Use of Hyperspectral Remote Sensing to Estimate Water Quality

Mbuh, Mbongowo J.

doi:10.5772/intechopen.89222

Cited by 3 publications

(3 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it is worth investigating the MODIS 250-500m images for this study because large numbers of relevant images are available close to the acquisition of archived data (Table 1). MODIS's two broad high-resolution bands (250m) have been used successfully for monitoring Total Suspended Sediments (TSS) and turbidity in inland lakes and estuaries ( [17,18,19,37]). However, its ability to detect other crucial parameters, such as phytoplankton pigments (Chl-a), is limited.…”

Section: Selection Of Archived Satellite Sensor Imagesmentioning

confidence: 99%

“…Wavelength comparison for MODIS 500m bands and TM/ETM+ bands For moderate resolution satellites, at the scan edge the projection of a MODIS and MERIS detector's instantaneous field of view (IFOV) onto the earth's surface is approximately 2.0 and 4.8 times larger than at nadir in the track and scan directions, respectively[37]. The larger pixel size (approximately 2 km x 4.8 km) would significantly reduce the correlation between image data and field measured WQP data.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Earth Observation Techniques to Assess Water Quality Monitoring in the Murray Darling Basin of Australia

Forghani

Islam

Kazemi

2021

OJC

View full text Add to dashboard Cite

The Murray Darling Basin Authority (MDBA) currently has been using a discrete field sampling technique for water quality monitoring that is expensive, time consuming and may not adequately represent the spatial variability of water quality relative to the entire water body. A pilot project was executed to assess the effectiveness of using earth observation data, supported by archived field-based observations for quantitative estimation of Water Quality Parameters (WQP) and detection of algal blooms in the River Murray. The selected pilot study area includes a 100km stretch of the River Murray between the Hume Dam and Yarrawonga Weir. The time frame for the archived field samples was between November 2008 and March 2011, when major algal blooms were occurring in this stretch of the Murray River.Analysis of the 2009 data shows that waters in sites in the Murray River downstream of the Hume Dam to the Yarrawonga Weir show more temporal than spatial variability in Chl-a and PC levels. The Chl-a concentration is relatively less in the Yarrawonga Weir than in the Murray River. The scatter plot of PC vs. Turbidity suggests that PC is a more significant parameter for the detection of Cyanobacteria than Chl-a. The field data represents the temporal bio-optical variability across the 2009 algal bloom events by successfully capturing the co-variations among Chlorophyll-a, Chycocyanin and turbidity at pre, during and post bloom conditions. The methodology has proved that the usefulness of an integrated earth observation and field based WQP technique to accurately map algal bloom events. The long term MDBA RMWQMP data for the 2009 bloom event is found partially compatible to the NOW Pilot study data in that only the data for the Heywood site that was used together for testing the WQP monitoring technique. The incompatibility of the RMWQMP data downstream of Yarrawonga Weir may be due to differing techniques used for determining Chlorophyll. The 2010 data was suitable for testing the technique for complex spatial bio-optical variability during the peak of the bloom in a large water storage. Lack of Chlorophyll measurements in 2010 data poses challenges in interpreting the relationship of bio-optical variability with the spatial distributions of bio-optical parameters. As relational parameters are absent, local information and expert advice will be required to develop plausible assumptions between the Chlorophyll -Phycocyanin relationship. The field sampled data for the 2010 bloom event acquired from the Hume Dam was used for comparative investigation of both moderate resolution sensors (MODIS and MERIS) and high resolution sensors (TM/TM+). The 2009 bloom event field samples of sites in the Yarrawonga Weir was used as an input with MODIS and MERIS and the data from all the sites was applied with TM/TM+. This paper will present an integrated earth observation and field based WQP technique to accurately map algal bloom events, and discuss challenges for real time earth observation data initiatives and future collaborative projec...

show abstract

Section: Selection Of Archived Satellite Sensor Imagesmentioning

confidence: 99%

mentioning

confidence: 99%

Earth Observation Techniques to Assess Water Quality Monitoring in the Murray Darling Basin of Australia

Forghani

Islam

Kazemi

2021

OJC

View full text Add to dashboard Cite

show abstract

“…In the perspective of developing countries like Mexico, budget constraints often limit the resources allocated for water management [30]. Accessing advanced equipment, such as hyperspectral sensors or drones equipped with high-resolution multispectral cameras, can pose a significant challenge due to financial restrictions [31,32]. In this context, the study's primary objective is to introduce an innovative and cost-effective solution for monitoring WQ in Lakes Cajititlán and Zapotlán.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Machine Learning Models for Remote Sensing of Water Quality in Lakes Cajititlán and Zapotlán, Jalisco—Mexico

Villota-González,

Sulbarán-Rangel,

Zurita-Martínez

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Remote sensing has emerged as a promising tool for monitoring water quality (WQ) in aquatic ecosystems. This study evaluates the effectiveness of remote sensing in assessing WQ parameters in Cajititlán and Zapotlán lakes in the state of Jalisco, Mexico. Over time, these lakes have witnessed a significant decline in WQ, necessitating the adoption of advanced monitoring techniques. In this research, satellite-based remote sensing data were combined with ground-based measurements from the National Water Quality Monitoring Network of Mexico (RNMCA). These data sources were harnessed to train and evaluate the performance of six distinct categories of machine learning (ML) algorithms aimed at estimating WQ parameters with active spectral signals, including chlorophyll-a (Chl-a), turbidity, and total suspended solids (TSS). Various limitations were encountered during the study, primarily due to atmospheric conditions and cloud cover. These challenges affected both the quality and quantity of the data. However, these limitations were overcome through rigorous data preprocessing, the application of ML techniques designed for data-scarce scenarios, and extensive hyperparameter tuning. The superlearner algorithm (SLA), which leverages a combination of individual algorithms, and the multilayer perceptron (MLP), capable of handling complex and non-linear problems, outperformed others in terms of predictive accuracy. Notably, in Lake Cajititlán, these models provided the most accurate predictions for turbidity (r2 = 0.82, RMSE = 9.93 NTU, MAE = 7.69 NTU), Chl-a (r2 = 0.60, RMSE = 48.06 mg/m3, MAE = 37.98 mg/m3), and TSS (r2 = 0.68, RMSE = 13.42 mg/L, MAE = 10.36 mg/L) when using radiometric data from Landsat-8. In Lake Zapotlán, better predictive performance was observed for turbidity (r2 = 0.75, RMSE = 2.05 NTU, MAE = 1.10 NTU) and Chl-a (r2 = 0.71, RMSE = 6.16 mg/m3, MAE = 4.97 mg/m3) with Landsat-8 radiometric data, while TSS (r2 = 0.72, RMSE = 2.71 mg/L, MAE = 2.12 mg/L) improved when Sentinel-2 data were employed. While r2 values indicate that the models do not exhibit a perfect fit, those approaching unity suggest that the predictor variables offer valuable insights into the corresponding responses. Moreover, the model’s robustness could be enhanced by increasing the quantity and quality of input variables. Consequently, remote sensing emerges as a valuable tool to support the objectives of WQ monitoring systems.

show abstract

UAV and satellite remote sensing for inland water quality assessments: a literature review

Wasehun,

Hashemi Beni,

Di Vittorio

2024

Environ Monit Assess

View full text Add to dashboard Cite

Use of Hyperspectral Remote Sensing to Estimate Water Quality

Cited by 3 publications

References 77 publications

Earth Observation Techniques to Assess Water Quality Monitoring in the Murray Darling Basin of Australia

Earth Observation Techniques to Assess Water Quality Monitoring in the Murray Darling Basin of Australia

Assessment of Machine Learning Models for Remote Sensing of Water Quality in Lakes Cajititlán and Zapotlán, Jalisco—Mexico

UAV and satellite remote sensing for inland water quality assessments: a literature review

Contact Info

Product

Resources

About