Marine ML Benchmark: A Comprehensive Benchmark for Machine Learning in Marine Science

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Zhang, Hanming
Format: Recurso digital
Sprache:Englisch
Veröffentlicht: Zenodo 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866902100141670400
author Zhang, Hanming
author_facet Zhang, Hanming
contents <p>A comprehensive benchmark dataset and codebase for evaluating machine learning models in marine science applications. This package includes:</p> <p>- 9 marine datasets (159,851 total samples) covering biotoxin detection, oceanographic measurements, satellite data, and phytoplankton analysis<br>- 37 pre-trained models across 5 algorithms (Random Forest, XGBoost, SVR, LSTM, Transformer)<br>- Complete reproducible pipeline with cross-platform scripts<br>- Publication-ready figures and tables<br>- Comprehensive documentation and methodology</p> <p>The benchmark evaluates both traditional machine learning and deep learning approaches on diverse marine science tasks, providing standardized evaluation metrics and reproducible results for the research community.</p> <p>Key Features:<br>- Cross-sectional and time-series marine datasets<br>- Traditional ML vs Deep Learning comparison<br>- Comprehensive data validation and sanity checks<br>- Publication-ready visualizations<br>- Complete reproducibility package<br>- Multi-platform support (Windows/Linux/Mac)</p> <p>This work supports reproducible research in marine machine learning and provides a foundation for future developments in the field.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17667247
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Marine ML Benchmark: A Comprehensive Benchmark for Machine Learning in Marine Science
Zhang, Hanming
machine learning marine science oceanography benchmark dataset deep learning time series analysis phytoplankton biotoxin detection satellite oceanography reproducible research
<p>A comprehensive benchmark dataset and codebase for evaluating machine learning models in marine science applications. This package includes:</p> <p>- 9 marine datasets (159,851 total samples) covering biotoxin detection, oceanographic measurements, satellite data, and phytoplankton analysis<br>- 37 pre-trained models across 5 algorithms (Random Forest, XGBoost, SVR, LSTM, Transformer)<br>- Complete reproducible pipeline with cross-platform scripts<br>- Publication-ready figures and tables<br>- Comprehensive documentation and methodology</p> <p>The benchmark evaluates both traditional machine learning and deep learning approaches on diverse marine science tasks, providing standardized evaluation metrics and reproducible results for the research community.</p> <p>Key Features:<br>- Cross-sectional and time-series marine datasets<br>- Traditional ML vs Deep Learning comparison<br>- Comprehensive data validation and sanity checks<br>- Publication-ready visualizations<br>- Complete reproducibility package<br>- Multi-platform support (Windows/Linux/Mac)</p> <p>This work supports reproducible research in marine machine learning and provides a foundation for future developments in the field.</p>
title Marine ML Benchmark: A Comprehensive Benchmark for Machine Learning in Marine Science
topic machine learning marine science oceanography benchmark dataset deep learning time series analysis phytoplankton biotoxin detection satellite oceanography reproducible research
url https://doi.org/10.5281/zenodo.17667247