Deep learning for water quality

Nature Water, Journal Year: 2024, Volume and Issue: 2(3), P. 228 - 241

Published: March 12, 2024

Language: Английский

---

Applications and perspectives of Generative Artificial Intelligence in agriculture

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 230, P. 109919 - 109919

Published: Jan. 10, 2025

Language: Английский

---

A Review of Application of Machine Learning in Storm Surge Problems

Journal of Marine Science and Engineering, Journal Year: 2023, Volume and Issue: 11(9), P. 1729 - 1729

Published: Sept. 1, 2023

The rise of machine learning (ML) has significantly advanced the field coastal oceanography. This review aims to examine existing deficiencies in numerical predictions storm surges and effort that been made improve predictive accuracy through application ML. readers are guided steps required implement ML algorithms, from first step formulating problems data collection determination input features model selection, development evaluation. Additionally, explores hybrid methods, which combine bilateral advantages data-driven methods physics-based models. Furthermore, strengths limitations predicting thoroughly discussed, research gaps identified. Finally, we outline a vision toward trustworthy reliable surge forecasting system by introducing novel physics-informed techniques. We meant provide primer for beginners experts ocean sciences who share keen interest methodologies context problems.

Language: Английский

---

Artificial Intelligence and Machine Learning for Green Shipping: Navigating towards Sustainable Maritime Practices

JOIV International Journal on Informatics Visualization, Journal Year: 2024, Volume and Issue: 8(1), P. 1 - 1

Published: March 1, 2024

This paper aims to investigate the role that artificial intelligence (AI) plays in promoting sustainability marine industry. The report demonstrates potential of AI-driven technology improve vessel operations, decrease emissions, and promote environmental stewardship. is shown by detailed examination existing trends, problems, possibilities. Several vital studies highlight significance policy interventions encourage use intelligence. These include financial incentives, legal frameworks, programs increase capability. Throughout this work, importance driving efficiency, safety, emphasized. work also highlights urgent need for action address climate change degradation sector. industry can lessen its carbon footprint, pollution, ecosystem health if it shifts various alternative fuels, renewable energy sources, technologies powered At end an appeal made policymakers, stakeholders, providers, urging them prioritize investments research development create collaboration speed up transition a sector more sustainable resilient.

Language: Английский

---

Modeling the dynamics of harmful algal bloom events in two bays from the northern Chilean upwelling system

Harmful Algae, Journal Year: 2024, Volume and Issue: 132, P. 102583 - 102583

Published: Jan. 21, 2024

Language: Английский

---

The Diversity of Artificial Intelligence Applications in Marine Pollution: A Systematic Literature Review

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(7), P. 1181 - 1181

Published: July 14, 2024

Marine pollution, a major disturbance to the sustainable use of oceans, is becoming more prevalent around world. Multidimensional and ocean governance have become increasingly focused on managing, reducing, eliminating marine pollution. Artificial intelligence has been used in recent years monitor control This systematic literature review, encompassing studies from Web Science Scopus databases, delineates extensive role artificial pollution management, revealing significant surge research application. review aims provide information better understanding application In 57% AI applications are for monitoring, 24% 19% prediction. Three areas emphasized: (1) detecting responding oil (2) monitoring water quality its practical application, (3) identifying plastic Each area benefits unique capabilities intelligence. If scientific community continues explore refine these technologies, convergence may yield sophisticated solutions environmental conservation. Although offers powerful tools treatment it does some limitations. Future recommendations include transferring experimental outcomes industrial broader sense; highlighting cost-effective advantages control; promoting legislation policy-making about controlling

Language: Английский

---

Predicting significant wave height in the South China Sea using the SAC-ConvLSTM model

Frontiers in Marine Science, Journal Year: 2024, Volume and Issue: 11

Published: Aug. 6, 2024

Introduction The precise forecasting of Significant wave height(SWH) is vital to ensure the safety and efficiency aquatic activities such as ocean engineering, shipping, fishing. Methods This paper proposes a deep learning model named SAC-ConvLSTM perform 24-hour prediction with SWH in South China Sea. long-term capability enhanced by using attention mechanism context vectors. ability evaluated mean absolute error (MAE), root square (RMSE), (MSE), Pearson correlation coefficient (PCC). Results experimental results show that optimal input sequence length for 12. Starting from 12 hours, consistently outperforms other models predictive performance. For prediction, this achieves RMSE, MAE, PCC values 0.2117 m, 0.1083 0.9630, respectively. In addition, introduction wind can improve accuracy prediction. also has good performance compared ConvLSTM during extreme weather, especially coastal areas. Discussion presents Through comparative validation, models. inclusion data enhances model's capability. performs well under weather conditions. physical oceanography, variables related include not only but factors period sea surface air pressure. future, additional be incorporated further

Language: Английский

---

A Deep Learning Approach of Artificial Neural Network With Attention Mechanism to Predicting Marine Biogeochemistry Data

Journal of Geophysical Research Biogeosciences, Journal Year: 2025, Volume and Issue: 130(3)

Published: March 1, 2025

Abstract Predicting marine biogeochemical data is an effective method to solve the problem of data‐scarcity and provides support for fundamental research in science. Machine learning techniques are commonly used improve stability accuracy predicting biogeochemistry data. However, current methods based on Random Forest (RF) Artificial Neural network (ANN) often struggle effectively capture intricate features ocean data, resulting suboptimal prediction accuracy. In this study, we develop a novel deep called artificial neural with attention mechanism (ANN‐att) We compare evaluate performance RF, ANN, ANN‐att two widely sets biogeochemistry: GLODAP v2.2022 MOSAIC 2.0. Our results show that higher than other by 6% 30% v.2.0. Additionally, maps surface dissolved oxygen Δ 14 C West Pacific demonstrate has significant advantage stronger nonlinear characteristics.

Language: Английский

---

A Spatiotemporal Machine Learning Framework for the Prediction of Metocean Conditions in the Gulf of Mexico: Application to Loop Current and Loop Current Eddy Forecasting

Offshore Technology Conference, Journal Year: 2025, Volume and Issue: unknown

Published: April 28, 2025

Abstract We are entering an exciting new era of data-driven weather prediction, where forecast models trained on historical data (including observations and reanalyses) offer alternative to directly solving the governing equations fluid dynamics. By capitalizing a vast amount available information – capturing their inherent patterns that not represented explicitly such machine learning-based techniques have potential increase accuracy, augmenting traditional physics-based equivalents. Here, we adapt apply promising learning framework originally proposed by present authors for regional prediction ocean waves operational forecasting Loop Current Eddies (LC/LCEs) in Gulf Mexico (GoM). The approach consists using attention-based long short-term memory recurrent neural network learn temporal from observations, is then combined with random forest based spatial nowcasting model, high-resolution reanalysis data, develop complete spatiotemporal basin. Since approaches typically physics-agnostic, identical developed can be used surface currents, only difference being training datasets which this exposed. This illustrated here period three months October 2022 December 2022, model driven observation sites northern GoM. As such, it unrealistic expect performance unseen week January 2023 equivalent smaller/simpler domains more favorable quantity, quality coverage/distribution input but, despite these severe constraints, ability plausible structure LC/LCE system nonetheless impressive. architecture MaLCOM allows easy interrogation behavior us better unpick explain its characteristics thus providing path inform further enhancements. While still at early stage refinement, extension currents demonstrates encouraging fundamentally different way metocean general, forecasts particular, generated offshore energy sector, leveraging sparse sensor networks as basis predictions (further extending value when collected additional purpose mind). Provided suitable coverage, quantity available, advent very low cost, able run on-demand, in-house, standard laptop or desktop computers herald opportunities improving real-time decision-making support planning workability.

Language: Английский

---

A spatiotemporal attention-augmented ConvLSTM model for ocean remote sensing reflectance prediction

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2024, Volume and Issue: 129, P. 103815 - 103815

Published: April 5, 2024

Remote sensing reflectance (Rrs) is an essential parameter in ocean color remote and a fundamental input for the estimation of elements. Predicting Rrs has potential to enable simultaneous prediction multiple marine environmental parameters, facilitating multi-perspective analysis changes. This paper proposes spatiotemporal attention-augmented ConvLSTM-based model prediction. The developed can predict up seven days by simultaneously learning features from time series auxiliary variables. According experiments, proposed achieves optimal performances on predictions at 443, 488, 555 nm, with Root Mean Squared Error (RMSE) Absolute Percentage (MAPE) first four less than 5.6*10-4 sr-1 8.6 %, respectively, which are better performance convolutional neural network (CNN), LSTM, CNN-LSTM, ConvLSTM. spatial temporal variations also compared evaluate effectiveness model, presenting consistent pattern between predicted observed Rrs. We found that integrating sea surface temperature (SST), photosynthetically available radiation (PAR), aerosol optical thickness 869 nm (AOT869) into improve accuracy various degrees. work suggests deep 7 convincing performance, providing critical data technical support ocean-related applications, such as algae bloom monitoring.

Language: Английский

---