Deep Learning-Based Water Quality Retrieval in an Impounded Lake Using Landsat 8 Imagery: An Application in Dongping Lake

Zhang, Hanwen; Xue, Baolin; Wang, Guo Qiang; Zhang, Xiaojing; Zhang, Qingzhu

doi:10.3390/rs14184505

Cited by 21 publications

(11 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Good chlorophyll predictions have been obtained in investigations that have used deep learning models and Landsat-8 in lakes, such as the case of [77][78][79]; as in the case of this research, these techniques can be improved by incorporating meteorological variables. The methodology of this study and other similar methodologies have applications in monitoring water quality and serve as an early warning tool for hydro-environmental management in inland water ecosystems, according to [35,81]. It is important to clarify that the precision in the models will always be greater when more input data are provided.…”

Section: Discussionmentioning

confidence: 99%

Estimation of Water Quality Parameters through a Combination of Deep Learning and Remote Sensing Techniques in a Lake in Southern Chile

Rodríguez-López,

Usta,

Duran-Llacer

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

In this study, we combined machine learning and remote sensing techniques to estimate the value of chlorophyll-a concentration in a freshwater ecosystem in the South American continent (lake in Southern Chile). In a previous study, nine artificial intelligence (AI) algorithms were tested to predict water quality data from measurements during monitoring campaigns. In this study, in addition to field data (Case A), meteorological variables (Case B) and satellite data (Case C) were used to predict chlorophyll-a in Lake Llanquihue. The models used were SARIMAX, LSTM, and RNN, all of which showed generally good statistics for the prediction of the chlorophyll-a variable. Model validation metrics showed that all three models effectively predicted chlorophyll as an indicator of the presence of algae in water bodies. Coefficient of determination values ranging from 0.64 to 0.93 were obtained, with the LSTM model showing the best statistics in any of the cases tested. The LSTM model generally performed well across most stations, with lower values for MSE (<0.260 (μg/L)2), RMSE (<0.510 ug/L), MaxError (<0.730 μg/L), and MAE (<0.442 μg/L). This model, which combines machine learning and remote sensing techniques, is applicable to other Chilean and world lakes that have similar characteristics. In addition, it is a starting point for decision-makers in the protection and conservation of water resource quality.

show abstract

Section: Discussionmentioning

confidence: 99%

Estimation of Water Quality Parameters through a Combination of Deep Learning and Remote Sensing Techniques in a Lake in Southern Chile

Rodríguez-López,

Usta,

Duran-Llacer

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The higher the water temperature, the larger the proportion of molecular ammonia [26] and the lower the DO. The results show that there is a correlation between ammonia nitrogen and total nitrogen at a certain proportion [36,38,39].…”

Section: Analysis Of Water Quality Characteristic Factorsmentioning

confidence: 90%

Water Environment Characteristics and Water Quality Assessment of Water Source of Diversion System of Project from Hanjiang to Weihe River

Chen

et al. 2023

IJERPH

View full text Add to dashboard Cite

The water source of the water diversion project from the Hanjiang River to the Weihe River is one of the most important drinking water sources in China. Its water quality is related to the water safety of the long-distance water diversion system from the Hanjiang to Weihe Rivers. In order to explore the spatiotemporal change trend of the water environment characteristics of the water source area and analyze the key factors that have a greater impact on it, this study collected 9 types of water environment physical and chemical parameters from 10 water quality monitoring sections from 2017 to 2019; the water environment characteristics of the water source area of the water diversion system from the Hanjiang River to the Weihe River were analyzed and evaluated by using the variance analysis method, the hierarchical cluster analysis method and the water quality identification index evaluation method. The results were as follows. (1) There was spatiotemporal heterogeneity in a number of physical and chemical parameters in the water body of the water source. In terms of time, the concentrations of CODMn, COD, BOD5 and F− were higher in the flood season (July–October) than in the non-flood season (November–June). The concentrations of DO, TP and TN in the non-flood season were higher than those in the flood season. Spatially, the concentration of physical and chemical parameters of the water body in the Huangjinxia Reservoir area was higher than that in the Sanhekou Reservoir area. (2) The water quality of the water source area was good. The comprehensive water quality reached the Class II water quality standard of surface water environmental quality. Time showed that the comprehensive water quality in the non-flood season was better than that in the flood season. Spatially, the overall water quality of the tributaries was better than that of the mainstream. TN is a key indicator that affects water quality. (3) The spatial and temporal differences in water quality in water source areas are mainly affected by factors such as rainfall, temperature and human activities. This study can provide a scientific and data basis for related research on maintaining and improving the quality of the ecological environment of the water source areas of the Hanjiang to Weihe River Water Diversion System.

show abstract

“…These space-based observations offer a wealth of data with excellent spectral, spatial, and temporal resolutions that facilitate the calculation of WQIs. Landsat images, for example, have been extensively used to estimate optical and non-optical WQIs, such as turbidity [15,16,19,20], total nitrogen (TN) and total phosphorus (TP) [7,15,16,[20][21][22], chlorophyll-a [16,[23][24][25], DO [16], total suspended solids (TSSs) [20,26], salinity [27,28], and ammonium [29]. Moderate Resolution Imaging Spectroradiometer images have been used to retrieve salinity [11,30], chlorophyll-a [30][31][32][33], colored dissolved organic material [30,34,35], TSS [31,36], TN [35][36][37][38], and TP [36][37][38].…”

Section: Introductionmentioning

confidence: 99%

Monitoring Water Quality Indicators over Matagorda Bay, Texas, Using Landsat-8

Bygate,

Ahmed

2024

Remote Sensing

View full text Add to dashboard Cite

Remote sensing datasets offer a unique opportunity to observe spatial and temporal trends in water quality indicators (WQIs), such as chlorophyll-a, salinity, and turbidity, across various aquatic ecosystems. In this study, we used available in situ WQI measurements (chlorophyll-a: 17, salinity: 478, and turbidity: 173) along with Landsat-8 surface reflectance data to examine the capability of empirical and machine learning (ML) models in retrieving these indicators over Matagorda Bay, Texas, between 2014 and 2023. We employed 36 empirical models to retrieve chlorophyll-a (12 models), salinity (2 models), and turbidity (22 models) and 4 ML families—deep neural network (DNN), distributed random forest, gradient boosting machine, and generalized linear model—to retrieve salinity and turbidity. We used the Nash–Sutcliffe efficiency coefficient (NSE), correlation coefficient (r), and normalized root mean square error (NRMSE) to assess the performance of empirical and ML models. The results indicate that (1) the empirical models displayed minimal effectiveness when applied over Matagorda Bay without calibration; (2) once calibrated over Matagorda Bay, the performance of the empirical models experienced significant improvements (chlorophyll-a—NRMSE: 0.91 ± 0.03, r: 0.94 ± 0.04, NSE: 0.89 ± 0.06; salinity—NRMSE: 0.24 ± 0, r: 0.24 ± 0, NSE: 0.06 ± 0; turbidity—NRMSE: 0.15 ± 0.10, r: 0.13 ± 0.09, NSE: 0.03 ± 0.03); (3) ML models outperformed calibrated empirical models when used to retrieve turbidity and salinity, and (4) the DNN family outperformed all other ML families when used to retrieve salinity (NRMSE: 0.87 ± 0.09, r: 0.49 ± 0.09, NSE: 0.23 ± 0.12) and turbidity (NRMSE: 0.63± 0.11, r: 0.79 ± 0.11, NSE: 0.60 ± 0.20). The developed approach provides a reference context, a structured framework, and valuable insights for using empirical and ML models and Landsat-8 data to retrieve WQIs over aquatic ecosystems. The modeled WQI data could be used to expand the footprint of in situ observations and improve current efforts to conserve, enhance, and restore important habitats in aquatic ecosystems.

show abstract

Deep Learning-Based Water Quality Retrieval in an Impounded Lake Using Landsat 8 Imagery: An Application in Dongping Lake

Cited by 21 publications

References 68 publications

Estimation of Water Quality Parameters through a Combination of Deep Learning and Remote Sensing Techniques in a Lake in Southern Chile

Estimation of Water Quality Parameters through a Combination of Deep Learning and Remote Sensing Techniques in a Lake in Southern Chile

Water Environment Characteristics and Water Quality Assessment of Water Source of Diversion System of Project from Hanjiang to Weihe River

Monitoring Water Quality Indicators over Matagorda Bay, Texas, Using Landsat-8

Contact Info

Product

Resources

About