Lecture notes in networks and systems, Год журнала: 2024, Номер unknown, С. 651 - 660
Опубликована: Янв. 1, 2024
Язык: Английский
Aquaculture International, Год журнала: 2023, Номер 32(3), С. 2791 - 2820
Опубликована: Окт. 10, 2023
Язык: Английский
Процитировано
54
Neurocomputing, Год журнала: 2024, Номер 599, С. 128096 - 128096
Опубликована: Июнь 22, 2024
Green artificial intelligence (AI) is more environmentally friendly and inclusive than conventional AI, as it not only produces accurate results without increasing the computational cost but also ensures that any researcher with a laptop can perform high-quality research need for costly cloud servers. This paper discusses green AI pivotal approach to enhancing environmental sustainability of systems. Described are solutions eco-friendly practices in other fields (green-by AI), strategies designing energy-efficient machine learning (ML) algorithms models (green-in tools accurately measuring optimizing energy consumption. Also examined role regulations promoting future directions sustainable ML. Underscored importance aligning considerations, fostering eco-conscious
Язык: Английский
Процитировано
53
Artificial Intelligence in Agriculture, Год журнала: 2025, Номер unknown
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
2
World Journal of Advanced Research and Reviews, Год журнала: 2024, Номер 21(1), С. 1999 - 2008
Опубликована: Янв. 25, 2024
The burgeoning threat of climate change has spurred an increased reliance on advanced technologies to comprehend and mitigate its far-reaching consequences. Artificial Intelligence (AI) Machine Learning (ML) have emerged as indispensable tools in research, offering unprecedented capabilities for predictive modeling assessing environmental impact. This review synthesizes the current state AI ML applications emphasizing their role understanding repercussions. Predictive models leveraging algorithms demonstrated remarkable efficacy forecasting patterns, extreme weather events, sea-level rise. These incorporate vast datasets encompassing meteorological, geospatial, oceanic information, enabling more accurate predictions future scenarios. Moreover, AI-driven excel recognizing intricate patterns non-linear relationships within data, enhancing capacity simulate complex systems. Environmental impact assessment stands a critical facet techniques are proving instrumental this regard. facilitate analysis diverse ecological parameters, including deforestation rates, biodiversity loss, carbon sequestration dynamics. By discerning nuanced immense datasets, systems contribute direct indirect consequences ecosystems. Despite these advancements, challenges persist, such need standardized data formats, model interpretability, ethical considerations. Additionally, integration findings into policy frameworks remains crucial frontier. As intersection AI, ML, research evolves, continuous interdisciplinary collaboration is essential harness full potential safeguarding our planet's future. illuminates landscape applications, providing insights efficacy, challenges, contributions advancing sustainability.
Язык: Английский
Процитировано
9
Mersin University Journal of Maritime Faculty, Год журнала: 2024, Номер 6(1), С. 1 - 16
Опубликована: Июнь 30, 2024
Within the context of rapid technological advancements, ethical dimensions maritime security are explored, focusing on challenges and opportunities brought about by emerging technologies their implications for practices. Potential risks related to technology misuse, such as privacy infringement, disproportionate use force, erosion human judgment accountability, emphasized. The importance adopting a balanced approach that considers both benefits advancements is stressed, well need robust governance frameworks international cooperation ensure responsible in security. research methodology involves systematic literature review scholarly articles, policy documents, relevant case studies field Ethical frameworks, including proportionality, necessity, transparency, rights, applied assess like unmanned systems, cyber threats, surveillance capabilities. significance training education personnel promoting accountable decision-making underscored, article proposes inclusion simulations effective tools examining practical application effectiveness real-world scenarios. By advocating proactive balances with principles, this contributes ongoing discourse ethics, providing valuable insights policymakers, practitioners, researchers field, offering roadmap fostering secure, transparent, rights-respecting domain.
Язык: Английский
Процитировано
5
Environmental Technology, Год журнала: 2024, Номер unknown, С. 1 - 16
Опубликована: Апрель 24, 2024
This study addresses a gap in municipal leachate (MUPL) treatment by introducing pioneering application of artificial intelligence (AI) the electrocoagulation/electroflocculation (EC/EF) process utilizing iron electrodes. The overarching aim is to demonstrate efficacy AI, particularly multi-layer perceptron (MLP)-based feed-forward neural network (ANN) incorporating Levenberg-Marquardt (LMb) algorithm, predicting and optimizing EC/EF outcomes for turbidity (TDY) removal. research methodology involved experimentation robust ANN data modeling. significance this work emerges from successful integration showcasing its potential advancing wastewater, demonstrated through strong positive correlation (0.994) between model predictions experimental outcomes. achieves remarkable 99.4% TDY removal at an electrolysis time 10 min contributes valuable insights into critical parameters influencing process. Results modeling exhibit high predictive accuracy, supported elevated R-squared values minimal mean square error. Statistical analyses underscore key parameters, highlighting influential roles current intensity settling time. emphasized favourable impact maintaining acidic pH range, as it reduced electrostatic repulsion particles, facilitating pollutant agglomeration, identified factor enhancing efficiency, reduction. Energy cost savings were realized not requiring temperature elevation. Achieving translates substantial reductions other pollutants present MUPL, thereby elevating water quality ensuring compliance.
Язык: Английский
Процитировано
4
Frontiers in Marine Science, Год журнала: 2025, Номер 12
Опубликована: Апрель 15, 2025
In the context of growing demand for sustainable development and conservation fish stocks, artificial intelligence (AI) technologies are essential supporting scientific stock management. Artificial technology provides an effective solution intelligent recognition information. This study used bibliometric analysis to review a sample 719 articles from WoSCC (Web Science Core Collection) database 2014-2024. The results revealed significant increase in number publications 2014-2024, with mainly China, USA (the United States) other developed countries. top three impactful journals Ecological Informatics, Computers Electronics Agriculture ICES Journal Marine Science. most frequent keyword co-occurrence was deep learning, best clustering effect computer vision. findings indicate that this evaluation holistic visualization research frontier AI information identification, our underscore global importance identification highlight publication trends, hotspots, future directions area. conclusion, provide valuable insights into emerging frontiers AI-based identification.
Язык: Английский
Процитировано
0
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
0
Intelligent Data Analysis, Год журнала: 2025, Номер unknown
Опубликована: Май 11, 2025
Adaptive Marine Intelligence and Sensing Architecture (AMISA) is a new framework that enables the enhancement of Autonomous Underwater Vehicle (AUV) capabilities with Artificial (AI) Internet Things (IoT). In response to increasing requirement for real-time monitoring marine ecosystems sustainable ocean management, proposed work built autonomous prediction, observation, analysis through data acquisition adaptive decision-making processes. It has some cutting-edge components, such as Predictive Environment Mapping (PEM), which mines both historical adaptively detect selectively focus on regions might undergo ecological changes, Dynamic Sensor Orchestration (DSO) an energy-saving mechanism activates sensors in ecologically critical areas. Multi-tier AI Processing (MTAP) introduces efficient hierarchical model structure preliminary event detection high-level anomaly analysis, tailoring processing diverse underwater conditions. Here, Energy-Conscious Path Optimization (ECPO) uses reinforcement learning manage route planning AUV conduct optimal energy usage cover high-priority The Smart Cloud Connectivity Protocol (SCCP) allows transmission by prioritizing essential findings supports alerts. Lastly, Continuous Learning (CAL) module autonomously evolve incremental updates models data.
Язык: Английский
Процитировано
0
CABI Reviews, Год журнала: 2024, Номер unknown
Опубликована: Фев. 5, 2024
Abstract In recent years, the integration of artificial intelligence (AI) has markedly bolstered productivity, especially in agriculture, mitigating environmental impacts like greenhouse gas emissions. This shift employs a range tech, IT, sensors, robotics, and AI, boosting output while curbing negative effects. Challenges persist, notably food scarcity climate threats for growing global population. By 2050, two billion more people will need sustenance, necessitating urgent agricultural innovation. article reviewed databases from 1985 to 2023 (Google Scholar, Scopus, ISI Web Knowledge), analyzing AI’s role agriculture. Keywords precision feeding, welfare, animal husbandry, management were used systematic literature review. Findings highlight pivotal addressing shortages. Investment emerging is crucial sustainable supply.
Язык: Английский
Процитировано
3