Article
Engineering, Marine
Seongho Ahn, Trung Duc Tran, Jongho Kim
Summary: This study presents a novel approach utilizing machine-learning techniques to forecast regional wave climates using long-term wave hindcast data. The study reveals that the model's performance in global wave forecasts is spatially heterogeneous, emphasizing the need for validation of wave forecasting models in different wave sites and sea states. As access to high-resolution regional wave hindcast data improves, the accuracy of the forecasts is expected to increase.
Article
Engineering, Marine
Yuval Yevnin, Shir Chorev, Ilan Dukan, Yaron Toledo
Summary: This paper presents a deep learning model for short-term wave height prediction that uses recent in-situ measurements and an available mid-range forecast. The model significantly improves the accuracy of wave height prediction and can be easily transferred to other locations.
Article
Environmental Sciences
Zejie Tu, Xingguo Gao, Jun Xu, Weikang Sun, Yuewen Sun, Dianpeng Su
Summary: A method for regional short-term water level forecasting was proposed, involving a simplified flow model, harmonic analysis, and LSTM. Corrections based on spatial background information were applied to improve prediction accuracy. Additional exploration of incorporating meteorological features into the LSTM network revealed limitations in accurately characterizing regional dynamic energy equilibrium processes.
Article
Computer Science, Information Systems
Noman Shabbir, Lauri Kutt, Muhammad Jawad, Oleksandr Husev, Ateeq Ur Rehman, Akber Abid Gardezi, Muhammad Shafiq, Jin-Ghoo Choi
Summary: This article discusses the challenges of wind energy forecasting in terms of grid reliability, flexibility, and power quality, as well as the application of machine learning and deep learning. By analyzing and training on Estonian wind energy data, various algorithms are compared and it is found that RNN-LSTM is the most suitable and effective method for wind energy forecasting.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Immunology
Tareq Hussein, Mahmoud H. Hammad, Ola Surakhi, Mohammed AlKhanafseh, Pak Lun Fung, Martha A. Zaidan, Darren Wraith, Nidal Ershaidat
Summary: This study improves the existing COVID-19 epidemic forecast models by considering the OMICRON variant and successfully captures the sudden changes using a time-delay neural network (TDNN).
Article
Environmental Sciences
Xue Dong, Xiaowen Tang, Jiajia Tang, Shengxiao Zhao, Yanyan Lu, Xiaofeng Chen
Summary: The impact of assimilating conventional weather observations on wind forecast over the nearshore region of the East China Sea was investigated. Multi-level wind measurements in the boundary layer from five masts near the coast were used to verify the numerical model forecasts. The results show that the wind forecasts were able to reproduce the main features of the observed wind field both onshore and offshore, but larger errors were found at the offshore masts.
Article
Computer Science, Artificial Intelligence
X. J. Luo, Lukumon O. Oyedele
Summary: The building energy consumption forecasting system consists of data acquisition, pre-processing, and data analytics layers, with a core hybrid GA and LSTM neural network model. The system performs well in real-life building tests, improving forecasting accuracy and robustness.
ADVANCED ENGINEERING INFORMATICS
(2021)
Article
Engineering, Mechanical
Xiuxing Yin, Zhansi Jiang
Summary: A real-time nonlinear model predictive controller is proposed for PA-WEC to maintain optimal wave energy extraction by tracking the reference PA-WEC velocity. Wave condition preview and nonlinear optimization based on Taylor series expansion are used to design the controller. The dynamics of PA-WEC are modeled and a pragmatic method is proposed to obtain the optimal reference velocity. A LSTM-RNN identifier is designed to identify the wave condition term. The proposed controller is validated under realistic wave conditions with higher power production compared to conventional control.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Civil
I-Feng Kao, Jia-Yi Liou, Meng-Hsin Lee, Fi-John Chang
Summary: The proposed SAE-RNN model combines stacked autoencoder (SAE) with recurrent neural network (RNN) for accurate and timely flood forecasts. The model compresses flood inundation depths into low-dimensional features, forecasts multistep-ahead flood features based on regional rainfall patterns, and reconstructs the forecasts into regional flood inundation depths. The model shows favorable results in minimizing hydrologic uncertainty and converting rainfall sequences into future flood features.
JOURNAL OF HYDROLOGY
(2021)
Article
Engineering, Marine
C. Gowri Shankar, Manasa Ranjan Behera
Summary: In a region like the Northern Indian Ocean basin, the study focused on the non-linear wave-wave interactions during cyclonic conditions by incorporating pre-existing wave effects into the numerical model. The results showed that using wave boundary conditions improved the agreement between simulated wave parameters and observed field data, as well as correlated well with in-situ measurements of surge.
Article
Energy & Fuels
Hao Chen, Yngve Birkelund, Fuqing Yuan
Summary: This study investigates the use of turbulence intensity for ultra-short-term predictions of wind power and speed in an Arctic wind farm, finding that turbulence does not statistically contribute to wind power or speed forecasts. The results illustrate the uncertainty of turbulence in wind power generation and demonstrate the unique stochasticity and complexity of wind speed and power.
Article
Immunology
Tareq Hussein, Mahmoud H. Hammad, Pak Lun Fung, Marwan Al-Kloub, Issam Odeh, Martha A. Zaidan, Darren Wraith
Summary: By utilizing short-term forecast and long-term forecast models, as well as a hybrid forecast model that combines both, it is possible to more accurately predict the development of the COVID-19 pandemic. Early enforcement of curfews and planned lockdown measures can effectively reduce the spread of the virus. Vaccination has also proven to be effective in reducing infection rates.
Article
Engineering, Ocean
Nan Wang, Qin Chen, Hongqing Wang, William D. Capurso, Lukasz M. Niemoczynski, Ling Zhu, Gregg A. Snedden
Summary: This paper introduces a novel framework that utilizes scientific machine learning methods to accurately and rapidly predict the long-term hydrodynamic forcing impacting living shorelines based on short-term measurements of water levels and wind waves. The study focuses on predicting wave energy spectra in shallow water using winds and tides as input features and short-term measurements of wave spectra and water depths as labels. The developed LSTM models accurately predict wave heights, peak periods, and energy spectra around the living shorelines, capturing complex wave dynamics. The findings provide valuable insights into the efficacy of living shorelines in attenuating wave energy and demonstrate the utility of this approach in assessing the effectiveness of such structures.
APPLIED OCEAN RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Donlapark Ponnoprat
Summary: Short-term precipitation forecasting is crucial for human activity planning, and a seasonally-integrated autoencoder (SSAE) model is proposed in this study to handle nonlinearity and detect seasonality in time series. Experimental results show that SSAE outperforms other models in various climates, and the seasonal component helps improve the correlation between forecast and actual values.
APPLIED SOFT COMPUTING
(2021)
Article
Energy & Fuels
Petr Spodniak, Kimmo Ollikka, Samuli Honkapuro
Summary: As the share of wind power generation increases, markets closer to real time are becoming more important, playing a significant role in price risk hedging, capacity markets, and other decision making processes in the future.
Article
Environmental Sciences
Yong Wan, Chongwei Zheng, Jie Zhang, Yongshou Dai, Ligang Li, Xiaojun Qu, Xiaoyu Zhang
JOURNAL OF COASTAL RESEARCH
(2020)
Article
Environmental Sciences
Chong-wei Zheng, Fang Liang, Jing-long Yao, Ju-chuan Dai, Zhan-sheng Gao, Ting-ting Hou, Zi-niu Xiao
JOURNAL OF COASTAL RESEARCH
(2020)
Article
Environmental Sciences
Lei Fan, Chong-Wei Zheng, Hong-Jin Zhou, Hai-Chuan Tang, Guo Zhang, Cheng-Zhi Gao, Feng-Wang Lang, Yuan-Bo Gao
JOURNAL OF COASTAL RESEARCH
(2020)
Article
Environmental Sciences
Cheng-zhi Gao, Chong-wei Zheng, Guo Zhang, Yun-dong Han, Feng Tian, Xiao-guang Liu, Lu-cai Wang, Da Zhang, Zi-niu Xiao
JOURNAL OF COASTAL RESEARCH
(2020)
Article
Oceanography
Chongwei Zheng, Bingchen Liang, Xuan Chen, Guoxiang Wu, Xiaofang Sun, Jinglong Yao
JOURNAL OF OCEAN UNIVERSITY OF CHINA
(2020)
Article
Multidisciplinary Sciences
Andres M. Cisneros-Montemayor, Marcia Moreno-Baez, Gabriel Reygondeau, William W. L. Cheung, Katherine M. Crosman, Pedro C. Gonzalez-Espinosa, Vicky W. Y. Lam, Muhammed A. Oyinlola, Gerald G. Singh, Wilf Swartz, Chong-wei Zheng, Yoshitaka Ota
Summary: The future of the global ocean economy is envisioned as advancing towards a 'blue economy' which emphasizes socially equitable, environmentally sustainable, and economically viable ocean industries. Differences in outlook on the capacity for establishing a blue economy exist, with key factors including national stability, corruption, and infrastructure. Policymakers must engage researchers and stakeholders to ensure evidence-based, collaborative planning that prioritizes local benefits and aligns with social, environmental, and economic goals.
Article
Green & Sustainable Science & Technology
Chong-wei Zheng
Summary: This study proposed to create a global oceanic WERD, with the Maritime Silk Road as a case study, which comprehensively includes not only the traditional focus of wave energy, but also adds seven new modules, aiming to provide scientific reference and decision support for the rational utilization of wave energy resources.
Article
Oceanography
Yang Shaobo, Xi Lintong, Li Xingfei, Zheng Chongwei
Summary: The study evaluated the wave energy resources around Sri Lankan waters and found extremely optimistic resources in the western, southern, and southeastern waters of the country. The period of June, July, August was identified with great advantages in terms of wave power density, wave energy effective storage, and contribution rate of wave energy.
JOURNAL OF OCEAN UNIVERSITY OF CHINA
(2021)
Article
Green & Sustainable Science & Technology
Shaobo Yang, Zegui Deng, Xingfei Li, Chongwei Zheng, Lintong Xi, Jucheng Zhuang, Zhenquan Zhang, Zhiyou Zhang
Summary: A hybrid model STL-CNN-PE combining STL and CNN was proposed to forecast significant wave height efficiently and accurately. Experimental results showed that this model provided more reliable forecasting values, faster speed, and similar precision compared with a single model.
Article
Thermodynamics
Chong-wei Zheng
Summary: This study proposes a wave energy classification scheme that takes into account energy, environmental risk, and cost factors, and suggests a dynamic self-adjusting energy classification method. The global wave energy resources are generally abundant, with significant regional differences in the wave energy classes obtained by the new scheme.
Article
Energy & Fuels
Zhenyu Li, Zi-niu Xiao, Chong-wei Zheng
Summary: The statistical characteristics of wind climate in mainland China were analyzed in this study, revealing the differences in wind speed distribution and trends in different regions and seasons. Overall, wind speed has been decreasing in all regions of China, but the trend has slowed down since the 1990s, with some regions even experiencing an increase in wind speed since 2000.
Article
Engineering, Electrical & Electronic
Keliu Long, Chongwei Zheng, Kun Zhang, Chuan Tian, Chong Shen
Summary: In this study, a positioning framework based on multiple transfer learning fusion using Generalized Policy Iteration (GPI) is proposed. With the introduction of techniques such as 1-Dimension Convolutional Autoencoder and Domain Adversarial Neural Network, the framework effectively addresses the challenges posed by dynamic environments in indoor positioning, providing accurate and stable localization performance.
IEEE SENSORS JOURNAL
(2022)
Review
Green & Sustainable Science & Technology
Chongwei Zheng
Summary: This article examines the classification scheme of wave energy and identifies the limitations of the current scheme. To address these limitations, a dynamic adaptive classification scheme for wave energy is proposed, along with the concept of future energy classification, with the aim of promoting the industrialization and scaling of wave energy.
Article
Energy & Fuels
Kaishan Wang, Di Wu, Kai Wu, Kun Yu, Chongwei Zheng
Summary: The navigation and utilization of the Arctic have attracted global interest due to its economic and strategic significance. This study analyzes the intergenerational variations in Arctic wind energy resources and finds that the Northeast Passage, Davis Strait, and Baffin Bay have favorable wind power density, effective wind speed occurrence, energy level frequency, stability, and resource reserves. However, the Barents Sea, Canada's northern archipelagos, and Greenland's vicinity have relatively poor wind energy resources.