Search

Stream corridor erosion can majorly contribute to the overall sediment and phosphorus load in urbanizing watersheds. However, the relative contribution of stream bed and bank erosion, compared with upland watershed sources and the potential for stream restoration to mitigate total contaminant loads, is poorly understood. In this study, a new method was developed, using the percent impervious cover (PIC) indicator of urbanization to evaluate the relative contribution of the stream corridor versus upland watershed contributions to observed total sediment and phosphorus loads in the receiving watercourse. This method was used to develop a cost-optimized mitigation plan, including implementing low-impact development (LID) stormwater infrastructure for urban areas and agricultural best management practices (BMPs) for rural areas in the watershed and stream restoration for the degraded stream reaches. A new cost–benefit analysis methodology is developed and used to assess the relative benefits of the mitigation measures for the case study of the Tannery Creek sub-watershed of the East Holland River in Ontario, Canada. The novel contributions of this study include the development of three relationships to estimate sediment and associated phosphorus loading based on contributing catchment area and land use, as well as a method to optimize the costs and benefits of planned mitigation measures. The results support stream restoration as an essential and cost-effective part of a comprehensive water quality watershed management plan to help maintain healthy streams in urbanized watersheds. [ABSTRACT FROM AUTHOR]

Dissolved oxygen (DO) is a key indicator of water quality and the health of an aquatic ecosystem. Aspiring to reach a more accurate forecasting approach for DO levels of natural streams, the present work proposes new graph-based and transformer-based deep learning models. The models were trained and validated using a network of real-time hydrometric and water quality monitoring stations for the Credit River Watershed, Ontario, Canada, and the results were compared with both benchmarking and state-of-the-art approaches. The proposed new Graph Neural Network Sample and Aggregate (GNN-SAGE) model was the best-performing approach, reaching coefficient of determination (R2) and root mean squared error (RMSE) values of 97% and 0.34 mg/L, respectively, when compared with benchmarking models. The findings from the Shapley additive explanations (SHAP) indicated that the GNN-SAGE benefited from spatiotemporal information from the surrounding stations, improving the model's results. Furthermore, temperature has been found to be a major input attribute for determining future DO levels. The results established that the proposed GNN-SAGE model outperforms the accuracy of existing models for DO forecasting, with great potential for real-time water quality management in urban watersheds. [ABSTRACT FROM AUTHOR]

In cold-climate regions, road salt is used as a deicer for winter road maintenance. The applied road salt melts ice and snow on roads and can be washed off through storm sewer systems into nearby urban streams, harming the freshwater ecosystem. Therefore, aiming to develop a precise and accurate model to determine future chloride concentration in the Credit River in Ontario, Canada, the present work makes use of a "Graph Neural Network"–"Sample and Aggregate" (GNN-SAGE). The proposed GNN-SAGE is compared to other models, including a Deep Neural Network-based transformer (DNN-Transformer) and a benchmarking persistence model for a 6 h forecasting horizon. The proposed GNN-SAGE surpassed both the benchmarking persistence model and the DNN-Transformer model, achieving RMSE and R2 values of 51.16 ppb and 0.88, respectively. Additionally, a SHAP analysis provides insight into the variables that influence the model's forecasting, showing the impact of the spatiotemporal neighboring data from the network and the seasonality variables on the model's result. The GNN-SAGE model shows potential for use in the real-time forecasting of water quality in urban streams, aiding in the development of regulatory policies to protect vulnerable freshwater ecosystems in urban areas. [ABSTRACT FROM AUTHOR]

Past studies described several dominant factors responsible for minimum runoff-generating areas (MRGAs) which are seldom backed by field observations. Here, soil moisture and runoff data for 45 rainfall events were collected from a small (21.62 ha) agricultural watershed in Ontario, Canada, using a remotely operated wireless sensor network system. The relationship developed between MRGA and basin moisture index (M) indicated that MRGAs are insensitive up to the threshold M value of 25 cm. A higher M leads to an exponential increase in the MRGA. Various factors (e.g. rainfall amount) affecting the spatiotemporal variability of MRGA were then identified. Statistical analyses (e.g. F-test) indicated a strong seasonal influence and showed that MRGA during spring, summer, and fall seasons was 34.3%, 8.0%, and 13.6%, respectively. The relationship of MRGA with rainfall amount, initial soil moisture content and rainfall intensity was the strongest for the summer season followed by fall and then spring. [ABSTRACT FROM AUTHOR]

Floods are one of the most lethal natural disasters. It is crucial to forecast the timing and evolution of these events and create an advanced warning system to allow for the proper implementation of preventive measures. This work introduced a new graph-based forecasting model, namely, graph neural network sample and aggregate (GNN-SAGE), to estimate river flooding. It then validated the proposed model in the Humber River watershed in Ontario, Canada. Using past precipitation and stage data from reference and neighboring stations, the proposed GNN-SAGE model could estimate the river stage for flooding events up to 24 h ahead, improving its forecasting performance by an average of 18% compared with the persistence model and 9% compared with the graph-based model residual gated graph convolutional network (GNN-ResGated), which were used as baselines. Furthermore, GNN-SAGE generated smaller errors than those reported in the current literature. The Shapley additive explanations (SHAP) revealed that prior data from the reference station was the most significant factor for all prediction intervals, with seasonality and precipitation being more influential for longer-range forecasts. The findings positioned the proposed GNN-SAGE model as a cutting-edge solution for flood forecasting and a valuable resource for devising early flood-warning systems. [ABSTRACT FROM AUTHOR]

Ascertaining the spatiotemporal accuracy of precipitation is a challenge for hydrologists and planners for flood protection measures. The objective of this study was to compare streamflow simulations using rain gauge and radar data from a watershed in Southern Ontario, Canada, using the Hydrologic Engineering Center's event-based distributed Hydrologic Modeling System (HEC-HMS). The model was run using the curve number (CN) and the Green and Ampt infiltration methods. The results show that the streamflow simulated with rain gauge data compared better with the observed streamflow than the streamflow simulated using radar data. However, when the Mean Field Bias (MFB) corrections were applied, the quality of the streamflow results obtained from radar rainfall data improved. The results showed no significant difference between the simulated streamflow using the SCS and the Green and Ampt infiltration approach. However, the SCS method is reasonably more appropriate for modeling the runoff at the sub-basin-scale than the Green and Ampt infiltration approach. With the SCS method, the simulated and observed runoff amount obtained using rain gauge rainfall showed an R2 value of 0.88 and 0.78 for MFB-corrected radar and 0.75 for radar only. For the Green and Ampt modeling option, the R2 value for the simulated and observed runoff amounts were 0.87 with rain gauge, 0.66 with radar only, and 0.68 with MFB-corrected radar rainfall inputs. The NSE values for rain gauge input ranged from 0.65 to 0.35. Overall, three values were less than 0.5 for streamflow for both the methods. For seven radar rainfall events, the NSE was greater than 0.5, with a range of very good to satisfactory. The analysis of RSR showed a very good comparison of stream flow using the SCS curve number method and Green and Ampt method using different rainfall inputs. Only one value, the 2 November 2003 event, was above 0.7 for rain gauge-based streamflow. The other RSR values were in the range of "very good". Overall, the study showed better results for the simulated runoff with the MFB-corrected radar rainfall when compared with the simulations obtained using radar rainfall only. Therefore, MFB-corrected radar could be explored as a substitute rainfall source. [ABSTRACT FROM AUTHOR]

Although access to safe drinking water is widely assumed to be universal, small drinking water systems in many countries continue to experience an unacceptably large number of drinking water advisories (DWAs). The goal of this research is to describe novel data mining tools that identify the factors contributing to DWAs in small drinking water systems. A dataset containing information related to First Nations drinking water systems in the Province of Ontario, Canada is used for the case study. A decision tree classifier (one of the fastest and most versatile predictive modeling algorithms currently available for data mining) visually maps out the relationship of system characteristics (e.g., source water, system age, and operator certification) to DWA likelihood. The developed model achieves an overall accuracy of 71 % during repeated cross-validation of predictive performance and is of utility when prioritizing future expenditures aimed at proactively reducing the risk of delivering compromised water. [ABSTRACT FROM AUTHOR]

This study comparatively evaluates the Hydrological Simulation Program-FORTRAN (HSPF) model and the Canadian ArcView Nutrient and Water Evaluation Tool (CANWET) for non-point source pollution (NPS) management in rural Ontario watersheds. Both models were calibrated, validated, and applied to a 52 km² headwater rural watershed known as the Canagagigue Creek near Elmira in the Grand River basin, Ontario, Canada. A comparison of the simulated and observed values for stream flow, surface runoff, subsurface runoff, evapotranspiration, and sediment yield showed that (Better Assessment Science Integrating Point and Nonpoint Sources) BASINS/HSPF and CANWET models have similar capabilities to simulate various hydrological processes at the watershed scale. The seasonal stream flow comparison between observed and simulated values from HSPF and CANWET showed Nash-Sutcliffe efficiency (Nash-E) coefficients of 0.80 and 0.72, respectively. The monthly comparison between the simulated and observed stream flow yielded Nash-E coefficients of 0.88 and 0.94 for HSPF and CANWET, respectively. Overall, both models predicted the components of the annual, seasonal, and monthly water budget accurately. There was a considerable difference in the monthly simulated sediment yield by both models. This difference is consistent with the surface runoff variation predicted by both models. Both models predicted sediment yield with early winter and spring storms which is typical for southern Ontario. [ABSTRACT FROM AUTHOR]

Copyright of Canadian Water Resources Journal / Revue Canadienne des Ressources Hydriques is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Canadian Water Resources Journal / Revue Canadienne des Ressources Hydriques is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Stormwater runoff containing pollutants deposited on highways from vehicular traffic and urban activities has been identified as a serious threat to aquatic habitats. Although many urban stormwater management technologies serve to reduce the concentrations of pollutants from being transported to larger bodies of water, these stormwater management installations do not always meet the provincial water quality guidelines. In summer 2007, a compost biofilter was installed in a ditch near Highway 8 in Kitchener, Ontario and monitored for 18 storm events spanned over two years for both flow rate and water quality. The main objectives of the study were to determine highway runoff quality and biofilter pollutant removal efficiency. This study shows that the key factors that affect the build-up of the pollutants on a highway are the average annual daily traffic (AADT) and the antecedent dry days (ADD), and the main factors that affect the wash-off of pollutants, include total rainfall depth and rainfall intensity. Before filtration, highway runoff contaminant levels often exceeded the Ontario Provincial Water Quality Objectives (PWQO). However, the biofilter reduced the total suspended solids, zinc, copper and polycyclic aromatic hydrocarbons by 42, 32, 29, and 66%. [ABSTRACT FROM AUTHOR]

Occurrence of increasing chloride concentrations in urban streams of cold climates, mainly due to road salt application, has raised concerns on its adverse effects on aquatic and terrestrial ecosystems. Therefore, there is a need for a better understanding of processes associated with road salt application and subsequent discharge into the environment in order to develop management practices to minimize detrimental effects of chlorides. The chloride mass analysis for the Highland Creek watershed based on four years of hourly monitoring data indicates that approximately 60% of the chlorides applied on the watershed enter streams prior to subsequent salting period, 85% of which occurs during the period between November and March. Contribution of private de-icing operations on chloride mass input within Highland Creek watershed was estimated to be approximately 38%, indicating its significance in overall chloride mass balance. Salt application rates, as well as chloride output in the streams, vary spatially based on land use, influencing chloride concentrations in surface waters. The estimated groundwater chloride concentration of 275 mg/L indicates that some aquatic organisms in Highland Creek would potentially be at risk even outside the winter period under dry weather flow conditions. [ABSTRACT FROM AUTHOR]

In cold regions, winter road safety is a major challenge for municipalities and provincial highway transportation agencies. Road salt is widely used to improve winter road conditions, but concerns have been raised about the effects of road salts on the environment. This paper describes a water quality monitoring program designed to measure both background chloride concentrations and the effects of road salt application on stream water quality in four watersheds (Humber River, Don River, Highland Creek, and Morningside tributary of Rouge River). located within the City of Toronto boundary. The effect of road salts on stream water quality was evaluated based on chloride concentration because of its conservative nature. A bilinear correlation was developed to transform measured specific conductance levels in stream water to chloride concentrations. There are no Ontario aquatic fresh water quality guidelines for chloride, but chloride concentrations in almost all the monitored streams in Toronto periodically exceeded chronic and acute chloride threshold levels of the United States Environmental Protection Agency. The City of Toronto has been proactive in its efforts to implement management practices to reduce the impact of road salt application on the environment while maintaining safe driving conditions for its road users. Normalized salt application rates in Toronto have been on a gradual declining trend in the last decade from about 0.08 to 0.07 tonnes of salt applied per centimetre of snowfall per kilometre of lane. With public safety in mind, further reductions in salt application rates are being considered to reduce the adverse environmental effects to acceptable limits. [ABSTRACT FROM AUTHOR]

The effectiveness of compost biofilters in removal of suspended sediments from stormwater runoff was evaluated. Field experiments were conducted in the summer of 2006 at the Guelph Turf Grass Institute, University of Guelph, to verify the sediment removal efficiency of the compost biofilter from synthetic stormwater runoff. The average sediment removal efficiency of 8-inch (20-cm) compost biofilters (socks) for 5, 10, and 15 rolls were 34, 48, and 60%, respectively. The average sediment removal efficiency for 18-inch (45-cm) socks for 5, 10, and 15 rolls were 69, 84, and 95%, respectively. The decrease in sediment removal efficiency of the biofilter over time was significant. The average sediment removal efficiency of 5 rolls of the 18-inch (45-cm) sock started to decrease gradually from 70 to 62, 58, 56, and 54% after 1, 5, 10, 15, and 20 consecutive runs. Sediment removal efficiency of the biofilter for sediment particles in the size range of clay was found to be 30%, while for coarser particles such as fine silt and coarse silt was 50 and 80% removal efficiencies, respectively. [ABSTRACT FROM AUTHOR]

Many forms of natural heritage manifested as streams, rivers, ponds, lakes and wetlands play an integral role in maintaining natural beauty, health and a high quality of life. Agricultural intensification in southern Ontario has contributed to elevated sediments, nutrient and bacteria levels in water bodies. Vegetative filter strips (VFS) are control measures that can partially remove sediments and pollutants adhered to sediments from overland runoff before entering water bodies. The objective of this study was to determine the effect of vegetation type, width of the filter strip, runoff flow rate and inflow sediment characteristics on effectiveness of the VFS in removing pollutants from runoff. The results show that sediment removal efficiency increased from 50 to 98% as the width of the filter increased from 2.5 to 20 m. In addition to the width of the filter strip, grass type and flow rate were also significant factors. This study indicates that the first five (5) metres of a filter strip are critical and effective in removal of suspended sediments. More than 95% of the aggregates larger than 40 pm in diameter were trapped within the first five metres of the filter strip. [ABSTRACT FROM AUTHOR]

Ontario's Stormwater Management, Planning and Design Manual released in March 2003 integrates some of the advancements made in stormwater management since the 1994 version of the Manual was published. Perhaps the most significant update is the recognition of in-stream erosion control and water balance objectives in addition to flood and water quality objectives for stormwater management. Specific design criteria which would allow these objectives to be achieved are not set out, but procedures that can assist in the development of criteria based on local watershed and receiving water conditions are described. While refinements will undoubtedly be needed, approaches to designing end-of-pipe facilities to prevent undesirable geomorphic changes are included. Approaches to protect groundwater and baseflow characteristics are also included although guidance on addressing potential trade-offs between groundwater quantity and quality is an additional challenge for the future. Little design guidance is available in Ontario on techniques to mitigate impacts on wetlands, however, developments from other jurisdictions may be transferable. The 2003 Manual promotes an integrated, treatment train approach to stormwater management that emphasizes prevention first, followed by lot-level and conveyance controls and finally, end-of-pipe controls. Some information on better site design techniques is incorporated but in comparison to other jurisdictions, less emphasis has been placed on low-impact development strategies. Ontario's approach to design for water quality (suspended solids) control has evolved little. To complement the prevention and treatment train philosophy, the removal efficiency approach to sizing end-of-pipe facilities needs to be used in conjunction with effluent criteria and/or minimum requirements for source protection. Significant advancements in stormwater modelling over the last decade are not well reflected in the Manual; the limited discussion of modelling focuses on an event-based approach. Whether event or continuous modelling is utilized, Ontario practitioners will need guidance on adapting input data to account for the anticipated effects of climate change. Development of sound guidance on monitoring increasingly complex, multi-objective stormwater management systems and the ecosystems they are designed to protect will be critical to ensure that the knowledge gained from performance evaluations may continue to be utilized to refine the design and management of stormwater systems. [ABSTRACT FROM AUTHOR]

Real-time monitoring of river water quality is at the forefront of a proactive urban water management strategy to meet the global challenge of vital freshwater resource sustainability. The concentration of dissolved oxygen (DO) is a primary indicator of the health state of the aquatic habitats, and its modeling is crucial for river water quality management. This paper investigates the importance of the choices of different techniques for preprocessing and stochastic modeling for developing a simple and reliable linear stochastic model for forecasting DO in urban rivers. We describe several methods of evaluation, preprocessing, and modeling for the DO parameter time series in the Credit River, Ontario, Canada, to achieve the optimum data preprocessing and input selection techniques and consequently obtain the optimum performance of the stochastic models as an effective river management tool. The Manly normalization and standardization (Std) methods were chosen for preprocessing the time series. Modeling the preprocessed time series using the stochastic autoregressive integrated moving average (ARIMA) model resulted in very accurate forecasts with a negligible difference from sole normalization and spectral analysis (Sf) methods. [ABSTRACT FROM AUTHOR]

The extensive use of road salts as deicers during winter months is causing the salinization of freshwater systems in cold climate regions worldwide. We analyzed 20 years (2001–2020) of data on lake water chemistry, land cover changes, and road salt applications for Lake Wilcox (LW) located in southern Ontario, Canada. The lake is situated within a rapidly urbanizing watershed in which, during the period of observation, on average 785 tons of road salt were applied annually. However, only about a quarter of this salt has reached the lake so far. That is, most salt has been retained in the watershed, likely through accumulation in soils and groundwater. Despite the high watershed salt retention, time series trend analyses for LW show significant increases in the dissolved concentrations of sodium (Na+) and chloride (Cl−), as well as those of sulfate (SO 4 2−), calcium (Ca2+), and magnesium (Mg2+). The relative changes in the major ion concentrations indicate a shift of the lake water chemistry from the mixed SO 4 2–-Cl–-Ca2+-Mg2+ type to the Na+-Cl- type. Salinization of LW has further been strengthening and lengthening the lake's summer stratification, which, in turn, has been enhancing hypoxia in the hypolimnion and increasing the internal loading of the limiting nutrient phosphorus. The theoretical salinity threshold at which fall overturn would become increasingly unlikely was estimated at around 1.23 g kg−1. A simple chloride mass balance model predicts that, under the current trend of impermeable land cover expansion, LW could reach this salinity threshold by mid-century. Our results also highlight the need for additional research on the accruing salt legacies in urbanizing watersheds because they represent potential long-term threats to water quality for receiving freshwater ecosystems and regional groundwater resources. [Display omitted] • Road salt use accompanying urban growth accelerates salinization of Lake Wilcox. • Salinization alters the lake's chemical water type and strengthens stratification. • Most salt applied till now has been retained in the watershed. • The watershed salt legacy may represent a long-term threat to water quality. • Ongoing salinization may prevent the lake's fall overturn by mid-century. [ABSTRACT FROM AUTHOR]

• Conducted 3-years of water temperature monitoring from three stormwater ponds. • Developed a new model to predict thermal profiles in stormwater wet ponds. • Developed a new model for pond outlet discharge temperature during storm events. • The model is used to showcase the cooling effects of pond max depth and outlet. • The new model can help protect thermally-sensitive aquatic life in urban streams. Discharges of warm water from shallow stormwater management ponds during summer months into receiving headwater streams pose a risk to aquatic ecosystems in urban watersheds, especially in cool- and cold-water streams. Physically based models such as MINUHET have been used to assess the effects of thermal loading on receiving streams. However, these models require a significant amount of data and are complex to calibrate and use for the optimized designs that ensure protection of vulnerable aquatic life in urban stream ecosystems. This research introduces a user friendly and more accurate machine learning method to predict thermal profiles in stormwater ponds and the pond outlet discharge temperature to the receiving streams during storm events. Monitoring data were collected between 2014 and 2016 from three stormwater ponds in southern Ontario to train and test the new model. The new model is used to demonstrate the degree to which cooling effects can be achieved from remedial actions such as increasing the pond depth by dredging one meter and if a bottom-draw outlet is used instead of a mid-depth draw outlet. The methods presented in this study can be used to support an improved stormwater management pond design guidelines based on the key design objective that the thermal regime of the stormwater pond outlet discharge water must match the thermal regime of the receiving stream. The main objective is to avoid any discernable warming of the stream due to the stormwater pond discharge under a range of summer temperatures and storm event sizes. [ABSTRACT FROM AUTHOR]

• Compiled a large data set of hourly climatic and pavement temperatures. • Developed a new model for real-time forecasting of pavement temperatures. • The new model can be used for precision salt application using smart salt trucks. • Precision salt application will improve environmental sustainability and road safety. Road authorities in cold climates regularly apply salt on roads, during winter, to ensure public safety. Pavement surface temperature is a significant parameter affecting snow and ice melting at the onset of a storm. Road temperature below the freezing point of the applied brine causes ice to form on the road surface. Excessive application of salt on the road can have adverse environmental impacts, especially to soil and water quality. Therefore, forecasting pavement temperature can optimize road salt application, while reducing costs, improving public safety, and reducing environmental impacts. This research aims to develop a reliable and accurate pavement surface temperature prediction tool using machine learning techniques. This study employs advanced deep neural network (DNN) learning techniques to predict pavement surface temperature for road salt management purposes. To validate the proposed methodology, this work used hourly solar radiation and air temperature data from Environment Canada, and pavement surface temperature data collected from the Road Weather Information System (RWIS), for sites around the city of Toronto, Ontario. The performance of the proposed DNN model, that integrates a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM), on pavement surface temperature forecasting, was evaluated against four other comparative machine learning methods, LSTM, Convolutional-LSTM (ConvLSTM), Sequence-to-Sequence (Seq2Seq), and Wavelet neural network (Wavenet) models. A dataset of 10,895 samples was collected as an hourly pavement surface temperature record in three timeframes from November 2009 to March 2014 on Highway 401 in southern Ontario, Canada. Experiments included predictions for 1-, 2-, 4- and 6-hours ahead, using as input features air temperature, solar radiation, and present pavement temperature. The proposed pavement temperature forecasting approach resulting from this investigation suggests our new approach is more accurate than previous models. These results reveal that the CNN-LSTM outperforms the four other models and creates predictions closer to the true pavement surface temperature. [ABSTRACT FROM AUTHOR]

Excessive phosphorus loading to inland freshwater lakes around the globe has resulted in nuisance plant growth along the waterfronts, degraded habitat for cold-water fisheries, and impaired beaches, marinas, and waterfront property. The direct atmospheric deposition of phosphorus can be a significant contributing source to inland lakes. The atmospheric deposition monitoring program for Lake Simcoe, Ontario, indicates roughly 20% of the annual total phosphorus load (2010-2014 period) is due to direct atmospheric deposition (both wet and dry deposition) on the lake. This novel study presents a first-time application of the genetic algorithm (GA) methodology to optimize the application of best management practices (BMPs) related to agriculture and mobile sources to achieve atmospheric phosphorus reduction targets and restore the ecological health of the lake. The novel methodology takes into account the spatial distribution of the emission sources in the airshed, the complex atmospheric long-range transport and deposition processes, cost and efficiency of the popular management practices, and social constraints related to the adoption of BMPs. The optimization scenarios suggest that the optimal overall capital investment of approximately $2M, $4M, and $10M annually can achieve roughly 3, 4, and 5 tonnes reduction in atmospheric P load to the lake, respectively. The exponential trend indicates diminishing returns for the investment beyond roughly $3M per year and that focusing much of this investment in the upwind, nearshore area will significantly impact deposition to the lake. The optimization is based on a combination of the lowest cost, most beneficial and socially acceptable management practices that develops a science-informed promotion of implementation/BMP adoption strategy. The geospatial aspect to the optimization (i.e., proximity and location with respect to the lake) will help land managers to encourage the use of these targeted best practices in areas that will most benefit from the phosphorus reduction approach., Implications: Excessive phosphorus loading to inland freshwater lakes around the globe has resulted in nuisance plant growth along the waterfronts, degraded habitat for cold water fisheries, and impaired beaches, marinas and waterfront property. This novel study presents a first-time application of the Genetic Algorithm methodology to optimize the application of best management practices related to agriculture and mobile sources to achieve atmospheric phosphorus reduction targets and restore the ecological health of the lake. The novel methodology takes into account the spatial distribution of the emission sources in the airshed, the complex atmospheric long-range transport and deposition processes, cost and efficiency of the popular management practices and social constraints related to the adoption of BMPs.