Monitoring water quality using proximal remote sensing technology.
TL;DR: In this article, the authors proposed the concept of proximal remote sensing for monitoring water quality in inland waters by using the proximal hyperspectral imager, developed by Nanjing Institute of Geography and Limnology, Chinese Academy of Sciences (CAS) and Hikvision Digital Technology, Ltd.
About: This article is published in Science of The Total Environment.The article was published on 2022-01-10. It has received 34 citations till now. The article focuses on the topics: Water quality & Environmental science.
Citations
More filters
TL;DR: In this article , the authors present the application of remote sensing for water quality retrieval, and mainly discuss the research progress in terms of data sources and retrieval modes, and summarize some retrieval algorithms for several specific water quality variables, including total suspended matter (TSM), chlorophyll-a (Chl-a), colored dissolved organic matter (CDOM), chemical oxygen demand (COD), total nitrogen (TN) and total phosphorus (TP).
Abstract: Water pollution has become one of the most serious issues threatening water environments, water as a resource and human health. The most urgent and effective measures rely on dynamic and accurate water quality monitoring on a large scale. Due to their temporal and spatial advantages, remote sensing technologies have been widely used to retrieve water quality data. With the development of hyper-spectral sensors, unmanned aerial vehicles (UAV) and artificial intelligence, there has been significant advancement in remotely sensed water quality retrieval owing to various data availabilities and retrieval methodologies. This article presents the application of remote sensing for water quality retrieval, and mainly discusses the research progress in terms of data sources and retrieval modes. In particular, we summarize some retrieval algorithms for several specific water quality variables, including total suspended matter (TSM), chlorophyll-a (Chl–a), colored dissolved organic matter (CDOM), chemical oxygen demand (COD), total nitrogen (TN) and total phosphorus (TP). We also discuss the significant challenges to atmospheric correction, remotely sensed data resolution, and retrieval model applicability in the domains of spatial, temporal and water complexity. Finally, we propose possible solutions to these challenges. The review can provide detailed references for future development and research in water quality retrieval.
31 citations
TL;DR: In this paper , the authors provide a systematic review of the literature that incorporates artificial intelligence and computer vision methods in the water resources sector with a focus on intelligent water body extraction and water quality detection and monitoring through remote sensing.
Abstract: Water features (e.g., water quantity and water quality) are one of the most important environmental factors essential to improving climate-change resilience. Remote sensing (RS) technologies empowered by artificial intelligence (AI) have become one of the most demanded strategies to automating water information extraction and thus intelligent monitoring. In this article, we provide a systematic review of the literature that incorporates artificial intelligence and computer vision methods in the water resources sector with a focus on intelligent water body extraction and water quality detection and monitoring through remote sensing. Based on this review, the main challenges of leveraging AI and RS for intelligent water information extraction are discussed, and research priorities are identified. An interactive web application designed to allow readers to intuitively and dynamically review the relevant literature was also developed.
12 citations
TL;DR: In this paper , a ground-based remote sensing system (GRSS) is proposed to monitor real-time chlorophyll a concentrations (Chla) in inland waters with a high frequency.
11 citations
TL;DR: In this article , two UAV flights were conducted (one in February and the other in December 2021) to acquire images of the Zhanghe River (China), and a total of 45 water samples were collected concurrently with the image acquisition.
Abstract: Timely monitoring of inland water quality using unmanned aerial vehicle (UAV) remote sensing is critical for water environmental conservation and management. In this study, two UAV flights were conducted (one in February and the other in December 2021) to acquire images of the Zhanghe River (China), and a total of 45 water samples were collected concurrently with the image acquisition. Machine learning (ML) methods comprising Multiple Linear Regression, the Least Absolute Shrinkage and Selection Operator, a Backpropagation Neural Network (BP), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) were applied to retrieve four water quality parameters: chlorophyll-a (Chl-a), total nitrogen (TN), total phosphors (TP), and permanganate index (CODMn). Then, ML models based on the stacking approach were developed. Results show that stacked ML models could achieve higher accuracy than a single ML model; the optimal methods for Chl-a, TN, TP, and CODMn were RF-XGB, BP-RF, RF, and BP-RF, respectively. For the testing dataset, the R2 values of the best inversion models for Chl-a, TN, TP, and CODMn were 0.504, 0.839, 0.432, and 0.272, the root mean square errors were 1.770 μg L−1, 0.189 mg L−1, 0.053 mg L−1, and 0.767 mg L−1, and the mean absolute errors were 1.272 μg L−1, 0.632 mg L−1, 0.045 mg L−1, and 0.674 mg L−1, respectively. This study demonstrated the great potential of combined UAV remote sensing and stacked ML algorithms for water quality monitoring.
10 citations
TL;DR: Considering the spectral response mechanisms of emergent plants, this paper coupled discrete wavelet transform (DWT) and fractional order discretization (FOD) techniques with three machine learning models (random forest (RF), bagging algorithm (bagging), and eXtreme Gradient Boosting (XGBoost)) to mine this potential spectral information.
Abstract: Controlling and managing surface source pollution depends on the rapid monitoring of total nitrogen in water. However, the complex factors affecting water quality (plant shading and suspended matter in water) make direct estimation extremely challenging. Considering the spectral response mechanisms of emergent plants, we coupled discrete wavelet transform (DWT) and fractional order discretization (FOD) techniques with three machine learning models (random forest (RF), bagging algorithm (bagging), and eXtreme Gradient Boosting (XGBoost)) to mine this potential spectral information. A total of 567 models were developed, and airborne hyperspectral data processed with various DWT scales and FOD techniques were compared. The effective information in the hyperspectral reflectance data were better emphasized after DWT processing. After DWT processing the original spectrum (OR), its sensitivity to TN in water was maximally improved by 0.22, and the correlation between FOD and TN in water was optimally increased by 0.57. The transformed spectral information enhanced the TN model accuracy, especially for FOD after DWT. For RF, 82% of the model R2 values improved by 0.02~0.72 compared to the model using FOD spectra; 78.8% of the bagging values improved by 0.01~0.53 and 65.0% of the XGBoost values improved by 0.01~0.64. The XGBoost model with DWT coupled with grey relation analysis (GRA) yielded the best estimation accuracy, with the highest precision of R2 = 0.91 for L6. In conclusion, appropriately scaled DWT analysis can substantially improve the accuracy of extracting TN from UAV hyperspectral images. These outcomes may facilitate the further development of accurate water quality monitoring in sophisticated global waters from drone or satellite hyperspectral data.
10 citations
References
More filters
[...]
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.
79,257 citations
TL;DR: Two brief case studies demonstrate that nutrient loading restriction is the essential cornerstone of aquatic eutrophication control, and results of a preliminary statistical analysis are presented consistent with the hypothesis that anthropogenic emissions of oxidized nitrogen could be influencing atmospheric levels of carbon dioxide via nitrogen stimulation of global primary production.
2,702 citations
TL;DR: The relationship between harmful algal blooms and eutrophication of coastal waters from human activities has been investigated in this paper, focusing on sources of nutrients, known effects of nutrient loading and reduction, new understanding of pathways of nutrient acquisition among HAB species, and relationships between nutrients and toxic algae.
Abstract: Although algal blooms, including those considered toxic or harmful, can be natural phenomena, the nature of the global problem of harmful algal blooms (HABs) has expanded both in extent and its public perception over the last several decades. Of concern, especially for resource managers, is the potential relationship between HABs and the accelerated eutrophication of coastal waters from human activities. We address current insights into the relationships between HABs and eutrophication, focusing on sources of nutrients, known effects of nutrient loading and reduction, new understanding of pathways of nutrient acquisition among HAB species, and relationships between nutrients and toxic algae. Through specific, regional, and global examples of these various relationships, we offer both an assessment of the state of understanding, and the uncertainties that require future research efforts. The sources of nutrients poten- tially stimulating algal blooms include sewage, atmospheric deposition, groundwater flow, as well as agricultural and aquaculture runoff and discharge. On a global basis, strong correlations have been demonstrated between total phos- phorus inputs and phytoplankton production in freshwaters, and between total nitrogen input and phytoplankton pro- duction in estuarine and marine waters. There are also numerous examples in geographic regions ranging from the largest and second largest U.S. mainland estuaries (Chesapeake Bay and the Albemarle-Pamlico Estuarine System), to the Inland Sea of Japan, the Black Sea, and Chinese coastal waters, where increases in nutrient loading have been linked with the development of large biomass blooms, leading to anoxia and even toxic or harmful impacts on fisheries re- sources, ecosystems, and human health or recreation. Many of these regions have witnessed reductions in phytoplankton biomass (as chlorophyll a) or HAB incidence when nutrient controls were put in place. Shifts in species composition have often been attributed to changes in nutrient supply ratios, primarily N:P or N:Si. Recently this concept has been extended to include organic forms of nutrients, and an elevation in the ratio of dissolved organic carbon to dissolved organic nitrogen (DOC:DON) has been observed during several recent blooms. The physiological strategies by which different groups of species acquire their nutrients have become better understood, and alternate modes of nutrition such as heterotrophy and mixotrophy are now recognized as common among HAB species. Despite our increased un- derstanding of the pathways by which nutrients are delivered to ecosystems and the pathways by which they are assimilated differentially by different groups of species, the relationships between nutrient delivery and the development of blooms and their potential toxicity or harmfulness remain poorly understood. Many factors such as algal species presence/ abundance, degree of flushing or water exchange, weather conditions, and presence and abundance of grazers contribute to the success of a given species at a given point in time. Similar nutrient loads do not have the same impact in different environments or in the same environment at different points in time. Eutrophication is one of several mechanisms by which harmful algae appear to be increasing in extent and duration in many locations. Although important, it is not the only explanation for blooms or toxic outbreaks. Nutrient enrichment has been strongly linked to stimulation of some harmful species, but for others it has not been an apparent contributing factor. The overall effect of nutrient over- enrichment on harmful algal species is clearly species specific.
2,500 citations
TL;DR: An adaptive neural network with asymmetric connections is introduced that bears a resemblance to the master/slave network of Lapedes and Farber but it is architecturally simpler.
Abstract: An adaptive neural network with asymmetric connections is introduced. This network is related to the Hopfield network with graded neurons and uses a recurrent generalization of the \ensuremath{\delta} rule of Rumelhart, Hinton, and Williams to modify adaptively the synaptic weights. The new network bears a resemblance to the master/slave network of Lapedes and Farber but it is architecturally simpler.
947 citations
TL;DR: Application of ANN ensembles has allowed the avoidance of chance correlations and satisfactory predictions of new data have been obtained for a wide range of numbers of neurons in the hidden layer.
Abstract: The application of feed forward back propagation artificial neural networks with one hidden layer (ANN) to perform the equivalent of multiple linear regression (MLR) has been examined using artificial structured data sets and real literature data. The predictive ability of the networks has been estimated using a training/ test set protocol. The results have shown advantages of ANN over MLR analysis. The ANNs do not require high order terms or indicator variables to establish complex structure-activity relationships. Overfitting does not have any influence on network prediction ability when overtraining is avoided by cross-validation. Application of ANN ensembles has allowed the avoidance of chance correlations and satisfactory predictions of new data have been obtained for a wide range of numbers of neurons in the hidden layer.
655 citations