A neural network‐based four‐band model for estimating the total absorption coefficients from the global oceanic and coastal waters

Cui, Tingwei; Quan, Wenting

doi:10.1002/2014jc010461

Cited by 5 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[] showed that the performance of the QAA algorithm is strongly dependent on the retrieval uncertainty of the total absorption coefficient at the reference band, but a simple empirical approach was applied for deriving this total absorption coefficient in the QAA algorithm. In fact, this empirical method could suppress some effects of backscattering signals, rather than removing them completely [ Chen et al ., ]. Consequently, the strong backscattering signals in the turbid coastal waters inevitably resulted in the large uncertainty present in the total absorption coefficient estimations [ Chen et al ., ], and then affected the QAAG results.…”

Section: Resultsmentioning

confidence: 99%

“…Note that the points at the high end were mainly taken from the turbid coastal zones where the backscattering signals were very strong. Chen et al [2015] showed that the performance of the QAA algorithm is strongly dependent on the retrieval uncertainty of the total absorption coefficient at the reference band, but a simple empirical approach was applied for deriving this total absorption coefficient in the QAA algorithm. In fact, this empirical method could suppress some effects of backscattering signals, rather than removing them completely [Chen et al, 2015].…”

Section: Test With the Global In Situ Data Setmentioning

confidence: 99%

See 1 more Smart Citation

Deriving colored dissolved organic matter absorption coefficient from ocean color with a neural quasi‐analytical algorithm

Chen

Zhou

et al. 2017

JGR Oceans

Self Cite

View full text Add to dashboard Cite

The objective of this study is to develop an approach to estimate the gelbstoff absorption coefficient (ag) from remote sensing reflectance (Rrs). This approach includes two components: the inherent optical properties are semianalytically derived from the Rrs by a neural quasianalytical algorithm (NQAA), and then the derivations are semianalytically extended to ag estimations using a band difference approach. This method is then evaluated with the various type of ocean color data including synthetic, field measured, and satellite‐observed data. The results show that the method can produce an excellent quantitative agreement between the estimated and known ag in ocean waters with a wide range of optical properties, while significantly reducing the effects of residual error in SeaWiFS Rrs, primarily from the imperfect atmospheric correction algorithm on the retrieval of ag in the clear open oceans. Furthermore, with the application of this new algorithm, the SeaWiFS ag products exhibit more spatially and temporally uniform results than the band ratio approach‐based ag retrieval algorithm. These results indicate that the new algorithm is an encouraging approach to process ocean color images for ag retrieval, although a greater number of independent tests with in situ and satellite data are required to further validate and improve this approach.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Test With the Global In Situ Data Setmentioning

confidence: 99%

Deriving colored dissolved organic matter absorption coefficient from ocean color with a neural quasi‐analytical algorithm

Chen

Zhou

et al. 2017

JGR Oceans

Self Cite

View full text Add to dashboard Cite

show abstract

“…The R rs spectra were synthesized with a database of inherent optical properties (IOP) presented in the International Ocean Color Coordinating Group report [ IOCCG , ]. The synthetic IOP data cover a wide range of aquatic environments and have been extensively used for model development and validation [ Chen et al ., ; Salama and Stein , ; Wang et al ., ; Wei and Lee , ; Wei et al ., ]. The remote‐sensing reflectance was simulated by Hydrolight 5.1 [ Mobley and Sundman , ].…”

Section: Evaluation Of the Qa Systemmentioning

confidence: 99%

“…For example, the widely used band ratio [O'Reilly et al, 1998] or band difference [Hu et al, 2012] algorithms for [CHL] rely on R rs data at both blue and green wavelengths. Semianalytical bio-optical algorithms require the R rs spectrum at more wavelengths as inputs [Ciotti et al, 1999;IOCCG, 2000IOCCG, , 2006. Thus, the QA of every individual R rs spectrum is fundamental for accurate remote sensing of water-column properties.…”

Section: Bio-optical Implications and Significancementioning

confidence: 99%

A system to measure the data quality of spectral remote sensing reflectance of aquatic environments

Wei

Lee

Shang

2016

J. Geophys. Res. Oceans

View full text Add to dashboard Cite

Spectral remote‐sensing reflectance (Rrs, sr−1) is the key for ocean color retrieval of water bio‐optical properties. Since Rrs from in situ and satellite systems are subject to errors or artifacts, assessment of the quality of Rrs data is critical. From a large collection of high quality in situ hyperspectral Rrs data sets, we developed a novel quality assurance (QA) system that can be used to objectively evaluate the quality of an individual Rrs spectrum. This QA scheme consists of a unique Rrs spectral reference and a score metric. The reference system includes Rrs spectra of 23 optical water types ranging from purple blue to yellow waters, with an upper and a lower bound defined for each water type. The scoring system is to compare any target Rrs spectrum with the reference and a score between 0 and 1 will be assigned to the target spectrum, with 1 for perfect Rrs spectrum and 0 for unusable Rrs spectrum. The effectiveness of this QA system is evaluated with both synthetic and in situ Rrs spectra and it is found to be robust. Further testing is performed with the NOMAD data set as well as with satellite Rrs over coastal and oceanic waters, where questionable or likely erroneous Rrs spectra are shown to be well identifiable with this QA system. Our results suggest that applications of this QA system to in situ data sets can improve the development and validation of bio‐optical algorithms and its application to ocean color satellite data can improve the short‐term and long‐term products by objectively excluding questionable Rrs data.

show abstract

“…However, the retrieval accuracy of SAKM model strongly depends on the estimation accuracy of quasi-analytical model (QAA)-derived a ( λ ) and b b ( λ ) [ 8 ]. Actually, the QAA model is able to suppress the effect of total backscattering coefficient, b b ( λ ), instead of eradicating it completely [ 14 ], which in turn lead to the violation of QAA model in turbid coastal waters. Moreover, Wang et al [ 10 ] and Chen et al [ 11 ] also suggested that some problems may be encountered, when the SAKM model is used to derive K d ( λ ) from turbid coastal waters.…”

Section: Introductionmentioning

confidence: 99%

A Neural Network Model for K(λ) Retrieval and Application to Global Kpar Monitoring

Chen

Zhu

et al. 2015

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Accurate estimation of diffuse attenuation coefficients in the visible wavelengths K d(λ) from remotely sensed data is particularly challenging in global oceanic and coastal waters. The objectives of the present study are to evaluate the applicability of a semi-analytical K d(λ) retrieval model (SAKM) and Jamet’s neural network model (JNNM), and then develop a new neural network K d(λ) retrieval model (NNKM). Based on the comparison of K d(λ) predicted by these models with in situ measurements taken from the global oceanic and coastal waters, all of the NNKM, SAKM, and JNNM models work well in K d(λ) retrievals, but the NNKM model works more stable and accurate than both SAKM and JNNM models. The near-infrared band-based and shortwave infrared band-based combined model is used to remove the atmospheric effects on MODIS data. The K d(λ) data was determined from the atmospheric corrected MODIS data using the NNKM, JNNM, and SAKM models. The results show that the NNKM model produces <30% uncertainty in deriving K d(λ) from global oceanic and coastal waters, which is 4.88-17.18% more accurate than SAKM and JNNM models. Furthermore, we employ an empirical approach to calculate K par from the NNKM model-derived diffuse attenuation coefficient at visible bands (443, 488, 555, and 667 nm). The results show that our model presents a satisfactory performance in deriving K par from the global oceanic and coastal waters with 20.2% uncertainty. The K par are quantified from MODIS data atmospheric correction using our model. Comparing with field measurements, our model produces ~31.0% uncertainty in deriving K par from Bohai Sea. Finally, the applicability of our model for general oceanographic studies is briefly illuminated by applying it to climatological monthly mean remote sensing reflectance for time ranging from July, 2002- July 2014 at the global scale. The results indicate that the high K d(λ) and K par values are usually found around the coastal zones in the high latitude regions, while low K d(λ) and K par values are usually found in the open oceans around the low-latitude regions. These results could improve our knowledge about the light field under waters at either the global or basin scales, and be potentially used into general circulation models to estimate the heat flux between atmosphere and ocean.

show abstract

A neural network‐based four‐band model for estimating the total absorption coefficients from the global oceanic and coastal waters

Cited by 5 publications

References 44 publications

Deriving colored dissolved organic matter absorption coefficient from ocean color with a neural quasi‐analytical algorithm

Deriving colored dissolved organic matter absorption coefficient from ocean color with a neural quasi‐analytical algorithm

A system to measure the data quality of spectral remote sensing reflectance of aquatic environments

A Neural Network Model for K(λ) Retrieval and Application to Global Kpar Monitoring

Contact Info

Product

Resources

About