Data-Driven Modeling for Transferable Sea State Estimation Between Marine Systems

Cheng, Xu; Li, Guoyuan; Han, Peihua; Skulstad, Robert; Chen, Shengyong; Zhang, Houxiang

doi:10.1109/tits.2021.3129916

Cited by 13 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work extends the efforts to tackle the challenge of poor generalization exhibited by data-driven models, building upon the groundwork laid by Cheng et al [8]. Our focus is on constructing a data-driven SSE model capable of seamless transfer between various ship types and consistent performance across different loading levels of the same ship.…”

Section: Introductionmentioning

confidence: 84%

“…In the context of SSE, the first transfer learning model was created by Cheng learning [8]. Despite achieving a competitive performance, this model required considerable training time due to its intricate structure.…”

Section: B Transfer Learningmentioning

confidence: 99%

“…In oceanography, the sea state is characterized by the overall wind, wave, and swell conditions at a specific open-sea location [5]. Four prevalent approaches exist for sea state estimation (SSE): wave-buoys, weather forecasts, meteorological satellites, and wave radars [6], [7], [8]. Each method, however, has its constraints.…”

Section: Introductionmentioning

confidence: 99%

“…While addressing the aforementioned challenges, transfer learning emerges as a promising solution. Cheng et al pioneered the development of the first SSE model using transfer learning techniques [8]. However, their approach relied on a convolutional neural network (CNN)-based Siamese network for similarity learning, yielding competitive results but introducing specific limitations: 1) Computational Complexity: The model's training process is computationally demanding and time-consuming.…”

Section: Introductionmentioning

confidence: 99%

“…More precisely, we endeavor to develop an SSE model utilizing ample source ship data alongside limited target ship data. In this pursuit, we frame the SSE problem as a time series classification task, aligning with prior research in the field [9], [6], [8].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

SAFENESS: A Semi-Supervised Transfer Learning Approach for Sea State Estimation Using Ship Motion Data

Cheng,

Li,

Skulstad

et al. 2024

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

Autonomous vessels have been identified as a promising innovation in advancing marine transportation, providing an effective means to mitigate the risk of accidents, pollution incidents, and carbon dioxide emissions. Accurate sea state estimation (SSE) plays a critical role in facilitating onboard decision-making and optimizing operational efficiency for autonomous ships. Traditional SSE approaches relying on external sensors, such as wave buoys and wave radars, are limited by cost considerations. Model-based methods are highly relying on the understanding of human knowledge to ships. Data-driven models also provide promising solutions, but their generalization is low. To address this challenge, a semi-supervised transfer learning approach for SSE (SAFENESS) is proposed. The model is trained using sufficient data in the source ship and limited data from the target ship and finally applied to the target ship. A data alignment algorithm is utilized to use the limited data of the target ship. To enhance the learning capability of the framework, two attention mechanisms are proposed, and a multi-class adversarial discriminator is introduced that can align the distributions of different domains. The effectiveness of our approach is validated through comprehensive comparisons with eleven established transfer learning methods, demonstrating the superiority of our model. The competitiveness of the proposed attention modules is verified by comparing them with state-ofthe-art attention modules. The significance of each component and the influence of key parameters have been thoroughly explored in the ablation and sensitivity analysis. Our method has potential applications in maritime safety, navigation, and operation optimization.

show abstract

Section: Introductionmentioning

confidence: 84%

Section: B Transfer Learningmentioning

confidence: 99%