Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Renal NR4A1 predicts ischemic AKI severity and recovery after partial nephrectomy.

Scientific reports·2026
Same author

Saturated cardiolipins are potent disruptors of inner mitochondrial membrane structure and function.

The Journal of biological chemistry·2026
Same author

AD-GPT: large language models in Alzheimer's disease.

BMC medical informatics and decision making·2026
Same author

Doubly Robust Estimators of the Restricted Mean Time in Favor Estimands in Individual- and Cluster-Randomized Trials.

Statistics in medicine·2026
Same author

RxnBench: A Multimodal Benchmark for Evaluating Large Language Models on Chemical Reaction Understanding from the Scientific Literature.

Journal of chemical information and modeling·2026
Same author

Genetic burden across core genes of the PI3K-AKT-mTOR pathway is associated with susceptibility to microscopic polyangiitis: a Chinese cohort study.

Frontiers in immunology·2026

Related Experiment Video

Updated: Jul 3, 2025

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

3.8K

A refined deep-learning-based algorithm for harmful-algal-bloom remote-sensing recognition using Noctiluca

Rongjie Liu1, Binge Cui2, Wenwen Dong2

  • 1First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China.

Journal of Hazardous Materials
|February 11, 2024
PubMed
Summary
This summary is machine-generated.

A new deep learning algorithm, HAB-Net, accurately identifies harmful algal blooms (HABs) in satellite images. This method improves recognition of unevenly distributed blooms, outperforming existing techniques.

Keywords:
Deep learningGF-1 wide field of viewHarmful algal bloomsRecognition algorithm

More Related Videos

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.4K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

539

Related Experiment Videos

Last Updated: Jul 3, 2025

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

3.8K
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.4K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

539

Area of Science:

  • Remote Sensing
  • Marine Biology
  • Artificial Intelligence

Background:

  • Harmful algal blooms (HABs) present recognition challenges due to their patchy and uneven distribution.
  • Existing methods for HAB detection often rely on thresholds, limiting their accuracy.

Purpose of the Study:

  • To develop a refined deep-learning algorithm (HAB-Net) for accurate HAB recognition in GF-1 Wide Field of View (WFV) images.
  • To overcome limitations of existing methods by enabling threshold-free HAB recognition.

Main Methods:

  • Integrated a pretrained image super-resolution model to enhance GF-1 WFV image resolution.
  • Utilized side-window convolution to improve HAB edge feature detection.
  • Constructed a convolutional encoder-decoder network for threshold-free recognition.

Main Results:

  • HAB-Net achieved 90.1% average precision and an 0.86 F1-score for HAB recognition.
  • Demonstrated over 4% improvement in F1-score compared to existing methods, particularly in marginal bloom areas.
  • Successfully applied to diverse marine environments and for detecting macroalgae like Sargassum.

Conclusions:

  • Deep learning offers potential for fine-grained HAB recognition, addressing challenges of uneven biomass distribution.
  • HAB-Net provides a robust and effective tool for monitoring HABs and similar distributed phenomena.
  • The algorithm's capabilities can be extended to detect other fine-scale, strip-distributed objects like oil spills and Ulva prolifera.