DECIPHERING THE DEEP: MACHINE LEARNING APPROACHES TO UNDERSTANDING OCEANIC ECOSYSTEMS DOI
Tymoteusz Miller, Adrianna Łobodzińska,

Oliwia Kaczanowska

et al.

ГРААЛЬ НАУКИ, Journal Year: 2024, Volume and Issue: 36, P. 526 - 534

Published: Feb. 26, 2024

This paper presents a detailed exploration of the transformative role Machine Learning (ML) in oceanographic research, encapsulating paradigm shift towards more efficient and comprehensive analysis marine ecosystems. It delves into multifaceted applications ML, ranging from predictive modeling ocean currents to in-depth biodiversity deciphering complexities deep-sea ecosystems through advanced computer vision techniques. The discussion extends challenges opportunities that intertwine with integration AI ML oceanography, emphasizing need for robust data collection, interdisciplinary collaboration, ethical considerations. Through series case studies thematic discussions, this underscores profound potential revolutionize our understanding preservation oceanic ecosystems, setting new frontier future research conservation strategies realm oceanography.

Language: Английский

Machine learning for efficient segregation and labeling of potential biological sounds in long-term underwater recordings DOI Creative Commons
Clea Parcerisas, Elena Schall, Kees te Velde

et al.

Frontiers in Remote Sensing, Journal Year: 2024, Volume and Issue: 5

Published: April 25, 2024

Studying marine soundscapes by detecting known sound events and quantifying their spatio-temporal patterns can provide ecologically relevant information. However, the exploration of underwater data to find identify possible interest be highly time-intensive for human analysts. To speed up this process, we propose a novel methodology that first detects all potentially acoustic then clusters them in an unsupervised way prior manual revision. We demonstrate its applicability on short deployment. detect events, deep learning object detection algorithm from computer vision (YOLOv8) is re-trained any (short) event. This done converting audio spectrograms using sliding windows longer than expected interest. The model event present window provides time frequency limits. With approach, multiple happening simultaneously detected. further explore possibilities limit input needed create annotations train model, active approach select most informative files iterative manner subsequent annotation. obtained models are trained tested dataset Belgian Part North Sea, evaluated robustness freshwater major European rivers. proposed outperforms random selection files, both datasets. Once detected, they converted embedded feature space BioLingual which classify different (biological) sounds. representations clustered way, obtaining classes. These classes manually revised. method applied unseen as tool help bioacousticians recurrent sounds save when studying patterns. reduces researchers need go through long recordings allows conduct more targeted analysis. It also framework monitor regardless whether sources or not.

Language: Английский

Citations

2

Enhanced Detection and Classification of Microplastics in Marine Environments Using Deep Learning DOI
Pensiri Akkajit, Md Eshrat E. Alahi, Arsanchai Sukkuea

et al.

Regional Studies in Marine Science, Journal Year: 2024, Volume and Issue: unknown, P. 103880 - 103880

Published: Oct. 1, 2024

Language: Английский

Citations

2

Priority Setting and Resource Allocation in Coastal Local Government Marine Regulatory Reform: Application of Machine Learning in Resource Optimization DOI Open Access
Yingying Tian, Qi Wang

Water, Journal Year: 2024, Volume and Issue: 16(11), P. 1544 - 1544

Published: May 27, 2024

This study investigates the prioritization and resource allocation strategies adopted by coastal local governments of Qingdao, Dalian, Xiamen in context marine regulatory reform aimed at enhancing efficiency. Data on relevant opinions, departmental requirements, existing allocations were collected through a questionnaire survey. A backpropagation (BP) neural network was then applied to analyze survey data, prioritize tasks, propose schemes. The findings demonstrate that integrating machine learning into regulation can significantly improve utilization efficiency, optimize task execution sequences, enhance scientific refined nature work. BP model exhibited strong predictive capabilities training set demonstrated good generalization abilities test set. performance varied slightly across different management levels. For level, accuracy, precision, recall rates 85%, 88%, 82%, respectively. supervisory these metrics 81%, 83%, 78%, At employee 79%, 76%, These results indicate provide differentiated recommendations based needs Additionally, model’s assessed employees’ years experience. employees with 0–5 experience, 84%, those 5–10 86%, 80%, over 10 data further confirm applicability effectiveness experience groups. Thus, adoption technologies for optimizing resources holds significant practical value, aiding enhancement capacity within governments.

Language: Английский

Citations

2

Meanders on the Move: Can AI-Based Solutions Predict Where They Will Be Located? DOI Open Access
Hossein Amini, Federico Monegaglia, Reza Shakeri

et al.

Water, Journal Year: 2024, Volume and Issue: 16(17), P. 2460 - 2460

Published: Aug. 29, 2024

Meandering rivers are complex geomorphic systems that play an important role in the environment. They provide habitat for a variety of plants and animals, help to filter water, reduce flooding. However, meandering also susceptible changes flow, sediment transport, erosion. These can be caused by natural factors such as climate change human activities dam construction agriculture. Studying is understanding their dynamics developing effective management strategies. traditional methods numerical analytical modeling studying time-consuming and/or expensive. Machine learning algorithms used overcome these challenges more efficient comprehensive way study rivers. In this study, we machine migration rate simulated using semi-analytical model investigate feasibility employing new method. We then multi-layer perceptron, eXtreme Gradient Boost, gradient boosting regressor, decision tree predict rate. The results show ML prediction rate, which turn planform position.

Language: Английский

Citations

2

DECIPHERING THE DEEP: MACHINE LEARNING APPROACHES TO UNDERSTANDING OCEANIC ECOSYSTEMS DOI
Tymoteusz Miller, Adrianna Łobodzińska,

Oliwia Kaczanowska

et al.

ГРААЛЬ НАУКИ, Journal Year: 2024, Volume and Issue: 36, P. 526 - 534

Published: Feb. 26, 2024

This paper presents a detailed exploration of the transformative role Machine Learning (ML) in oceanographic research, encapsulating paradigm shift towards more efficient and comprehensive analysis marine ecosystems. It delves into multifaceted applications ML, ranging from predictive modeling ocean currents to in-depth biodiversity deciphering complexities deep-sea ecosystems through advanced computer vision techniques. The discussion extends challenges opportunities that intertwine with integration AI ML oceanography, emphasizing need for robust data collection, interdisciplinary collaboration, ethical considerations. Through series case studies thematic discussions, this underscores profound potential revolutionize our understanding preservation oceanic ecosystems, setting new frontier future research conservation strategies realm oceanography.

Language: Английский

Citations

1