scispace - formally typeset
Journal ArticleDOI: 10.1080/01431161.2020.1846222

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

04 Mar 2021-International Journal of Remote Sensing (Informa UK Limited)-Vol. 42, Iss: 5, pp 1841-1866
Abstract: Water-quality monitoring for small urban waterbodies by remote sensing gets to be difficult due to the coarse spatial resolution of remote-sensing imagery. The recently launched Sentinel-2 produces...

... read more

Citations
  More

6 results found


Open accessJournal ArticleDOI: 10.3390/W13050650
28 Feb 2021-Water
Abstract: In order to use in situ sensed reflectance to monitor the concentrations of chlorophyll-a (Chl-a) and total suspended particulate (TSP) of waters in the Pearl River Delta, which is featured by the highly developed network of rivers, channels and ponds, 135 sets of simultaneously collected water samples and reflectance were used to test the performance of the traditional empirical models (band ratio, three bands) and the machine learning models of a back-propagation neural network (BPNN). The results of the laboratory analysis with the water samples show that the Chl-a ranges from 3 to 256 µg·L−1 with an average of 39 µg·L−1 while the TSP ranges from 8 to 162 mg·L−1 and averages 42.5 mg·L−1. Ninety sets of 135 samples are used as training data to develop the retrieval models, and the remaining ones are used to validate the models. The results show that the proposed band ratio models, the three-band combination models, and the corresponding BPNN models are generally successful in estimating the Chl-a and the TSP, and the mean relative error (MRE) can be lower than 30% and 25%, respectively. However, the BPNN models have no better performance than the traditional empirical models, e.g., in the estimation of TSP on the basis of the reflectance at 555 and 750 nm (R555 and R750, respectively), the model of BPNN (R555, R750) has an MRE of 23.91%, larger than that of the R750/R555 model. These results suggest that these traditional empirical models are usable in monitoring the optically active water quality parameters of Chl-a and TSP for eutrophic and turbid waters, while the machine learning models have no significant advantages, especially when the cost of training samples is considered. To improve the performance of machine learning models in future applications on the basis of ground sensor networks, large datasets covering various water situations and optimization of input variables of band configuration should be strengthened.

... read more

4 Citations


Open accessJournal ArticleDOI: 10.29328/JOURNAL.ABSE.1001013
09 Jun 2021-
Abstract: 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.

... read more

1 Citations


Journal ArticleDOI: 10.1016/J.SCITOTENV.2021.149805
Xiao Sun1, Yunlin Zhang1, Kun Shi1, Yibo Zhang1  +4 moreInstitutions (1)
Abstract: Accurate, high spatial and temporal resolution water quality monitoring in inland waters is vital for environmental management. However, water quality monitoring in inland waters by satellite remote sensing remains challenging due to low signal-to-noise ratios (SNRs) and instrumental resolution limitations. We propose the concept of proximal remote sensing for monitoring water quality. The proximal hyperspectral imager, developed by Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences (CAS) and Hikvision Digital Technology, Ltd., is a high spatial, temporal and spectral resolution (1 nm) sensor for continuous observation, allowing for effective and practical long-term monitoring of inland water quality. In this study, machine learning and empirical algorithms were developed and validated using in situ total nitrogen (TN), total phosphorus (TP), chemical oxygen demand (COD) concentrations and spectral reflectance from Lake Taihu (N = 171), the Liangxi River (N = 94) and the Fuchunjiang Reservoir (N = 109) covering different water quality. Our dataset includes a large range for three key water quality parameters of TN from 0.93 to 6.46 mg/L, TP from 0.04 to 0.62 mg/L, and COD from 1.32 to 15.41 mg/L. Overall, the back-propagation (BP) neural network model had an accuracy of over 80% for TN (R2 = 0.84, RMSE = 0.33 mg/L, and MRE = 11.4%) and over 90% for TP (R2 = 0.93, RMSE = 0.02 mg/L, and MRE = 12.4%) and COD (R2 = 0.91, RMSE = 0.66 mg/L, and MRE = 9.3%). Our results show that proximal remote sensing combined with machine learning algorithms has great potential for monitoring water quality in inland waters.

... read more

Topics: Water quality (53%)

1 Citations


Journal ArticleDOI: 10.1016/J.ENVPOL.2021.117734
Hongwei Guo1, Jinhui Jeanne Huang1, Xiaotong Zhu1, Bo Wang1  +3 moreInstitutions (1)
Abstract: Dissolved oxygen (DO) is an effective indicator for water pollution. However, since DO is a non-optically active parameter and has little impact on the spectrum captured by satellite sensors, research on estimating DO by remote sensing at multiple spatiotemporal scales is limited. In this study, the support vector regression (SVR) models were developed and validated using the remote sensing reflectance derived from both Landsat and Moderate Resolution Imaging Spectroradiometer (MODIS) data and synchronous DO measurements (N = 188) and water temperature of Lake Huron and three other inland waterbodies (N = 282) covering latitude between 22–45 °N. Using the developed models, spatial distributions of the annual and monthly DO variability since 1984 and the annual monthly DO variability since 2000 in Lake Huron were reconstructed for the first time. The impacts of five climate factors on long-term DO trends were analyzed. Results showed that the developed SVR-based models had good robustness and generalization (average R2 = 0.91, root mean square percentage error = 2.65%, mean absolute percentage error = 4.21%), and performed better than random forest and multiple linear regression. The monthly DO estimates by Landsat and MODIS data were highly consistent (average R2 = 0.88). From 1984 to 2019, the oxygen loss in Lake Huron was 6.56%. Air temperature, incident shortwave radiation flux density, and precipitation were the main climate factors affecting annual DO of Lake Huron. This study demonstrated that using SVR-based models, Landsat and MODIS data could be used for long-term DO retrieval at multiple spatial and temporal scales. As data-driven models, combining spectrum and water temperature as well as extending the training set to cover more DO conditions could effectively improve model robustness and generalization.

... read more

1 Citations


Open accessJournal ArticleDOI: 10.3390/RS13183560
07 Sep 2021-Remote Sensing
Abstract: 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.

... read more


References
  More

59 results found


Journal ArticleDOI: 10.1080/01431169608948714
Stuart K. McFeeters1Institutions (1)
Abstract: The Normalized Difference Water Index (NDWI) is a new method that has been developed to delineate open water features and enhance their presence in remotely-sensed digital imagery. The NDWI makes use of reflected near-infrared radiation and visible green light to enhance the presence of such features while eliminating the presence of soil and terrestrial vegetation features. It is suggested that the NDWI may also provide researchers with turbidity estimations of water bodies using remotely-sensed digital data.

... read more

3,140 Citations


Journal ArticleDOI: 10.4319/LO.1977.22.2.0361
Robert E. Carlson1Institutions (1)
Abstract: A numerical trophic state index for lakes has been developed that incorporates most lakes in a scale of 0 to 100. Each major division ( 10, 20, 30, etc. ) represents a doubling in algal biomass. The index number can bc calculated from any of several parameters, including Secchi disk transparency, chlorophyll, and total phosphorus. My purpose here is to present a new approach to the trophic classification of lakes. This new approach was developed because of frustration in communicating to the public both the current nature or status of lakes and their future condition after restoration when the traditional trophic classification system is used. The system presented hcrc, termed a trophic state index (TSI), involves new methods both of defining trophic status and of determining that status in lakes. All trophic classification is based on the division of the trophic continuum, howcvcr this is defined, into a series of classes termed trophic states. Traditional systems divide the continuum into three classes: oligotrophic, mesotrophic, and cutrophic. There is often no clear delineation of these divisions. Determinations of trophic state are made from examination of several diverse criteria, such as shape of the oxygen curve, species composition of the bottom fauna or of the phytoplankton, conccntrations of nutrients, and various measures of biomass or production. Although each changes from oligotrophy to eutrophy, the changes do not occur at sharply defined places, nor do they all occur at the same place or at the same rate. Some lakes may be considered oligotrophic by one criterion and eutrophic by another; this problem is

... read more

Topics: Trophic state index (75%), Trophic level (61%)

3,105 Citations


Open accessJournal ArticleDOI: 10.1029/98JC02160
Abstract: A large data set containing coincident in situ chlorophyll and remote sensing reflectance measurements was used to evaluate the accuracy, precision, and suitability of a wide variety of ocean color chlorophyll algorithms for use by SeaWiFS (Sea-viewing Wide Field-of-view Sensor). The radiance-chlorophyll data were assembled from various sources during the SeaWiFS Bio-optical Algorithm Mini-Workshop (SeaBAM) and is composed of 919 stations encompassing chlorophyll concentrations between 0.019 and 32.79 μg L−1. Most of the observations are from Case I nonpolar waters, and ∼20 observations are from more turbid coastal waters. A variety of statistical and graphical criteria were used to evaluate the performances of 2 semianalytic and 15 empirical chlorophyll/pigment algorithms subjected to the SeaBAM data. The empirical algorithms generally performed better than the semianalytic. Cubic polynomial formulations were generally superior to other kinds of equations. Empirical algorithms with increasing complexity (number of coefficients and wavebands), were calibrated to the SeaBAM data, and evaluated to illustrate the relative merits of different formulations. The ocean chlorophyll 2 algorithm (OC2), a modified cubic polynomial (MCP) function which uses Rrs490/Rrs555, well simulates the sigmoidal pattern evident between log-transformed radiance ratios and chlorophyll, and has been chosen as the at-launch SeaWiFS operational chlorophyll a algorithm. Improved performance was obtained using the ocean chlorophyll 4 algorithm (OC4), a four-band (443, 490, 510, 555 nm), maximum band ratio formulation. This maximum band ratio (MBR) is a new approach in empirical ocean color algorithms and has the potential advantage of maintaining the highest possible satellite sensor signal: noise ratio over a 3-orders-of-magnitude range in chlorophyll concentration.

... read more

Topics: SeaWiFS (67%), Ocean color (58%), Chlorophyll a (52%) ... read more

2,257 Citations


Journal ArticleDOI: 10.1016/J.ISPRSJPRS.2010.11.001
Giorgos Mountrakis1, Jungho Im1, Caesar Ogole1Institutions (1)
Abstract: A wide range of methods for analysis of airborne- and satellite-derived imagery continues to be proposed and assessed. In this paper, we review remote sensing implementations of support vector machines (SVMs), a promising machine learning methodology. This review is timely due to the exponentially increasing number of works published in recent years. SVMs are particularly appealing in the remote sensing field due to their ability to generalize well even with limited training samples, a common limitation for remote sensing applications. However, they also suffer from parameter assignment issues that can significantly affect obtained results. A summary of empirical results is provided for various applications of over one hundred published works (as of April, 2010). It is our hope that this survey will provide guidelines for future applications of SVMs and possible areas of algorithm enhancement.

... read more

2,109 Citations


Min Shao1, Xiaoyan Tang1, Yuanhang Zhang1, Wenjun Li1Institutions (1)
Abstract: City clusters are made up of groups of large, nearly contiguous cities with many adjoining satellite cities and towns. Over the past two decades, such clusters have played a leading role in the economic growth of China, owing to their collective economic capacity and interdependency. However, the economic boom has led to a general decline in environmental quality. This paper will review the development and current status of the major environmental problems caused by city clusters, focusing on water and air pollution, and suggest possi- ble strategies for solving these problems. Currently, deteriorating water quality is of major concern to the pub- lic and decision makers alike, and more than three-quarters of the urban population are exposed to air quality that does not meet the national ambient air quality standards of China. Furthermore, this pollution is charac- terized by high concentrations of both primary and secondary pollutants. Environmental pollution issues are therefore much more complex in China than in western countries. China is expected to quadruple its GDP by 2020 (using 2000 as the base year for comparison) and, consequently, will face even more serious environmen- tal challenges. Improving energy efficiency and moderating the consumption of natural resources are essential if China is to achieve a balance between economic development and environmental health.

... read more

569 Citations