Regression-Based Networked Virtual Buoy Model for Offshore Wave Height Prediction DOI Creative Commons
Eleonora M. Tronci,

Matteo Vitale,

Therese Patrosio

et al.

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(4), P. 728 - 728

Published: April 5, 2025

Accurate wave height measurements are critical for offshore wind farm operations, marine navigation, and environmental monitoring. Wave buoys provide essential real-time data; however, their reliability is compromised by harsh conditions, resulting in frequent data gaps due to sensor failures, maintenance issues, or extreme weather events. These disruptions pose significant risks decision-making logistics safety planning. While numerical models machine learning techniques have been explored prediction, most approaches rely heavily on historical from the same buoy, limiting applicability when target offline. This study addresses these limitations developing a virtual buoy model using network-based data-driven approach with Random Forest Regression (RFR). By leveraging surrounding buoys, proposed ensures continuous estimation even case of malfunctioning physical sensors. The methodology tested across four sites, including operational farms, evaluating sensitivity predictions placement feature selection. demonstrates high accuracy incorporates k-nearest neighbors (kNN) imputation strategy mitigate loss. findings establish RFR as scalable computationally efficient alternative sensing, thereby enhancing resilience, safety, efficiency.

Language: Английский

Data-Driven Models for Significant Wave Height Forecasting: Comparative Analysis of Machine Learning Techniques DOI Creative Commons
Ahmet Durap

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103573 - 103573

Published: Dec. 1, 2024

Language: Английский

Citations

4
Deep Learning-Based Real-Time Surf Detection Model During Typhoon Events DOI Creative Commons

Yongying Shi,

Guangjun Xu, Yuli Liu

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(6), P. 1039 - 1039

Published: March 16, 2025

Surf during typhoon events poses severe threats to coastal infrastructure and public safety. Traditional monitoring approaches, including in situ sensors numerical simulations, face inherent limitations capturing surf impacts—sensors are constrained by point-based measurements, while simulations require intensive computational resources for real-time monitoring. Video-based offers promising potential continuous observation, yet the development of deep learning models detection remains underexplored, primarily due lack high-quality training datasets from events. To bridge this gap, we propose a lightweight YOLO (You Only Look Once) based framework detection. A novel dataset 2855 labeled images with annotations, collected five at Chongwu Tide Gauge Station, captures diverse scenarios such as daytime, nighttime, extreme weather conditions. The proposed YOLOv6n model achieved 99.3% mAP50 161.8 FPS, outperforming both other variants traditional two-stage detectors accuracy efficiency. Scaling analysis further revealed that 2–5 M parameters provide an optimal trade-off between These findings demonstrate effectiveness YOLO-based video systems detection, offering practical reliable solution hazard under

Language: Английский

Citations

0
Dynamics in salinity diffusion influenced by anthropogenic pressures and climate change: a case study of the Aghien lagoon (Abidjan, Côte d’Ivoire) DOI

Bi Sehi GOE,

Amidou Dao, Akahoua D. V. Brou

et al.

International Journal of River Basin Management, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 14

Published: March 24, 2025

By 2070, the Aghien Lagoon, which is influenced by both riverine and marine inputs, expected to experience cumulative effects of anthropogenic activities particularly opening Comoe river estuary climate change. However, medium-term impact these pressures on lagoon's salinity dynamics has never been assessed. This study aims evaluate influence factors lagoon up 2070. To this end, discharge water level data were collected. Depth measurements tributaries conducted before after estuary. The collected then used validate a hydrodynamic diffusion model. Simulations indicated that sea rise under SSP5-8.5 scenario would result in increase approximately 0.3 PSU, representing 200% rise. appears have no effect northern part lagoon, where abstraction take place. Consequently, Lagoon could potentially be for drinking production Nevertheless, more comprehensive understanding vertical variation within necessitates three-dimensional modelling.

Language: Английский

Citations

0
Regression-Based Networked Virtual Buoy Model for Offshore Wave Height Prediction DOI Creative Commons
Eleonora M. Tronci,

Matteo Vitale,

Therese Patrosio

et al.

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(4), P. 728 - 728

Published: April 5, 2025

Accurate wave height measurements are critical for offshore wind farm operations, marine navigation, and environmental monitoring. Wave buoys provide essential real-time data; however, their reliability is compromised by harsh conditions, resulting in frequent data gaps due to sensor failures, maintenance issues, or extreme weather events. These disruptions pose significant risks decision-making logistics safety planning. While numerical models machine learning techniques have been explored prediction, most approaches rely heavily on historical from the same buoy, limiting applicability when target offline. This study addresses these limitations developing a virtual buoy model using network-based data-driven approach with Random Forest Regression (RFR). By leveraging surrounding buoys, proposed ensures continuous estimation even case of malfunctioning physical sensors. The methodology tested across four sites, including operational farms, evaluating sensitivity predictions placement feature selection. demonstrates high accuracy incorporates k-nearest neighbors (kNN) imputation strategy mitigate loss. findings establish RFR as scalable computationally efficient alternative sensing, thereby enhancing resilience, safety, efficiency.

Language: Английский

Citations

0