Retrieval of Total Phosphorus Concentration in the Surface Water of Miyun Reservoir Based on Remote Sensing Data and Machine Learning Algorithms

Some essential water conservation areas in China have continuously suffered from various serious problems such as water pollution and water quality deterioration in recent decades and thus called for real-time water pollution monitoring system underwater resources management. On the basis of the remote sensing data and ground monitoring data, this study firstly constructed a more accurate retrieval model for total phosphorus (TP) concentration by comparing 12 machine learning algorithms, including support vector machine (SVM), artificial neural network (ANN), Bayesian ridge regression (BRR), lasso regression (Lasso), elastic net (EN), linear regression (LR), decision tree regressor (DTR), K neighbor regressor (KNR), random forest regressor (RFR), extra trees regressor (ETR), AdaBoost regressor (ABR) and gradient boosting regressor (GBR). Then, this study applied the constructed retrieval model to explore the spatial-temporal evolution of the Miyun Reservoir and finally assessed the water quality. The results showed that the model of TP concentration built by the ETR algorithm had the best accuracy, with the coefficient R2 reaching over 85% and the mean absolute error lower than 0.000433. The TP concentration in Miyun Reservoir was between 0.0380 and 0.1298 mg/L, and there was relatively significant spatial and temporal heterogeneity. It changed remarkably during the periods of the flood season, winter tillage, planting, and regreening, and it was lower in summer than in other seasons. Moreover, the TP in the southwest part of the reservoir was generally lower than in the northeast, as there was less human activities interference. According to the Environmental Quality Standard for the surface water environment, the water quality of Miyun Reservoir was overall safe, except only for an over-standard case occurrence in the spring and September. These conclusions can provide a significant scientific reference for water quality monitoring and management in Miyun Reservoir.

[1]  Zhongfeng Qiu,et al.  Detection of Total Phosphorus Concentrations of Turbid Inland Waters Using a Remote Sensing Method , 2014, Water, Air, & Soil Pollution.

[2]  Ronghua Ma,et al.  Climate- and human-induced changes in suspended particulate matter over Lake Hongze on short and long timescales , 2017 .

[3]  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 .

[4]  T. Louw,et al.  Water quality assessment using a portable UV optical absorbance nitrate sensor with a scintillator and smartphone camera , 2021, Water SA.

[5]  Victor Chang,et al.  Towards an improved Adaboost algorithmic method for computational financial analysis , 2019, J. Parallel Distributed Comput..

[6]  Zhaoning Gong,et al.  Retrieval and Evaluation of Chlorophyll-a Concentration in Reservoirs with Main Water Supply Function in Beijing, China, Based on Landsat Satellite Images , 2021, International journal of environmental research and public health.

[7]  Robert A. Shuchman,et al.  Spatial and temporal variability of inherent and apparent optical properties in western Lake Erie: Implications for water quality remote sensing , 2019, Journal of Great Lakes Research.

[8]  X. Lei,et al.  3-D hydro-environmental simulation of Miyun reservoir, Beijin , 2014 .

[9]  Abbas Parsaie,et al.  Water quality prediction using machine learning methods , 2018 .

[10]  L. Vilas,et al.  Neural network estimation of chlorophyll a from MERIS full resolution data for the coastal waters of Galician rias (NW Spain) , 2011 .

[11]  Changchun Huang,et al.  Long-term variation of phytoplankton biomass and physiology in Taihu lake as observed via MODIS satellite. , 2019, Water research.

[12]  Xiaoling Chen,et al.  Long-Term Distribution Patterns of Chlorophyll-a Concentration in China's Largest Freshwater Lake: MERIS Full-Resolution Observations with a Practical Approach , 2014, Remote. Sens..

[13]  Jan Dirk Wegner,et al.  Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network , 2019 .

[14]  Andrew J. Sekellick,et al.  Modeling drivers of phosphorus loads in Chesapeake Bay tributaries and inferences about long-term change. , 2018, The Science of the total environment.

[15]  Mike Tsionas,et al.  Diagnosing and correcting the effects of multicollinearity: Bayesian implications of ridge regression , 2019, Tourism Management.

[16]  Palanisamy Shanmugam,et al.  Classification of algal bloom species from remote sensing data using an extreme gradient boosted decision tree model , 2019, International Journal of Remote Sensing.

[17]  Wang Meilin,et al.  Retrieval model for total nitrogen concentration based on UAV hyper spectral remote sensing data and machine learning algorithms – A case study in the Miyun Reservoir, China , 2021 .

[18]  Yongnian Gao,et al.  Remote sensing estimation of the total phosphorus concentration in a large lake using band combinations and regional multivariate statistical modeling techniques. , 2015, Journal of environmental management.

[19]  M. Kishino,et al.  Retrieval of Chlorophyll a, suspended solids, and colored dissolved organic matter in Tokyo Bay using ASTER data , 2005 .

[20]  Xiaoling Chen,et al.  Radiometric cross-calibration of Gaofen-1 WFV cameras using Landsat-8 OLI images: A solution for large view angle associated problems , 2016 .

[21]  H. Xie,et al.  Modeling alpine grassland forage phosphorus based on hyperspectral remote sensing and a multi-factor machine learning algorithm in the east of Tibetan Plateau, China , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[22]  Haifeng Li,et al.  Automatic fast double KNN classification algorithm based on ACC and hierarchical clustering for big data , 2018, Int. J. Commun. Syst..

[23]  D. Chapman,et al.  Developments in water quality monitoring and management in large river catchments using the Danube River as an example , 2016 .

[24]  Peter D. Hunter,et al.  A global approach for chlorophyll-a retrieval across optically complex inland waters based on optical water types , 2019, Remote Sensing of Environment.

[25]  Raimund Rolfes,et al.  Neural network assisted multiscale analysis for the elastic properties prediction of 3D braided composites under uncertainty , 2018 .

[26]  Qun'ou Jiang,et al.  Incorporating Temporal and Spatial Variations of Groundwater into the Construction of a Water-Based Ecological Network: A Case Study in Denko County , 2017 .

[27]  M. Ashraf,et al.  Artificial neural network model to predict transport parameters of reactive solutes from basic soil properties. , 2019, Environmental pollution.

[28]  The Impact of Correlated and/or Interacting Predictor Omission on Estimated Regression Coefficients in Linear Regression , 2019, Journal of Statistical Theory and Practice.

[29]  Ahmed El-Shafie,et al.  Towards a time and cost effective approach to water quality index class prediction , 2019, Journal of Hydrology.

[30]  Eckhard Hitzer,et al.  Feature Extraction Using Conformal Geometric Algebra for AdaBoost Algorithm Based In-plane Rotated Face Detection , 2019, Advances in Applied Clifford Algebras.

[31]  A. Wimmer,et al.  Silver Nanoparticle Levels in River Water: Real Environmental Measurements and Modeling Approaches—A Comparative Study , 2019, Environmental Science & Technology Letters.

[32]  F. Qaderi,et al.  Prediction of the groundwater remediation costs for drinking use based on quality of water resource, using artificial neural network , 2017 .

[33]  José M. Sempere,et al.  Modeling of Decision Trees Through P Systems , 2019, New Generation Computing.

[34]  Caicai Xu,et al.  Temporal and spatial variability of phytoplankton in Lake Poyang: The largest freshwater lake in China , 2013 .

[35]  Jafar Y. Al-Jawad,et al.  A comprehensive optimum integrated water resources management approach for multidisciplinary water resources management problems. , 2019, Journal of environmental management.

[36]  Chengguang Lai,et al.  Tree-ring-width based streamflow reconstruction based on the random forest algorithm for the source region of the Yangtze River, China , 2019 .

[37]  Benjamín Barán,et al.  Spectrum defragmentation algorithms in elastic optical networks , 2019, Opt. Switch. Netw..

[38]  Jie Liu,et al.  Data integration by multi-tuning parameter elastic net regression , 2018, BMC Bioinformatics.

[39]  Chunxiang Qian,et al.  Combination of Support Vector Machine and K-Fold cross validation to predict compressive strength of concrete in marine environment , 2019, Construction and Building Materials.

[40]  Dieu Tien Bui,et al.  A comparative study of support vector machine and logistic model tree classifiers for shallow landslide susceptibility modeling , 2019, Environmental Earth Sciences.

[41]  Yaojie Zhang,et al.  Forecasting crude oil prices with a large set of predictors: Can LASSO select powerful predictors? , 2019 .

[42]  Zhenyao Shen,et al.  Predicting fecal coliform using the interval-to-interval approach and SWAT in the Miyun watershed, China , 2017, Environmental Science and Pollution Research.

[43]  D. Diner,et al.  The MISR radiometric calibration process , 2007 .

[44]  Manchun Li,et al.  Parallel relative radiometric normalisation for remote sensing image mosaics , 2014, Comput. Geosci..

[45]  Cheng Sun,et al.  National assessment of spatiotemporal loss in agricultural pesticides and related potential exposure risks to water quality in China. , 2019, The Science of the total environment.

[46]  W. Hao,et al.  Inversion of soil moisture content in the farmland in middle and lower reaches of Syr Darya River Basin based on multi-source remotely sensed data , 2019, JOURNAL OF NATURAL RESOURCES.

[47]  Yue Zhang,et al.  Integrated water resources management for an inland river basin in China , 2019, Watershed Ecology and the Environment.

[48]  Zhenyao Shen,et al.  Quantifying effects of conservation practices on non-point source pollution in the Miyun Reservoir Watershed, China , 2019, Environmental Monitoring and Assessment.

[49]  Fangling Pu,et al.  Combining Artificial Neural Networks with Causal Inference for Total Phosphorus Concentration Estimation and Sensitive Spectral Bands Exploration Using MODIS , 2020, Water.

[50]  Kerrie Mengersen,et al.  A Decision Tree Approach for Spatially Interpolating Missing Land Cover Data and Classifying Satellite Images , 2019, Remote. Sens..

[51]  M. Kim,et al.  A convolutional neural network regression for quantifying cyanobacteria using hyperspectral imagery , 2019, Remote Sensing of Environment.

[52]  P. Pachura,et al.  CHARACTERISTICS OF SPATIAL DISTRIBUTION OF PHOSPHORUS AND NITROGEN IN THE BOTTOM SEDIMENTS OF THE WATER RESERVOIR PORAJ , 2017 .

[53]  V. Muhandiki,et al.  Water resources management and Integrated Water Resources Management implementation in Malawi: Status and implications for lake basin management , 2017 .