scholarly journals A Predictive Model of Chlorophyll a in Western Lake Erie Based on Artificial Neural Network

2021 ◽  
Vol 11 (14) ◽  
pp. 6529
Author(s):  
Qi Wang ◽  
Song Wang
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Artificial Neural Network ◽  
Chlorophyll A ◽  
Lake Erie ◽  
Ann Model ◽  
Meteorological Forcing ◽  
Chl A ◽  
Western Lake ◽  
Western Lake Erie

The reoccurrence of algal blooms in western Lake Erie (WLE) since the mid-1990s, under increased system stress from climate change and excessive nutrients, has shown the need for developing management tools to predict water quality. In this study, process-based model GLM-AED (General Lake Model-Aquatic Ecosystem Dynamics) and statistical model ANN (artificial neural network) were developed with meteorological forcing derived from surface buoys, airports, and land-based stations and historical monitoring nutrients, to predict water quality in WLE from 2002 to 2015. GLM-AED was calibrated with observed water temperature and chlorophyll a (Chl-a) from 2002 to 2015. For ANN, during the training period (2002–2010), the inputs included meteorological forcing and nutrient concentrations, and the target was Chl-a simulated by calibrated GLM-AED due to the lack of continuously daily measured Chl-a concentrations. During the testing period (2011–2015), the predicted Chl-a concentrations were compared with the observations. The results showed that the ANN model has higher accuracy with lower Chl-a RMSE and MAE values than GLM-AED during 2011 and 2015. Lastly, we applied the established ANN model to predict the future 10-year water quality of WLE, which showed that the probability of adverse health effects would be moderate, so more intense water resources management should be implemented.

Novel application of a back-propagation artificial neural network model formulated to predict algal bloom

1997 ◽  
Vol 36 (5) ◽  
pp. 89-97 ◽  
Author(s):  
Ken-ichi Yabunaka ◽  
Masaaki Hosomi ◽  
Akihiko Murakami
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Artificial Neural Network ◽  
Chlorophyll A ◽  
Algal Bloom ◽  
Back Propagation ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Ann Model ◽  
Chlorophyll A Concentration

This paper describes the novel application of an artificial neural network (ANN) model based on the back-propagation method formulated to predict algal bloom by simulating the future growth of five phytoplankton species and the chlorophyll a concentration in the second largest lake in Japan: eutrophic freshwater Lake Kasumigaura. Comparison of observed and calculated values showed that (i) seasonal variations in the biomass of Microcystis spp. were well-predicted with respect to the timing and magnitude of algal bloom, and (ii) the concentration of chlorophyll a, as an indicator of the total biomass of phytoplankton, was well predicted in general. The resultant correlations for the other species, however, showed that model learning was insufficient to effectively predict species biomass; thereby indicating that some unknown factors which are not represented by the set of water quality parameters used as model input data affect phytoplankton growth. A sensitivity analysis performed on input parameters showed that chlorophyll a concentration was mainly affected by PO4-P concentration, while cyanobacteria and diatom species were affected by NO3-N and NH4-N concentrations, respectively. These results indicate that the “algal bloom” ANN model achieved reasonable effectiveness with respect to learning the relationship between the selected water quality parameters and algal bloom.

scholarly journals Spatial and temporal variability of inherent and apparent optical properties in western Lake Erie: Implications for water quality remote sensing

2019 ◽  
Vol 45 (3) ◽  
pp. 490-507 ◽  
Author(s):  
Michael J. Sayers ◽  
Karl R. Bosse ◽  
Robert A. Shuchman ◽  
Steven A. Ruberg ◽  
Gary L. Fahnenstiel ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Water Quality ◽  
Optical Properties ◽  
Temporal Variability ◽  
Lake Erie ◽  
Spatial And Temporal Variability ◽  
Western Lake ◽  
Western Lake Erie

Water Quality Forecast Based on BP-Artificial Neural Network Model in Qiantang River

2014 ◽  
Vol 668-669 ◽  
pp. 994-998
Author(s):  
Jin Ting Ding ◽  
Jie He
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Artificial Neural Network ◽  
Ph Value ◽  
Back Propagation ◽  
Ammonia Nitrogen ◽  
Quality Parameters ◽  
Ann Model ◽  
Qiantang River ◽  
Artificial Neural

This study aims at providing a back propagation-artificial neural network (BP-ANN) model on forecasting the water quality change trend of Qiantang River basin. To achieve this goal, a three-layer (one input layer, one hidden layer, and one output layer) BP-ANN with the LM regularization training algorithm was used. Water quality variables such as pH value, dissolved oxygen, permanganate index and ammonia-nitrogen was selected as the input data to obtain the output of the neural network. The ANN structure with 17 hidden neurons obtained the best selection. The comparison between the original measured and forecast values of the ANN model shows that the relative errors, with a few exceptions, were lower than 9%. The results indicated that the BP neural network can be satisfactorily applied to forecast precise water quality parameters and is suitable for pre-alarm of water quality trend.

Weather, Landscape, and Management Effects on Nitrate and Soluble Phosphorus Concentrations in Subsurface Drainage in the Western Lake Erie Basin

2018 ◽  
Vol 61 (1) ◽  
pp. 223-232 ◽  
Author(s):  
Lindsay A. Pease ◽  
Norman R. Fausey ◽  
Jay F. Martin ◽  
Larry C. Brown
Keyword(s):  
Water Quality ◽  
Lake Erie ◽  
Subsurface Drainage ◽  
Quality Data ◽  
P Loss ◽  
Western Lake ◽  
Soluble Phosphorus ◽  
Management Factors ◽  
Soluble P ◽  
Western Lake Erie

Abstract. Subsurface drainage, while an important and necessary agricultural production practice in the Midwest, contributes nitrate (NO3-N) and soluble phosphorus (P) to surface waters. Eutrophication (i.e., excessive enrichment of surface water by NO3-N and soluble P) supports harmful algal blooms in receiving waters. The magnitude of NO3-N and soluble P loss in subsurface drainage varies greatly by landscape, weather, and field management factors. This study evaluated both the relative and combined impacts of these factors on observed NO3-N and soluble P concentrations in subsurface drainage water in the Western Lake Erie Basin watershed. Water quality data from multiple drainage outlet sites in northwest Ohio provided evidence that the primary management factors affecting NO3-N and soluble P loss were the amount and time of fertilizer application. Results strongly support following Tri-State fertilizer recommendations and 4R nutrient stewardship principles to reduce the risk of NO3-N and soluble P loss. Results also provided evidence of NO3-N and soluble P transport to subsurface drains via different pathways. Due to differences in NO3-N and soluble P transport through the soil profile (via baseflow and preferential flow, respectively), management approaches taken to reduce one nutrient may exacerbate losses of the other. Further research is needed to address potential changes in field hydrology (and consequently the in-field transport of soluble nutrients) from different types of agricultural best management practices (BMPs) and to evaluate optimal stacking of BMPs to achieve reductions in both NO3-N and soluble P loss. Controlled drainage has a high potential for stacking with other BMPs because it is primarily a physical discharge and load reduction practice. Keywords: Agriculture, Eutrophication, Nutrient transport, Regression analysis, Water quality.

Using artificial intelligence for CyanoHAB niche modeling: discovery and visualization of Microcystis–environmental associations within western Lake Erie

2014 ◽  
Vol 71 (11) ◽  
pp. 1642-1654 ◽  
Author(s):  
David F. Millie ◽  
Gary R. Weckman ◽  
Gary L. Fahnenstiel ◽  
Hunter J. Carrick ◽  
Ehsan Ardjmand ◽  
...  
Keyword(s):  
Chlorophyll A ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Lake Erie ◽  
Three Dimensional ◽  
Response Surfaces ◽  
Ecological Niche Models ◽  
Wind Speeds ◽  
Western Lake ◽  
Western Lake Erie

Cyanobacterial harmful algal blooms (CyanoHABs), mainly composed of the genus Microcystis, occur frequently throughout the Laurentian Great Lakes. We used artificial neural networks (ANNs) involving 31 hydrological and meteorological predictors to model total phytoplankton (as chlorophyll a) and Microcystis biomass from 2009 to 2011 in western Lake Erie. Continuous ANNs provided modeled-measured correspondences (and modeling efficiencies) ranging from 0.87 to 0.97 (0.75 to 0.94) and 0.71 to 0.90 (0.45 to 0.88) for training–cross-validation and test data subsets of chlorophyll a concentrations and Microcystis biovolumes, respectively. Classification ANNs correctly assigned up to 94% of instances for Microcystis presence–absence. The influences of select predictors on phytoplankton and CyanoHAB niches were visualized using biplots and three-dimensional response surfaces. These then were used to generate mathematical expressions for the relationships between modeled CyanoHAB outcomes and the direct and interactive influences of environmental factors. Based on identified conditions (∼40 to 50 μg total phosphorus (TP)·L−1, 22 to 26 °C, and prolonged wind speeds less than ∼19 km·h−1) underlying the likelihood of occurrence and accumulation of phytoplankton and Microcystis, a “target” concentration of 30 μg TP·L−1 appears appropriate for alleviating blooms. ANNs generated robust ecological niche models for Microcystis, providing a predictive framework for quantitative visualization of nonlinear CyanoHAB–environmental interactions.

An Evaluation of Effects of Groundwater Exchange on Nearshore Habitats and Water Quality of Western Lake Erie

2005 ◽  
Vol 31 ◽  
pp. 45-63 ◽  
Author(s):  
Sheridan K. Haack ◽  
Brian P. Neff ◽  
Donald O. Rosenberry ◽  
Jacqueline F. Savino ◽  
Scott C. Lundstrom
Keyword(s):  
Water Quality ◽  
Lake Erie ◽  
Western Lake ◽  
Groundwater Exchange ◽  
Western Lake Erie

scholarly journals Predicting Runoff Chloride Concentrations in Suburban Watersheds Using an Artificial Neural Network (ANN)

Hydrology ◽  
2020 ◽  
Vol 7 (4) ◽  
pp. 80
Author(s):  
Khurshid Jahan ◽  
Soni M. Pradhanang
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Artificial Neural Network ◽  
Sodium Chloride ◽  
Stormwater Runoff ◽  
Quality Data ◽  
Ann Model ◽  
Water Quality Data ◽  
Artificial Neural Network Ann ◽  
Chloride Concentrations

Road salts in stormwater runoff, from both urban and suburban areas, are of concern to many. Chloride-based deicers [i.e., sodium chloride (NaCl), magnesium chloride (MgCl2), and calcium chloride (CaCl2)], dissolve in runoff, travel downstream in the aqueous phase, percolate into soils, and leach into groundwater. In this study, data obtained from stormwater runoff events were used to predict chloride concentrations and seasonal impacts at different sites within a suburban watershed. Water quality data for 42 rainfall events (2016–2019) greater than 12.7 mm (0.5 inches) were used. An artificial neural network (ANN) model was developed, using measured rainfall volume, turbidity, total suspended solids (TSS), dissolved organic carbon (DOC), sodium, chloride, and total nitrate concentrations. Water quality data were trained using the Levenberg-Marquardt back-propagation algorithm. The model was then applied to six different sites. The new ANN model proved accurate in predicting values. This study illustrates that road salt and deicers are the prime cause of high chloride concentrations in runoff during winter and spring, threatening the aquatic environment.

Sign in / Sign up

Export Citation Format

Share Document