Classification of Nitrate Polluting Activities through Clustering of Isotope Mixing Model Outputs

Apportionment of nitrate (NO 3 − ) sources in surface water and classification of monitoring locations according to NO 3 − 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 NO 3 − source apportionment using 2 yr of δ 15 N‐NO 3 − and δ 18 O‐NO 3 − data from 29 locations within river basins in Flanders (Belgium) and five expert‐defined NO 3 − polluting activities, (ii) used the NO 3 − source contributions as input to an unsupervised learning algorithm (k‐means clustering) to reclassify sampling locations into NO 3 − 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 δ 11 B results, manure/sewage was identified as a major NO 3 − source, whereas soil N, fertilizer NO 3 − , and NH 4 + in fertilizer and rain were intermediate sources and NO 3 − in precipitation was a minor source. The k‐means clustering algorithm allowed classification of NO 3 − 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 NO 3 − polluting activities can be identified via clustering of NO 3 − 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 NO 3 − concentrations alone.