Yongzhen Fan, Wei Li, Kenneth J. Voss, Charles K. Gatebe, and Knut Stamnes, "Neural network method to correct bidirectional effects in water-leaving radiance," Appl. Opt. 55, 10-21 (2016)
Ocean color algorithms that rely on “atmospherically corrected” nadir water-leaving radiances to infer information about marine constituents such as the chlorophyll concentration depend on a reliable method to convert the angle-dependent measured radiances from the observation direction to the nadir direction. It is also important to convert the measured radiances to the nadir direction when comparing and merging products from different satellite missions. The standard correction method developed by Morel and coworkers requires knowledge of the chlorophyll concentration. Also, the standard method was developed based on the Case 1 (open ocean) assumption, which makes it unsuitable for Case 2 situations such as turbid coastal waters. We introduce a neural network method to convert the angle-dependent water-leaving radiance (or the corresponding remote sensing reflectance) from the observation direction to the nadir direction. This method relies on neither an “atmospheric correction” nor prior knowledge of the water constituents or the inherent optical properties. It directly converts the remote sensing reflectance from an arbitrary slanted viewing direction to the nadir direction by using a trained neural network. This method is fast and accurate, and it can be easily adapted to different remote sensing instruments. Validation using NuRADS measurements in different types of water shows that this method is suitable for both Case 1 and Case 2 waters. In Case 1 or chlorophyll-dominated waters, our neural network method produces corrections similar to those of the standard method. In Case 2 waters, especially sediment-dominated waters, a significant improvement was obtained compared to the standard method.
Peng-Wang Zhai, Yongxiang Hu, Charles R. Trepte, David M. Winker, Patricia L. Lucker, Zhongping Lee, and Damien B. Josset Appl. Opt. 54(13) 4061-4069 (2015)
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Coefficient of Determination () of Derived Nadir a
All Cases ()
Clean ()
Moderate/Turbid ()
[nm]
No BRDF
MAG02
NN
No BRDF
MAG02
NN
No BRDF
MAG02
NN
No BRDF
MAG02
NN
412
0.9820
0.9975
0.9996
0.9950
0.9970
0.9979
0.9821
0.9975
0.9996
0.9900
0.9935
0.9990
443
0.9803
0.9961
0.9995
0.9925
0.9962
0.9992
0.9803
0.9961
0.9995
0.9902
0.9902
0.9987
490
0.9805
0.9904
0.9995
0.9879
0.9944
0.9992
0.9803
0.9903
0.9995
0.9878
0.9800
0.9987
510
0.9818
0.9877
0.9996
0.9866
0.9942
0.9991
0.9815
0.9875
0.9996
0.9870
0.9754
0.9988
560
0.9855
0.9819
0.9997
0.9849
0.9938
0.9988
0.9853
0.9816
0.9997
0.9864
0.9662
0.9991
620
0.9896
0.9872
0.9998
0.9836
0.9953
0.9984
0.9895
0.9872
0.9998
0.9881
0.9739
0.9995
665
0.9901
0.9900
0.9998
0.9785
0.9916
0.9982
0.9900
0.9900
0.9998
0.9877
0.9786
0.9995
From the synthetic dataset using the isotropic assumption, i.e., no BRDF correction, the MAG02 algorithm, and our NN algorithm results are shown at all wavelengths for all synthetic data, “clear” water synthetic data, “moderate/turbid” water synthetic data, and data with large viewing angles.
From the synthetic dataset using the isotropic assumption, i.e., no BRDF correction, the MAG02 algorithm, and our NN algorithm results are shown at all wavelengths for all synthetic data, “clear” water synthetic data, “moderate/turbid” water synthetic data, and data with large viewing angles.
From the synthetic dataset using the isotropic assumption, i.e., no BRDF correction, the MAG02 algorithm, and our NN algorithm results are shown at all wavelengths for all synthetic data, “clear” water synthetic data, “moderate/turbid” water synthetic data, and data with large viewing angles.
Derived from NuRADS measurements using the NN and MAG02 algorithms. Results are shown at all wavelengths for the four validation datasets: BP09, SORTIE, BIOSOPE, and OCCV.
Derived from NuRADS measurements using the NN and MAG02 algorithms. Results are shown at all wavelengths for the four validation datasets: BP09, SORTIE, BIOSOPE, and OCCV.
Derived from NuRADS measurements using the NN and MAG02 algorithms. Results are shown at all wavelengths for the four validation datasets: BP09, SORTIE, BIOSOPE, and OCCV.
Tables (6)
Table 1.
Coefficient of Determination () of Derived Nadir a
All Cases ()
Clean ()
Moderate/Turbid ()
[nm]
No BRDF
MAG02
NN
No BRDF
MAG02
NN
No BRDF
MAG02
NN
No BRDF
MAG02
NN
412
0.9820
0.9975
0.9996
0.9950
0.9970
0.9979
0.9821
0.9975
0.9996
0.9900
0.9935
0.9990
443
0.9803
0.9961
0.9995
0.9925
0.9962
0.9992
0.9803
0.9961
0.9995
0.9902
0.9902
0.9987
490
0.9805
0.9904
0.9995
0.9879
0.9944
0.9992
0.9803
0.9903
0.9995
0.9878
0.9800
0.9987
510
0.9818
0.9877
0.9996
0.9866
0.9942
0.9991
0.9815
0.9875
0.9996
0.9870
0.9754
0.9988
560
0.9855
0.9819
0.9997
0.9849
0.9938
0.9988
0.9853
0.9816
0.9997
0.9864
0.9662
0.9991
620
0.9896
0.9872
0.9998
0.9836
0.9953
0.9984
0.9895
0.9872
0.9998
0.9881
0.9739
0.9995
665
0.9901
0.9900
0.9998
0.9785
0.9916
0.9982
0.9900
0.9900
0.9998
0.9877
0.9786
0.9995
From the synthetic dataset using the isotropic assumption, i.e., no BRDF correction, the MAG02 algorithm, and our NN algorithm results are shown at all wavelengths for all synthetic data, “clear” water synthetic data, “moderate/turbid” water synthetic data, and data with large viewing angles.
From the synthetic dataset using the isotropic assumption, i.e., no BRDF correction, the MAG02 algorithm, and our NN algorithm results are shown at all wavelengths for all synthetic data, “clear” water synthetic data, “moderate/turbid” water synthetic data, and data with large viewing angles.
From the synthetic dataset using the isotropic assumption, i.e., no BRDF correction, the MAG02 algorithm, and our NN algorithm results are shown at all wavelengths for all synthetic data, “clear” water synthetic data, “moderate/turbid” water synthetic data, and data with large viewing angles.
Derived from NuRADS measurements using the NN and MAG02 algorithms. Results are shown at all wavelengths for the four validation datasets: BP09, SORTIE, BIOSOPE, and OCCV.
Derived from NuRADS measurements using the NN and MAG02 algorithms. Results are shown at all wavelengths for the four validation datasets: BP09, SORTIE, BIOSOPE, and OCCV.
Derived from NuRADS measurements using the NN and MAG02 algorithms. Results are shown at all wavelengths for the four validation datasets: BP09, SORTIE, BIOSOPE, and OCCV.