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.

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.