发表机构
Plymouth Marine Laboratory; National Center for Earth Observation, Plymouth Marine Laboratory; University of Exeter（普利茅斯海洋实验室; 普利茅斯海洋实验室国家地球观测中心; 埃克塞特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究采用随机森林和TabPFN等机器学习模型，利用多光谱卫星数据估算浮游植物诊断色素浓度，其表现优于仅基于叶绿素-a的基线模型，展现了从卫星数据提取生态信息的潜力。
AI 中文摘要
浮游植物在海洋生态系统和全球碳循环中发挥着核心作用，不同类群对海洋生物地球化学过程的贡献存在差异。尽管已有标准技术可用于从海洋颜色数据监测浮游植物浓度，但其群落组成仍难以在大尺度上观测。叶绿素-a是卫星海洋颜色观测中广泛可得的指标，常被用作浮游植物生物量的衡量标准，但它提供的分类组成信息有限。辅助色素（其中一些是重要浮游植物类群的诊断指标）能提供群落结构的额外信息，但由于光谱分辨率有限以及与叶绿素-a存在强协方差，从海洋颜色数据中反演这些辅助色素颇具挑战性。本研究评估用于从多光谱卫星观测估算诊断色素浓度的机器学习方法，使用包含33640项高效液相色谱（HPLC）测量值的全球数据集，该数据集与欧空局海洋颜色气候变化倡议（OC-CCI）反射率数据相匹配，我们比较了基于多光谱反射率训练的随机森林（Random Forest）和TabPFN模型，与仅使用叶绿素-a的基线模型的表现。采用时间分层验证方案以降低自相关的影响。结果显示，多光谱模型的表现始终优于仅基于卫星衍生叶绿素-a的方法，表明海洋颜色反射率包含与色素识别相关的额外信息。不同色素的改进程度存在差异，与叶绿素-a强相关的色素改进幅度有限，而其他色素则表现出显著提升。这些发现凸显了机器学习从卫星数据中提取超越传统基于叶绿素方法的生态相关信息的潜力。
英文摘要
Phytoplankton play a central role in marine ecosystems and the global carbon cycle, with different groups contributing differently to ocean biogeochemical processes. While standard techniques exist for monitoring phytoplankton concentration from ocean-colour data, their community composition remains difficult to observe at large scales. Chlorophyll-a, widely available from satellite ocean-colour observations, is commonly used as a measure of phytoplankton biomass but provides limited information on taxonomic composition. Accessory pigments, some of which are diagnostic of important phytoplankton groups, offer additional information on community structure, but their retrieval from ocean-colour data is challenging because of limited spectral resolution and strong covariance with chlorophyll-a. In this study, we evaluate machine learning methods for estimating diagnostic pigment concentrations from multispectral satellite observations. Using a global dataset of 33,640 High Performance Liquid Chromatography (HPLC) measurements matched with ESA Ocean Colour Climate Change Initiative (OC-CCI) reflectance data, we compare Random Forest and TabPFN models trained on multispectral reflectance with baseline models using chlorophyll-a alone. A temporally stratified validation scheme is employed to reduce the effects of autocorrelation. Results show that multispectral models consistently outperform approaches based solely on satellite-derived chlorophyll-a, demonstrating that ocean-colour reflectance contains additional information relevant to pigment discrimination. Improvements vary by pigment, with those strongly correlated with chlorophyll-a showing limited gains, while others exhibit substantial improvement. These findings highlight the potential of machine learning to extract ecologically relevant information from satellite data beyond conventional chlorophyll-based approaches.
CommentsSubmitted to Frontiers of Marine Science. 21 pages, 8 Figures
