Application of classification machine learning algorithms for characterizing nutrient transport in a clay plain agricultural watershed.

Excess nutrients in surface water and groundwater can lead to water quality deterioration in available water resources. Thus, the classification of nutrient concentrations in water resources has gained significant attention during recent decades. Machine learning (ML) algorithms are considered an efficient tool to describe nutrient loss from agricultural land to surface water and groundwater. Previous studies have applied regression and classification ML algorithms to predict nutrient concentrations in surface water and/or groundwater, or to categorize an output variable using a limited number of input variables. However, there have been no studies that examined the application of different ML classification algorithms in agricultural settings to classify various output variables using a wide range of input variables. In this study, twenty-four ML classification algorithms were implemented on a dataset from three locations within the Upper Parkhill watershed, an agricultural watershed in southern Ontario, Canada. Nutrient concentrations in surface water were classified using geochemical and physical water parameters of surface water and groundwater (e.g., pH), climate and field conditions as the input variables. The performance of these algorithms was evaluated using four evaluation metrics (e.g., classification accuracy) to identify the optimal algorithm for classifying the output variables. Ensemble bagged trees was found to be the optimal ML algorithm for classifying nitrate concentration in surface water (accuracy of 90.9%), while the weighted KNN was the most appropriate algorithm for categorizing the total phosphorus concentration (accuracy of 87%). The ensemble subspace discriminant algorithm gave the highest overall classification accuracy for the concentration of soluble reactive phosphorus and total dissolved phosphorus in surface water with an accuracy of 79.2% and 77.9%, respectively. This study exemplifies that ML algorithms can be used to signify exceedance of recommended concentrations of nutrients in surface waters in agricultural watersheds. Results are useful for decision makers to develop nutrient management strategies.

Investigating relationships between climate controls and nutrient flux in surface waters, sediments, and subsurface pathways in an agricultural clay catchment of the Great Lakes Basin.

Water quality within agricultural catchments is governed by management practices and climate conditions that control the transport, storage, and exchange of nutrients between components of the hydrologic cycle. This study aims to improve knowledge of nitrogen (N) and phosphorus (P) transport in low permeability agricultural watersheds by considering spatial and temporal trends of surface water nutrient concentrations in relation to hydroclimatic drivers, sediment quality, shallow hyporheic exchange, groundwater quality, and tile drain discharge over a 14-month field study in a clay hydrosystem of the Lake Huron basin, one of the five Great Lakes. Results found that events of varying magnitude and intensity enhanced nutrient release from overland flow and subsurface pathways. Tile drain discharge was found to be a consistent and elevated source of P and N to surface waters when flowing, mobilizing both diffuse nutrients from fertilizer application and legacy stores in the vadose zone. Surface water quality was temporally variable at the seasonal and event scale. Targeted sampling following fertilization periods, snowmelt, and moderate precipitation events revealed catchment wide elevated nutrient concentrations, emphasizing the need for targeted sampling regimes. Controls other than discharge magnitude and overland flow were found to contribute to peak nutrient concentrations, including internal nitrate loading, soil-snowmelt interaction, catchment wetness, and freeze thaw cycles. Sediments were found to store P in calcium minerals and have a high P storage capacity. Instream mechanisms such as sediment P fixation and hyporheic exchange may play a role in mediating surface water quality, but currently have no discernable benefit to year-round surface water nutrient concentrations. Best management practices need to focus on reducing sources of agricultural nutrients (e.g., field phosphorus concentrations and tile drain discharge loading) at the watershed scale to reduce nutrient concentrations and export in flashy clay catchments.

Spatiotemporal variations of nitrogen and phosphorus in a clay plain hydrological system in the Great Lakes Basin.

Nutrient imbalance in groundwater and surface water resources can have severe implications on human and aquatic life, including contamination of drinking water sources and the degradation of ecosystems. A field-based watershed-scale study was completed to investigate nutrient dynamics and hydrologic processes in an agriculturally-dominant clay plain system within the Great Lakes Basin. Spatial and temporal variations of nitrogen and phosphorus were examined by sampling groundwater and surface water regularly over a period of one year (June 2017 to July 2018) for nutrients including nitrate, soluble reactive phosphorus, total dissolved phosphorus and total reactive phosphorus. Nitrate transport from surrounding agricultural land to surface water was intensified with an increase in precipitation events in spring and early winter and phosphorus transport to surface water was increased during freeze-thaw cycles in the winter. The results are pertinent to the improvement of current nutrient and water management policies in clay plain systems where nutrient imbalances in surface water are a concern.