热带海洋学报
熱帶海洋學報
열대해양학보
JOURNAL OF TROPICAL OCEANOGRAPHY
2015年
4期
37-47
,共11页
姚林杰%曹文熙%王桂芬%许占堂%胡水波%周雯%李彩
姚林傑%曹文熙%王桂芬%許佔堂%鬍水波%週雯%李綵
요림걸%조문희%왕계분%허점당%호수파%주문%리채
吸收光谱%浮游植物粒级结构%支持向量机%叶绿素a
吸收光譜%浮遊植物粒級結構%支持嚮量機%葉綠素a
흡수광보%부유식물립급결구%지지향량궤%협록소a
absorption spectra%phytoplankton size class%support vector machine%chlorophylls-a
文章采用支持向量机模型反演浮游植物的粒级结构。模型的输入量为浮游植物的吸收光谱、总叶绿素 a 浓度值。将该模型分别应用于南海数据集和NASA bio-Optical Marine Algorithm Dataset (NOMAD)全球大洋数据集。以浮游植物的吸收光谱做为输入向量时,南海数据集和 NOMAD 数据集反演微微型(pico)、微型(nano)和小型(micro)粒级浮游植物的平均绝对误差(APD)分别是46.1%、61.6%、55.0%和36.3%、44.6%、43.3%;决定系数(R2)分别为0.604、0.423、0.491和0.460、0.702、0.829。以浮游植物的吸收光谱和总叶绿素a浓度值做为输入向量时,南海数据集和NOMAD数据集反演 pico、nano 和 micro 粒级的平均绝对误差分别是19.2%、31.9%、31.6%和35.3%、35.4%、38.2%;决定系数分别为0.837、0.805、0.600和0.713、0.758、0.810。结果显示以吸收光谱和总叶绿素a浓度值作为输入变量的反演精度,比以吸收光谱作为输入变量的反演精度高。由此看出支持向量机模型对于两个数据集的反演结果很理想,该模型的提出为多光谱遥感反演浮游植物的粒级结构提供一个重要手段。
文章採用支持嚮量機模型反縯浮遊植物的粒級結構。模型的輸入量為浮遊植物的吸收光譜、總葉綠素 a 濃度值。將該模型分彆應用于南海數據集和NASA bio-Optical Marine Algorithm Dataset (NOMAD)全毬大洋數據集。以浮遊植物的吸收光譜做為輸入嚮量時,南海數據集和 NOMAD 數據集反縯微微型(pico)、微型(nano)和小型(micro)粒級浮遊植物的平均絕對誤差(APD)分彆是46.1%、61.6%、55.0%和36.3%、44.6%、43.3%;決定繫數(R2)分彆為0.604、0.423、0.491和0.460、0.702、0.829。以浮遊植物的吸收光譜和總葉綠素a濃度值做為輸入嚮量時,南海數據集和NOMAD數據集反縯 pico、nano 和 micro 粒級的平均絕對誤差分彆是19.2%、31.9%、31.6%和35.3%、35.4%、38.2%;決定繫數分彆為0.837、0.805、0.600和0.713、0.758、0.810。結果顯示以吸收光譜和總葉綠素a濃度值作為輸入變量的反縯精度,比以吸收光譜作為輸入變量的反縯精度高。由此看齣支持嚮量機模型對于兩箇數據集的反縯結果很理想,該模型的提齣為多光譜遙感反縯浮遊植物的粒級結構提供一箇重要手段。
문장채용지지향량궤모형반연부유식물적립급결구。모형적수입량위부유식물적흡수광보、총협록소 a 농도치。장해모형분별응용우남해수거집화NASA bio-Optical Marine Algorithm Dataset (NOMAD)전구대양수거집。이부유식물적흡수광보주위수입향량시,남해수거집화 NOMAD 수거집반연미미형(pico)、미형(nano)화소형(micro)립급부유식물적평균절대오차(APD)분별시46.1%、61.6%、55.0%화36.3%、44.6%、43.3%;결정계수(R2)분별위0.604、0.423、0.491화0.460、0.702、0.829。이부유식물적흡수광보화총협록소a농도치주위수입향량시,남해수거집화NOMAD수거집반연 pico、nano 화 micro 립급적평균절대오차분별시19.2%、31.9%、31.6%화35.3%、35.4%、38.2%;결정계수분별위0.837、0.805、0.600화0.713、0.758、0.810。결과현시이흡수광보화총협록소a농도치작위수입변량적반연정도,비이흡수광보작위수입변량적반연정도고。유차간출지지향량궤모형대우량개수거집적반연결과흔이상,해모형적제출위다광보요감반연부유식물적립급결구제공일개중요수단。
In this study, a support vector machine (SVM) model was introduced to retrieve phytoplankton size classes (PSCs), from phytoplankton absorption spectra and total chlorophyll-a concentration.The performance of this model was validated with the South China Sea and NASA bio-Optical Marine Algorithm Dataset (NOMAD) datasets. The results of the model, which used phytoplankton absorption spectra as the only input parameter, showed that the absolute percentage differences (APD) were 46.1% (pico), 61.6% (nano) and 36.3% (micro) for the South China Sea dataset, and were 36.3% (pico), 44.6%(nano) ,44.3% (micro) for NOMAD dataset; It also showed that the determination coefficents (R2) were 0.604 (pico), 0.423 (nano) and 0.491 (micro) for the South China Sea dataset, and were 0.460 (pico), 0.702 (nano) and 0.829 (micro) for the NOMAD dataset. The SVM model that used both absorption spectra and chlorophyll-a concentration of phytoplankton showed that the APD were 19.2%, 31.9%, 31.6%and determination coefficents of phytoplankton size classes (pico, nano, and micro) were 0.837, 0.805, 0.600 for the South China Sea data-set. Using the same method, the result of SVM model showed that the APD were 35.3%, 35.4%, 38.2% and determination coefficents of phytoplankton size classes (pico, nano, and micro) were 0.713, 0.758, 0.810 for the NOMAD data set. The SVM model trained using phytoplankton absorption spectra and total chlorophyll-a concentration performed more effectively than that using only phytoplankton absorption spectra. The performance of the SVM model was shown to be satisfactory, and the model opens the way to an appliaction to estimate PSCs by using hyperspectral measurements.