Comment on essd-2024-125 DOI Creative Commons
Le Gao, Yuan Guo, Xiaofeng Li

et al.

Published: June 3, 2024

Abstract. Since 2008, the Yellow Sea has experienced a world's largest-scale marine disasters, known as green tide, marked by rapid proliferation and accumulation of large floating algae. Leveraging advanced AI models, namely AlgaeNet GANet, this study comprehensively extracted analyzed tide occurrences using optical Moderate Resolution Imaging Spectroradiometer (MODIS) images microwave Sentinel-1 Synthetic Aperture Radar (SAR) images. Most importantly, presents continuous seamless weekly average coverage dataset with resolution 500 m, integrating high precise daily SAR data during each week breakout. The uncertainty assessment product shows it is completely consistent overall direct (R2=1 RMSE=0). Additionally, individual case verification in 2019 also that conforms to life pattern outbreaks exhibits parabolic curve-like characteristics, an low (R2=0.89 RMSE=275 km2).This offers reliable long-term spanning 15 years, facilitating research forecasting, climate change analysis, numerical simulation disaster prevention planning Sea. accessible through Oceanographic Data Center, Chinese Academy Sciences (CASODC), along comprehensive reuse instructions provided at http://dx.doi.org/10.12157/IOCAS.20240410.002 (Gao et al., 2024).

Language: Английский

Remote Sensing of Ulva Prolifera Green Tide in the Yellow Sea Using Multisource Satellite Data: Progress and prospects DOI
Xinliang Pan, Mengmeng Cao, Longxiao Zheng

et al.

IEEE Geoscience and Remote Sensing Magazine, Journal Year: 2024, Volume and Issue: 12(4), P. 110 - 131

Published: Aug. 27, 2024

Language: Английский

Citations

5
Approaches, challenges and prospects for modeling macroalgal dynamics in the green tide: The case of Ulva prolifera DOI

Hu Chang,

Ping Zuo,

Yuru Yan

et al.

Marine Pollution Bulletin, Journal Year: 2025, Volume and Issue: 215, P. 117897 - 117897

Published: March 31, 2025

Language: Английский

Citations

0
Weekly green tide mapping in the Yellow Sea with deep learning: integrating optical and synthetic aperture radar ocean imagery DOI Creative Commons
Le Gao, Yuan Guo, Xiaofeng Li

et al.

Earth system science data, Journal Year: 2024, Volume and Issue: 16(9), P. 4189 - 4207

Published: Sept. 13, 2024

Abstract. Since 2008, the Yellow Sea has experienced world's largest-scale marine disaster, green tide, marked by rapid proliferation and accumulation of large floating algae. Leveraging advanced artificial intelligence (AI) models, namely AlgaeNet GANet, this study comprehensively extracted analyzed tide occurrences using optical Moderate Resolution Imaging Spectroradiometer (MODIS) images microwave Sentinel-1 synthetic aperture radar (SAR) images. However, due to cloud rain interference varying observation frequencies two types satellites, daily coverage time series throughout entire life cycle often contain gaps missing frames, resulting in discontinuity limiting their use. Therefore, presents a continuous seamless weekly average dataset with resolution 500 m, integrating highly precise SAR data for each week during breakout. The uncertainty assessment shows that product conforms pattern outbreaks exhibits parabolic-curve-like characteristics, low (R2=0.89 RMSE=275 km2). This offers reliable long-term spanning 15 years, facilitating research forecasting, climate change analysis, numerical simulation, disaster prevention planning Sea. is accessible through Oceanographic Data Center, Chinese Academy Sciences (CASODC), along comprehensive reuse instructions provided at https://doi.org/10.12157/IOCAS.20240410.002 (Gao et al., 2024).

Language: Английский

Citations

2
Automatic Detection of Floating Ulva prolifera Bloom from Optical Satellite Imagery DOI Creative Commons
Hailong Zhang,

Quan Qin,

Deyong Sun

et al.

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(4), P. 680 - 680

Published: April 19, 2024

Annual outbreaks of floating Ulva prolifera blooms in the Yellow Sea have caused serious local environmental and economic problems. Rapid effective monitoring from satellite observations with wide spatial-temporal coverage can greatly enhance disaster response efforts. Various sensors remote sensing methods been employed for detection, yet automatic rapid detection remains challenging mainly due to complex observation scenarios present different images, even within a single image. Here, reliable fully method was proposed extraction features using Tasseled-Cap Greenness (TCG) index top-of-atmosphere reflectance (RTOA) data. Based on TCG characteristics Ulva-free targets, adaptive threshold (LAT) approach utilized automatically select moving pixel windows. When tested HY1C/D-Coastal Zone Imager (CZI) method, termed TCG-LAT achieved over 95% accuracy though cross-comparison VBFAH indexes visually determined threshold. It exhibited robust performance against water backgrounds under non-optimal observing conditions sun glint cloud cover. The further applied multiple HY1C/D-CZI images bloom 2023. Moreover, promising results were obtained by applying optical sensors, including GF-Wide Field View Camera (GF-WFV), HJ-Charge Coupled Device (HJ-CCD), Sentinel2B-Multispectral (S2B-MSI), Geostationary Ocean Color (GOCI-II). is poised integration into operational systems enable nearshore waters, facilitated availability near-real-time images.

Language: Английский

Citations

1
Weekly Green Tide Mapping in the Yellow Sea with Deep Learning: Integrating Optical and SAR Ocean Imagery DOI Creative Commons
Le Gao, Yuan Guo, Xiaofeng Li

et al.

Published: May 6, 2024

Abstract. Since 2008, the Yellow Sea has experienced a world's largest-scale marine disasters, known as green tide, marked by rapid proliferation and accumulation of large floating algae. Leveraging advanced AI models, namely AlgaeNet GANet, this study comprehensively extracted analyzed tide occurrences using optical Moderate Resolution Imaging Spectroradiometer (MODIS) images microwave Sentinel-1 Synthetic Aperture Radar (SAR) images. Most importantly, presents continuous seamless weekly average coverage dataset with resolution 500 m, integrating high precise daily SAR data during each week breakout. The uncertainty assessment product shows it is completely consistent overall direct (R2=1 RMSE=0). Additionally, individual case verification in 2019 also that conforms to life pattern outbreaks exhibits parabolic curve-like characteristics, an low (R2=0.89 RMSE=275 km2).This offers reliable long-term spanning 15 years, facilitating research forecasting, climate change analysis, numerical simulation disaster prevention planning Sea. accessible through Oceanographic Data Center, Chinese Academy Sciences (CASODC), along comprehensive reuse instructions provided at http://dx.doi.org/10.12157/IOCAS.20240410.002 (Gao et al., 2024).

Language: Английский

Citations

0
Comment on essd-2024-125 DOI Creative Commons

Qianguo Xing

Published: June 2, 2024

Abstract. Since 2008, the Yellow Sea has experienced a world's largest-scale marine disasters, known as green tide, marked by rapid proliferation and accumulation of large floating algae. Leveraging advanced AI models, namely AlgaeNet GANet, this study comprehensively extracted analyzed tide occurrences using optical Moderate Resolution Imaging Spectroradiometer (MODIS) images microwave Sentinel-1 Synthetic Aperture Radar (SAR) images. Most importantly, presents continuous seamless weekly average coverage dataset with resolution 500 m, integrating high precise daily SAR data during each week breakout. The uncertainty assessment product shows it is completely consistent overall direct (R2=1 RMSE=0). Additionally, individual case verification in 2019 also that conforms to life pattern outbreaks exhibits parabolic curve-like characteristics, an low (R2=0.89 RMSE=275 km2).This offers reliable long-term spanning 15 years, facilitating research forecasting, climate change analysis, numerical simulation disaster prevention planning Sea. accessible through Oceanographic Data Center, Chinese Academy Sciences (CASODC), along comprehensive reuse instructions provided at http://dx.doi.org/10.12157/IOCAS.20240410.002 (Gao et al., 2024).

Language: Английский

Citations

0
Comment on essd-2024-125 DOI Creative Commons
Le Gao, Yuan Guo, Xiaofeng Li

et al.

Published: June 3, 2024

Abstract. Since 2008, the Yellow Sea has experienced a world's largest-scale marine disasters, known as green tide, marked by rapid proliferation and accumulation of large floating algae. Leveraging advanced AI models, namely AlgaeNet GANet, this study comprehensively extracted analyzed tide occurrences using optical Moderate Resolution Imaging Spectroradiometer (MODIS) images microwave Sentinel-1 Synthetic Aperture Radar (SAR) images. Most importantly, presents continuous seamless weekly average coverage dataset with resolution 500 m, integrating high precise daily SAR data during each week breakout. The uncertainty assessment product shows it is completely consistent overall direct (R2=1 RMSE=0). Additionally, individual case verification in 2019 also that conforms to life pattern outbreaks exhibits parabolic curve-like characteristics, an low (R2=0.89 RMSE=275 km2).This offers reliable long-term spanning 15 years, facilitating research forecasting, climate change analysis, numerical simulation disaster prevention planning Sea. accessible through Oceanographic Data Center, Chinese Academy Sciences (CASODC), along comprehensive reuse instructions provided at http://dx.doi.org/10.12157/IOCAS.20240410.002 (Gao et al., 2024).

Language: Английский

Citations

0