2021
DOI: 10.3389/fmars.2021.637759
|View full text |Cite
|
Sign up to set email alerts
|

Efficacy of Feedforward and LSTM Neural Networks at Predicting and Gap Filling Coastal Ocean Timeseries: Oxygen, Nutrients, and Temperature

Abstract: Ocean data timeseries are vital for a diverse range of stakeholders (ranging from government, to industry, to academia) to underpin research, support decision making, and identify environmental change. However, continuous monitoring and observation of ocean variables is difficult and expensive. Moreover, since oceans are vast, observations are typically sparse in spatial and temporal resolution. In addition, the hostile ocean environment creates challenges for collecting and maintaining data sets, such as inst… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
14
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 20 publications
(14 citation statements)
references
References 41 publications
0
14
0
Order By: Relevance
“…Multiple studies recently presented deep learning methods for reconstructing hydrographic profiles from satellites. Proof-of-concept papers established the important capabilities of self-organizing maps (SOM; e.g., Charantonis et al, 2015;Gueye et al, 2014) and feed-forward or long short-term memory (LSTM) neural networks for hydrographic profile predictions (e.g., Lu, 2019;Jiang et al, 2021;Contractor and Roughan, 2021;Buongiorno Nardelli, 2020;Su et al, 2021;Sammartino et al, 2020). NNs can also efficiently reconstruct Argo interpolated fields (Gou et al, 2020;Meng et al, 2021).…”
Section: Introductionmentioning
confidence: 99%
“…Multiple studies recently presented deep learning methods for reconstructing hydrographic profiles from satellites. Proof-of-concept papers established the important capabilities of self-organizing maps (SOM; e.g., Charantonis et al, 2015;Gueye et al, 2014) and feed-forward or long short-term memory (LSTM) neural networks for hydrographic profile predictions (e.g., Lu, 2019;Jiang et al, 2021;Contractor and Roughan, 2021;Buongiorno Nardelli, 2020;Su et al, 2021;Sammartino et al, 2020). NNs can also efficiently reconstruct Argo interpolated fields (Gou et al, 2020;Meng et al, 2021).…”
Section: Introductionmentioning
confidence: 99%
“…1). An FFNN is a one-way, multi-layer structure network that includes an input layer, hidden layers, and an output layer (Abdar et al, 2021;Contractor and Roughan, 2021;Gabella, 2021;LeCun et al, 2012;Moussa et al, 2016;Vikas Gupta, 2017). The zero layer is called the input layer, the last layer is called the output layer, and the other intermediate layers are called the hidden layers.…”
Section: Independent Ocean Products For Evaluation and Comparisonmentioning
confidence: 99%
“…The subsurface thermohaline structure can be well predicted based on LSTM and its variants, and the accuracy is higher than methods such as random forests (RFs) [30], recurrent neural network (RNN) [31], support vector regression (SVR), and multilayer perceptron regressor (MLPR) [32]. LSTM is not only suitable for the inversion of ocean subsurface temperature but also has a good application in predicting other ocean internal parameters [33], such as the time series reconstruction of global ocean heat content for the upper 2000 m [34]. Because of ocean data's inherent spatial nonlinearity and temporal dependence, traditional LSTM and CNN cannot fully exploit the temporal and spatial properties of ocean data.…”
Section: Introductionmentioning
confidence: 99%