scholarly journals Purely satellite data–driven deep learning forecast of complicated tropical instability waves

2020 ◽  
Vol 6 (29) ◽  
pp. eaba1482
Author(s):  
Gang Zheng ◽  
Xiaofeng Li ◽  
Rong-Hua Zhang ◽  
Bin Liu
Keyword(s):  
Deep Learning ◽  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Satellite Data ◽  
Numerical Models ◽  
Learning Model ◽  
Sea Surface ◽  
Data Driven ◽  
Instability Wave ◽  
Deep Learning Model

Forecasting fields of oceanic phenomena has long been dependent on physical equation–based numerical models. The challenge is that many natural processes need to be considered for understanding complicated phenomena. In contrast, rules of the processes are already embedded in the time-series observation itself. Thus, inspired by largely available satellite remote sensing data and the advance of deep learning technology, we developed a purely satellite data–driven deep learning model for forecasting the sea surface temperature evolution associated with a typical phenomenon: a tropical instability wave. During the testing period of 9 years (2010–2019), our model accurately and efficiently forecasts the sea surface temperature field. This study demonstrates the strong potential of the satellite data–driven deep learning model as an alternative to traditional numerical models for forecasting oceanic phenomena.

A hybrid CNN-LSTM based model for the prediction of sea surface temperature using time-series satellite data.

2020 ◽  
Author(s):  
Pavan Kumar Jonnakuti ◽  
Udaya Bhaskar Tata Venkata Sai
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Satellite Data ◽  
Time Series Data ◽  
Sea Surface ◽  
Machine Learning Techniques ◽  
Global Ocean ◽  
Series Data

<p>Sea surface temperature (SST) is a key variable of the global ocean, which affects air-sea interaction processes. Forecasts based on statistics and machine learning techniques did not succeed in considering the spatial and temporal relationships of the time series data. Therefore, to achieve precision in SST prediction we propose a deep learning-based model, by which we can produce a more realistic and accurate account of SST ‘behavior’ as it focuses both on space and time. Our hybrid CNN-LSTM model uses multiple processing layers to learn hierarchical representations by implementing 3D and 2D convolution neural networks as a method to better understand the spatial features and additionally we use LSTM to examine the temporal sequence of relations in SST time-series satellite data. Widespread studies, based on the historical satellite datasets spanning from 1980 - present time, in Indian Ocean region shows that our proposed deep learning-based CNN-LSTM model is extremely capable for short and mid-term daily SST prediction accurately exclusive based on the error estimates (obtained from LSTM) of the forecasted data sets.</p><p><strong>Keywords: Deep Learning, Sea Surface Temperature, CNN, LSTM, Prediction.</strong></p><p> </p>

scholarly journals Deep Learning of Sea Surface Temperature Patterns to Identify Ocean Extremes

2021 ◽  
Vol 13 (4) ◽  
pp. 744
Author(s):  
J. Xavier Prochaska ◽  
Peter C. Cornillon ◽  
David M. Reiman
Keyword(s):  
Deep Learning ◽  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Sea Surface ◽  
Space Distribution ◽  
Western Boundary ◽  
Learning Modules ◽  
Ocean Science ◽  
The Many ◽  
Future Work

We performed an out-of-distribution (OOD) analysis of ∼12,000,000 semi-independent 128 × 128 pixel2 sea surface temperature (SST) regions, which we define as cutouts, from all nighttime granules in the MODIS R2019 Level-2 public dataset to discover the most complex or extreme phenomena at the ocean’s surface. Our algorithm (ULMO) is a probabilistic autoencoder (PAE), which combines two deep learning modules: (1) an autoencoder, trained on ∼150,000 random cutouts from 2010, to represent any input cutout with a 512-dimensional latent vector akin to a (non-linear) Empirical Orthogonal Function (EOF) analysis; and (2) a normalizing flow, which maps the autoencoder’s latent space distribution onto an isotropic Gaussian manifold. From the latter, we calculated a log-likelihood (LL) value for each cutout and defined outlier cutouts to be those in the lowest 0.1% of the distribution. These exhibit large gradients and patterns characteristic of a highly dynamic ocean surface, and many are located within larger complexes whose unique dynamics warrant future analysis. Without guidance, ULMO consistently locates the outliers where the major western boundary currents separate from the continental margin. Prompted by these results, we began the process of exploring the fundamental patterns learned by ULMO thereby identifying several compelling examples. Future work may find that algorithms such as ULMO hold significant potential/promise to learn and derive other, not-yet-identified behaviors in the ocean from the many archives of satellite-derived SST fields. We see no impediment to applying them to other large remote-sensing datasets for ocean science (e.g., SSH and ocean color).

Deep Learning for Sea Temperature Eddy signature Classification

2021 ◽  
Author(s):  
Evangelos Moschos ◽  
Alexandre Stegner ◽  
Olivier Schwander ◽  
Patrick Gallinari
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Mediterranean Sea ◽  
Satellite Imagery ◽  
Mesoscale Eddies ◽  
Sea Surface ◽  
Sea Temperature ◽  
Cloud Coverage

<p>Mesoscale eddies are oceanic vortices with radii of tens of kilometers, which live on for several months or even years. They carry large amounts of heat, salt, nutrients, and pollutants from their regions of formation to remote areas, making it important to detect and track them. Using satellite altimetric maps, mesoscale eddies have been detected via remote sensing with advancing performance over the last years <strong>[1]</strong>. However, the spatio-temporal interpolation between satellite track measurements, needed to produce these maps, induces a limit to the spatial resolution (1/12° in the Med Sea) and large amounts of uncertainty in non-measured areas.</p><p>Nevertheless, mesoscale oceanic eddies also have a visible signature on other satellite imagery such as Sea Surface Temperature (SST), portraying diverse patterns of coherent vortices, temperature gradients, and swirling filaments. Learning the regularities of such signatures defines a challenging pattern recognition task, due to their complex structure but also to the cloud coverage which can corrupt a large fraction of the image.</p><p>We introduce a novel Deep Learning approach to classify sea temperature eddy signatures <strong>[2]</strong>. We create a large dataset of SST patches from satellite imagery in the Mediterranean Sea, containing Anticyclonic, Cyclonic, or No Eddy signatures, based on altimetric eddy detections of the DYNED-Atlas <strong>[3]</strong>. Our trained Convolutional Neural Network (CNN) can differentiate between these signatures with an accuracy of more than 90%, robust to a high level of cloud coverage.</p><p>We furtherly evaluate the efficiency of our classifier on SST patches extracted from oceanographic numerical model outputs in the Mediterranean Sea. Our promising results suggest that the CNN could complement the detection, tracking, and prediction of the path of mesoscale oceanic eddies.</p><p><strong>[1]</strong> <em>Chelton, D. B., Schlax, M. G. and Samelson, R. M. (2011). Global observations of nonlinear mesoscale eddies. Progress in oceanography, 91(2),167-216.</em></p><p><strong>[2]</strong> <em>E. Moschos, A. Stegner, O. Schwander and P. Gallinari, "Classification of Eddy Sea Surface Temperature Signatures Under Cloud Coverage," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 3437-3447, 2020, doi: 10.1109/JSTARS.2020.3001830.</em></p><p><strong>[3]</strong> <em>https://www.lmd.polytechnique.fr/dyned/</em></p>

scholarly journals Observed and projected sea surface temperature seasonal changes in the Western English Channel from satellite data and CMIP5 multi-model ensemble

2016 ◽  
Vol 37 (6) ◽  
pp. 2831-2849 ◽  
Author(s):  
Blandine L'Hévéder ◽  
Sabrina Speich ◽  
Olivier Ragueneau ◽  
Francis Gohin ◽  
Philippe Bryère
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Satellite Data ◽  
Seasonal Changes ◽  
Sea Surface ◽  
English Channel ◽  
Model Ensemble

Contrasting Responses of the Hadley Circulation to Equatorially Asymmetric and Symmetric Meridional Sea Surface Temperature Structures

2016 ◽  
Vol 29 (24) ◽  
pp. 8949-8963 ◽  
Author(s):  
Juan Feng ◽  
Jianping Li ◽  
Feifei Jin ◽  
Zhengyu Liu ◽  
Xing Nan ◽  
...  
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Numerical Models ◽  
Hadley Circulation ◽  
Temporal Variations ◽  
Sea Surface ◽  
Amplitude Variation ◽  
Asymmetric Mode ◽  
Tropical Sea

Abstract The impacts of different meridional structures of tropical sea surface temperature (SST) on the Hadley circulation (HC) in the annual mean are investigated during the period 1948–2013. By decomposing the variations in SST and the HC into two components—that is, the equatorially asymmetric (SEA for SST, and HEA for HC) and the equatorially symmetric (SES for SST, and HES for HC) parts—it is shown that the long-term variability in SEA and SES captures well the temporal variations in equatorially asymmetric and symmetric variations in SST. The variation in HEA is closely linked to that of SEA, and the variation in HES is connected with that of SES. However, the response of HEA to a given amplitude variation in SEA is stronger (by ~5 times) than that of HES to the same amplitude variation in SES. This point is further verified by theoretical and numerical models, indicating that the meridional structure of SST plays a crucial role in determining the anomalies in HC. This result may explain why the principal mode of HC is dominated by an equatorially asymmetric mode in its long-term variability.

Sign in / Sign up

Export Citation Format

Share Document