Hybrid coupled modeling of the tropical Pacific using neural networks

Abstract

[1] To investigate the potential for improving hybrid coupled models (HCM) of the tropical Pacific by the use of neural network (NN) methods for nonlinear regression, NN was introduced for the nonlinear parameterization of the subsurface temperature in the Lamont ocean model and for the nonlinear estimation of the wind stress anomalies (WSA) from the sea surface temperature anomalies (SSTA). For comparison, corresponding linear regression (LR) models were also built. By combining the NN or the LR version of the ocean model and the atmospheric model, four HCMs resulted. For the coupled model Niño3 SSTA spectrum, using NN in the ocean model produced a much broader spectrum than using LR, which gave basically a single narrow spectral peak. Using NN in the atmospheric model in addition to the ocean model further broadened the SSTA spectrum, yielding a spectrum with two main peaks as observed. Principal component analysis (PCA) and nonlinear PCA (NLPCA) were used to analyze the SSTA and WSA. By comparing the NLPCA mode 1 and the PCA mode 1, we found that all the coupled models (including the original Lamont coupled model) were too linear compared to the observations. However, using NN in the ocean model and in the atmospheric model, we were able to alleviate the weak nonlinearity in the coupled models.

Tsunami Early Warning System — An Indian Ocean Perspective

“…Neural networks can be trained to solve problems that are difficult for conventional computers. Neural networks have been trained to perform complex functions in diverse fields of application which include nonlinear regression, classification, identification, pattern recognition and control systems [Bishop, 1995;Hinton, 1992;Li et al, 2005;Navone and Ceccatto, 1994;Silverman and Dracup, 2000;Venkatesan et al, 1997]. The supervised training methods are commonly used, but other networks can be obtained from unsupervised training techniques which can be used where there are no input/output pairs as such but only input data.…”

Sea surface temperature patterns in the Tropical Atlantic: Principal component analysis and nonlinear principal component analysis

“…The first mode pattern captures the zonal mode pattern in the tropical Atlantic (Zebiak 1993;Carton and Huang 1994;Huang and Shukla 1997;Handoh and Bigg 2000;Ruiz-Barradas et al 2000). By multiplying EOF1 with its related PC, we observe some typical ACT cold years, such as 1990such as , 1992such as , 1997such as , 2005such as , and warm years 1984such as , 1987such as (Caniaux et al 2011. At the end of 1964 and again in 1967, there was a general cooling over most of the Atlantic and particularly strong in the east.…”

“…It has been applied on SST to study climate variations in the tropical Pacific (e.g., Hsieh 2001;Li et al 2005). In particular, it has shown that the spatial variability associated with the ENSO phenomenon is non-linear (Hsieh 2004(Hsieh , 2007.…”

Neural network emulations for complex multidimensional geophysical mappings: Applications of neural network techniques to atmospheric and oceanic satellite retrievals and numerical modeling

“…These two concepts have been debated by Chevallier [2005] and Krasnopolsky et al [2005c] and are discussed in sections 4.2 and 4.3. Another type of hybrid model (hybrid coupled model, where a simplified atmosphere is described by a neural network model and the ocean is described by a dynamical model) was introduced and described by Tang and Hsieh [2003] and Li et al [2005].…”