Hybrid Forecasting for Functional Time Series of Dissolved Oxygen Profiles
Hybrid Forecasting for Functional Time Series of Dissolved Oxygen Profiles
复制标题
DOI：
10.1080/26941899.2022.2152401
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Luke Durell;J. Scott;A. Hering
中科院分区：
文献类型：
--
作者：
Luke Durell;J. Scott;A. Hering
将机器学习(ML)和传统的统计建模相结合是一个活跃的研究领域，有证据表明，将这两种方法结合起来可以提高模型的性能。在湖泊生态学中，探索这样的模型是必要的，因为最近的研究表明，传统的水动力学模型往往产生糟糕的短期预测。因此，在本文中，我们比较了混合模型、最大似然模型和统计模型在湖泊溶解氧(DO)剖面功能预测中的应用。函数数据具有独特的结构，其中观测数据就是函数，最近提出了几种函数数据的最大似然模型。本文中的混合模型首先获取函数主成分(FPC)来降维，然后使用前馈神经网络(NN)、递归神经网络或随机森林(RF)来预测FPC分数。纯粹的ML神经网络和RF模型独立地预测函数中的每一项测量。给出了功能统计模型和持久性模型，以供参考。比较了这七种模型的预测性能，并利用训练数据的子集建立了预测带来估计预测的不确定性。基于射频的模型预测效果最好，并且所有模型的预测频段都提供了良好的平均覆盖率。
Hybridizing machine learning (ML) and traditional statistical modeling is an active area of research, with evidence that integrating the two approaches may improve model performance. In lake ecology, exploring such models is necessary because recent research shows that traditional hydrodynamic models often produce poor short-term forecasts. Thus, in this paper, we compare a selection of hybrid, ML, and statistical models in functional forecasting of dissolved oxygen (DO) profiles in a lake. Functional data have a unique structure wherein the observations are functions, and several ML models for functional data have been recently proposed. The hybrid models in this paper first obtain functional principal components (FPCs) to reduce the dimension, and FPC scores are then forecast using a feed-forward neural network (NN), a recurrent NN, or a random forest (RF). Purely ML NN and RF models forecast each measurement in the functions independently. A functional-statistical model and the persistence model are provided for reference. The forecast performance of these seven models is compared, and prediction bands are built using a subset of the training data to estimate the prediction uncertainty. The RF-based models forecast the best, and the prediction bands of all models provide good average coverage.