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

Contractor, Steefan; Roughan, Moninya

doi:10.3389/fmars.2021.637759

Cited by 20 publications

(14 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

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%

Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks

et al. 2022

View full text Add to dashboard Cite

Abstract. Despite the ever-growing number of ocean data, the interior of the ocean remains undersampled in regions of high variability such as the Gulf Stream. In this context, neural networks have been shown to be effective for interpolating properties and understanding ocean processes. We introduce OSnet (Ocean Stratification network), a new ocean reconstruction system aimed at providing a physically consistent analysis of the upper ocean stratification. The proposed scheme is a bootstrapped multilayer perceptron trained to predict simultaneously temperature and salinity (T−S) profiles down to 1000 m and the mixed-layer depth (MLD) from surface data covering 1993 to 2019. OSnet is trained to fit sea surface temperature and sea level anomalies onto all historical in situ profiles in the Gulf Stream region. To achieve vertical coherence of the profiles, the MLD prediction is used to adjust a posteriori the vertical gradients of predicted T−S profiles, thus increasing the accuracy of the solution and removing vertical density inversions. The prediction is generalized on a 1/4∘ daily grid, producing four-dimensional fields of temperature and salinity, with their associated confidence interval issued from the bootstrap. OSnet profiles have root mean square error comparable with the observation-based Armor3D weekly product and the physics-based ocean reanalysis Glorys12. The lowest confidence in the prediction is located north of the Gulf Stream, between the shelf and the current, where the thermohaline variability is large. The OSnet reconstructed field is coherent even in the pre-Argo years, demonstrating the good generalization properties of the network. It reproduces the warming trend of surface temperature, the seasonal cycle of surface salinity and mesoscale structures of temperature, salinity and MLD. While OSnet delivers an accurate interpolation of the ocean stratification, it is also a tool to study how the ocean stratification relates to surface data. We can compute the relative importance of each input for each T−S prediction and analyse how the network learns which surface feature influences most which property and at which depth. Our results demonstrate the potential of machine learning methods to improve predictions of ocean interior properties from observations of the ocean surface.

show abstract

Section: Introductionmentioning

confidence: 99%

Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…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%

Reconstructing ocean subsurface salinity at high resolution using a machine learning approach

Tian

Cheng

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

Abstract. A gridded ocean subsurface salinity dataset with global coverage is useful for research on climate change and its variability. Here, we explore a machine learning approach to reconstruct a high-resolution (0.25° × 0.25°) ocean subsurface (0–2000 m) salinity dataset for the period 1993–2018 by merging in situ salinity profile observations with high-resolution (0.25° × 0.25°) satellite remote sensing altimetry absolute dynamic topography (ADT), sea surface temperature (SST), sea surface wind (SSW) field data, and a coarse resolution (1° × 1°) gridded salinity product. We show that the feed-forward neural network approach can effectively transfer small-scale spatial variations in ADT, SST and SSW fields into the 0.25° × 0.25° salinity field. The root-mean-square error (RMSE) can be reduced by ~11 % on a global-average basis compared with the 1° × 1° salinity gridded field. The reduction in RMSE is much larger in the upper ocean than the deep ocean, because of stronger mesoscale variations in the upper layers. Besides, the new 0.25° × 0.25° reconstruction shows more realistic spatial signals in the regions with strong mesoscale variations, e.g., the Gulf Stream, Kuroshio, and Antarctic Circumpolar Current regions, than the 1° × 1° resolution product, indicating the efficiency of the machine learning approach in bringing satellite observations together with in situ observations. The large-scale salinity patterns from 0.25° × 0.25° data are consistent with the 1° × 1°gridded salinity field, suggesting the persistence of the large-scale signals in the high-resolution reconstruction. The successful application of machine learning in this study provides an alternative approach for ocean and climate data reconstruction that can complement the existing data assimilation and objective analysis methods. The reconstructed IAP0.25° dataset is freely available at http://dx.doi.org/10.12157/IOCAS.20220711.001 (Tian et al., 2022).

show abstract

“…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%

Subsurface Temperature Reconstruction for the Global Ocean from 1993 to 2020 Using Satellite Observations and Deep Learning

Jiang

Wang

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

The reconstruction of the ocean’s 3D thermal structure is essential to the study of ocean interior processes and global climate change. Satellite remote sensing technology can collect large-scale, high-resolution ocean observation data, but only at the surface layer. Based on empirical statistical and artificial intelligence models, deep ocean remote sensing techniques allow us to retrieve and reconstruct the 3D ocean temperature structure by combining surface remote sensing observations with in situ float observations. This study proposed a new deep learning method, Convolutional Long Short-Term Memory (ConvLSTM) neural networks, which combines multisource remote sensing observations and Argo gridded data to reconstruct and produce a new long-time-series global ocean subsurface temperature (ST) dataset for the upper 2000 m from 1993 to 2020, which is named the Deep Ocean Remote Sensing (DORS) product. The data-driven ConvLSTM model can learn the spatiotemporal features of ocean observation data, significantly improves the model’s robustness and generalization ability, and outperforms the LighGBM model for the data reconstruction. The validation results show our DORS dataset has high accuracy with an average R2 and RMSE of 0.99/0.34 °C compared to the Argo gridded dataset, and the average R2 and NRMSE validated by the EN4-Profile dataset over the time series are 0.94/0.05 °C. Furthermore, the ST structure between DORS and Argo has good consistency in the 3D spatial morphology and distribution pattern, indicating that the DORS dataset has high quality and strong reliability, and well fills the pre-Argo data gaps. We effectively track the global ocean warming in the upper 2000 m from 1993 to 2020 based on the DORS dataset, and we further examine and understand the spatial patterns, evolution trends, and vertical characteristics of global ST changes. From 1993 to 2020, the average global ocean temperature warming trend is 0.063 °C/decade for the upper 2000 m. The 3D temperature trends revealed significant spatial heterogeneity across different ocean basins. Since 2005, the warming signal has become more significant in the subsurface and deeper ocean. From a remote sensing standpoint, the DORS product can provide new and robust data support for ocean interior process and climate change studies.

show abstract

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

Cited by 20 publications

References 41 publications

Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks

Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks

Reconstructing ocean subsurface salinity at high resolution using a machine learning approach

Subsurface Temperature Reconstruction for the Global Ocean from 1993 to 2020 Using Satellite Observations and Deep Learning

Contact Info

Product

Resources

About