Real-time discrimination of contamination source composed of multiple pollutants in surface water based on deep learning and UV–Vis spectral abundance estimation methodology

Li, Qingbo; Liu, Rui; Bi, Zhiqi

doi:10.1016/j.saa.2023.123635

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spectral unmixing from remote sensing is an innovative approach to addressing the issue of identifying sources of surface water pollution. Based on the different spectral characteristics of contamination sources, this method estimates the proportions of different polluted water sources (endmembers) in the contaminated surface water . When the proportion of a certain polluted water source exceeds the pollution threshold, it is considered that the contribution of the polluted water source to the pollution is significant.…”

Section: Introductionmentioning

confidence: 99%

“…Based on the different spectral characteristics of contamination sources, this method estimates the proportions of different polluted water sources (endmembers) in the contaminated surface water. 8 When the proportion of a certain polluted water source exceeds the pollution threshold, it is considered that the contribution of the polluted water source to the pollution is significant. When faced with multiple pollution sources in surface water, the spectral unmixing method can ensure that all pollution sources are identified, which is more applicable compared with pattern recognition, that can only identify a single pollution source.…”

Section: ■ Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Multiple Surface Water Contamination Sources Based on UV–Vis Spectral Unmixing with Turbidity Adaptiveness

Li,

Shao,

Wei

et al. 2024

ACS EST Water

Self Cite

View full text Add to dashboard Cite

Surface water contamination incidents are typically caused by an enterprise's excessive or clandestine illegal discharge. Accurate and rapid identification of pollution sources is crucial for timely pollution control and the enforcement of penalties for the responsible enterprises. At present, the identification of water pollution sources based on UV−Vis spectroscopy mostly relies on pattern recognition. However, this method is suitable only for identifying a single pollution source and cannot differentiate mixtures of multiple pollution sources. To solve this problem, an enhanced spectral unmixing method is proposed in this paper to identify multiple sources of contamination in surface water. In this method, the spectra of multiple pollution sources are used as endmembers to unmix the spectrum of the polluted surface water. The proportions (abundances) of each pollution source are then calculated to identify the pollution sources and determine the types of pollution discharge enterprises. Generally, the linear unmixing model is suitable for low-turbidity surface water, while the nonlinear unmixing model is suitable for high-turbidity surface water. A single linear or nonlinear unmixing model is not adaptive to turbidity variations in polluted surface water. Therefore, an unsupervised threshold SK-Hype hybrid unmixing algorithm is proposed in this paper. A weighted nonlinear fluctuation of endmembers is introduced to the linear function to characterize the turbidity change of surface water, and its weight is adaptively determined by the mixing mechanism of the target mixture. In this paper, experiments were conducted to unmix turbid polluted water and polluted surface water. The experimental results demonstrate that the algorithm presented in this paper exhibits higher accuracy in identifying sources of surface water pollution with turbidity adaptiveness.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: ■ Introductionmentioning

confidence: 99%

Identification of Multiple Surface Water Contamination Sources Based on UV–Vis Spectral Unmixing with Turbidity Adaptiveness

Li,

Shao,

Wei

et al. 2024

ACS EST Water

Self Cite

View full text Add to dashboard Cite

show abstract

A new method for the rapid identification of external water types in rainwater pipeline networks using UV–Vis absorption spectroscopy

Chen,

Zhao,

Zhu

et al. 2025

Spectrochimica Acta Part A: Molecular and Biomolecular Spectros

View full text Add to dashboard Cite

Wetland Landscape Dynamics and Multi-Functional Assessment of Wuhan City, China

Yan,

Gan,

Zhao

et al. 2024

Water

View full text Add to dashboard Cite

Under the dual pressures of rapid urbanization and intensifying global climate change, China has proposed governance policies aimed at promoting ecological urban construction. Wetland landscapes play a key role in sustaining human and social well-being. As a significant city in the middle reaches of the Yangtze River, Wuhan’s wetland resources play an irreplaceable role in maintaining the regional ecological balance and promoting sustainable economic and social development. However, urbanization poses a severe challenge to the ecological service functions of wetlands. Consequently, in this study, we analyzed the spatial–temporal evolution patterns of the sub-functional systems of carbon sequestration, biodiversity conservation, water yield, and water purification in five wetland types in Wuhan City from 2000 to 2020 by using the CASA model and InVEST model. Then, a wetland multi-functional assessment framework was constructed to quantify the comprehensive multi-function score. It is imperative to unravel the underlying mechanisms driving the changes in wetland functions and to explore the equilibrium point between wetland conservation and urban sustainable development. Our results show that the wetland area of Wuhan City decreased from 5077.33 km2 in 2000 to 4696.60 km2 in 2020, and the wetland multi-functions exhibited significant spatial heterogeneity from 2000 to 2020. Wetland carbon sequestration increased from 0.94 Tg in 2000 to 1.11 Tg in 2020. The wetland habitat quality declined from 0.13 in 2000 to 0.11 in 2020. The water production of the wetlands increased from 5.43 × 109 t in 2000 to 22.59 × 109 t in 2020. The wetland N loss decreased from 55,850.58 t in 2000 to 49,209.93 t in 2020. The highest multi-function score was in paddy fields, which increased from 0.41 ± 0.12 to 0.51 ± 0.12, followed by tidal flats, which increased from 0.39 ± 0.14 to 0.50 ± 0.16, and the lowest was rivers, which also increased from 0.33 ± 0.12 to 0.41 ± 0.14. The multi-function score was closely related to the wetland type and urban development direction over the past two decades, and it was negatively correlated with production and living density, providing new ideas for wetland ecological protection and construction in Wuhan City.

show abstract

Real-time discrimination of contamination source composed of multiple pollutants in surface water based on deep learning and UV–Vis spectral abundance estimation methodology

Cited by 3 publications

References 15 publications

Identification of Multiple Surface Water Contamination Sources Based on UV–Vis Spectral Unmixing with Turbidity Adaptiveness

Identification of Multiple Surface Water Contamination Sources Based on UV–Vis Spectral Unmixing with Turbidity Adaptiveness

A new method for the rapid identification of external water types in rainwater pipeline networks using UV–Vis absorption spectroscopy

Wetland Landscape Dynamics and Multi-Functional Assessment of Wuhan City, China

Contact Info

Product

Resources

About