A machine learning-based strategy for estimating non-optically active water quality parameters using Sentinel-2 imagery

Guo, Hongwei; Huang‬‬‬‬, Jinhui Jeanne; Chen, Bowen; Guo, Xiaolong; Singh, Vijay P.

doi:10.1080/01431161.2020.1846222

Cited by 85 publications

(53 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic idea of SVR regression is finding a regression hyperplane in a high-dimensional space so that all the data in the set are at the closest distance to that plane [63]. To use SVR to better solve the problems in regression fitting, Vapnik et al [64] introduced an insensitive cost function (ε) based on SVR classification, which forms the SVR model [48,50]. Given a training dataset D = {(x 1, y 1 ), (x 2, y 2 ), .…”

Section: Svrmentioning

confidence: 99%

“…In the last decade, machine learning techniques have been increasingly used for remote sensing studies on water quality parameters relating to inland waters [47][48][49]. Machine learning algorithms can cope with nonlinearity and other complex regression problems and have greater potential and advantages for CDOM estimation than empirical methods [50].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Algorithms for Chromophoric Dissolved Organic Matter (CDOM) Estimation Based on Landsat 8 Images

Sun

Zhang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Chromophoric dissolved organic matter (CDOM) is crucial in the biogeochemical cycle and carbon cycle of aquatic environments. However, in inland waters, remotely sensed estimates of CDOM remain challenging due to the low optical signal of CDOM and complex optical conditions. Therefore, developing efficient, practical and robust models to estimate CDOM absorption coefficient in inland waters is essential for successful water environment monitoring and management. We examined and improved different machine learning algorithms using extensive CDOM measurements and Landsat 8 images covering different trophic states to develop the robust CDOM estimation model. The algorithms were evaluated via 111 Landsat 8 images and 1708 field measurements covering CDOM light absorption coefficient a(254) from 2.64 to 34.04 m−1. Overall, the four machine learning algorithms achieved more than 70% accuracy for CDOM absorption coefficient estimation. Based on model training, validation and the application on Landsat 8 OLI images, we found that the Gaussian process regression (GPR) had higher stability and estimation accuracy (R2 = 0.74, mean relative error (MRE) = 22.2%) than the other models. The estimation accuracy and MRE were R2 = 0.75 and MRE = 22.5% for backpropagation (BP) neural network, R2 = 0.71 and MRE = 24.4% for random forest regression (RFR) and R2 = 0.71 and MRE = 24.4% for support vector regression (SVR). In contrast, the best three empirical models had estimation accuracies of R2 less than 0.56. The model accuracies applied to Landsat images of Lake Qiandaohu (oligo-mesotrophic state) were better than those of Lake Taihu (eutrophic state) because of the more complex optical conditions in eutrophic lakes. Therefore, machine learning algorithms have great potential for CDOM monitoring in inland waters based on large datasets. Our study demonstrates that machine learning algorithms are available to map CDOM spatial-temporal patterns in inland waters.

show abstract

Section: Svrmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning Algorithms for Chromophoric Dissolved Organic Matter (CDOM) Estimation Based on Landsat 8 Images

Sun

Zhang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Biological toxins are complex chemical compounds that have a wide range of water solubility, reactivity, and degradability in the environment. In addition, a speci ic compound such as botulinum can have varying degrees of stability and toxicity in the aqueous medium between types A, B, C, D, and E [53][54][55].…”

Section: Soil and Gastrointestinal Tract Of Healthy Humans And Animalsmentioning

confidence: 99%

Assessment and sensitive analysis of biological water risks in water resources with application of classical mass transfer computations

Jalali¹,

Gheibi²,

Aghlmand³

et al. 2021

Ann Biomed Sci Eng

View full text Add to dashboard Cite

Due to the urgent need for water in all parts of industrial or developing societies, water supply, and transmission facilities are suitable targets for biological risks. Given that even a short interruption in water supply and water supply operations has a great impact on daily activities in the community, the deliberate contamination of urban water resources has irreparable consequences in the field of public health, and the economy of society will follow. Unfortunately, most officials in the public health control departments in our country have received limited training in detecting accidental or intentional contamination of water resources and dealing with the spread of waterborne diseases both naturally and intentionally. For this reason, there is low preparedness in the responsible agencies to deal with waterborne diseases during biological risks. In the first step of this research, a review study has been conducted on water biological risks and operational strategies to deal with them. In the following, it has studied how Escherichia coli (E. coli) bacteria spread in aqueous media. In this regard, the kinetic model of the studied microorganism was analyzed based on the implementation of (Fick Law) in polar coordinates and the combination of (Dirac Distribution) with (Legendre polynomial) distribution. Finally, after studying the factors affecting the microbial pollutant emission coefficient, the effects of all three factors of linear velocity, linear motion time period, and angle of motion on the pollutant emission flux and biofilm diffusion time in the water supply network environment were investigated. Studies have shown that the linear velocity parameter of Escherichia coli with a nonlinear relationship has the greatest effects on the release of microbial contaminants.

show abstract

“…However, estimating TN, TP, and COD concentrations in inland waters presents a great challenge. As the above parameters are not optically active at the sensed wavelengths [14], it is difficult to directly correlate remote sensing spectral characteristics with TN, TP, and COD concentrations [15], so most of the current studies using conventional remote sensing monitoring methods focus on WQPs with optical activity. In terms of WQPs retrieval, previous studies were based mainly on different correlation algorithms of empirical, semi-analytical, and matrix retrieval models.…”

Section: Introductionmentioning

confidence: 99%

Retrieving Inland Reservoir Water Quality Parameters Using Landsat 8-9 OLI and Sentinel-2 MSI Sensors with Empirical Multivariate Regression

Meng

Zhang

Zhang³

2022

IJERPH

View full text Add to dashboard Cite

Improving water quality is one of the top priorities in the global agenda endorsed by the United Nations. To ensure the achievement of this goal, governments have developed plans to continuously monitor the status of inland waters. Remote sensing provides a low-cost, high-frequency, and practical complement to monitoring systems that can cover a large area. However, it is crucial to evaluate the suitability of sensors for retrieving water quality parameters (WQPs), owing to differences in spatial and spectral sampling from different satellites. Taking Shanmei Reservoir in Fuzhou City, Fujian Province as a case study, this study collected and sorted the water quality data measured at the site in 2020 to 2022 and Landsat 8-9 OLI and Sentinel-2 MSI images, simulated the chlorophyll-a (Chl-a) concentration, algae density, and turbidity using empirical multivariate regression, and explored the relationship between different WQPs using correlation analysis and principal component analysis (PCA). The results showed that the fitting effect of Landsat OLI data was better than that of the Sentinel-2 MSI data. The coefficient of determination (R2) values of Chl-a, algal density, and turbidity simulated by Landsat OLI data were 0.70, 0.81, and 0.80, respectively. Furthermore, the parameters of its validation equation were also smaller than those of Sentinel MSI data. The spatial distribution of three key WQPs retrieved from Landsat OLI data shows their values were generally low, with the mean values of the Chl-a concentration, algal density, and turbidity being 4.25 μg/L, 4.11 × 106 cells/L, and 1.86 NTU, respectively. However, from the end of February 2022, the values of the Chl-a concentration and algae density in the reservoir gradually increase, and the risk of water eutrophication also increases. Therefore, it is still necessary to pay continuous attention and formulate corresponding water quality management measures. The correlation analysis shows that the three key WQPs in this study have a high correlation with pH, water temperature (WT), and dissolved oxygen (DO). The results of PCA showed that pH, DO, Chl-a concentration, WT, TN, and CODMn were dominant in PC1, explaining 35.57% of the total variation, and conductivity, algal density, and WT were dominant in PC2, explaining 13.34% of the total variation. Therefore, the water quality of the Shanmei Reservoir can be better evaluated by measuring pH, conductivity, and WT at the monitoring station, or by establishing the regression fitting equations between DO, CODMn, and TN. The regression algorithm used in this study can identify the most important water quality features in the Shanmei Reservoir, which can be used to monitor the nutritional status of the reservoir and provide a reference for other similar inland water bodies.

show abstract

A machine learning-based strategy for estimating non-optically active water quality parameters using Sentinel-2 imagery

Cited by 85 publications

References 60 publications

Machine Learning Algorithms for Chromophoric Dissolved Organic Matter (CDOM) Estimation Based on Landsat 8 Images

Machine Learning Algorithms for Chromophoric Dissolved Organic Matter (CDOM) Estimation Based on Landsat 8 Images

Assessment and sensitive analysis of biological water risks in water resources with application of classical mass transfer computations

Retrieving Inland Reservoir Water Quality Parameters Using Landsat 8-9 OLI and Sentinel-2 MSI Sensors with Empirical Multivariate Regression

Contact Info

Product

Resources

About