Centro de Informática, Universidade Federal de Pernambuco, Recife, Pernambuco, Brazil.
Sci Rep. 2022 Jan 11;12(1):487. doi: 10.1038/s41598-021-04238-z.
The sea surface temperature (SST) is an environmental indicator closely related to climate, weather, and atmospheric events worldwide. Its forecasting is essential for supporting the decision of governments and environmental organizations. Literature has shown that single machine learning (ML) models are generally more accurate than traditional statistical models for SST time series modeling. However, the parameters tuning of these ML models is a challenging task, mainly when complex phenomena, such as SST forecasting, are addressed. Issues related to misspecification, overfitting, or underfitting of the ML models can lead to underperforming forecasts. This work proposes using hybrid systems (HS) that combine (ML) models using residual forecasting as an alternative to enhance the performance of SST forecasting. In this context, two types of combinations are evaluated using two ML models: support vector regression (SVR) and long short-term memory (LSTM). The experimental evaluation was performed on three datasets from different regions of the Atlantic Ocean using three well-known measures: mean square error (MSE), mean absolute percentage error (MAPE), and mean absolute error (MAE). The best HS based on SVR improved the MSE value for each analyzed series by [Formula: see text], [Formula: see text], and [Formula: see text] compared to its respective single model. The HS employing the LSTM improved [Formula: see text], [Formula: see text], and [Formula: see text] concerning the single LSTM model. Compared to literature approaches, at least one version of HS attained higher accuracy than statistical and ML models in all study cases. In particular, the nonlinear combination of the ML models obtained the best performance among the proposed HS versions.
海面温度（SST）是与全球气候、天气和大气事件密切相关的环境指标。它的预测对于支持政府和环境组织的决策至关重要。文献表明，对于 SST 时间序列建模，单一机器学习（ML）模型通常比传统统计模型更准确。然而，这些 ML 模型的参数调整是一项具有挑战性的任务，特别是在处理复杂现象（如 SST 预测）时。与 ML 模型的指定不当、过拟合或欠拟合相关的问题可能导致预测表现不佳。本工作提出使用混合系统（HS），通过残差预测将（ML）模型结合起来，作为增强 SST 预测性能的一种替代方法。在此背景下，使用两种 ML 模型（支持向量回归（SVR）和长短期记忆（LSTM））评估了两种类型的组合。使用三个来自大西洋不同区域的数据集，通过三个著名的指标（均方误差（MSE）、平均绝对百分比误差（MAPE）和平均绝对误差（MAE））对实验评估进行了评估。基于 SVR 的最佳 HS 与各自的单一模型相比，改善了每个分析序列的 MSE 值[公式：见文本]、[公式：见文本]和[公式：见文本]。采用 LSTM 的 HS 与单一 LSTM 模型相比，改善了[公式：见文本]、[公式：见文本]和[公式：见文本]。与文献方法相比，在所有研究案例中，至少有一个版本的 HS 达到了比统计和 ML 模型更高的准确性。特别是，在提出的 HS 版本中，ML 模型的非线性组合获得了最佳性能。
