内陆水体浮游藻类遥感监测与预警技术
doi: 10.11918/202601128
何声远 , 于水利 , 黎雷
同济大学 环境科学与工程学院,上海 200092
基金项目: 国家“万人计划”青年拔尖人才(04002350146)
Remote sensing monitoring and early warning technologies for phytoplankton in inland waters
He Shengyuan , Yu Shuili , Li Lei
College of Environmental Science and Engineering, Tongji University, Shanghai 200092 , China
摘要
内陆水体富营养化引发的浮游藻类水华频发已成为全球性的水环境挑战,遥感技术凭借宏观、快速的优势,为藻华爆发的精准防控提供了时空连续的观测手段。本文综述了内陆水体浮游藻类遥感监测与预警的研究进展,梳理了从藻华提取、色素浓度反演、种群识别到藻华一维时序及时空分布预测的技术体系,并重点探讨了基于数据驱动的人工智能模型在上述领域的应用优势,以及多源数据、多平台的协同监测模式。结果表明:人工智能方法与多源协同观测显著提升了复杂光学环境下的监测与预警精度,在一定程度上能弥补单一传感器时空分辨率不足及易受云层遮挡的短板;长时序遥感观测与数据驱动方法的深度耦合推动了一维时序预测和时空分布预测的发展。然而,现有模型仍面临小样本过拟合风险高及物理可解释性较弱等挑战。未来研究应深化多源数据协同以及探索数据增强等技术突破样本依赖瓶颈,并发展融合藻华演变机制的过程-数据双驱动模型,以提高鲁棒性与可解释性。
Abstract
Eutrophication-induced frequent phytoplankton blooms in inland waters have become a global water environment challenge. Relying on macroscopic and rapid advantages, remote sensing technology provides spatiotemporally continuous observation methods for the precise prevention and control of algal bloom outbreaks. This paper reviewed the research progress of remote sensing monitoring and early warning for phytoplankton in inland waters, systematically summarized the technical systems ranging from algal bloom extraction, pigment concentration retrieval, and taxonomic identification to one-dimensional time series prediction and spatiotemporal distribution prediction of algal blooms, and focused on discussing the application advantages of data-driven artificial intelligence models in the above fields, as well as the collaborative monitoring models of multi-source data and multiple platforms. The results show that artificial intelligence methods and multi-source collaborative observations significantly improve the monitoring and early warning accuracy in complex optical environments and to a certain extent compensate for the shortcomings of single sensors, such as insufficient spatiotemporal resolution and susceptibility to cloud occlusion; the deep coupling of long-term remote sensing observations and data-driven methods promotes the development of one-dimensional time series prediction and spatiotemporal distribution prediction. However, existing models still face challenges such as high risks of overfitting with small samples and weak physical interpretability. Future research should further deepen multi-source data synergy, explore technologies such as data augmentation to break through the sample dependence bottleneck, and develop a process-data dual-driven model integrating algal bloom evolution mechanisms to improve robustness and interpretability.
内陆水体是人类赖以生存的重要淡水资源,承载着供水、灌溉及生态调节等关键功能[1-2]。但在全球气候变化与人类活动的双重驱动下,内陆水体富营养化问题日益严峻,频繁爆发的浮游藻类水华已经成为全球性的水环境问题[3-4]。其中蓝藻水华在中国太湖[5-6]、美国伊利湖[7]和英国内伊湖[8]等地区频发,严重威胁了附近居民的饮用水安全。硅藻水华则会对自来水厂的混凝沉淀、过滤等工艺造成堵塞等不良影响[9-10],甲藻水华也在内陆湖泊水库中频频出现[11-12]。
藻类的直接检测技术主要包括显微镜镜检、分子生物学与流式细胞术等,虽然在藻类识别和定量分析上具有很高的精度优势,但是存在实验流程复杂、成本高和适用范围窄等问题[13-14]。另一方面,水质自动监测系统可以依靠在线荧光传感器实时测定叶绿素a(Chlorophyll-a,Chl-a)、藻蓝蛋白(Phycocyanin,PC)等参数[15-16],解决了成本和时间连续性的问题,但孤立的监测点位也无法反映藻华在水域中的空间分布[17]。相比之下,遥感技术因其范围广和周期性监测的特点,为大尺度、长时序地认知水体状况及其变化提供了不可或缺的技术手段,并已经在海洋、内陆水体等监测任务中得到了检验[18-19]。
浮游藻类含有的关键色素会对不同波长光表现出反射率特征[20-22],遥感技术能基于此实现从藻华范围识别到参数定量反演的多维度监测。随着对地观测和计算机技术的更新迭代,该领域正呈现出新的发展趋势。在数据源上,向着多源异构数据融合的范式转变:一方面,构建了多源协同观测体系,利用时空融合、无人机等方式弥补光学卫星在时空分辨率及云层干扰下的短板[23-24];另一方面,引入了气象、水文等环境因子与遥感光谱进行耦合,以提升复杂环境下的模型精度[25-26]。在方法与任务上,人工智能技术的深度介入推动了从传统模型向数据驱动的转变[27-28],应用目标也正从现状监测向解决藻华何时发生的早期预警跨越[29]。
近年来,关于内陆水体浮游藻类遥感监测的综述不断出现。较早期的研究[30]梳理了基于遥感监测体系的发展趋势,但在人工智能应用方面探讨较少。近期研究[31-32]虽然丰富了机器学习的相关应用,然而关注点还集中于现状监测方面。随着技术发展,相关研究[33]开始探讨藻华预测的相关模型,内容上更侧重对不同算法的讨论。鉴于此,本文旨在突破现有综述局限,系统梳理藻华范围提取、色素定量反演、种群精细化识别以及早期预警的完整技术体系,并将早期预警技术重构为一维时序预测与时空分布预测两类应用维度,重点探讨监测手段从单一到协同、反演方法从经验到智能的演变规律,以期为内陆水体富营养化的精准治理与应急决策提供科学依据。
1 内陆水体浮游藻类遥感监测关键技术
1.1 藻华爆发识别与提取
可见光和红外范围的光谱差异是识别遥感图像中藻华区域的关键,早期的识别方法主要基于光谱特征来构建阈值指数。归一化植被指数(normalized difference vegetation index,NDVI)[34]和浮游藻类指数(floating algae index,FAI)[35]是区分藻华和水体最为普遍的方法,因其计算简捷方便而被广泛使用。研究者也提出了适用性更强的光谱指数,如基于短波红外波段优化的调整浮游藻类指数(adjusted floating algae index,AFAI)[36]以及针对高浊水体开发的抗浑浊藻华指数(anti-turbid algal bloom index,ATBI)[37]等。但在面对较为复杂的内陆水体环境时,仅凭线性指数难以稳定区分藻华与背景干扰。机器学习因其较强的非线性拟合能力已被证明是藻华识别的有效工具,如随机森林(random forest,RF)[38-39]、支持向量机(support vector machine,SVM)[40]以及极限梯度提升算法(extreme gradient boosting,XGBoost)[41]等模型能够利用光谱数据中的非线性关系,在不同水体中表现出良好的适用性。然而,上述方法完全基于像元光谱数据进行识别,忽视了图像的空间信息。以U-Net等为代表的深度学习技术则能够实现光谱和空间特征的联合提取[42],如 Zhu等[27]根据巢湖藻类的季节性光谱差异构建了双U-Net模型,在实现了90%以上识别精度的同时也很好地捕捉和保留藻华的轮廓。此外,为了改善深度学习的计算负担,轻量化模型的构建成为新的研究方向,能够显著减少模型参数数量和训练时间[43]。
在数据源方面,卫星的时空分辨率限制是藻华动态监测面临的一个难题。MODIS、GOCI(及GOCI-II)等高频次传感器适合捕捉藻华的短期变化[44-46],Landsat-8 OLI、Sentinel-2 MSI等高分辨率传感器则提供了更精细的空间细节[47-48]。但是单一卫星平台无法兼得高时空分辨率[49],且图像质量易受云层覆盖影响。为突破这一瓶颈,基于多源卫星的时空数据融合技术成为研究热点,该技术利用多源图像中时空信息的互补性生成高时空分辨率数据集[50]。例如,Zhao等[23]基于时空加权回归方法融合了MODIS与Landsat图像,重构了30 m分辨率的日尺度藻华监测数据,但此类方法还是依赖于线性假设。近年来,基于深度学习的时空融合可以捕捉异构数据间的非线性关联,进而优化融合图像的空间细节与光谱精度[51],为高时空分辨率的藻华监测提供了可参考的技术路径。
尽管多源卫星在一定程度上缓解了时空分辨率矛盾,但云雨天气和卫星固定运行周期仍然会造成不可避免的观测盲区,近地遥感与主动遥感技术则提供了重要补充。近年来,无人机遥感带来空间分辨率的巨大提升,而且其按需获取影像的优势也有效填补了卫星过境的空窗期[52-53]。在此基础上,有关研究[24,54]通过捕捉精细的图像纹理信息实现了对小尺度藻华的精准识别,并发现无人机遥感能有效修正卫星反演存在的面积高估。另一方面,合成孔径雷达(synthetic aperture radar,SAR)作为一种主动遥感技术,为光学卫星遥感的云层覆盖问题提供了解决路径。SAR系统能够穿透云层,无论天气状况如何都能提供图像,其在藻华聚集区域会因为后向散射受到抑制而出现暗区,从而实现进一步的识别提取。但低风速下的水面平滑效应也会产生类似暗区从而造成混淆[55]。相关研究中,SVM能基于暗区的纹理、形状等多维特征,将藻华与低风速区域区分开来[56-57]。Phetanan等[58]则使用了深度学习方法,将Sentinel-1影像数据输入Faster R-CNN模型,以自动识别和提取藻华。上述藻华识别方法的原理、研究区域及数据源等情况列于表1。
表1基于遥感的藻华识别提取算法
Tab.1Remote sensing-based algorithms for algal bloom identification and extraction
1.2 色素浓度定量反演
Chl-a和PC是监测内陆水体浮游藻类生物量及群落结构的两个关键指标[59-60]。其中,Chl-a广泛存在于所有真核藻类和水生植被中,是衡量浮游植物总生物量的通用代理。PC则是蓝藻的标志性色素,有助于蓝藻即便在浑浊的水体中也能高效捕获光能用于光合作用[61]。从光学机理来看,Chl-a在440 nm和670 nm附近存在吸收峰,浓度增加时也会在700 nm附近有一个显著的反射峰,PC在620 nm附近有明显的吸收峰,为色素浓度的反演奠定了物理基础。传统的反演方法包括经验法、半经验法/半分析法和分析法,其中常用的有双波段比[62-63]、三波段[64-65]、四波段模型[66-67]和生物光学模型[68]等。经验法与半经验法/半分析法虽然相对简单且应用广泛,但面对内陆水体复杂的光学性质难以保持稳定的反演精度。
随着人工智能技术的发展,研究者们逐步将机器学习模型应用到色素反演当中[28],以卷积神经网络(convolutional neural network,CNN)为代表的深度学习模型逐渐崭露头角。与依赖人工特征构建的常规机器学习方法不同,CNN是一类可以使用卷积运算来从原始数据中提取特征的模型[69],在遥感领域也被广泛运用于分类和回归问题。根据输入数据的维度特性与特征提取方式的不同,常见的CNN定量反演模型可以分为1D-CNN与2D-CNN两类架构,图1展示了两种类型的对比。1D-CNN专为序列数据设计[70],同样适用于挖掘连续光谱曲线中的精细特征。基于实测高光谱数据,Hong等[71]提出了一种结合注意力机制的1D-CNN模型来实现Chl-a和PC的反演,相比生物光学模型取得了更高的整体精度。而针对非连续的多光谱数据,常规的卷积池化操作可能导致短序列中关键信息的丢失。为此,相关研究在构建基于Sentinel-2多光谱数据的1D-CNN模型时,均采用了无池化层的架构,有利于保留更完整的特征信息[48,72]。另一方面,2D-CNN架构侧重于利用空间邻域信息来辅助反演。例如,Pyo等[73]提出了一种点中心回归CNN,其输入是以目标点为中心的图像窗口。在此基础上,注意力机制作为一种特征自适应加权方法,是筛选关键空间区域与波段的有效工具,能进一步提高2D-CNN在复杂水体环境下的反演精度[74]。
图1不同维度的CNN模型藻类色素反演流程
Fig.1Workflow of algal pigment retrieval based on CNN models with different dimensions
尽管人工智能手段可以显著提升反演精度,但其“黑箱”性质在面对内陆水体的时空异质性时存在明显局限。仅依赖数据驱动去拟合水质参数和光谱反射率难以解释由复杂环境导致的动态变化,导致模型在跨区域、跨季节应用时面临泛化性问题[75-76]。从原理上看,光照、温度等环境因素对浮游藻类的生长存在重要影响[4,77],是浮游藻类监测过程中的重要变量。因此,将环境数据引入反演体系成为新的突破方向。针对不同数据源的Chl-a反演研究表明,包含气象数据的模型取得了最优的性能指标,充分证实了环境因素的关键作用[78]。另外,Zhang等[26]在呼伦湖的研究表明,将气象因子(如温度、降水、日照等)作为辅助变量输入机器学习模型,能有效弥补单一光谱数据的不足。Wang等[79]针对岱海的研究同样发现,将现场测量的盐度因子与遥感波段共同作为输入特征,随机森林模型的决定系数R2从0.64跃升至0.92。这些结果表明,引入区域相关的环境因素能有助于模型更准确地学习遥感光谱与色素浓度之间的非线性关系。相关色素反演方法及其应用情况见表2。
表2基于遥感的藻类色素定量反演算法
Tab. 2 Remote sensing-based algorithms for quantitative retrieval of algal pigments
1.3 浮游藻类种群识别
针对浮游藻类种群的遥感监测研究,在大洋等一类水体中已有较为广泛的应用,然而针对内陆水体的相关研究却相对缺乏[80-82]。在机理层面,不同藻种的光学吸收及散射特征差异导致的反射率光谱可分性是建立遥感识别算法的前提。图2展示了蓝藻(铜绿微囊藻Microcystis aeruginosa、灰假鱼腥藻Pseudanabaena cinerea)、绿藻(小球藻Chlorella sp.)及硅藻(小环藻Cyclotella meneghiniana)在反射率光谱上的差别。相关研究中,Hunter等[83]基于受控实验测试了4类浮游植物种群基于遥感光谱上的分类能力,但也指出基于主成分分析方法的精度随着光谱分辨率的降低而逐渐下降。此外,当Chl-a浓度较低时,水体背景噪声会严重干扰特征提取,体现了基于反射率的方法在低生物量条件下的局限[84]。Zhu等[85]则尝试实现实验到应用的转变,基于实验室培养藻液和实测反射率构建了差异指数分类模型,将其应用于Sentinel-3 OLCI影像获取了太湖优势藻种的空间分布格局,但分类精度发生明显下降,表明仅依靠受控实验建立的模型难以迁移到真实水体。
而在基于实际水体环境的研究中,浮游植物群落结构与遥感反射率之间呈现高度非线性关系[86]。基于数据驱动的机器学习技术凭借其强大的非线性拟合能力,能够从混合光谱中捕捉不同藻类种群的信号。Yan等[87]基于实测数据构建机器学习模型,利用Sentinel-3 OLCI数据在呼伦湖实现了三大优势藻群生物量丰度的定量回归。而针对藻类种群训练样本难以获取的难题,将原位高光谱传感器与荧光探针监测相结合能够快速构建包含不同类群色素浓度的丰富数据集[16]。然而,无论是传统的实地采样与形态学鉴定还是原位荧光监测手段都难以兼顾高分类精度与大样本量的需求。为此,跨学科的数据协同成为新的突破口。Liu等[88]利用环境DNA宏条形码技术高效获取了浮游植物类群的相对丰度信息,并结合Sentinel-2数据及多种水质参数,构建了基于梯度提升树的机器学习模型,成功识别出鄱阳湖中驱动水华的关键类群。这种基于多源数据协同的监测体系,也为富营养化湖泊浮游植物群落结构的精细化监测奠定了基础。
图2不同浮游植物藻种的遥感反射率光谱对比
Fig.2Comparison of remote sensing reflectance spectra among different phytoplankton species
2 内陆水体藻华爆发预警技术
在实现了对藻华的现状监测后,构建具有前瞻性的早期预警能力,对于降低生态灾害风险以及减少经济损失具有重要意义[29,89]。藻华预测模型可以分为过程驱动和数据驱动两种。过程驱动主要基于藻华爆发理论和数值模拟技术进行分析[90-91],但也面临藻华生长机制不明确和水动力过程复杂的挑战。相比之下,遥感技术的进步与人工智能的飞速发展为数据驱动模型带来了重大机遇。该类方法不依赖于物理或生物方程,而是通过从海量数据中挖掘演变规律来实现预测。在具体应用层面,基于遥感的数据驱动模型主要包括一维时序预测和时空分布预测两种,如图3所示。前者侧重于预报全湖或特定站点的藻华强度指标随时间的演变趋势,后者则是推演藻华在像素尺度上的空间连续分布。
2.1 一维时序预测
这类研究旨在回答“何时发生”以及“强度如何”的问题,其模型输出通常为一维时间序列数值。相关方法并不依赖卫星图像的空间信息,而是先通过反演算法将遥感数据转化为Chl-a浓度、蓝藻指数或水华总面积等定量指标,构建出长时序的数据集。随后,这些衍生的时序数据被作为输入特征或预测目标,输入到模型中以挖掘其随时间的演变规律。这种方式一定程度弥补了传统实地采样在时间连续性和空间代表性上的不足,为数据驱动模型提供了高频、长时序的训练样本。
基于遥感数据可以实现针对全湖尺度的宏观指标预测,简单统计模型或传统机器学习模型都表现出了较好的适用性。其中,基于移动平均的统计模型能对高风险藻华实现短期的有效预警,但无法捕捉由突发状况导致的剧烈波动,也在更长周期的推演中精度显著下降[92]。而针对次月尺度下的藻华复杂变化,融合气象与水文等多源变量的机器学习算法能实现更为精准的预测[25,93]。进一步地,为了充分挖掘藻华演变过程中存在的复杂非线性动态及长时序依赖特征,深度学习技术成为主流趋势。相比传统机器学习模型,长短时记忆网络(long short-term memory,LSTM)凭借其记忆单元结构,在利用时间序列数据挖掘演变特征上展现出独特的优势[94]。而针对单一模型在多源数据特征提取上的局限,CNN-LSTM这类复合架构能利用CNN提取气象数据与历史时序中的高维特征,再驱动LSTM进行时序推演,有效提升了模型对复杂动态变化的捕捉能力[95]。
图3基于遥感数据的藻华预测与早期预警技术路线
Fig.3Technical route of algal bloom prediction and early warning based on remote sensing data
2.2 时空分布预测
时空分布预测主要是针对藻华在二维水域上的动态变化过程,其本质是利用历史时刻的遥感数据及环境因子,预测未来时刻在像素尺度上的发生概率或覆盖情况。将长序列遥感数据与贝叶斯理论的概率框架相结合,是实现时空分布预测的有效途径。贝叶斯方法的核心在于利用遥感影像中像素级的历史分布规律构建先验概率,从而实现对未来藻华时空分布的推演[96-97],但也因此缺乏对突发事件的应对能力。不同于侧重静态概率计算的统计方法,Zhao等[98]构建了一种由遥感数据驱动的元胞自动机框架,利用氮磷浓度的空间分布特征实现对藻华从爆发中心向周边动态扩散的模拟。然而,该模型建立在无风、无流的理想化假设之上,且模拟过程中未能实现营养盐浓度的动态更新。基于人工智能的方法能够从海量高维数据中挖掘规律[44,99],但其训练精度也受限于高质量数据集。在小样本情况下,参数庞大的深度学习模型容易对训练数据产生过拟合,导致其泛化能力显著降低。考虑到模型训练对大规模标注样本的依赖, Ananias等[100-101]开发了基于光谱指数的无监督标签自动生成框架,为缺乏实测数据的区域提供了低成本的工程化解决方案。针对云层遮挡导致的数据缺失,Tang等[102]利用物理模型模拟的连续数据填补了遥感观测的空白,构建出较完备的数据集以驱动ConvLSTM模型,实现了对未来14 d藻华分布的预测。但数据驱动模型大多是基于“端到端”的架构,未考虑中间步骤,只通过输入遥感和气象水文等数据得到预测结果,也限制了预测精度的进一步提升。
在全球变暖等气候变化的背景下,藻华的表面漂移速度会显著加快[103],即使是日尺度预测也难以捕捉其快速的生消演变,这对藻华高频时空观测提出了更高的要求。相关研究中,基于GOCI的高频数据提供了解决方案,其小时级重访优势可以构建高时间分辨率的预测模型,成功实现了对藻华短时间内快速变化过程的精细化捕捉[44-45]。此外,Himawari-8卫星也被用于更短时间尺度(10 min)的太湖藻华预测,但相关研究仅尝试了未来10 min的预测,应用价值有待提升[99]。表3归纳了上述藻华预警方法在数据源、预测形式等方面的差异。
表3基于遥感的藻华爆发预警算法
Tab.3Remote sensing-based algorithms for early warning of algal bloom outbreaks
3 结论
本文系统梳理了内陆水体浮游藻类遥感监测与早期预警技术的最新研究进展,通过对关键技术与应用模式的综合分析,得出以下主要结论:
1)基于数据驱动的人工智能方法在藻类监测预警全链条中发挥了重要作用,特别是在内陆水体复杂光学性质下能有效捕捉非线性关系与特征。但机器学习或深度学习模型均依赖于数据集的质量与规模,这在一定程度上限制了模型的泛化性能。为突破这一局限,未来研究一方面可尝试深度耦合气象、水文等环境驱动因子,以物理变量弥补单纯光谱数据集的不足;另一方面,可进一步探索利用深度学习或物理模拟的数据增强技术,或通过积极引入具备通用特征提取能力的遥感基础模型降低标注成本,以突破对数据集的依赖。
2)非光学及近地遥感手段是常规光学卫星受限时的重要补充,能够有效实现复杂天气条件及小范围区域下的浮游植物精准监测。未来可以进一步寻求不同平台间的联动机制,建立多源数据重构算法与协同观测网络,从而实现优势互补的立体化监测。另一方面,也可以重点依托新兴的卫星星座(如“吉林一号”、“珠海一号”等),构建高频高分协同观测网,以精准捕捉浮游植物的短期动态演变。
3)浮游植物种群精细化识别是水环境治理的重要方向,目前人工智能手段在内陆水体藻类种群生物量反演中已取得了较好的效果。但传统的实地采样手段难以高效获取大量的真值标签,导致用于驱动模型训练的精细化数据集严重匮乏。未来应探索跨学科的数据高效获取新范式,例如拓展环境DNA技术或原位传感设备与高光谱遥感的交叉融合,以更高效、自动化的方式丰富种群特征数据库,以驱动高精度的种群识别训练。
4)浮游植物的预测预警是实现精准防控的关键,但现有的一维时序预测无法体现藻华的空间分布特征,而大多数时空分布预测模型仅采用了“端到端”的数据驱动架构,忽视了藻华生长和水动力过程的影响。下一代高精度模型应致力于结合水动力输送、藻类生物群落迁移等关键物理与生态机制,作为先验知识或物理约束融入深度学习框架。同时可进一步关注物理信息神经网络或可微分建模等前沿交叉架构,实现过程驱动与数据驱动的优势互补。
图1不同维度的CNN模型藻类色素反演流程
Fig.1Workflow of algal pigment retrieval based on CNN models with different dimensions
图2不同浮游植物藻种的遥感反射率光谱对比
Fig.2Comparison of remote sensing reflectance spectra among different phytoplankton species
图3基于遥感数据的藻华预测与早期预警技术路线
Fig.3Technical route of algal bloom prediction and early warning based on remote sensing data
表1基于遥感的藻华识别提取算法
Tab.1Remote sensing-based algorithms for algal bloom identification and extraction
表2基于遥感的藻类色素定量反演算法
表3基于遥感的藻华爆发预警算法
Tab.3Remote sensing-based algorithms for early warning of algal bloom outbreaks
Carpenter S R, Stanley E H, Vander Zanden M J. State of the world’s freshwater ecosystems:physical,chemical,and biological changes[J]. Annual Review of Environment and Resources,2011,36:89. DOI:10.1146/annurev-environ-021810-094524
Palmer S C J, Kutser T, Hunter P D. Remote sensing of inland waters:challenges,progress and future directions[J]. Remote Sensing of Environment,2015,157:1. DOI:10.1016/j.rse.2014.09.021
Feng Lian, Wang Ying, Hou Xuejiao,et al. Harmful algal blooms in inland waters[J]. Nature Reviews Earth & Environment,2024,5(9):632. DOI:10.1038/s43017-024-00578-2
Paerl H W, Huisman J. Blooms like it hot[J]. Science,2008,320(5872):57. DOI:10.1126/science.1155398
Qin Boqiang, Zhu Guangwei, Gao Guang,et al. A drinking water crisis in Lake Taihu, China:linkage to climatic variability and lake management[J]. Environmental Management,2010,45(1):105. DOI:10.1007/s00267-009-9393-6
Guo Lucie. Doing battle with the green monster of Taihu Lake[J]. Science,2007,317(5842):1166. DOI:10.1126/science.317.5842.1166
Steffen M M, Davis T W, McKay R M L,et al. Ecophysiological examination of the Lake Erie Microcystis bloom in 2014:linkages between biology and the water supply shutdown of Toledo, OH[J]. Environmental Science & Technology,2017,51(12):6745. DOI:10.1021/acs.est.7b00856
Reid N, Reyne M I, O’Neill W,et al. Unprecedented harmful algal bloom in the UK and Ireland’s largest lake associated with gastrointestinal bacteria,microcystins and anabaenopeptins presenting an environmental and public health risk[J]. Environment International,2024,190:108934. DOI:10.1016/j.envint.2024.108934
Joh G, Choi Y S, Shin J K,et al. Problematic algae in the sedimentation and filtration process of water treatment plants[J]. Journal of Water Supply: Research and Technology-Aqua,2011,60(4):219. DOI:10.2166/aqua.2011.035
文刚, 白愿楠, 王茹, 等. 淡水硅藻水华成因与控制技术研究进展[J]. 环境科学研究,2024,37(2):316.Wen Gang, Bai Yuannan, Wang Ru,et al. Review of causes and control technologies of freshwater diatom blooms[J]. Research of Environmental Sciences,2024,37(2):316. DOI:10.13198/j.issn.1001-6929.2023.08.13
Song Yang, Shen Lian, Zhang Linglei,et al. Study of a hydrodynamic threshold system for controlling dinoflagellate blooms in reservoirs[J]. Environmental Pollution,2021,278:116822. DOI:10.1016/j.envpol.2021.116822
Huang Tinglin, Wen Chengcheng, Wang Sai,et al. Controlling spring dinoflagellate blooms in a stratified drinking water reservoir via artificial mixing:effects,mechanisms,and operational thresholds[J]. Science of The Total Environment,2022,847:157400. DOI:10.1016/j.scitotenv.2022.157400
Chin Chwan Chuong J J, Rahman M, Ibrahim N,et al. Harmful microalgae detection:biosensors versus some conventional methods[J]. Sensors,2022,22(9):3144. DOI:10.3390/s22093144
Gifford S R, St Amand A, Graham J L,et al. Comparison of imaging flow cytometry and microscopy for freshwater algal bloom detection[J]. Lake and Reservoir Management,2024,40(3):222. DOI:10.1080/10402381.2024.2370828
Marcé R, George G, Buscarinu P,et al. Automatic high frequency monitoring for improved lake and reservoir management[J]. Environmental Science & Technology,2016,50(20):10784. DOI:10.1021/acs.est.6b01604
Keller S, Maier P M, Riese F M,et al. Hyperspectral data and machine learning for estimating CDOM,chlorophyll a,diatoms,green algae and turbidity[J]. International Journal of Environmental Research and Public Health,2018,15(9):1881. DOI:10.3390/ijerph15091881
Chawla I, Karthikeyan L, Mishra A K. A review of remote sensing applications for water security:quantity,quality,and extremes[J]. Journal of Hydrology,2020,585:124826. DOI:10.1016/j.jhydrol.2020.124826
Chen Lei, Liu Leizhen, Liu Shasha,et al. The application of remote sensing technology in inland water quality monitoring and water environment science:recent progress and perspectives[J]. Remote Sensing,2025,17(4):667. DOI:10.3390/rs17040667
Ma Jingwu, Ma Renfeng, Pan Qi,et al. A global review of progress in remote sensing and monitoring of marine pollution[J]. Water,2023,15(19):3491. DOI:10.3390/w15193491
Mishra S, Mishra D R, Lee Z,et al. Quantifying cyanobacterial phycocyanin concentration in turbid productive waters:a quasi-analytical approach[J]. Remote Sensing of Environment,2013,133:141. DOI:10.1016/j.rse.2013.02.004
Gitelson A. The peak near 700 nm on radiance spectra of algae and water:relationships of its magnitude and position with chlorophyll concentration[J]. International Journal of Remote Sensing,1992,13(17):3370. DOI:10.1080/01431169208904125
Gitelson A A, Keydan G P, Merzlyak M N. Three-band model for noninvasive estimation of chlorophyll,carotenoids,and anthocyanin contents in higher plant leaves[J]. Geophysical Research Letters,2006,33(11): L11402. DOI:10.1029/2006GL026457
Zhao Yongquan, Liu Desheng, Wei Xiaofang. Monitoring cyanobacterial harmful algal blooms at high spatiotemporal resolution by fusing Landsat and MODIS imagery[J]. Environmental Advances,2020,2:100008. DOI:10.1016/j.envadv.2020.100008
张娟, 姚晓军, 陈进轩, 等. 基于无人机影像和深度学习技术的青海湖刚毛藻水华提取研究[J]. 湖泊科学,2026,38(1):130.Zhang Juan, Yao Xiaojun, Chen Jinxuan,et al. Extraction of Cladophora blooms in Lake Qinghai based on unmanned aerial vehicle(UAV)imagery and deep learning techniques[J]. Journal of Lake Sciences,2026,38(1):130. DOI:10.18307/2026.0115
Gupta A, Hantush M M, Govindaraju R S. Sub-monthly time scale forecasting of harmful algal blooms intensity in Lake Erie using remote sensing and machine learning[J]. Science of the Total Environment,2023,900:165781. DOI:10.1016/j.scitotenv.2023.165781
Zhang Siyuan, A Yinglan, Wang Libo,et al. Monitoring of low chl-a concentration in Hulun Lake based on fusion of remote sensing satellite and ground observation data[J]. Remote Sensing,2024,16(10):1811. DOI:10.3390/rs16101811
Zhu Shengyuan, Wu Yinglei, Ma Xiaoshuang. Deep learning-based algal bloom identification method from remote sensing images—take China’s Chaohu Lake as an example[J]. Sustainability,2023,15(5):4545. DOI:10.3390/su15054545
Sun Yuan, Wang Denghui, Li Lei,et al. Application of remote sensing technology in water quality monitoring:from traditional approaches to artificial intelligence[J]. Water Research,2024,267:122546. DOI:10.1016/j.watres.2024.122546
Stroming S, Robertson M, Mabee B,et al. Quantifying the human health benefits of using satellite information to detect cyanobacterial harmful algal blooms and manage recreational advisories in US lakes[J]. GeoHealth,2020,4(9):e2020GH000254. DOI:10.1029/2020GH000254
来莱, 张玉超, 景园媛, 等. 富营养化水体浮游植物遥感监测研究进展[J]. 湖泊科学,2021,33(5):1299.Lai Lai, Zhang Yuchao, Jing Yuanyuan,et al. Research progress on remote sensing monitoring of phytoplankton in eutrophic water[J]. Journal of Lake Sciences,2021,33(5):1299. DOI:10.18307/2021.0502
Wang Simeng, Qin Boqiang. Application of optical remote sensing in harmful algal blooms in lakes:a review[J]. Remote Sensing,2025,17(8):1381. DOI:10.3390/rs17081381
Rolim S B A, Veettil B K, Vieiro A P,et al. Remote sensing for mapping algal blooms in freshwater lakes:a review[J]. Environmental Science and Pollution Research,2023,30(8):19602. DOI:10.1007/s11356-023-25230-2
Caballero C B, Martins V S, Paulino R S,et al. The need for advancing algal bloom forecasting using remote sensing and modeling:progress and future directions[J]. Ecological Indicators,2025,172:113244. DOI:10.1016/j.ecolind.2025.113244
陈云, 戴锦芳. 基于遥感数据的太湖蓝藻水华信息识别方法[J]. 湖泊科学,2008,20(2):181.Chen Yun, Dai Jinfang. Extraction methods of cyanobacteria bloom in Lake Taihu based on RS data[J]. Journal of Lake Sciences,2008,20(2):181. DOI:10.18307/2008.0207
Hu Chuanmin, Lee Zhongping, Ma Ronghua,et al. Moderate Resolution Imaging Spectroradiometer(MODIS)observations of cyanobacteria blooms in Taihu Lake, China[J]. Journal of Geophysical Research: Oceans,2010,115(C4): C04002. DOI:10.1029/2009JC005511
Fang Chong, Song Kaishan, Li Lin,et al. Spatial variability and temporal dynamics of HABs in Northeast China[J]. Ecological Indicators,2018,90:282. DOI:10.1016/j.ecolind.2018.03.006
Du Yichen, Li Junsheng, Zhang Bing,et al. Monitoring cyanobacterial blooms in China’s large lakes based on MODIS from both Terra and Aqua satellites with a novel automatic approach[J]. International Journal of Applied Earth Observation and Geoinformation,2024,129:103830. DOI:10.1016/j.jag.2024.103830
Yang Chen, Tan Zhenyu, Li Yimin,et al. Unlocking the potential of multisource satellites for harmonized algal bloom detection in plateau lakes[J]. IEEE Geoscience and Remote Sensing Letters,2025,22:1501705. DOI:10.1109/LGRS.2025.3554486
Yang Chen, Tan Zhenyu, Li Yimin,et al. A comparative analysis of machine learning methods for algal bloom detection using remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2023,16:7960. DOI:10.1109/JSTARS.2023.3310162
Ananias P H M, Negri R G. Anomalous behaviour detection using one-class support vector machine and remote sensing images:a case study of algal bloom occurrence in inland waters[J]. International Journal of Digital Earth,2021,14(7):938. DOI:10.1080/17538947.2021.1907462
Kaiser D, Qu J J. Detecting harmful algae blooms(HABs)on the Ohio River using Landsat and Google Earth Engine[J]. Remote Sensing,2025,17(24):4010. DOI:10.3390/rs17244010
Fan Xiangsuo, Yan Chuan, Fan Jinlong,et al. Improved U-Net remote sensing classification algorithm fusing attention and multiscale features[J]. Remote Sensing,2022,14(15):3591. DOI:10.3390/rs14153591
Wang Nan, Tan Zhenyu, Yang Chen,et al. A deep learning approach for extracting cyanobacterial blooms in eutrophic lakes from satellite imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2025,18:13725. DOI:10.1109/JSTARS.2025.3571766
Luo Chichang, Wang Xiang, Chen Yuan,et al. Predictive modeling of cyanobacterial blooms and diurnal variation analysis based on GOCI[J]. Water,2025,17(5):749. DOI:10.3390/w17050749
Wang Siqi, Zhang Xiang, Wang Chao,et al. Temporal continuous monitoring of cyanobacterial blooms in Lake Taihu at an hourly scale using machine learning[J]. Science of The Total Environment,2023,857:159480. DOI:10.1016/j.scitotenv.2022.159480
Huang Bo, Gu Yanzhen, Liu Cong,et al. Climatological annual mean and seasonal variations in spatial energy spectra of satellite-observed sea-surface chlorophyll-a concentration in the East China Sea[J]. Journal of Marine Science and Engineering,2025,13(2):198. DOI:10.3390/jmse13020198
Liu Miao, Ling Hong, Wu Dan,et al. Sentinel-2 and Landsat-8 observations for harmful algae blooms in a small eutrophic lake[J]. Remote Sensing,2021,13(21):4479. DOI:10.3390/rs13214479
Xu Jiajun, Pan Jiayi, Devlin A T. Variations in chlorophyll-a concentration in response to hydrodynamics in a flow-through lake:remote sensing and modeling studies[J]. Ecological Indicators,2023,148:110128. DOI:10.1016/j.ecolind.2023.110128
Wasehun E T, Hashemi Beni L, Di Vittorio C A. UAV and satellite remote sensing for inland water quality assessments:a literature review[J]. Environmental Monitoring and Assessment,2024,196:277. DOI:10.1007/s10661-024-12342-6
Guo Dizhou, Li Zhenhong, Gao Xu,et al. RealFusion:a reliable deep learning-based spatiotemporal fusion framework for generating seamless fine-resolution imagery[J]. Remote Sensing of Environment,2025,321:114689. DOI:10.1016/j.rse.2025.114689
Zheng Dongxue, Lü Aifeng. MosaicFormer:a novel approach to remote sensing spatiotemporal data fusion for lake water monitors[J]. Remote Sensing,2025,17(7):1138. DOI:10.3390/rs17071138
Maes W H, Steppe K. Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture[J]. Trends in Plant Science,2019,24(2):152. DOI:10.1016/j.tplants.2018.11.007
Bansod B, Singh R, Thakur R,et al. A comparision between satellite based and drone based remote sensing technology to achieve sustainable development:a review[J]. Journal of Agriculture and Environment for International Development,2017,111:383. DOI:10.12895/jaeid.20172.690
Ajmeria R, Gundu L, Goswami S,et al. Automatic area estimation of algal blooms in water bodies from UAV images using texture analysis[J]. Water Science and Engineering,2024,17(1):69. DOI:10.1016/j.wse.2023.08.001
Wang Ganlin, Li Junsheng, Zhang Bing,et al. Synthetic aperture radar detection and characteristic analysis of cyanobacterial scum in Lake Taihu[J]. Journal of Applied Remote Sensing,2017,11(1):012006. DOI:10.1117/1. JRS.11.012006
Wu Lin, Wang Le, Min Lin,et al. Discrimination of algal-bloom using spaceborne SAR observations of great lakes in China[J]. Remote Sensing,2018,10(5):767. DOI:10.3390/rs10050767
Wang Ganlin, Li Junsheng, Zhang Bing,et al. Monitoring cyanobacteria-dominant algal blooms in eutrophicated Taihu Lake in China with synthetic aperture radar images[J]. Chinese Journal of Oceanology and Limnology,2015,33(1):143. DOI:10.1007/s00343-015-4019-8
Phetanan K, Kwon D H, Lee J,et al. SAR remote sensing for monitoring harmful algal blooms using deep learning models[J]. GIScience & Remote Sensing,2025,62(1):2524202. DOI:10.1080/15481603.2025.2524202
Guan Qi, Feng Lian, Hou Xuejiao,et al. Eutrophication changes in fifty large lakes on the Yangtze Plain of China derived from MERIS and OLCI observations[J]. Remote Sensing of Environment,2020,246:111890. DOI:10.1016/j.rse.2020.111890
Wang Xiangyu, Fang Chong, Song Kaishan,et al. Monitoring phycocyanin concentrations in high-latitude inland lakes using Sentinel-3 OLCI data:the case of Lake Hulun, China[J]. Ecological Indicators,2023,155:110960. DOI:10.1016/j.ecolind.2023.110960
Wheeler S M, Morrissey L A, Levine S N,et al. Mapping cyanobacterial blooms in Lake Champlain′s Missisquoi Bay using QuickBird and MERIS satellite data[J]. Journal of Great Lakes Research,2012,38(Sup.1):69. DOI:10.1016/j.jglr.2011.06.009
Li Yunmei, Wang Qiao, Wu Chuanqing,et al. Estimation of chlorophyll a concentration using NIR/red bands of MERIS and classification procedure in inland turbid water[J]. IEEE Transactions on Geoscience and Remote Sensing,2012,50(3):993. DOI:10.1109/TGRS.2011.2163199
Sòria-Perpinyà X, Vicente E, Urrego P,et al. Remote sensing of cyanobacterial blooms in a hypertrophic lagoon(Albufera of València, Eastern Iberian Peninsula)using multitemporal Sentinel-2 images[J]. Science of The Total Environment,2020,698:134305. DOI:10.1016/j.scitotenv.2019.134305
Chen Shuisen, Fang Ligang, Li Hongli,et al. Evaluation of a three-band model for estimating chlorophyll-a concentration in tidal reaches of the Pearl River Estuary, China[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2011,66(3):361. DOI:10.1016/j.isprsjprs.2011.01.004
Hunter P D, Tyler A N, Carvalho L,et al. Hyperspectral remote sensing of cyanobacterial pigments as indicators for cell populations and toxins in eutrophic lakes[J]. Remote Sensing of Environment,2010,114(11):2713. DOI:10.1016/j.rse.2010.06.006
Le Chengfeng, Li Yunmei, Zha Yong,et al. A four-band semi-analytical model for estimating chlorophyll a in highly turbid lakes:the case of Taihu Lake, China[J]. Remote Sensing of Environment,2009,113(6):1181. DOI:10.1016/j.rse.2009.02.005
Liu Ge, Simis S G H, Li Lin,et al. A four-band semi-analytical model for estimating phycocyanin in inland waters from simulated MERIS and OLCI data[J]. IEEE Transactions on Geoscience and Remote Sensing,2018,56(3):1379. DOI:10.1109/TGRS.2017.2761996
Giardino C, Brando V E, Dekker A G,et al. Assessment of water quality in Lake Garda(Italy)using Hyperion[J]. Remote Sensing of Environment,2007,109(2):191. DOI:10.1016/j.rse.2006.12.017
Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM,2017,60(6):84. DOI:10.1145/3065386
Kiranyaz S, Avci O, Abdeljaber O,et al.1D convolutional neural networks and applications:a survey[J]. Mechanical Systems and Signal Processing,2021,151:107398. DOI:10.1016/j.ymssp.2020.107398
Hong S M, Cho K H, Park S,et al. Estimation of cyanobacteria pigments in the main rivers of South Korea using spatial attention convolutional neural network with hyperspectral imagery[J]. GIScience & Remote Sensing,2022,59(1):559. DOI:10.1080/15481603.2022.2037887
Salah M, Higa H, Ishizaka J,et al.1D convolutional neural network-based chlorophyll-a retrieval algorithm for Sentinel-2 multispectral instrument in various trophic states[J]. Sensors and Materials,2023,35:3754. DOI:10.18494/SAM4331
Pyo J C, Duan Hongtao, Baek S,et al. A convolutional neural network regression for quantifying cyanobacteria using hyperspectral imagery[J]. Remote Sensing of Environment,2019,233:111350. DOI:10.1016/j.rse.2019.111350
He Ruyan, Lv Zijun, Yang Yumiao,et al. Inversion of river water quality parameters from UAV hyperspectral data using a spatial-spectral attention CNN:a case study in Shenzhen[J]. Science of Remote Sensing,2025,12:100282. DOI:10.1016/j.srs.2025.100282
Wang Honghao, Liu Chun, Li Lei,et al. High-precision inversion of urban river water quality via integration of riparian spatial structures and river spectral signatures[J]. Water Research,2025,278:123378. DOI:10.1016/j.watres.2025.123378
Zhou Xiaoteng, Liu Chun, Carrion D,et al. Spectro-environmental factors integrated ensemble learning for urban river network water quality remote sensing[J]. Water Research,2024,267:122544. DOI:10.1016/j.watres.2024.122544
Huisman J, Codd G A, Paerl H W,et al. Cyanobacterial blooms[J]. Nature Reviews Microbiology,2018,16(8):478. DOI:10.1038/s41579-018-0040-1
Rodríguez-López L, Alvarez D, Bustos Usta D,et al. Chlorophyll-a detection algorithms at different depths using in situ,meteorological,and remote sensing data in a Chilean lake[J]. Remote Sensing,2024,16(4):647. DOI:10.3390/rs16040647
Wang Nan, Wang Zhiguo, Huang Pingping,et al. Inversion method for chlorophyll-a concentration in high-salinity water based on hyperspectral remote sensing data[J]. Sensors,2024,24(13):4181. DOI:10.3390/s24134181
Bracher A, Bouman H A, Brewin R J W,et al. Obtaining phytoplankton diversity from ocean color:a scientific roadmap for future development[J]. Frontiers in Marine Science,2017,4:55. DOI:10.3389/fmars.2017.00055
Alvain S, Moulin C, Dandonneau Y,et al. Seasonal distribution and succession of dominant phytoplankton groups in the global ocean:a satellite view[J]. Global Biogeochemical Cycles,2008,22(3): GB3001. DOI:10.1029/2007GB003154
Hirata T, Hardman-Mountford N J, Brewin R J W,et al. Synoptic relationships between surface chlorophyll-a and diagnostic pigments specific to phytoplankton functional types[J]. Biogeosciences,2011,8(2):312. DOI:10.5194/bg-8-311-2011
Hunter P D, Tyler A N, Présing M,et al. Spectral discrimination of phytoplankton colour groups:the effect of suspended particulate matter and sensor spectral resolution[J]. Remote Sensing of Environment,2008,112(4):1539. DOI:10.1016/j.rse.2007.08.003
Xi Hongyan, Hieronymi M, Röttgers R,et al. Hyperspectral differentiation of phytoplankton taxonomic groups:a comparison between using remote sensing reflectance and absorption spectra[J]. Remote Sensing,2015,7(11):14798. DOI:10.3390/rs71114781
Zhu Yuxin, Li Yunmei, Bi Shun,et al. Spatial and temporal distribution analysis of dominant algae in Lake Taihu based on ocean and land color instrument data[J]. Ecological Indicators,2023,155:110959. DOI:10.1016/j.ecolind.2023.110959
Qiu Yixuan, Fan Zhongya, Feng Huiyun,et al. Estimation of phytoplankton community composition from satellite data using a fuzzy and probabilistic combination model in mountainous reservoirs:a case of Huating Lake in spring and summer[J]. Ecological Informatics,2025,89:103153. DOI:10.1016/j.ecoinf.2025.103153
Yan Zhaojiang, Fang Chong, Song Kaishan,et al. Spatiotemporal variation in biomass abundance of different algal species in Lake Hulun using machine learning and Sentinel-3 images[J]. Scientific Reports,2025,15:2739. DOI:10.1038/s41598-025-87338-4
Liu Xianglin, Deng Yanqing, Chen Sizhi,et al. Identifying key taxa for algal blooms in a large aquatic ecosystem through machine learning[J]. Environmental Science & Technology,2025,59(38):20505. DOI:10.1021/acs.est.5c08910
Moeltner K, Fanara T, Foroutan H,et al. Harmful algal blooms and toxic air:the economic value of improved forecasts[J]. Marine Resource Economics,2023,38(1):2. DOI:10.1086/722598
Wang Chao, Feng Tao, Wang Peifang,et al. Understanding the transport feature of bloom-forming Microcystis in a large shallow lake:a new combined hydrodynamic and spatially explicit agent-based modelling approach[J]. Ecological Modelling,2017,343:26. DOI:10.1016/j.ecolmodel.2016.10.017
Ndong M, Bird D, Nguyen Quang T,et al. A novel Eulerian approach for modelling cyanobacteria movement:thin layer formation and recurrent risk to drinking water intakes[J]. Water Research,2017,127:201. DOI:10.1016/j.watres.2017.10.021
Matthews M W. Near-term forecasting of cyanobacteria and harmful algal blooms in lakes using simple univariate methods with satellite remote sensing data[J]. Inland Waters,2023,13(1):68. DOI:10.1080/20442041.2022.2145839
Ai Haiping, Zhang Kai, Sun Jiachun,et al. Short-term Lake Erie algal bloom prediction by classification and regression models[J]. Water Research,2023,232:119710. DOI:10.1016/j.watres.2023.119710
Bagherian K, Fernández-Figueroa E G, Rogers S R,et al. Predicting chlorophyll-a concentration and harmful algal blooms in Lake Okeechobee using time-series MODIS satellite imagery and long short-term memory[J]. Journal of the ASABE,2024,67(5):1197. DOI:10.13031/ja.15995
Cao Hongye, Han Ling, Li Liangzhi. A deep learning method for cyanobacterial harmful algae blooms prediction in Taihu Lake, China[J]. Harmful Algae,2022,113:102189. DOI:10.1016/j.hal.2022.102189
Du Yichen, Zhao Huan, Li Junsheng,et al. Cyanobacterial blooms prediction in China’s large hypereutrophic lakes based on MODIS observations and Bayesian theory[J]. Journal of Hazardous Materials,2024,480:136057. DOI:10.1016/j.jhazmat.2024.136057
Mu Meng, Li Yunmei, Bi Shun,et al. Prediction of algal bloom occurrence based on the naive Bayesian model considering satellite image pixel differences[J]. Ecological Indicators,2021,124:107416. DOI:10.1016/j.ecolind.2021.107416
Zhao Fei, Zhang Sujin, Chen Ruonan,et al. A modified cyanobacteria prediction model based on cellular automata model using N and P concentration reverse data:a case study in Taihu Lake[J]. Environmental Science and Pollution Research,2022,29(23):34553. DOI:10.1007/s11356-022-18612-5
Li Hu, Qin Chengxin, He Weiqi,et al. Learning and inferring the diurnal variability of cyanobacterial blooms from high-frequency time-series satellite-based observations[J]. Harmful Algae,2023,123:102383. DOI:10.1016/j.hal.2023.102383
Ananias P H M, Negri R G, Bressane A,et al. ABF:a data-driven approach for algal bloom forecasting using machine intelligence and remotely sensed data series[J]. Software Impacts,2023,17:100518. DOI:10.1016/j.simpa.2023.100518
Ananias P H M, Negri R G, Dias M A,et al. A fully unsupervised machine learning framework for algal bloom forecasting in inland waters using MODIS time series and climatic products[J]. Remote Sensing,2022,14(17):4283. DOI:10.3390/rs14174283
Tang Yufei, Feng Yingqi, Fung Sasha,et al. Spatiotemporal deep-learning-based algal bloom prediction for Lake Okeechobee using multisource data fusion[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:8327. DOI:10.1109/JSTARS.2022.3208620
Wang Denghui, Li Lei, Ning Rongsheng,et al. Satellite tracking reveals the speed up of the lacustrine algal bloom drift in response to climate change[J]. Environmental Science & Technology,2024,58(26):11734. DOI:10.1021/acs.est.4c03391