Value and limitations of machine learning in high-frequency nutrient data for gap-filling, forecasting, and transport process interpretation.

High-frequency monitoring of water quality in catchments brings along the challenge of post-processing large amounts of data. Moreover, monitoring stations are often remote and technical issues resulting in data gaps are common. Machine learning algorithms can be applied to fill these gaps, and to a certain extent, for predictions and interpretation. The objectives of this study were (1) to evaluate six different machine learning models for gap-filling in a high-frequency nitrate and total phosphorus concentration time series, (2) to showcase the potential added value (and limitations) of machine learning to interpret underlying processes, and (3) to study the limits of machine learning algorithms for predictions outside the training period. We used a 4-year high-frequency dataset from a ditch draining one intensive dairy farm in the east of The Netherlands. Continuous time series of precipitation, evapotranspiration, groundwater levels, discharge, turbidity, and nitrate or total phosphorus were used as predictors for total phosphorus and nitrate concentrations respectively. Our results showed that the random forest algorithm had the best performance to fill in data-gaps, with R2 higher than 0.92 and short computation times. The feature importance helped understanding the changes in transport processes linked to water conservation measures and rain variability. Applying the machine learning model outside the training period resulted in a low performance, largely due to system changes (manure surplus and water conservation) which were not included as predictors. This study offers a valuable and novel example of how to use and interpret machine learning models for post-processing high-frequency water quality data.

Climate variability effects on eutrophication of groundwater, lakes, rivers, and coastal waters in the Netherlands.

Many aquatic ecosystems in densely populated delta areas worldwide are under stress from overexploitation and pollution. Global population growth will lead to further increasing pressures in the coming decades, while climate change may amplify the consequences for chemical and ecological water quality. In this study, we explored the effects of climatic variability on eutrophication of groundwater, streams, rivers, lakes, estuaries, and marine waters in the Netherlands. We exploited the relatively dense monitoring information from the Dutch part of the Rhine-Meuse delta to evaluate the water quality response on climatic variability, in combination with anthropogenic pressures. Our results show that water quality of all water systems in the Netherlands is affected by climate variability in several ways: 1) through the process of global climate change (mainly temperature and sea level rise), 2) through changes Atlantic ocean circulation patterns (more southwestern winds), 3) through changes in continental precipitation and river discharge fluctuations, and 4) through local climatic fluctuations. The impact of climate variability propagates through the hydrological system 'from catchment to coast'. The fluctuations in water quality induced by climatic variability shown in this study give a preview for the potential effects of climate change.