为了提高太阳电池阵多变量预测的精度,解决阳电池阵遥测参数存在周期波动与增长性互相耦合的问题,提出一种基于STL-Prophet-Informer模型的太阳电池阵多变量预测算法.该算法首先应用局部加权周期趋势分解算法(seasonal and trend decomp...为了提高太阳电池阵多变量预测的精度,解决阳电池阵遥测参数存在周期波动与增长性互相耦合的问题,提出一种基于STL-Prophet-Informer模型的太阳电池阵多变量预测算法.该算法首先应用局部加权周期趋势分解算法(seasonal and trend decomposition procedure based on loess,STL)对太阳电池阵的多个参数分解为趋势分量、周期分量和残差分量,然后采用对趋势性数据预测效果较好的Prophet预测趋势分量,Informer模型预测周期分量和残差分量,最后将各分量预测结果相加后得到总的太阳电池阵参数预测值.以某卫星太阳电池阵实际遥测数据做算例分析,提出算法的各项误差评价指标和单一的Informer模型、LSTM模型等相比有明显减小,将该组合预测模型用于太阳电池阵多变量参数预测中,可以提高参数预测精度,提升卫星自主运行性能.展开更多
Internal waves can bring nutrients to the upper level of water bodies and facilitate phytoplankton photosynthesis.Internal waves occur frequently in the northern portion of the South China Sea and inflict an important...Internal waves can bring nutrients to the upper level of water bodies and facilitate phytoplankton photosynthesis.Internal waves occur frequently in the northern portion of the South China Sea and inflict an important effect on chlorophyll a distribution.In this study,in-situ observation and satellite remote sensing data were used to study the effects of internal waves on chlorophyll a distribution.Based on the in-situ observations,lower chlorophyll a concentrations were present in the middle and bottom level in areas in which internal waves occur frequently,while the surface chlorophyll a distribution increased irregularly,and a small area with relatively higher chlorophyll a concentrations was observed in the area around the Dongsha Island.Satellite remote sensing showed that the chlorophyll a concentration increased in the area near Dongsha Island,where internal waves frequently occurred.The results of the increased chlorophyll a concentration in the surface water near Dongsha Island in the northern portion of the South China Sea indicated that internal waves could uplift phytoplankton and facilitate phytoplankton growth.展开更多
文摘为了提高太阳电池阵多变量预测的精度,解决阳电池阵遥测参数存在周期波动与增长性互相耦合的问题,提出一种基于STL-Prophet-Informer模型的太阳电池阵多变量预测算法.该算法首先应用局部加权周期趋势分解算法(seasonal and trend decomposition procedure based on loess,STL)对太阳电池阵的多个参数分解为趋势分量、周期分量和残差分量,然后采用对趋势性数据预测效果较好的Prophet预测趋势分量,Informer模型预测周期分量和残差分量,最后将各分量预测结果相加后得到总的太阳电池阵参数预测值.以某卫星太阳电池阵实际遥测数据做算例分析,提出算法的各项误差评价指标和单一的Informer模型、LSTM模型等相比有明显减小,将该组合预测模型用于太阳电池阵多变量参数预测中,可以提高参数预测精度,提升卫星自主运行性能.
基金Supported by the Knowledge Innovation Program of the Chinese Academy of Sciences (No.KZCX1-YW-12-01)the National High Technology Research and Development Program of China (863 Program) (No.2008AA09Z112)+4 种基金the National Basic Research Program of China (973 Program) (No.2010CB951200)the National Natural Sciences Foundation of China (No.40876092)the Program of Guangdong Provincial Science & Technology (No.2008B030303026)the Natural Sciences Foundation of Guangdong Province (No.8351030101000002)the Project of Knowledge Innovation of the South China Sea Institute of Oceanology (No.LYQY200701)
文摘Internal waves can bring nutrients to the upper level of water bodies and facilitate phytoplankton photosynthesis.Internal waves occur frequently in the northern portion of the South China Sea and inflict an important effect on chlorophyll a distribution.In this study,in-situ observation and satellite remote sensing data were used to study the effects of internal waves on chlorophyll a distribution.Based on the in-situ observations,lower chlorophyll a concentrations were present in the middle and bottom level in areas in which internal waves occur frequently,while the surface chlorophyll a distribution increased irregularly,and a small area with relatively higher chlorophyll a concentrations was observed in the area around the Dongsha Island.Satellite remote sensing showed that the chlorophyll a concentration increased in the area near Dongsha Island,where internal waves frequently occurred.The results of the increased chlorophyll a concentration in the surface water near Dongsha Island in the northern portion of the South China Sea indicated that internal waves could uplift phytoplankton and facilitate phytoplankton growth.