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.

A comparative evaluation of the continuous and event-based modelling approaches for identifying critical source areas for sediment and phosphorus losses.

Proper identification of critical source areas (CSAs) is important for economic viability of any best management practices (BMPs) aimed at reducing sediment and phosphorus loads to receiving water bodies. Both continuous and event-based hydrologic and water quality models are widely used to identify and assess CSAs, however, their comparative assessment is lacking. In this study, we have used continuous Soil and Water Assessment Tool (SWAT) and event-based Agriculture Non-Point Source (AGNPS) pollution models to identify CSAs for sediment and phosphorus in a watershed in Ontario, Canada. Along with their original version, both models were re-conceptualized to incorporate saturation excess mechanism of runoff generation, which is also refereed as variable source area (VSA) integration. The models were set-up using high resolution spatial, crop- and land-management, and meteorological dataset; and calibrated with reasonable accuracy against streamflow, sediment and phosphorus concentration data at multiple locations. Threshold value (t-value) approach was used to identify CSA areas in the watershed. Results showed that both models were in agreement (up to 96% of fields) that summer season did not constitute hot-moments (<6% of the watershed area as CSAs) for both sediment and phosphorus. SWAT models identified winter (~50% of watershed area as CSA) and AGNPS models identified early spring (~50% of watershed areas as CSAs) season as the hot-moment for both sediment and phosphorus. Contrasting result, as indicated by low (1%) matching in field CSA potential, was observed in autumn season. In the same season, VSA integrated SWAT and AGNPS models showed better matching (43% for sediment and 31% for phosphorus), highlighting the importance of VSA integration in the models. Qualitative validation of model-based CSA potential with oblique aerial-photograph-based CSA potential in two soil moisture conditions (wetter and drier) indicated slightly better performance of the SWAT models, and over-prediction of the AGNPS models. However, a more comprehensive analysis based on more detailed field observations is needed to further confirm the results.

Phosphorus loss assessment tools: a review of underlying concepts and applicability in cold climates.

Identifying critical source areas (CSAs) of a watershed by phosphorus (P) loss assessment tools is essential for optimal placement of beneficial management practices (BMPs) to address diffuse P pollution. However, lack of significant progress in tackling diffuse P pollution could be, in part, associated with inefficacy of P loss assessment tools for accurately identifying CSAs. Phosphorus loss assessment tools have been developed to simulate P loss from the landscape where runoff is mainly driven by rainfall events. Therefore, they may underperform in cold climates where the land is often frozen during winter and runoff is dominated by snowmelt. This paper (i) reviews the strengths and weaknesses of current P loss assessment tools and their underlying assumptions in simulating soil P dynamics and P transfer to runoff, and (ii) highlights a number of challenges associated with modeling P transfer from agricultural land to surface waters in cold climates. Current P loss assessment tools do not appear to fully represent hydrological and biogeochemical processes responsible for P loss from CSAs, particularly in cold climates. Effort should be made to develop P loss assessment tools that are capable of considering P dynamics through the landscape as a result of abiotic perturbations that are common in cold climates, predicting runoff and P movement over frozen/partially frozen soils, and considering material-P connectivity between landscape and surface waters. Evaluating P loss assessment tools with water quality data is necessary to ensure such modifications result in improved identification of CSAs.

Reconstruction of post-traumatic long bone defect with vascularised free fibula: A series of 28 cases.

INTRODUCTION: The severe long bone defects usually follow high-energy trauma and are often associated with a significant soft-tissue injury. The goal of management of these open long bone defects is to provide stable fixation with maintenance of limb length and soft-tissue coverage. The purpose of this article is to present the clinic-radiological outcome, complications and treatment of post-traumatic long bone defect with vascularised fibula transfer. MATERIALS AND METHODS: Retrospective records of 28 patients were analysed who presented with post-traumatic long bone defects and in whom reconstruction with vascularised free fibula was done. Demographic data were recorded and clinical and radiological assessment was done. RESULTS: Out of 28 patients in whom vascularised free fibula transfer was carried out three flaps were lost while non-union occur in three patients. Three patients developed a stress fracture of transferred free fibula in the post-operative period. Few of the patients experienced some problems in the donor leg; however, all of them improved in subsequent follow-up. DISCUSSION: It is clearly evident from this study that timing of surgery plays an important role in the micro-vascular reconstruction in trauma cases. All the complication like flap loss, non-union or delayed union occur in patients in whom reconstruction was delayed. CONCLUSION: The free vascularised fibula graft is a viable method for the reconstruction of skeletal defects of more than 6 cm, especially in cases of scarred and avascular recipient sites or in patients with combined bone and soft-tissue defects. Results are best when the reconstruction is done within 1 week of trauma.