Sea surface temperature effects on the modelled track and intensity of tropical cyclone Gonu

Alimohammadi, Mehriar; Malakooti, Hossein; Rahbani, Maryam

doi:10.1080/1755876x.2021.1911125

Cited by 2 publications

(2 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So far, researchers have proposed many methods to predict SST, which can be classified into two categories. One category is known as the numerical prediction based on oceanography physics [4][5][6], which uses a series of complex physical equations to describe SST variation rules. Another category is data-driven models such as support vector machine (SVM) [7] and artificial neural network (ANN) [8], which automatically learn the SST change trend from SST data.…”

Section: Introductionmentioning

confidence: 99%

A TMA-Seq2seq Network for Multi-Factor Time Series Sea Surface Temperature Prediction

He¹,

Li²,

Hao³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Sea surface temperature (SST) is closely related to global climate change, ocean ecosystem, and ocean disaster. Accurate prediction of SST is an urgent and challenging task. With a vast amount of ocean monitoring data are continually collected, data-driven methods for SST time-series prediction show promising results. However, they are limited by neglecting complex interactions between SST and other ocean environmental factors, such as air temperature and wind speed. This paper uses multi-factor time series SST data to propose a sequence-to-sequence network with two-module attention (TMA-Seq2seq) for long-term time series SST prediction. Specifically, TMA-Seq2seq is an LSTM-based encoder-decoder architecture facilitated by factorand temporal-attention modules and the input of multi-factor time series. It takes six-factor time series as the input, namely air temperature, air pressure, wind speed, wind direction, SST, and SST anomaly (SSTA). A factor attention module is first designed to adaptively learn the effect of different factors on SST, followed by an encoder to extract factor-attention weighted features as feature representations. And then, a temporal attention module is designed to adaptively select the hidden states of the encoder across all time steps to learn more robust temporal relationships. The decoder follows the temporalattention module to decode the feature vector concatenated from the weighted features and original input feature. Finally, we use a fully-connect layer to map the feature into prediction results. With the two attention modules, our model effectively improves the prediction accuracy of SST since it can not only extract relevant factor features but also boost the long-term dependency. Extensive experiments on the datasets of China Coastal Sites (CCS) demonstrate that our proposed model outperforms other methods, reaching 98.29% in prediction accuracy (PACC) and 0.34 in root mean square error (RMSE). Moreover, SST prediction experiments in China's East, South, and Yellow Sea site data show that the proposed model has strong robustness and multi-site applicability.

show abstract

Section: Introductionmentioning

confidence: 99%

A TMA-Seq2seq Network for Multi-Factor Time Series Sea Surface Temperature Prediction

He¹,

Li²,

Hao³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…The mechanisms responsible for such features, however, have not been discussed. Alimohammadi et al (2021) emphasized the role of the SSTs in the track of TC Gonu, not just its magnitude but the spatial pattern as well, and stressed the important role of the observed SST gradient on its trajectory. TC Gonu also had substantial impacts in the ocean state, with warmer and high saline water flowing in from the Arabian Gulf to the Sea of Oman (Wang et al, 2012).…”

mentioning

confidence: 99%

Key Factors Modulating the Threat of the Arabian Sea's Tropical Cyclones to the Gulf Countries

2022

View full text Add to dashboard Cite

The Arabian Sea is a body of water located in the northwestern Indian Ocean. It extends to about 25°N and from the shores of Somalia on the western side, to the Arabian Peninsula (AP), Iran and Pakistan on the northwestern and northern sides, and western India on the eastern side (Qasim, 1982). The atmospheric circulation here is dominated by the Asian monsoon system, with prevailing low-level southwesterly winds in the summer season and northeasterly winds in the winter months (Schott et al., 2009). Tropical cyclone (hereafter TC) formation is unfavorable in July and August due to the (a) presence of substantial vertical wind shear, when the strong low-level southwesterly winds co-occur with upper-level easterlies associated with the Asian summer monsoon anticyclone (Basha et al., 2020), and (b) copious amounts of precipitation that lower the sea surface temperatures (SSTs) through local air-sea interactions (Fu et al., 2002). Hence, TCs typically form in the pre-monsoon (May and June) or post-monsoon (October and November) months, with an average of one storm per season (Al-Maskari, 2012;Gray, 1968). Cooler SSTs, prevailing anticyclonic relative vorticity, and higher vertical wind shear arising from the presence of the subtropical jet at upper-levels prevent storms from developing in the winter months (Evan & Camargo, 2011). The main trigger of TC formation in the northern Indian Ocean is the Madden-Julian Oscillation (MJO; Madden & Julian, 1994), which is the dominant mode of tropical intraseasonal (30-90 days) variability. The MJO is characterized by regions of enhanced/suppressed convection that propagate eastwards across the tropics, with a poleward component in the boreal summer season (Kawamura et al., 1996). Krishnamohan et al. (2012) reported that roughly 82% of the TCs which formed in the area from 1979 to 2008 occurred during active phase of the MJO. There is also considerable interannual variability, with the higher SSTs and a more favorable dynamic and thermodynamic forcing in Central Pacific El Nino and Southern Oscillation (ENSO; Ashok & Yamagata, 2009) as opposed to eastern Pacific El Nino Southern Oscillation (ENSO) events, leading to an increased likelihood of TC formation in the Arabian Sea (Sumesh & Ramesh Kumar, 2013). The recent increase in SSTs in the basin in conjunction with the Pacific Decadal Oscillation (Mantua & Hare, 2002) also contributes to more active TC seasons (Rajeevan et al., 2013).While TCs are regularly seen in the Arabian Sea, it is rare for them to move into the Sea of Oman, a small body of water that borders Oman, the United Arab Emirates (UAE), Iran and western Pakistan. Only two such occurrences have been reported since 1900 (Mahmoud, 2021): TC Gonu in 2007 which, as of 2021, is the strongest TC

show abstract

Sea surface temperature effects on the modelled track and intensity of tropical cyclone Gonu

Cited by 2 publications

References 71 publications

A TMA-Seq2seq Network for Multi-Factor Time Series Sea Surface Temperature Prediction

A TMA-Seq2seq Network for Multi-Factor Time Series Sea Surface Temperature Prediction

Key Factors Modulating the Threat of the Arabian Sea's Tropical Cyclones to the Gulf Countries

Contact Info

Product

Resources

About