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

Abstract

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

A stable isotope approach and its application for identifying nitrate source and transformation process in water

“…B is widely used in fertilizer, manure, and household products and is difficult to remove by sewage treatment (Barth 2000 Xue et al (2013) identified the NO − 3 sources in five polluted areas of the Flanders watershed in Belgium. The results showed that relatively high 11 B values, which were consistent with those found in agricultural manure, were associated with groundwater beneath agricultural areas and in groundwater below areas of agriculture and horticulture.…”

Application of Nitrogen and Oxygen Isotopes for Source and Fate Identification of Nitrate Pollution in Surface Water: A Review

“…Because B is not affected by transformation processes, the combined use of δ 11 B and the dual isotopes of nitrate have great benefits of the correct identification of nitrate source. Xue et al [66], by using δ 15 N, δ 18 O and δ 11 B, found that the major sources of the nitrate of surface water in the Flanders area of Belgium were manure and domestic sewage. Widory et al [72] used δ 11 B to evaluate the contribution of domestic sewage to nitrate.…”

Decision-tree-model identification of nitrate pollution activities in groundwater: A combination of a dual isotope approach and chemical ions

“…This procedure continues until all instances are classified. A more detailed description of a decision tree model can be found in Xue et al (2013). WEKA 3.4.10 software was used to explore decision trees.…”

“…Spruill et al (2002) successfully classified five NO 3 − sources (fertilizer on crops, fertilizer on golf courses, irrigation spray from hog wastes, and leachate from poultry litter and septic systems) in groundwater based on a classification tree model using N isotopes, anions and cations. The basis of a classification/decision tree model is the creation of a hierarchical tree based on a dataset of known classes, which is then used to predict classes from another independent dataset with the same parameters but unknown classes (Xue et al, 2013). The sites investigated in this study are located in an intensive agricultural region, where 66.5% of irrigation water comes from groundwater (Liu et al, 2005).…”