Prediction of algal bloom occurrence based on the naive Bayesian model considering satellite image pixel differences

Abstract Bloom occurrence probability prediction is a critical issue for freshwater resource management and protection. As the mechanism of algal blooms is not understood, the construction of prediction model mainly depends on statistical data. Therefore, knowledge on prior bloom occurrence derived from statistical data plays a significant role in establishing a prediction model. In this study, a naive Bayesian model incorporating prior information was constructed to predict algal bloom occurrence probabilities 1–7 days in advance under different weather conditions in Dianchi Lake. The proposed model utilised the following data from the MODIS images, the floating algae index (FAI) for the previous 7 days and five meteorological variables (mean wind speed, air pressure, relative humidity on the prediction day, accumulated sunshine hours in the previous 3 days, and accumulated air temperature in the previous 7 days). The prior probabilities of each pixel were calculated on a monthly timescale to highlight the bloom’s temporal-spatial differences, and the 1–7 day posterior probabilities were calculated by combining the prior and conditional probabilities. The predictive effect was tested by the area under the receiver-operating characteristic curve (AUC), and the results showed the number of pixels with estimation predictions classified as ‘Good+’ and ‘Excellent’ were 91.3%, 91.4%, 82.7%, 83.3%, 89.0%, 86.6%, and 90.0% for the predictions on days 1–7, respectively. Additionally, the independent validation datasets showed that the percentage of correctly classified instances (CCI%) of approximately 90% of the pixels were greater than 50%. The proposed algal bloom prediction model based on the naive Bayesian method has pixel-level prediction abilities, is applicable to other inland water systems, and can provide a reference for water environment risk forecasting and management.

[1]  Kenji Mizuguchi,et al.  Applying the Naïve Bayes classifier with kernel density estimation to the prediction of protein-protein interaction sites , 2010, Bioinform..

[2]  Liangxiao Jiang,et al.  Improving Tree augmented Naive Bayes for class probability estimation , 2012, Knowl. Based Syst..

[3]  Min Zhang,et al.  Contributions of meteorology to the phenology of cyanobacterial blooms: implications for future climate change. , 2012, Water research.

[4]  Mati Kahru,et al.  Cyanobacterial blooms cause heating of the sea surface , 1993 .

[5]  A. Michalak,et al.  Using Landsat to extend the historical record of lacustrine phytoplankton blooms: A Lake Erie case study , 2017 .

[6]  Naftali Tishby,et al.  Margin based feature selection - theory and algorithms , 2004, ICML.

[7]  Ying Xu,et al.  Stricter nutrient criteria are required to mitigate the impact of climate change on harmful cyanobacterial blooms , 2019, Journal of Hydrology.

[8]  James S. Clark,et al.  Tree growth inference and prediction from diameter censuses and ring widths. , 2007, Ecological applications : a publication of the Ecological Society of America.

[9]  J. Brookes,et al.  The influence of changes in wind patterns on the areal extension of surface cyanobacterial blooms in a large shallow lake in China. , 2015, The Science of the total environment.

[10]  Casey Brown,et al.  Climate informed flood frequency analysis and prediction in Montana using hierarchical Bayesian modeling , 2008 .

[11]  C. Stow,et al.  Using a Bayesian hierarchical model to improve Lake Erie cyanobacteria bloom forecasts , 2014 .

[12]  B. Efron Bayes' Theorem in the 21st Century , 2013, Science.

[13]  Srinivas Murali,et al.  A Bayesian Model to Predict Survival After Left Ventricular Assist Device Implantation. , 2018, JACC. Heart failure.

[14]  D. A. Suriamihardja,et al.  Sediment Texture and Topography Features Control on Coastal Morphodynamics State , 2017 .

[15]  Chuanqing Wu,et al.  Long-term observation of cyanobacteria blooms using multi-source satellite images: a case study on a cloudy and rainy lake , 2019, Environmental Science and Pollution Research.

[16]  Gregory L Boyer,et al.  Health impacts from cyanobacteria harmful algae blooms: Implications for the North American Great Lakes. , 2016, Harmful algae.

[17]  C. Robert,et al.  Bayesian Modeling Using WinBUGS , 2009 .

[18]  H. Paerl,et al.  Adaptation to High-Intensity, Low-Wavelength Light among Surface Blooms of the Cyanobacterium Microcystis aeruginosa , 1985, Applied and environmental microbiology.

[19]  J C Ho,et al.  Widespread global increase in intense lake phytoplankton blooms since the 1980s , 2019, Nature.

[20]  I Nyoman Arnawan,et al.  Implementation of Data Mining To Predict Period of Students Study Using Naive Bayes Algorithm , 2017 .

[21]  Marcin Woźniak,et al.  Risk Assessment of Hypertension in Steel Workers Based on LVQ and Fisher-SVM Deep Excavation , 2019, IEEE Access.

[22]  R. Stone Ecology. China aims to turn tide against toxic lake pollution. , 2011, Science.

[23]  Shaohua Lei,et al.  Quantifying Spatiotemporal Dynamics of the Column-Integrated Algal Biomass in Nonbloom Conditions Based on OLCI Data: A Case Study of Lake Dianchi, China , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[24]  H. Paerl,et al.  Blooms Like It Hot , 2008, Science.

[25]  Chuanmin Hu A novel ocean color index to detect floating algae in the global oceans , 2009 .

[26]  Richard P. Stumpf,et al.  Forecasting annual cyanobacterial bloom biomass to inform management decisions in Lake Erie , 2016 .

[27]  Lei Wang,et al.  A Novel Probability Model for LncRNA–Disease Association Prediction Based on the Naïve Bayesian Classifier , 2018, Genes.

[28]  Richard P. Stumpf,et al.  Interannual Variability of Cyanobacterial Blooms in Lake Erie , 2012, PloS one.

[29]  Xiaohan Liu,et al.  Long-term remote monitoring of total suspended matter concentration in Lake Taihu using 250 m MODIS-Aqua data , 2015 .

[30]  E. Berdalet,et al.  Harmful Algal Blooms : A scientific summary for policy makers , 2015 .

[31]  Sangmok Lee,et al.  Improved Prediction of Harmful Algal Blooms in Four Major South Korea’s Rivers Using Deep Learning Models , 2018, International journal of environmental research and public health.

[32]  F. Ricci,et al.  A model predicting the PSP toxic dinoflagellate Alexandrium minutum occurrence in the coastal waters of the NW Adriatic Sea , 2019, Scientific Reports.

[33]  J. K. Moore,et al.  Wind speed influence on phytoplankton bloom dynamics in the Southern Ocean Marginal Ice Zone , 2007 .

[34]  E. Rantajärvi,et al.  Effect of sampling frequency on detection of natural variability in phytoplankton: unattended high-frequency measurements on board ferries in the Baltic Sea , 1998 .

[35]  Wei Chen,et al.  Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and naïve Bayes tree for landslide susceptibility modeling. , 2018, The Science of the total environment.

[36]  Xavier Robin,et al.  pROC: an open-source package for R and S+ to analyze and compare ROC curves , 2011, BMC Bioinformatics.

[37]  Ronghua Ma,et al.  Moderate Resolution Imaging Spectroradiometer (MODIS) observations of cyanobacteria blooms in Taihu Lake, China , 2010 .

[38]  Anas Ghadouani,et al.  Effects of rainfall patterns on toxic cyanobacterial blooms in a changing climate: between simplistic scenarios and complex dynamics. , 2012, Water research.

[39]  Wen Long,et al.  Ecological forecasting in Chesapeake Bay: Using a mechanistic-empirical modeling approach , 2013 .

[40]  Ali Dag,et al.  Predicting graft survival among kidney transplant recipients: A Bayesian decision support model , 2018, Decis. Support Syst..

[41]  S. S. F. Zmnako,et al.  Reliability and validity of a Central Kurdish version of the Dizziness Handicap Inventory , 2019, Scientific Reports.

[42]  Racha Elkadiri,et al.  Mapping and Forecasting Onsets of Harmful Algal Blooms Using MODIS Data over Coastal Waters Surrounding Charlotte County, Florida , 2018, Remote. Sens..

[43]  Xiaohan Liu,et al.  Long-term MODIS observations of cyanobacterial dynamics in Lake Taihu: Responses to nutrient enrichment and meteorological factors , 2017, Scientific Reports.

[44]  K. Chatziioannou,et al.  Impact of Bayesian Priors on the Characterization of Binary Black Hole Coalescences. , 2017, Physical review letters.

[45]  J. Tollefson Ocean scientists work to forecast huge plankton blooms in Arabian Sea. , 2018 .

[46]  J. Landsberg,et al.  The Effects of Harmful Algal Blooms on Aquatic Organisms , 2002 .

[47]  Vivek Narayanan,et al.  Fast and Accurate Sentiment Classification Using an Enhanced Naive Bayes Model , 2013, IDEAL.

[48]  Changchun Huang,et al.  Satellite data regarding the eutrophication response to human activities in the plateau lake Dianchi in China from 1974 to 2009. , 2014, The Science of the total environment.

[49]  E. Berdalet,et al.  Global Ecology and Oceanography of Harmful Algal Blooms, GEOHAB Core Research Project: HABs in Benthic Systems , 2012 .

[50]  S. Watson,et al.  A Bayesian risk assessment framework for microcystin violations of drinking water and recreational standards in the Bay of Quinte, Lake Ontario, Canada. , 2019, Water research.

[51]  T. Platt,et al.  Development of a conceptual warning system for toxic levels of Alexandrium fundyense in the Bay of Fundy based on remote sensing data , 2018, Remote Sensing of Environment.

[52]  S. Acosta-Jurado,et al.  Transcriptomic Studies of the Effect of nod Gene-Inducing Molecules in Rhizobia: Different Weapons, One Purpose , 2017, Genes.

[53]  Cayelan C Carey,et al.  Resilience to Blooms , 2011, Science.

[54]  Min Zhang,et al.  Nutrient reduction magnifies the impact of extreme weather on cyanobacterial bloom formation in large shallow Lake Taihu (China). , 2016, Water research.

[55]  David B. Dunson,et al.  Bayesian Data Analysis , 2010 .

[56]  Djoerd Hiemstra,et al.  The Importance of Prior Probabilities for Entry Page Search , 2002, SIGIR '02.

[57]  Jennifer P. Cannizzaro,et al.  Remote detection of cyanobacteria blooms in an optically shallow subtropical lagoonal estuary using MODIS data , 2019, Remote Sensing of Environment.

[58]  Junjie Liu,et al.  Meteorological and hydrological conditions driving the formation and disappearance of black blooms, an ecological disaster phenomena of eutrophication and algal blooms. , 2016, The Science of the total environment.

[59]  Hui Liu,et al.  Analysis of cyanobacteria bloom in the Waihai part of Dianchi Lake, China , 2012, Ecol. Informatics.

[60]  J. Leppänen,et al.  The influence of weather conditions (temperature and wind) on cyanobacterial bloom development in the Gulf of Finland (Baltic Sea) , 2003 .

[61]  Fitriana Harahap,et al.  Implementation of Naïve Bayes Classification Method for Predicting Purchase , 2018, 2018 6th International Conference on Cyber and IT Service Management (CITSM).

[62]  J. Tollefson Ocean scientists work to forecast huge plankton blooms in Arabian Sea , 2018, Nature.

[63]  R. O’Brien,et al.  A Caution Regarding Rules of Thumb for Variance Inflation Factors , 2007 .

[64]  Min Zhang,et al.  Fourteen-Year Record (2000-2013) of the Spatial and Temporal Dynamics of Floating Algae Blooms in Lake Chaohu, Observed from Time Series of MODIS Images , 2015, Remote. Sens..