Wave Height Inversion and Sea State Classification Based on Deep Learning of Radar Sea Clutter Data

Author(s):  
Ningbo Liu ◽  
Xingyu Jiang ◽  
Hao Ding ◽  
Yanan Xu ◽  
Jian Guan
2021 ◽  
Vol 13 (2) ◽  
pp. 195
Author(s):  
He Wang ◽  
Jingsong Yang ◽  
Jianhua Zhu ◽  
Lin Ren ◽  
Yahao Liu ◽  
...  

Sea state estimation from wide-swath and frequent-revisit scatterometers, which are providing ocean winds in the routine, is an attractive challenge. In this study, state-of-the-art deep learning technology is successfully adopted to develop an algorithm for deriving significant wave height from Advanced Scatterometer (ASCAT) aboard MetOp-A. By collocating three years (2016–2018) of ASCAT measurements and WaveWatch III sea state hindcasts at a global scale, huge amount data points (>8 million) were employed to train the multi-hidden-layer deep learning model, which has been established to map the inputs of thirteen sea state related ASCAT observables into the wave heights. The ASCAT significant wave height estimates were validated against hindcast dataset independent on training, showing good consistency in terms of root mean square error of 0.5 m under moderate sea condition (1.0–5.0 m). Additionally, reasonable agreement is also found between ASCAT derived wave heights and buoy observations from National Data Buoy Center for the proposed algorithm. Results are further discussed with respect to sea state maturity, radar incidence angle along with the limitations of the model. Our work demonstrates the capability of scatterometers for monitoring sea state, thus would advance the use of scatterometers, which were originally designed for winds, in studies of ocean waves.


2020 ◽  
pp. 1-12
Author(s):  
Hu Jingchao ◽  
Haiying Zhang

The difficulty in class student state recognition is how to make feature judgments based on student facial expressions and movement state. At present, some intelligent models are not accurate in class student state recognition. In order to improve the model recognition effect, this study builds a two-level state detection framework based on deep learning and HMM feature recognition algorithm, and expands it as a multi-level detection model through a reasonable state classification method. In addition, this study selects continuous HMM or deep learning to reflect the dynamic generation characteristics of fatigue, and designs random human fatigue recognition experiments to complete the collection and preprocessing of EEG data, facial video data, and subjective evaluation data of classroom students. In addition to this, this study discretizes the feature indicators and builds a student state recognition model. Finally, the performance of the algorithm proposed in this paper is analyzed through experiments. The research results show that the algorithm proposed in this paper has certain advantages over the traditional algorithm in the recognition of classroom student state features.


Author(s):  
Céline Drouet ◽  
Nicolas Cellier ◽  
Jérémie Raymond ◽  
Denis Martigny

In-service monitoring can help to increase safety of ships especially regarding the fatigue assessment. For this purpose, it is compulsory to know the environmental conditions encountered: wind, but also the full directional wave spectrum. During the EU TULCS project, a full scale measurements campaign has been conducted onboard the CMA-CGM 13200 TEU container ship Rigoletto. She has been instrumented to measure deformation of the ship as well as the sea state encountered during its trip. This paper will focus on the sea state estimation. Three systems have been installed to estimate the sea state encountered by the Rigoletto: An X-band radar from Ocean Waves with WAMOS® system and two altimetric wave radars from RADAC®. Nevertheless, the measured significant wave height can be disturbed by several external elements like bow waves, sprays, sea surface ripples, etc… Furthermore, ship motions are also measured and can provide another estimation of the significant wave height using a specific algorithm developed by DCNS Research for the TULCS project. As all those estimations are inherently different, it is necessary to make a fusion of those data to provide a single estimation (“best estimate”) of the significant wave height. This paper will present the data fusion process developed for TULCS and show some first validation results.


2014 ◽  
Vol 21 (1) ◽  
pp. 95-106
Author(s):  
Luka Mudronja ◽  
Marko Katalinić ◽  
Rino Bošnjak ◽  
Pero Vidan ◽  
Joško Parunov

AbstractThis paper presents operability guidelines for seafarers on a product tanker which navigates in the Adriatic Sea during heavy weather. Tanker route starts from the Otranto strait in the south to the island Krk in the north of Adriatic Sea. Heavy weather is caused by south wind called jugo (blowing from E-SE to SS-E, sirocco family). Operability guidelines are given based on an operability criteria platform for presenting ship seakeeping characteristics. Operability criteria considered in this paper are propeller emergence, deck wetness and bow acceleration of a product tanker. Limiting values of mentioned criteria determine sustainable speed. Heavy weather is described by extreme sea state of 7.5 m wave height. Wave spectrum used in this paper is Tabain spectrum which is developed specifically for Adriatic Sea. Seafarer's approach of decisions making in extreme weather is also shown and servers as a guideline for further research of the authors.


1988 ◽  
Vol 1 (21) ◽  
pp. 48 ◽  
Author(s):  
Akira Kimura

The probability distribution of the maximum run of irregular wave height is introduced theoretically. Probability distributions for the 2nd maximum, 3rd maximum and further maximum runs are also introduced. Their statistical properties, including the means and their confidence regions, are applied to the verification of experiments with irregular waves in the realization of a "severe sea state" in the test.


2021 ◽  
Author(s):  
Stefan Dinger ◽  
Andrei Casali ◽  
Frank Lind ◽  
Azwan Hadi Keong ◽  
Johnny Bårdsen ◽  
...  

Abstract Coiled tubing (CT) operations in the Norwegian continental shelf (NCS) often require a long and large-outside-diameter pipe due to big diameter completions, deep wells, and the need for high annular velocity during fluid circulation. However, getting the CT string onboard becomes a challenge when the crane lifting limit is 35 t, and using a standalone crane barge increases the cost of the operation. The alternative is spooling the CT from a vessel to the platform. Boat spooling is done by placing the CT string on a floating vessel with dynamic positioning while the standard CT injector head is secured at the edge of the platform to pull the pipe from the vessel to an empty CT reel on the platform. The boat is equipped with a CT guide; special tension clamps; and an emergency disconnect system, which consists of a standard CT shear-seal blowout preventer. The technique requires careful study of the platform structure for placement of the injector head support frame, metocean data of the field, and equipment placement on the vessel and platform. The boat spooling operation of a 7,700-m long, 58.7-t, 2.375-in.-outside-diameter CT string was successfully executed for a platform at 70-m height from mean sea level. The total operating time from hooking up the vessel to successfully spooling the string only took 12 hours. Historically for the region, the method has been attempted in sea state of up to 4-m wave height and 16 knots maximum wind speed. For this operation, the spooling was carried out during an average sea state of 2-m wave height and 15-knot wind speed. The continuous CT string allows a telemetry cable to be installed inside the pipe after the CT is spooled onto the platform reel, enabling real-time downhole measurements during the intervention. Such installation is not possible or presents high risk if the CT string is taken onboard by splicing two sections of pipe together with a spoolable connector or butt welding. From a cost perspective, the boat-spooling operation had up to 80% direct cost saving for the operator when compared to other methods of lifting a single CT string onboard, such as using a motion-compensated barge crane. The planning for the boat spooling included several essential contingency plans. Performing a CT boat spooling operation in a complex environment is possible and opens new opportunities to use longer and heavier CT strings, with lower mobilization costs. Such strings enable more advanced and efficient interventions, with the option of using real-time CT downhole measurements during the execution of a wide range of production startup work. This, in turn, is critical to support the drilling of more extended reach wells, which allow access to untapped reservoirs.


2021 ◽  
pp. 307-314
Author(s):  
Huan Cai ◽  
Min Xia ◽  
Li Nie ◽  
Yihan Wu ◽  
Yangsong Zhang

Sign in / Sign up

Export Citation Format

Share Document