Loop Current SSH Forecasting: A New Domain Partitioning Approach for a Machine Learning Model

Justin L Wang,Hanqi Zhuang,Ali Ibrahim,Laurent Chérubin,Ali Muhamed Ali

doi:10.3390/forecast3030036

Abstract

A divide-and-conquer (DAC) machine learning approach was first proposed by Wang et al. to forecast the sea surface height (SSH) of the Loop Current System (LCS) in the Gulf of Mexico. In this DAC approach, the forecast domain was divided into non-overlapping partitions, each of which had their own prediction model. The full domain SSH prediction was recovered by interpolating the SSH across each partition boundaries. Although the original DAC model was able to predict the LCS evolution and eddy shedding more than two months and three months in advance, respectively, growing errors at the partition boundaries negatively affected the model forecasting skills. In the study herein, a new partitioning method, which consists of overlapping partitions is presented. The region of interest is divided into 50%-overlapping partitions. At each prediction step, the SSH value at each point is computed from overlapping partitions, which significantly reduces the occurrence of unrealistic SSH features at partition boundaries. This new approach led to a significant improvement of the overall model performance both in terms of features prediction such as the location of the LC eddy SSH contours but also in terms of event prediction, such as the LC ring separation. We observed an approximate 12% decrease in error over a 10-week prediction, and also show that this method can approximate the location and shedding of eddy Cameron better than the original DAC method.

Highlights

The Gulf of Mexico (GoM) is a semi-enclosed basin whose circulation is dominated by the Loop Current (LC), which sheds large anticyclonic eddies called Loop Current eddies (LCE) at varying time intervals [1]
While the Divide and Conquer (DAC) method was relatively effective in forecasting the eddy frontal positions, merging the sea surface height (SSH) predictions across the partitions contributed to error propagation
In order to mitigate this DAC model error, we proposed in the study a new prediction domain partition approach in which the partitions are overlapping

Summary

Introduction

The Gulf of Mexico (GoM) is a semi-enclosed basin whose circulation is dominated by the Loop Current (LC), which sheds large anticyclonic eddies called Loop Current eddies (LCE) at varying time intervals [1]. In order to reduce the computational costs associated with the handling of large datasets, the region of interest was partitioned into smaller non-overlapping sub-regions In such an approach, the local features associated with the LC evolution and eddy shedding can be resolved. An empirical orthogonal function (EOF) decomposition was applied to the SSH in order to reduce its dimension At this point, each time series of principle components from each partition was independently predicted with local expert LSTM networks. The SSH value at each prediction point is obtained by a weighted average of the SSH values of the same point in the overlapping region of the partitions This procedure avoids the progressive smoothing process across partition boundaries, which was implemented in the original DAC method. Forecast experiments were conducted for approximately eighty 20-week sliding windows over the testing period

Recurrent Learning

Divide and Conquer Prediction Model of the Gom SSH

Sinusoidal-Weighted Overlapped Partitioning

LSTM Forecasting of the Gom SSH with Overlapping Partitions

Findings

Conclusions