Article
Computer Science, Interdisciplinary Applications
Buddhadev Sasmal, Abdelazim G. Hussien, Arunita Das, Krishna Gopal Dhal
Summary: Aquila Optimizer (AO) is a well-known nature-inspired optimization algorithm (NIOA) based on the prey grabbing behavior of Aquila, which was created in 2021. AO, as a population-based NIOA, has quickly demonstrated its effectiveness in complex and nonlinear optimization. This study aims to provide an updated survey on the topic, accurately reporting on the designed enhanced AO variations and their applications. Rigorous comparisons between AO and other NIOAs are conducted over mathematical benchmark functions to properly assess AO, and the experimental results show that AO achieves competitive outcomes.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Environmental Sciences
En Shi, Yanchen Shang, Yafeng Li, Miao Zhang
Summary: In this study, a self-adapting algorithm called BP-ANN was proposed to analyze cumulative risks to the water environment by combining tools from WWF, DEG, and USEPA. After optimization, the model had six hidden layers and showed a correlation coefficient with LM exceeding 80%. The findings suggest that the BP-ANN model is applicable for predicting cumulative risks and sensitive to factors such as the number of wastewater treatment facilities and treatment rate along the river.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2021)
Article
Multidisciplinary Sciences
Olusola Bamisile, Dongsheng Cai, Ariyo Oluwasanmi, Chukwuebuka Ejiyi, Chiagoziem C. Ukwuoma, Oluwasegun Ojo, Mustapha Mukhtar, Qi Huang
Summary: This study develops and compares multiple AI models for solar irradiance prediction. Through training and testing with data from six African countries, it is found that different models are suitable for different solar irradiance estimation tasks, with XG Boost performing the best overall. The study also shows that the models have more accurate predictions for hourly solar irradiance compared to daily average and minute timesteps.
SCIENTIFIC REPORTS
(2022)
Article
Green & Sustainable Science & Technology
Hailei Zhao
Summary: Green supply chain finance is a new financing method that promotes corporate capital flow and environmental protection. The study shows that BP neural network technology has a positive effect on the risk management of green finance in supply chains. The risks of green supply chain finance are more hidden, diverse, and complex, and the BP neural network's strong nonlinear mapping ability and flexible network structure help in managing these risks effectively.
Review
Environmental Sciences
Jozef Lisowski
Summary: This article introduces a combined method of remote sensing, artificial neural networks, and game theory to develop a system for safe ship traffic management at sea. It uses serial data transmission from ARPA anti-collision radar to support the computer-assisted maneuvering decisions of navigators when encountering a large number of ships. The safe and optimal trajectory of a ship is determined using static optimization, dynamic programming with neural constraints, and positional and matrix games. The presented algorithms are then used for computer calculations in a real navigational situation in the Skagerrak-Kattegat Straits recorded on the radar screen of the r/v HORYZONT II research/training vessel.
Review
Biodiversity Conservation
Chinnathambi Pothiraj, Tamilselvan Amutha Gokul, Kamatchi Ramesh Kumar, Arumugam Ramasubramanian, Ayyappan Palanichamy, Karthikeyan Venkatachalam, Paolo Pastorino, Damia Barcelo, Paulraj Balaji, Caterina Faggio
Summary: Microplastics, measuring less than 5 mm in size, have become a significant environmental concern in marine ecosystems worldwide. They primarily originate from the breakdown of larger plastic debris and pose ecological risks to marine organisms when ingested. Approximately 80% of microplastics come from terrestrial sources, including skincare products, tire production, and improper plastic disposal near coastal areas.
ECOLOGICAL INDICATORS
(2023)
Article
Biodiversity Conservation
Paolo Vassallo, Daniele Bellardini, Michela Castellano, Giulia Dapueto, Paolo Povero
Summary: This research is part of the LTER project, which conducts ecological research on a multi-decade scale. It focuses on studying the variability of zooplankton groups in the Portofino marine protected area and compares the data from 2003-2005 with that from 2018-2019. The analysis shows that environmental changes have led to increased system functioning costs and changes in the mesozooplankton community.
Article
Automation & Control Systems
ChiYan Lee, Hideyuki Hasegawa, Shangce Gao
Summary: Complex-valued neural networks (CVNNs) have shown superior performance in handling complex-valued data and signals. Researchers have made significant improvements in the learning algorithms and activation functions of CVNNs. This paper provides a comprehensive survey of recent advancements in CVNNs and discusses their structure, applications, and future research directions.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Computer Science, Artificial Intelligence
Wen Wei, Qiwen Zhang
Summary: This paper constructs a rural financial ecological environment evaluation system by combining machine learning and improved neural network algorithms. Through optimizing input layer structure, weight assignment, factor analysis, and particle swarm optimization, the system successfully avoids traditional algorithm defects and meets basic needs.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Environmental Sciences
Cui Wang, Aiyong Lin, Conghu Liu
Summary: This study proposes an assessment method based on the emergy ecological footprint for marine ecological security evaluation. By measuring the emergy of the natural and economic elements of the marine ecosystem, an ecological security evaluation index is constructed. A dynamic evaluation is conducted based on long time series data to reveal the change trend of ecological security. Using the Guangxi marine ecosystem as a case study, the results show that the ecosystem has been in an ecologically secure state but has experienced deteriorating conditions since 2010. Targeted suggestions are put forward based on the findings.
FRONTIERS IN MARINE SCIENCE
(2023)
Article
Engineering, Marine
Chuang Zhang, Xiaofan Zhang, Songtao Liu, Muzhuang Guo
Summary: Ship fires have high possibility of occurrence, large load, fast spreading, high difficulty in extinguishing, and serious losses. A ship fire risk evaluation indicator system was constructed based on the causes and severity of the fires. A comprehensive evaluation method for the fuzzy broad learning system (FBLS) was proposed and applied to the field of risk assessment for the first time, demonstrating effectiveness and accuracy. The proposed FBLS method was used to predict actual cases, and the results showed consistency with the level determined by the accident investigation report.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Optics
Jiangtao Yang, Xinyun Xu, Xin Chen, Yin Wang, Ruizhen Liu
Summary: This study proposes a robust Cubature Kalman filter (CKF) data-fusion algorithm to address the accuracy issue of the polarized light/inertial heading measurement system in complex environments. The algorithm is demonstrated to effectively filter out poor measurements. Additionally, a random forest regression (RFR) neural network model is introduced to tackle the problem of the polarized light compass signal loss in underground passages.
Article
Engineering, Marine
Yun Zhang, Hui Ma, Jianliang Xu, Hao Su, Jing Zhang
Summary: Adaptive control methods are used to adapt to coastal and nearshore physics for offshore steel structures subject to harmful vibrations. A compensating measure containing the ocean environment is proposed to decrease the dependence on accurate characteristics of the offshore platform. Numerical experiments show the effectiveness of the adaptive controller in reducing excessive vibration.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Green & Sustainable Science & Technology
Dunwen Liu, Chao Liu, Yu Tang, Chun Gong
Summary: This study focused on a highway project in Zhejiang, China, where a meteorological data monitoring system was used to monitor the meteorological factors and soil moisture of high side slopes in real time. The correlation between soil moisture and meteorological factors was investigated, and a back propagation (BP) neural network regression model optimized with genetic algorithm (GA) was proposed for soil moisture prediction. The results showed that the model improved the prediction accuracy of soil moisture and had significant implications for ecological conservation.
Article
Environmental Sciences
Ling Cai, Junlang Liang, Zhouhua Guo, Yurong Ouyang, Ming Yang, Juanjuan Dai
Summary: The coordination between marine economic development and ecological environment protection is an important issue for the development of coastal cities. This study established an evaluation system to assess the coordination between marine economic development and ecological environment protection in coastal cities of China. The statistical analysis results showed that China has paid increasing attention to marine ecological environment protection since 2012. The evaluation results demonstrated that Shanghai and Shandong Provinces had the best coordination between marine economic development and marine ecological environment protection in 2016. The data showed that marine economic development and marine ecological environment protection complement and promote each other.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)