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.

Nitrate sources and transformation processes in groundwater of a coastal area experiencing various environmental stressors.

In coastal salinized groundwater systems, contamination from various nitrate (NO3) inputs combined with complex hydrogeochemical processes make it difficult to distinguish NO3 sources and identify potential NO3 transformtation processes. Effective field-based NO3 studies in coastal areas are needed to improve the understanding of NO3 contamination dynamics in groundwater of such complex coastal systems. This study focuses on a typical Mediterranean coastal agricultural area, located in Tunisia, experiencing substantial NO3 contamination from multiple anthropogenic sources. Here, multiple isotopic tracers (δ18OH2O, δ2HH2O, δ15NNO3, δ18ONO3, and δ11B) combined with a Bayesian isotope MixSIAR model are used (i) to identify the major NO3 sources and their contributions, and (ii) to describe the potential NO3 transformation processes. The measured NO3 concentrations in groundwater are above the natural baseline threshold, suggesting anthropogenic influence. The measured isotopic composition of NO3 indicates that manure, soil organic matter, and sewage are the potential sources of NO3, while δ11B values constrain the NO3 contamination to manure; a finding that is supported by the results of MixSIAR model revealing that manure-derived NO3 dominates over other likely sources. Nitrate derived from manure in the study area is attributed to organic fertilizers used to promote crop growth, and livestock that deposit manure directly on the ground surface. Evidence for ongoing denitrification in groundwaters of the study area is supported by an enrichment in both 15N and 18O in the remaining NO3, although isotopic mass balances between the measured and the theoretical δ18ONO3 values also suggest the occurrence of nitrification. The simultaneous occurrence of these biogeochemical processes with heterogeneous distribution across the study area reflect the complexity of interactions within the investigated coastal aquifer. The multiple isotopic tracer approach used here can identify the effect of multiple NO3 anthropogenic activities in coastal environments, which is fundamental for sustainable groundwater resources management.

Using isotopic tracers to enhance routine watershed monitoring - Insights from an intensively managed agricultural catchment.

Experimental (research-based) and non-research-based watershed monitoring programs often differ with respect to sampling frequency, monitored variables, and monitoring objectives. Isotopic variables, which are more commonly incorporated in research-based programs, can provide an indication of water sources and the transit time of water in a catchment. These variables may be a valuable complement to traditional water quality monitoring variables and have the potential to support improved hydrologic process-related insights from long term monitoring programs that typically have low resolution sampling. The purpose of this investigation is to explore the utility of incorporating isotopic variables (specifically δ18O, δ2H, and 222Rn) into routine monthly sampling regimes by comparing insights gained from these variables to monitoring only specific conductivity and chloride. A complete annual cycle of monthly groundwater and surface water monitoring data collected from the Upper Parkhill watershed in southwestern Ontario, Canada was used to characterize baseline watershed conditions, evaluate watershed resilience to climate change, and examine contamination vulnerability. Study results provide an improved understanding of appropriate tracer use in agricultural regions with isotopic variables able to provide important insights into the seasonality of hydrologic phenomena, such as the timing of groundwater recharge. A comparison of monitoring variables to present-day hydro-meteorological conditions suggests the importance of a winter dominated hydrologic regime and the potential influence of changes in precipitation on groundwater-surface water interactions. Estimated transit time dynamics indicate the likelihood for rapid contaminant transport through surface and shallow subsurface flow and highlight the possible effects of agricultural tile drainage. The sampling approach and data analysis methods adopted in this study provide the basis for improving routine watershed monitoring programs in agricultural regions.

Impacts of soil, climate, and phenology on retention of dissolved agricultural nutrients by permanent-cover buffers.

Nutrient losses from farms affects environmental and human health, but retention by riparian buffers can vary by nutrient identity, flow path, soil texture, seasonality, and buffer width. On conventional farms with corn, we test the relationships between levels of dissolved nitrogen (N) and phosphorus (P) in downslope surface-water, and flow paths relating to porewater in soils (to 40 cm deep), groundwater of the saturated zone (to 2.5 m deep), soil nutrient pools, and changes in plant biomass and tissue quality by season. We found that the major drivers of surface-water nutrients were multi-factor and nutrient-specific, variously relating to soil, climate, vegetation uptake, and tiling on clay soils. N retention was best explained by soil type, with 10 times more surface-water N in the sand versus clay setting, despite identical fertilization rates on corn. P retention was best explained by precipitation and time of year. Vegetation uptake was strongest for shallow-soil porewater, and was greatest in buffers where root biomass was 20 times greater by weight. We were unable to detect any impact of vegetative uptake on groundwater nutrients. Overall, peak nutrient inputs to surface-water were in early summer, fall, and winter - all times when plant uptake is low. Buffers appear to be a necessary component of nutrient capture on farms, but insufficient unless partnered with measures that reduce nutrient flows at times when plants are inactive.

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.

A GIS-based groundwater pollution potential using DRASTIC, modified DRASTIC, and bivariate statistical models.

The objective of the current study is groundwater vulnerability assessment using DRASTIC, modified DRASTIC, and three statistical bivariate models (frequency ratio (FR), evidential belief function (EBF), and weights-of-evidence (WOE)) for Sari-Behshahr plain, Iran. A total of 218 wells were sampled for nitrate concentration measurement in 2015. Datasets were generated using results from 109 wells having nitrate concentrations greater than 50 mg/L. The nitrate data were divided into two groups of 70% (76 locations as training dataset) for modeling and 30% (33 locations as a testing dataset) for model validation. Finally, five groundwater potential pollution (GPP) maps were produced by the training dataset and then evaluated using the testing dataset and receiver operating characteristic (ROC) method. Results of the ROC method showed that the WOE model had the highest predictive power, followed by EBF, FR, modified DRASTIC, and DRASTIC models. Results of the maps obtained revealed that high and very high pollution potential covered the southern part of the study areas, where big cities are located. Results of the present study can be replicated in other locations for identifying groundwater contaminant prone areas.

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.

Rapid transport from the surface to wells in fractured rock: a unique infiltration tracer experiment.

A unique infiltration tracer experiment was performed whereby a fluorescent dye was applied to the land surface in an agricultural field, near Perth, Ontario, Canada, to simulate the transport of solutes to two pumped monitoring wells drilled into the granitic gneiss aquifer. This experiment, interpreted using the discrete-fracture capability of the numerical model HydroGeoSphere, showed that solute transport from the surface through thin soil (less than 2m) to wells in fractured bedrock can be extremely rapid (on the order of hours). Also, it was demonstrated that maximum concentrations of contaminants originating from the ground surface will not necessarily be the highest in the shallow aquifer horizon. These are important considerations for both private and government-owned drinking water systems that draw water from shallow fractured bedrock aquifers. This research illustrates the extreme importance of protecting drinking water at the source.