Neural net modeling of estuarine indicators: Hindcasting phytoplankton biomass and net ecosystem production in the Neuse (North Carolina) and Trout (Florida) Rivers, USA

Millie, David F.; Weckman, Gary R.; Paerl, Hans W.; Pinckney, James L.; Bendis, Brian J.; Pigg, Ryan J.; Fahnenstiel, Gary L.

doi:10.1016/j.ecolind.2005.08.021

Cited by 18 publications

(37 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Measured:modeled correspondences for regression models were less than that for comparable ANNs, indicating that networks outperformed linear models (data not shown). This greater performance was anticipated; in theory, an ANN encompasses linear regression and because of a model architecture suited for identifying the nonlinear complexities of a biotic response to environmental forcing, should perform as well or better than regression models (Gonzalez 2000;Millie et al 2006bMillie et al , 2012. However, multicollinearity existed among the independent variables, and the predictor-response surfaces and biplots arising from the ANNs depicted interacting, nonlinear predictor influences.…”

Section: Discussionmentioning

confidence: 92%

“…Predictive performances for test data were slightly less; modeled values generally underestimated concentrations greater than 45 g CHL a·L −1 and over-or underestimated biovolumes less than 10 8 m 3 ·L −1 , whereas the correct assignment for instances in which biovolumes were absent declined substantially. These decreases in prediction performances likely arose from inadequate data representation within training subsets, thereby precluding optimal model development (e.g., Millie et al 2006b). Instances of <ϳ45 g CHL a·L −1 and >10 8 m 3 Microcystis·L -1 were 4.3-and 1.7-fold greater, respectively, in the database than instances of greater and lesser concentrations or biovolumes, respectively.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Millie

Weckman

Fahnenstiel

et al. 2014

Can. J. Fish. Aquat. Sci.

View full text Add to dashboard Cite

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 presenceabsence. The influences of select predictors on phytoplankton and CyanoHAB niches were visualized using biplots and threedimensional 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 (ϳ40 to 50 g total phosphorus (TP)·L −1 , 22 to 26°C, and prolonged wind speeds less than ϳ19 km·h −1 ) underlying the likelihood of occurrence and accumulation of phytoplankton and Microcystis, a "target" concentration of 30 g 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. Résumé: Les fleurs d'eau de cyanobactéries nuisibles (CyanoHAB), constituées principalement du genre Microcystis, sont fréquentes dans tous les Grands Lacs laurentiens. Nous avons utilisé des réseaux neuronaux artificiels (« ANNs ») incluant 31 prédicteurs hydrologiques et météorologiques pour modéliser la biomasse de phytoplancton totale (chlorophylle a) et de Microcystis, de 2009 à 2011, dans la partie occidentale du lac Érié. Des ANNs continus ont fourni des correspondances modèle-mesures (et des valeurs d'efficacité de la modélisation) allant de 0,87 à 0,97 (0,75 à 0,94) et de 0,71 à 0,90 (0,45 à 0,88) pour des sous-ensembles de données d'entraînement-de contrevalidation et d'essai des concentrations de la chlorophylle a et des biovolumes de Microcystis, respectivement. Les ANNs de classification ont affecté correctement jusqu'à 94 % des cas d'absence ou de présence de Microcystis. Les influences de prédicteurs sélectionnés sur les niches de phytoplancton et de CyanoHAB ont été visualisées à l'aide de diagrammes de double projection et de surfaces de réponse tridimensionnelles, qui ont ensuite été utilisés pour produire des expressions mathématiques pour les relations entre les CyanoHAB modélisées et les influences directes et interactives de facteurs environnementaux. À la lumière des conditions cernées (ϳ40 à 50 g phosphore total (PT)·L −1 , de 22 à 26°C et des vitesses du vent soutenues inférieures à ϳ19 km·h −1 ) sous-tendant la probabilité de présence et d'accumulation de phytoplancto...

show abstract

Section: Discussionmentioning

confidence: 92%

Section: Discussionmentioning

confidence: 99%

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

Millie

Weckman

Fahnenstiel

et al. 2014

Can. J. Fish. Aquat. Sci.

View full text Add to dashboard Cite

show abstract

“…The disadvantages of ANNs include (i) being computationally intensive, (ii) parameters must be determined with few guidelines, (iii) no standard procedure to define architecture, (iv) no global method for determining when to stop training and prevent overtraining, (v) sensitivity to the composition of the training data set and initial network parameters and (vi) they can be used as "black boxes" requiring no understanding of processes or relationships that are occurring (Millie et al, 2006;Ozesmi et al, 2006). However, many of these disadvantages (Ozesmi et al, 2006) can be addressed by (i) understanding the relevance of the input variables, (ii) using techniques (e.g.…”

Section: Discussionmentioning

confidence: 99%

“…ANNs are non-parametric models that reproduce correlated patterns between variables through repetitive data processing (i.e. learning) (Millie et al, 2006). ANNs have been applied within the disciplines of water engineering and ecological sciences for the varied purposes of classification of catchment characteristics, function approximation, optimisation of modelling parameters and prediction of environmental variables (Chen et al, 2008;Palani et al, 2008).…”

Section: Introductionmentioning

confidence: 99%

Proactive management of estuarine algal blooms using an automated monitoring buoy coupled with an artificial neural network

Coad¹,

Cathers

Ball

et al. 2014

Environmental Modelling & Software

View full text Add to dashboard Cite

“…Therefore, these models are more accepted by decision makers because they offer a transparency that ANNs do not provide. However, ANNs have historically outperformed their regressive counterparts in many forms of science and engineering including: physical [1], chemical [2], communication [3], financial [4], and ecological [5] systems.…”

Section: Introductionmentioning

confidence: 99%

Using a heuristic approach to derive a grey-box model through an artificial neural network knowledge extraction technique

Young

Weckman

2009

Neural Comput & Applic

View full text Add to dashboard Cite

Artificial neural networks (ANNs) are primarily used in academia for their ability to model complex nonlinear systems. Though ANNs have been used to solve practical problems in industry, they are not typically used in nonacademic environments because they are not very well understood, complicated to implement, or have the reputation of being a ''black-box'' model. Few mathematical models exist that outperform ANNs. If a highly accurate model can be constructed, the knowledge should be used to understand and explain relationships in a system. Output surfaces can be analyzed in order to gain additional knowledge about a system being modeled. This paper presents a systematic approach to derive a ''grey-box'' model from the knowledge obtained from the ANN. A database for an automobile's gas mileage performance is used as a case study for the proposed methodology. The results show a greater ability to generalize system behavior than other benchmarked methods.

show abstract

Neural net modeling of estuarine indicators: Hindcasting phytoplankton biomass and net ecosystem production in the Neuse (North Carolina) and Trout (Florida) Rivers, USA

Cited by 18 publications

References 74 publications

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

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

Proactive management of estuarine algal blooms using an automated monitoring buoy coupled with an artificial neural network

Using a heuristic approach to derive a grey-box model through an artificial neural network knowledge extraction technique

Contact Info

Product

Resources

About