scholarly journals Retrieval of Chlorophyll-a and Total Suspended Solids Using Iterative Stepwise Elimination Partial Least Squares (ISE-PLS) Regression Based on Field Hyperspectral Measurements in Irrigation Ponds in Higashihiroshima, Japan

2017 ◽  
Vol 9 (3) ◽  
pp. 264 ◽  
Author(s):  
Zuomin Wang ◽  
Kensuke Kawamura ◽  
Yuji Sakuno ◽  
Xinyan Fan ◽  
Zhe Gong ◽  
...  
Sensors ◽  
2018 ◽  
Vol 18 (8) ◽  
pp. 2656 ◽  
Author(s):  
Zuomin Wang ◽  
Yuji Sakuno ◽  
Kazuhiko Koike ◽  
Shizuka Ohara

Harmful algal blooms (HABs) occur frequently in the Seto Inland Sea, bringing significant economic and environmental losses for the area, which is well known as one of the world’s most productive fisheries. Our objective was to develop a quantitative model using in situ hyperspectral measurements in the Seto Inland Sea to estimate chlorophyll a (Chl-a) concentration, which is a significant parameter for detecting HABs. We obtained spectra and Chl-a data at six stations from 12 ship-based surveys between December 2015 and September 2017. In this study, we used an iterative stepwise elimination partial least squares (ISE-PLS) regression method along with several empirical and semi-analytical methods such as ocean chlorophyll, three-band model, and two-band model algorithms to retrieve Chl-a. Our results showed that ISE-PLS using both the water-leaving reflectance (RL) and the first derivative reflectance (FDR) had a better predictive ability with higher coefficient of determination (R2), lower root mean squared error (RMSE), and higher residual predictive deviation (RPD) values (R2 = 0.77, RMSE = 1.47 and RPD = 2.1 for RL; R2 = 0.78, RMSE = 1.45 and RPD = 2.13 for FDR). However, in this study the ocean chlorophyll (OC) algorithms had poor predictive ability and the three-band and two-band model algorithms did not perform well in areas with lower Chl-a concentrations. These results support ISE-PLS as a potential coastal water quality assessment method using hyperspectral measurements.


1996 ◽  
Vol 47 (6) ◽  
pp. 763 ◽  
Author(s):  
EG Abal ◽  
WC Dennison

Correlations between water quality parameters and seagrass depth penetration were developed for use as a biological indicator of integrated light availability and long-term trends in water quality. A year-long water quality monitoring programme in Moreton Bay was coupled with a series of seagrass depth transects. A strong gradient between the western (landward) and eastern (seaward) portions of Moreton Bay was observed in both water quality and seagrass depth range. Higher concentrations of chlorophyll a, total suspended solids, dissolved and total nutrients, and light attenuation coefficients in the water column and correspondingly shallower depth limits of the seagrass Zostera capricorni were observed in the western portions of the bay. Relatively high correlation coefficient values (r2 > 0.8) were observed between light attenuation coefficient, total suspended solids, chlorophyll a, total Kjeldahl nitrogen and Zostera capricorni depth range. Low correlation coefficient values (r2 < 0.8) between seagrass depth range and dissolved inorganic nutrients were observed. Seagrasses had disappeared over a five-year period near the mouth of the Logan River, a turbid river with increased land use in its watershed. At a site 9 km from the river mouth, a significant decrease in seagrass depth range corresponded to higher light attenuation, chlorophyll a, total suspended solids and total nitrogen content relative to a site 21 km from the river mouth. Seagrass depth penetration thus appears to be a sensitive bio-indicator of some water quality parameters, with application for water quality management.


2014 ◽  
Vol 70 (5) ◽  
Author(s):  
Nor Fazila Rasaruddin ◽  
Mas Ezatul Nadia Mohd Ruah ◽  
Mohamed Noor Hasan ◽  
Mohd Zuli Jaafar

This paper shows the determination of iodine value (IV) of pure and frying palm oils using Partial Least Squares (PLS) regression with application of variable selection. A total of 28 samples consisting of pure and frying palm oils which acquired from markets. Seven of them were considered as high-priced palm oils while the remaining was low-priced. PLS regression models were developed for the determination of IV using Fourier Transform Infrared (FTIR) spectra data in absorbance mode in the range from 650 cm-1 to 4000 cm-1. Savitzky Golay derivative was applied before developing the prediction models. The models were constructed using wavelength selected in the FTIR region by adopting selectivity ratio (SR) plot and correlation coefficient to the IV parameter. Each model was validated through Root Mean Square Error Cross Validation, RMSECV and cross validation correlation coefficient, R2cv. The best model using SR plot was the model with mean centring for pure sample and model with a combination of row scaling and standardization of frying sample. The best model with the application of the correlation coefficient variable selection was the model with a combination of row scaling and standardization of pure sample and model with mean centering data pre-processing for frying sample. It is not necessary to row scaled the variables to develop the model since the effect of row scaling on model quality is insignificant.


2020 ◽  
Vol 113 ◽  
pp. 106236 ◽  
Author(s):  
Mohammadmehdi Saberioon ◽  
Jakub Brom ◽  
Václav Nedbal ◽  
Pavel Souc̆ek ◽  
Petr Císar̆

Author(s):  
Yin Jian-Chuan ◽  
Zou Zao-Jian ◽  
Xu Feng

Partial least squares (PLS) regression is used for identifying the hydrodynamic derivatives in the Abkowitz model for ship maneuvering motion. To identify the dynamic characteristics in ship maneuvering motion, the derivatives of hydrodynamic model's outputs are set as the target output of the PLS identification model. To verify the effectiveness of PLS parametric identification method in processing data with high dimensionality and heavy multicollinearity, the identified results of the hydrodynamic derivatives from the simulated 20 deg/20 deg zigzag test are compared with the planar motion mechanism (PMM) test results. The performance of PLS regression is also compared with that of the conventional least squares (LS) regression using the same dataset. Simulation results show the satisfactory identification and generalization performances of PLS regression and its superiority in comparison with the LS method, which demonstrates its capability in processing measurement data with high dimensionality and heavy multicollinearity, especially in processing data with small sample size.


Sign in / Sign up

Export Citation Format

Share Document