IEEE Transactions on Geoscience and Remote Sensing · 2022 · 86 citations · 40 references
Natural SciencesData ScienceEarth SciencesCryosphere StudiesForecastingMachine LearningClimate ModelingDeep LearningSea Ice StudiesSea Surface TemperatureSeasonal ForecastingTime Series ForecastingConvolutional Neural NetworksDeep Learning For ForecastingDeep Learning For Time Series ForecastingDeep Learning-based ForecastingEncoder-decoder ArchitecturesFully Convolutional NetworksMeltingSea Ice Concentration Time Series
This study proposes a purely data-driven model for the weekly prediction of daily sea ice concentration (SIC) of the pan-Arctic (90 N, 45 N, 180 E, 180 W) during the melting season. The model, SICNet, adopts an encoder–decoder framework with fully convolutional networks (FCNs) and can predict the SIC (covering <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$320\times224$ </tex-math></inline-formula> grids, each with a resolution of 25 km) one-week lead with high accuracy. We design a temporal–spatial attention module (TSAM) to help SICNet capture spatiotemporal dependencies from SIC sequences. The satellite-derived SIC data of 33 years (1988–2020) from the National Snow and Ice Data Center (NSIDC) are employed to train and test the model, 1988–2015 for training, and 2016–2020 for testing. SICNet achieves the mean absolute error (MAE) of 2.67%, the mean absolute percentage error (MAPE) of 8.67%, and the Nash–Sutcliffe efficiency (NSE) of 0.9784 in weekly predicting of SIC during the melting season. SICNet achieves better performance than existing deep-learning-based models. The TSAM reduced the MAE from 2.73% to 2.67%. We evaluate the model’s performance by recursively predicting, from seven- to 28-day leads. We employ the binary accuracy (BACC) metric to measure the accuracy of the predicted sea ice extent (SIE) and compare SICNet with the anomaly persistence (Persist). SICNet shows better performance than Persist with an average BACC on the 28th day of 2016–2019 over 90% (90.17%). For the 28-day lead predictions of three extreme minimum SIE in September 2007, 2012, and 2020, SICNet outperforms Persist with an average improvement of 1.84% in BACC and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.16 milkm^{2}$ </tex-math></inline-formula> in the SIE error.
40
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Deep learning for multi-year ENSO forecasts
Yoo‐Geun Ham, Jeong-Hwan Kim, Jing‐Jia Luo · Nature · 2019 · 1.3K citations
Deep-learning-based information mining from ocean remote-sensing imagery
Xiaofeng Li, Bin Liu, Gang Zheng et al. · National Science Review · 2020 · 395 citations · Full text