A Comprehensive Ensemble Model for Marine Atmospheric Boundary-Layer Prediction in Meteorologically Sparse and Complex Regions: A Case Study in the South China Sea

Marine atmospheric boundary-layer height (MABLH) is crucial for ocean heat, momentum, and substance transfer, affecting ocean circulation, climate, and ecosystems. Due to the unique geographical location of the South China Sea (SCS), coupled with its complex atmospheric environment and sparse ground-based observation stations, accurately determining the MABLH remains challenging. Coherent Doppler wind lidar (CDWL), as a laser-based active remote sensing technology, provides high-resolution wind profiling by transmitting pulsed laser beams and analyzing backscattered signals from atmospheric aerosols. In this study, we developed a stacking optimal ensemble model (SOEM) to estimate MABLH in the vicinity of the site by integrating CDWL measurements from a representative SCS site with ERA5 (fifth-generation reanalysis dataset from the European Centre for Medium-Range Weather Forecasts) data from December 2019 to May 2021. Based on the categorization of the total cloud cover data into weather conditions such as clear/slightly cloudy, cloudy/transitional, and overcast/rainy, the SOEM demonstrates enhanced performance with an average mean absolute percentage error of 3.7%, significantly lower than the planetary boundary-layer-height products of ERA5. The SOEM outperformed random forest, extreme gradient boosting, and histogram-based gradient boosting models, achieving a robustness coefficient (R2) of 0.95 and the lowest mean absolute error of 32 m under the clear/slightly cloudy condition. The validation conducted in the coastal city of Qingdao further confirmed the superiority of the SOEM in resolving meteorological heterogeneity. The predictions of the SOEM aligned well with CDWL observations during Typhoon Sinlaku (2020), capturing dynamic disturbances in MABLH. Overall, the SOEM provides a precise approach for estimating convective boundary-layer height, supporting marine meteorology, onshore wind power, and coastal protection applications.

Authors

Institutions

Publication Details

Journal
Remote Sensing
Published
2025-06-13
DOI
https://doi.org/10.3390/rs17122046
Citations
2
Primary Topic
Oceanographic and Atmospheric Processes
Type
article
Field-Weighted Citation Impact
3.59

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A Comprehensive Ensemble Model for Marine Atmospheric Boundary-Layer Prediction in Meteorologically Sparse and Complex Regions: A Case Study in the South China Sea

Yehui Chen, Gang Sun, Ningquan Weng, Tao Luo et al.
2 citations
Remote Sensing
Oceanographic and Atmospheric Processes
3.59
article

A Comprehensive Ensemble Model for Marine Atmospheric Boundary-Layer Prediction in Meteorologically Sparse and Complex Regions: A Case Study in the South China Sea

Yehui Chen, Gang Sun, Ningquan Weng, Tao Luo, Ying Liu, Wenyue Zhu, Liu Qing, Xiaomei Jin
article en
2 citations

Abstract

Marine atmospheric boundary-layer height (MABLH) is crucial for ocean heat, momentum, and substance transfer, affecting ocean circulation, climate, and ecosystems. Due to the unique geographical location of the South China Sea (SCS), coupled with its complex atmospheric environment and sparse ground-based observation stations, accurately determining the MABLH remains challenging. Coherent Doppler wind lidar (CDWL), as a laser-based active remote sensing technology, provides high-resolution wind profiling by transmitting pulsed laser beams and analyzing backscattered signals from atmospheric aerosols. In this study, we developed a stacking optimal ensemble model (SOEM) to estimate MABLH in the vicinity of the site by integrating CDWL measurements from a representative SCS site with ERA5 (fifth-generation reanalysis dataset from the European Centre for Medium-Range Weather Forecasts) data from December 2019 to May 2021. Based on the categorization of the total cloud cover data into weather conditions such as clear/slightly cloudy, cloudy/transitional, and overcast/rainy, the SOEM demonstrates enhanced performance with an average mean absolute percentage error of 3.7%, significantly lower than the planetary boundary-layer-height products of ERA5. The SOEM outperformed random forest, extreme gradient boosting, and histogram-based gradient boosting models, achieving a robustness coefficient (R2) of 0.95 and the lowest mean absolute error of 32 m under the clear/slightly cloudy condition. The validation conducted in the coastal city of Qingdao further confirmed the superiority of the SOEM in resolving meteorological heterogeneity. The predictions of the SOEM aligned well with CDWL observations during Typhoon Sinlaku (2020), capturing dynamic disturbances in MABLH. Overall, the SOEM provides a precise approach for estimating convective boundary-layer height, supporting marine meteorology, onshore wind power, and coastal protection applications.

Remote SensingVol. 17(12)
University of Science and Technology of China (CN), Chinese Academy of Sciences (CN), Anhui Institute of Optics and Fine Mechanics (CN), Anhui Xinhua University (CN)
State Key Laboratory of Pulsed Power Laser Technology
Openalex Percentile: Top 8%
Oceanographic and Atmospheric Processes
3.59
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.