Mapping Water Quality Parameters in Urban Rivers from Hyperspectral Images Using a New Self-Adapting Selection of Multiple Artificial Neural Networks

Protection of water environments is an important part of overall environmental protection; hence, many people devote their efforts to monitoring and improving water quality. In this study, a self-adapting selection method of multiple artificial neural networks (ANNs) using hyperspectral remote sensing and ground-measured water quality data is proposed to quantitatively predict water quality parameters, including phosphorus, nitrogen, biochemical oxygen demand (BOD), chemical oxygen demand (COD), and chlorophyll a. Seventy-nine ground measured data samples are used as training data in the establishment of the proposed model, and 30 samples are used as testing data. The proposed method based on traditional ANNs of numerical prediction involves feature selection of bands, self-adapting selection based on multiple selection criteria, stepwise backtracking, and combined weighted correlation. Water quality parameters are estimated with coefficient of determination R2 ranging from 0.93 (phosphorus) to 0.98 (nitrogen), which is higher than the value (0.7 to 0.8) obtained by traditional ANNs. MPAE (mean percent of absolute error) values ranging from 5% to 11% are used rather than root mean square error to evaluate the predicting precision of the proposed model because the magnitude of each water quality parameter considerably differs, thereby providing reasonable and interpretable results. Compared with other ANNs with backpropagation, this study proposes an auto-adapting method assisted by the above-mentioned methods to select the best model with all settings, such as the number of hidden layers, number of neurons in each hidden layer, choice of optimizer, and activation function. Different settings for ANNS with backpropagation are important to improve precision and compatibility for different data. Furthermore, the proposed method is applied to hyperspectral remote sensing images collected using an unmanned aerial vehicle for monitoring the water quality in the Shiqi River, Zhongshan City, Guangdong Province, China. Obtained results indicate the locations of pollution sources.

[1]  Jamil Amanollahi,et al.  Evaluating the accuracy of ANN and LR models to estimate the water quality in Zarivar International Wetland, Iran , 2017, Natural Hazards.

[2]  Paul J. Harrison,et al.  Estimating carbon, nitrogen, protein, and chlorophyll a from volume in marine phytoplankton , 1994 .

[3]  Min Chen,et al.  A Weighted Algorithm Based on Normalized Mutual Information for Estimating the Chlorophyll-a Concentration in Inland Waters Using Geostationary Ocean Color Imager (GOCI) Data , 2015, Remote. Sens..

[4]  Mohamad Javad Alizadeh,et al.  Development of wavelet-ANN models to predict water quality parameters in Hilo Bay, Pacific Ocean. , 2015, Marine pollution bulletin.

[5]  Yebao Wang,et al.  Remote-sensing estimation of dissolved inorganic nitrogen concentration in the Bohai Sea using band combinations derived from MODIS data , 2016 .

[6]  M. Yusoff,et al.  Removal of COD, ammoniacal nitrogen and colour from stabilized landfill leachate by anaerobic organism , 2013, Applied Water Science.

[7]  Katalin Blix,et al.  Developing a New Machine-Learning Algorithm for Estimating Chlorophyll-a Concentration in Optically Complex Waters: A Case Study for High Northern Latitude Waters by Using Sentinel 3 OLCI , 2019, Remote. Sens..

[8]  Qiaozhen Guo,et al.  Study on Retrieval of Chlorophyll-a Concentration Based on Landsat OLI Imagery in the Haihe River, China , 2016 .

[9]  P. Glibert,et al.  Eutrophication, harmful algae and biodiversity - Challenging paradigms in a world of complex nutrient changes. , 2017, Marine pollution bulletin.

[10]  Weichun Ma,et al.  Developing a PCA–ANN Model for Predicting Chlorophyll a Concentration from Field Hyperspectral Measurements in Dianshan Lake, China , 2015, Water Quality, Exposure and Health.

[11]  Ying Cao,et al.  Fractionation and ecological risk of metals in urban river sediments in Zhongshan City, Pearl River Delta. , 2011, Journal of environmental monitoring : JEM.

[12]  Tung-Ching Su,et al.  A study of a matching pixel by pixel (MPP) algorithm to establish an empirical model of water quality mapping, as based on unmanned aerial vehicle (UAV) images , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[13]  Marc M. Van Hulle,et al.  Speeding Up the Wrapper Feature Subset Selection in Regression by Mutual Information Relevance and Redundancy Analysis , 2006, ICANN.

[14]  Naoki Fujii,et al.  Improved MODIS-Aqua Chlorophyll-a Retrievals in the Turbid Semi-Enclosed Ariake Bay, Japan , 2018, Remote. Sens..

[15]  Minoru Okumura,et al.  A simple visual method for the determination of phosphorus in environmental waters , 1987 .

[16]  Dan Olteanu,et al.  F: Regression Models over Factorized Views , 2016, Proc. VLDB Endow..

[17]  Zhigang Cao,et al.  Remote Sensing Estimation of Lake Total Phosphorus Concentration Based on MODIS: A Case Study of Lake Hongze , 2019, Remote. Sens..

[18]  Soonju Yu,et al.  Relationships between water quality parameters in rivers and lakes: BOD5, COD, NBOPs, and TOC , 2016, Environmental Monitoring and Assessment.

[19]  D. J. Gans.  Use of a preliminary test in comparing two sample means , 1981 .

[20]  Kevin Winter,et al.  Remote sensing of cyanobacteria-dominant algal blooms and water quality parameters in Zeekoevlei, a small hypertrophic lake, using MERIS , 2010 .

[21]  K. K. Satpathy,et al.  Heavy metal contamination, major ion chemistry and appraisal of the groundwater status in coastal aquifer, Kalpakkam, Tamil Nadu, India , 2017 .

[22]  M. Wong,et al.  Screening of Organochlorines in Freshwater Fish Collected from the Pearl River Delta, People’s Republic of China , 2004, Archives of environmental contamination and toxicology.

[23]  Alexandre Castagna,et al.  A Review of Protocols for Fiducial Reference Measurements of Downwelling Irradiance for the Validation of Satellite Remote Sensing Data over Water , 2019, Remote. Sens..

[24]  G. Williams,et al.  Evaluating Remote Sensing Model Specification Methods for Estimating Water Quality in Optically Diverse Lakes throughout the Growing Season , 2018, Hydrology.

[25]  K. Ali,et al.  Application of a partial least-squares regression model to retrieve chlorophyll-a concentrations in coastal waters using hyper-spectral data , 2016, Ocean Science Journal.

[26]  Fi-John Chang,et al.  Modeling water quality in an urban river using hydrological factors--data driven approaches. , 2015, Journal of environmental management.

[27]  Mohamad Awad,et al.  Sea water chlorophyll-a estimation using hyperspectral images and supervised Artificial Neural Network , 2014, Ecol. Informatics.

[28]  Shiv O. Prasher,et al.  DISCRIMINANT ANALYSIS OF HYPERSPECTRAL DATA FOR ASSESSING WATER AND NITROGEN STRESSES IN CORN , 2005 .

[29]  Xingyuan Song,et al.  Empirical Estimation of Total Nitrogen and Total Phosphorus Concentration of Urban Water Bodies in China Using High Resolution IKONOS Multispectral Imagery , 2015 .

[30]  I. Chaubey,et al.  Using hyperspectral data to quantify water-quality parameters in the Wabash River and its tributaries, Indiana , 2015 .

[31]  Francis Gohin,et al.  Annual cycles of chlorophyll- a , non-algal suspended particulate matter, and turbidity observed from space and in-situ in coastal waters , 2011 .

[32]  Marian Crudu,et al.  Adsorption Decolorization Technique of Textile/Leather - Dye Containing Effluents , 2016 .

[33]  Qiu Liping,et al.  Modified DAT/IAT Process for Removal of Ammonia Nitrogen from Domestic Sewage , 2008, 2008 2nd International Conference on Bioinformatics and Biomedical Engineering.

[34]  James F. Bramante,et al.  Optimization of a Semi-Analytical Algorithm for Multi-Temporal Water Quality Monitoring in Inland Waters with Wide Natural Variability , 2015, Remote. Sens..

[35]  Adel Shalaby,et al.  Evaluation of Mariut Lake water quality using Hyperspectral Remote Sensing and laboratory works , 2017 .

[36]  E. J. Wilson,et al.  Excess nitrogen deposition: issues for consideration. , 1988, Environmental pollution.

[37]  J. Burkholder,et al.  Harmful algal blooms and eutrophication: Nutrient sources, composition, and consequences , 2002 .

[38]  Van Pham Dang Tri,et al.  Remote Sensing for Monitoring Surface Water Quality in the Vietnamese Mekong Delta: The Application for Estimating Chemical Oxygen Demand in River Reaches in Binh Dai, Ben Tre , 2017 .

[39]  A. Boukabache,et al.  Methods for assessing biochemical oxygen demand (BOD): a review. , 2014, Water research.

[40]  Xinyan Fan,et al.  Retrieval of Chlorophyll-a and Total Suspended Solids Using Iterative Stepwise Elimination Partial Least Squares (ISE-PLS) Regression Based on Field Hyperspectral Measurements in Irrigation Ponds in Higashihiroshima, Japan , 2017, Remote. Sens..

[41]  S. C. Liewa,et al.  Monitoring water quality in Singapore reservoirs with hyperspectral remote sensing technology , 2019 .

[42]  Hiroshi Kobayashi,et al.  Multi-Algorithm Indices and Look-Up Table for Chlorophyll-a Retrieval in Highly Turbid Water Bodies Using Multispectral Data , 2017, Remote. Sens..

[43]  Ritula Thakur,et al.  Analysis of water quality parameters by hyperspectral imaging in Ganges River , 2018, Spatial Information Research.

[44]  Kaishan Song,et al.  Hyperspectral Remote Sensing of Total Phosphorus (TP) in Three Central Indiana Water Supply Reservoirs , 2012, Water, Air, & Soil Pollution.

[45]  S. Carpenter,et al.  Human Impact on Erodable Phosphorus and Eutrophication: A Global Perspective , 2001 .

[46]  Anatoly A. Gitelson,et al.  The peak near 700 nm on radiance spectra of algae and water: relationships of its magnitude and position with chlorophyll concentration , 1992 .

[47]  Chuiqing Zeng,et al.  The impacts of environmental variables on water reflectance measured using a lightweight unmanned aerial vehicle (UAV)-based spectrometer system , 2017 .

[48]  Lin Wang,et al.  Optimizing echo state network with backtracking search optimization algorithm for time series forecasting , 2019, Eng. Appl. Artif. Intell..

[49]  Suresh Sharma,et al.  Characterization of Temporal and Spatial Variability of Phosphorus Loading to Lake Erie from the Western Basin Using Wavelet Transform Methods , 2018, Hydrology.

[50]  Guoxia Zhang,et al.  Brachybacterium zhongshanense sp. nov., a cellulose-decomposing bacterium from sediment along the Qijiang River, Zhongshan City, China. , 2007, International journal of systematic and evolutionary microbiology.

[51]  Walter K. Dodds,et al.  Nitrogen, phosphorus, and eutrophication in streams , 2016 .

[52]  Vassiliki Markogianni,et al.  An Appraisal of the Potential of Landsat 8 in Estimating Chlorophyll-a, Ammonium Concentrations and Other Water Quality Indicators , 2018, Remote. Sens..

[53]  Salah Bourennane,et al.  Hyperspectral Image Classification Based on Parameter-Optimized 3D-CNNs Combined with Transfer Learning and Virtual Samples , 2018, Remote. Sens..

[54]  Christos S. Akratos,et al.  An artificial neural network model and design equations for BOD and COD removal prediction in horizontal subsurface flow constructed wetlands , 2008 .

[55]  Zhou Wang,et al.  Monitoring of Urban Black-Odor Water Based on Nemerow Index and Gradient Boosting Decision Tree Regression Using UAV-Borne Hyperspectral Imagery , 2019, Remote. Sens..

[56]  Josef Hejzlar,et al.  Determination of low chemical oxygen demand values in water by the dichromate semi-micro method , 1990 .

[57]  Leonardo Campos Inocencio,et al.  An Alternative Method of Spatial Autocorrelation for Chlorophyll Detection in Water Bodies Using Remote Sensing , 2017 .

[58]  Oliver Zielinski,et al.  SmartFluo: A Method and Affordable Adapter to Measure Chlorophyll a Fluorescence with Smartphones , 2017, Sensors.

[59]  Richard H. Wendt,et al.  The impact of detergent phosphorus bans on receiving water quality , 1984 .

[60]  Shie-Yui Liong,et al.  An ANN application for water quality forecasting. , 2008, Marine pollution bulletin.

[61]  Zhihao Qin,et al.  Estimating crop chlorophyll content with hyperspectral vegetation indices and the hybrid inversion method , 2016 .

[62]  Kuo-Pei Tsai,et al.  Management of Target Algae by Using Copper-Based Algaecides: Effects of Algal Cell Density and Sensitivity to Copper , 2016, Water, Air, & Soil Pollution.

[63]  Luis Deban,et al.  Assessment of seasonal and polluting effects on the quality of river water by exploratory data analysis , 1998 .

[64]  Daniele Riccio,et al.  REMOTE SENSING MONITORING , 2013 .

[65]  Emanuela Gobbi,et al.  Prediction of milled maize fumonisin contamination by multispectral image analysis. , 2010 .

[66]  Ridhi Saluja,et al.  Characterization and modeling of bio-optical properties of water in a lentic ecosystem using in-situ hyperspectral remote sensing , 2016, Asia-Pacific Remote Sensing.

[67]  Jennifer A. Scott,et al.  Preconditioning of Linear Least Squares by Robust Incomplete Factorization for Implicitly Held Normal Equations , 2016, SIAM J. Sci. Comput..

[68]  Sanghyun Park,et al.  Optimizing Semi-Analytical Algorithms for Estimating Chlorophyll-a and Phycocyanin Concentrations in Inland Waters in Korea , 2017, Remote. Sens..