluting activities that corresponded well to the expert-defined classifications. A decision tree model of physicochemical parameters allowed us to correctly classify 50 to 100% of the sampling locations as compared with the k-means clustering approach. We suggest that NO3- polluting activities can be identified via clustering of NO3 source contributions from samples representing an entire river basin. Classification of future monitoring locations into these classes could use decision tree models based on physicochemical data. The latter approach holds a substantial degree of uncertainty but provides more inherent information for dedicated abatement strategies than monitoring of NO3- concentrations alone.