Modeling algal atypical proliferation in La Barca reservoir using L-SHADE optimized gradient boosted regression trees: a case study

Algal atypical proliferation is a consequence of water fertilization (also called eutrophication) and a worldwide environmental concern since water quality and its uses are seriously compromised. Prevention is the most effective measure given that once the algal proliferation starts, it is too difficult and costly to stop the process. This article presents a nonparametric machine learning algorithm that combines the gradient boosted regression tree (GBRT) model and an improved differential evolution algorithm (L-SHADE) for better understanding and control of the algal abnormal proliferation (usually estimated from Chlorophyll-a and Total Phosphorus concentrations) from physicochemical and biological variable values obtained in a northern Spain reservoir. This L-SHADE technique involves the optimization of the GBRT hyperparameters during the training process. Apart from successfully estimating algal atypical growth (coefficients of determination equal to 0.91 and 0.93 for Chlorophyll-a and Total Phosphorus concentrations were obtained, respectively), this hybrid model allows here to establish the ranking of each independent biological and physicochemical variable according to its importance in the algal enhanced growth.

[1]  Ana Villa,et al.  Determining suspended solids and total phosphorus from turbidity: comparison of high-frequency sampling with conventional monitoring methods , 2019, Environmental Monitoring and Assessment.

[2]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[3]  Jürg Bloesch,et al.  Eutrophication of Lake Tasaul, Romania—proposals for rehabilitation , 2009, Environmental science and pollution research international.

[4]  Mingyue Ding,et al.  Gradient boosting for single image super-resolution , 2018, Inf. Sci..

[5]  Dimitra Kitsiou,et al.  Coastal marine eutrophication assessment: a review on data analysis. , 2011, Environment international.

[6]  George Tsirtsis,et al.  Ecological quality scales based on phytoplankton for the implementation of Water Framework Directive in the Eastern Mediterranean , 2010 .

[7]  R. Dennis Cook,et al.  Cross-Validation of Regression Models , 1984 .

[8]  D. Correll,et al.  Phosphorus: a rate limiting nutrient in surface waters. , 1999, Poultry science.

[9]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[10]  M. Puig,et al.  Intracellular and dissolved microcystin in reservoirs of the river Segura basin, Murcia, SE Spain. , 2005, Toxicon : official journal of the International Society on Toxinology.

[11]  C. Reynolds.  The Ecology of Phytoplankton , 2006 .

[12]  P. Leavitt,et al.  Unabated nitrogen pollution favours growth of toxic cyanobacteria over chlorophytes in most hypereutrophic lakes. , 2020, Environmental science & technology.

[13]  A. Redden,et al.  Effects of increases in salinity on phytoplankton in the Broadwater of the Myall Lakes, NSW, Australia , 2008, Hydrobiologia.

[14]  Guohua Wu,et al.  Differential evolution with multi-population based ensemble of mutation strategies , 2016, Inf. Sci..

[15]  Sheng-rui Wang,et al.  Effects of dissolved oxygen supply level on phosphorus release from lake sediments , 2008 .

[16]  Henrik Madsen,et al.  Multi-site solar power forecasting using gradient boosted regression trees , 2017 .

[17]  James J. Roberts,et al.  Seasonal and interannual effects of hypoxia on fish habitat quality in central Lake Erie , 2011 .

[18]  Ángel Borja,et al.  Assessing the environmental quality status in estuarine and coastal systems: Comparing methodologies and indices , 2008 .

[19]  David W. Schindler,et al.  Eutrophication of lakes cannot be controlled by reducing nitrogen input: Results of a 37-year whole-ecosystem experiment , 2008, Proceedings of the National Academy of Sciences.

[20]  R. Steedman,et al.  Changes in phytoplankton communities following logging in the drainage basins of three boreal forest lakes in northwestern Ontario (Canada), 1991-2000 , 2003 .

[21]  Yuling Huang,et al.  Variation of Dissolved Oxygen in the Experiments of Occurrence & Disappearance for Microcystis Bloom☆ , 2013 .

[22]  R. D. Grundy,et al.  Strategies for control of man-made eutrophication , 1971 .

[23]  Yan Dong,et al.  Road surface temperature prediction based on gradient extreme learning machine boosting , 2018, Comput. Ind..

[24]  J. Friedman.  Stochastic gradient boosting , 2002 .

[25]  Zongxue Xu,et al.  Prediction of algal blooming using EFDC model: Case study in the Daoxiang Lake , 2011 .

[27]  D. Bronk,et al.  DON as a source of bioavailable nitrogen for phytoplankton , 2006 .

[28]  Sang Won Yoon,et al.  A dynamic gradient boosting machine using genetic optimizer for practical breast cancer prognosis , 2019, Expert Syst. Appl..

[29]  Souhaib Ben Taieb,et al.  A gradient boosting approach to the Kaggle load forecasting competition , 2014 .

[30]  David J. Barnes,et al.  Introduction to Modeling for Biosciences , 2010 .

[31]  D. Sano,et al.  Surface-retained organic matter of Microcystis aeruginosa inhibiting coagulation with polyaluminum chloride in drinking water treatment. , 2010, Water research.

[32]  E. Doğan,et al.  Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique. , 2009, Journal of environmental management.

[33]  V. W. Lambou,et al.  Chlorophyll, Phosphorus, Secchi Disk, and Trophic State , 1982 .

[34]  Milan Stehlík,et al.  Missing chaos in global climate change data interpreting , 2016 .

[35]  Iztok Fister,et al.  Adaptation and Hybridization in Nature-Inspired Algorithms , 2015 .

[36]  P. Rocca,et al.  Differential Evolution as Applied to Electromagnetics , 2011, IEEE Antennas and Propagation Magazine.

[37]  Gregory Dobler,et al.  Patterns of waste generation: A gradient boosting model for short-term waste prediction in New York City. , 2017, Waste management.

[38]  Jun Yang,et al.  Extreme gradient boosting model to estimate PM2.5 concentrations with missing-filled satellite data in China , 2019, Atmospheric Environment.

[39]  Ingrid Chorus and Jamie Bartram,et al.  Toxic Cyanobacteria in Water , 2022 .

[40]  S. Fields.  Global Nitrogen: Cycling out of Control , 2004, Environmental health perspectives.

[41]  K. Schilling,et al.  Use of water quality surrogates to estimate total phosphorus concentrations in Iowa rivers , 2017 .

[42]  M. Bauer,et al.  Landsat-based Remote Sensing of Lake Water Quality Characteristics, Including Chlorophyll and Colored Dissolved Organic Matter (CDOM) , 2005 .

[43]  Mark Landry,et al.  Probabilistic gradient boosting machines for GEFCom2014 wind forecasting , 2016 .

[44]  Vinay Kumar Gadi,et al.  Spatial and temporal variation of hydraulic conductivity and vegetation growth in green infrastructures using infiltrometer and visual technique , 2017 .

[45]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[46]  Christian Pierdzioch,et al.  Predicting Recessions With Boosted Regression Trees , 2017 .

[47]  I. Marasović,et al.  Eutrophication influence on phytoplankton community composition in three bays on the eastern Adriatic coast , 2016 .

[48]  V. Smith,et al.  Low Nitrogen to Phosphorus Ratios Favor Dominance by Blue-Green Algae in Lake Phytoplankton , 1983, Science.

[49]  D. Findlay,et al.  Responses of Diatom and Chrysophyte Assemblages in Lake 227 Sediments to Experimental Eutrophication , 1994 .

[50]  Patrick L. Brezonik,et al.  Effect of Organic Color and Turbidity of Secchi Disk Transparency , 1978 .

[51]  P. N. Suganthan,et al.  Differential Evolution Algorithm With Strategy Adaptation for Global Numerical Optimization , 2009, IEEE Transactions on Evolutionary Computation.

[52]  Lionel Ho,et al.  Elucidating the factors influencing the biodegradation of cylindrospermopsin in drinking water sources , 2008, Environmental toxicology.

[53]  J. C. Vega,et al.  Phytoplankton structure and dynamics in Lake Sanabria and Valparaíso reservoir (NW Spain) , 2000, Hydrobiologia.

[54]  M. Futter,et al.  An evaluation of high frequency turbidity as a proxy for riverine total phosphorus concentrations. , 2019, The Science of the total environment.

[55]  H. Paerl,et al.  Evidence for the Importance of Atmospheric Nitrogen Deposition to Eutrophic Lake Dianchi, China. , 2017, Environmental science & technology.

[56]  A. Landis,et al.  Eutrophication potential of food consumption patterns. , 2010, Environmental science & technology.

[57]  R. Peters.  Predictive Model of the Effects on Lake Metabolism of Decreased Airborne Litterfall through Riparian Deforestation , 1995 .

[58]  Helmut Hillebrand,et al.  BIOVOLUME CALCULATION FOR PELAGIC AND BENTHIC MICROALGAE , 1999 .

[59]  Lucien Hoffmann,et al.  Distribution of Hepatotoxic Cyanobacterial Blooms in Belgium and Luxembourg , 2005, Hydrobiologia.

[60]  C. Pérez-Martínez,et al.  Temporal occurrence of Ceratium hirundinella in Spanish reservoirs , 2001, Hydrobiologia.

[61]  R. Rosenberg,et al.  Introduction to Environmental and Economic Consequences of Hypoxia , 2011 .

[62]  M. Teixeira,et al.  Comparing dissolved air flotation and conventional sedimentation to remove cyanobacterial cells of Microcystis aeruginosa: Part I: The key operating conditions , 2006 .

[63]  A. Malik,et al.  Artificial neural network modeling of the river water quality—A case study , 2009 .

[64]  Stephen R Carpenter,et al.  Reducing Phosphorus to Curb Lake Eutrophication is a Success. , 2016, Environmental science & technology.

[65]  Hongjuan Wu,et al.  Effects of nitrogen and phosphorus on phytoplankton composition and biomass in 15 subtropical, urban shallow lakes in Wuhan, China , 2011 .

[66]  Yong Liu,et al.  Ecological–economic modeling as a tool for watershed management: A case study of Lake Qionghai watershed, China , 2008 .

[67]  Arthur C. Sanderson,et al.  JADE: Adaptive Differential Evolution With Optional External Archive , 2009, IEEE Transactions on Evolutionary Computation.

[68]  Antonio Quesada,et al.  Toxicity of Aphanizomenon ovalisporum (Cyanobacteria) in a Spanish water reservoir , 2006 .