[1] The influences of the directional variations and the polarization of the marine reflectance on the retrieval of the inherent optical properties (IOP) (i.e., absorption, scattering, and backscattering coefficients) of water constituents in coastal waters are examined. First, an inversion algorithm based on artificial neural network (NN) methodology is developed using a synthetic data set. The simulations were carried out using a radiative transfer model that accounts for the polarization state of light in the ocean. The simulated data included various directional effects of the particles. The data set is also constrained by observations collected in optically representative coastal waters. In particular, the relationships that exist between the IOP were taken into account, thus making the data set realistic. The results showed that the total IOP were correctly retrieved while the performance of the algorithm to derive the IOP of each water component significantly degrades. However, the inclusion of the directional variations and the polarization of the reflectance in the algorithm improved the accuracy of retrieval of the scattering properties by 15%-60% and 65%-75%, respectively. The phytoplankton and noncovarying particles (i.e., nonalgal particles) scattering and backscattering coefficients were derived with an accuracy of 25% and 15% respectively. These results demonstrate the potential of using the polarized signal to separate the total IOP into contribution of biogenic and highly refractive particles in coastal waters. Therefore the development of in situ instrumentation able to measure the polarization properties of the particles is recommended.Citation: Chami, M., and M. D. Platel (2007), Sensitivity of the retrieval of the inherent optical properties of marine particles in coastal waters to the directional variations and the polarization of the reflectance,
We introduce a new recombination operator, the Maximum Homologous Crossover for Linear Genetic Programming. In contrast to standard crossover, it attempts to preserve similar structures from parents, by aligning them according to their homology, thanks to an algorithm used in Bio-Informatics. To highlight disruptive effects of crossover operators, we introduce the Royal Road landscapes and the Homology Driven Fitness problem, for Linear Genetic Programming. Two variants of the new crossover operator are described and tested on this landscapes. Results show a reduction in the bloat phenomenon and in the frequency of deleterious crossovers.
Abstract. Genetic Programming (GP) has been shown to be a good method of predicting functions that solve inverse problems. In this context, a solution given by GP generally consists of a sole predictor. In contrast, Stack-based GP systems manipulate structures containing several predictors, which can be considered as teams of predictors. Work in Machine Learning reports that combining predictors gives good results in terms of both quality and robustness. In this paper, we use Stack-based GP to study different cooperations between predictors. First, preliminary tests and parameter tuning are performed on two GP benchmarks. Then, the system is applied to a real-world inverse problem. A comparative study with standard methods has shown limits and advantages of teams prediction, leading to encourage the use of combinations taking into account the response quality of each team member.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.