城市绿地生态系统多角度高光谱光化学反射植被指数与光能利用率的关系

Relationship between photochemical reflectance index with multi-angle hyper-spectrum and light use efficiency in urban green-land ecosystems

光能利用率(LUE)是陆地生态系统总初级生产力(GPP)估算的一个重要参数。LUE的准确估算对于在区域甚至全球尺度上使用LUE模型估算GPP是非常重要的。一个基于通量塔的观测视场与通量观测足迹在时空上相匹配的自动多角度遥感平台为LUE在站点尺度上的准确估算提供了一个好方法。该文基于通量塔涡度相关(EC)和自动多角度高光谱连续观测获取的连续30 min的数据,在站点空间尺度和0.5 h与日时间尺度上,探讨了城市绿地生态系统秋季光化学反射植被指数(PRI)与LUE之间的关系。研究发现,反映植被叶面积和色素变化的植被绿度指数在秋季呈现逐渐下降的趋势,表征了植被冠层的状态与结构变化,叶片从绿色逐渐变黄凋落,植被冠层叶片的叶绿素逐渐减少,裸露的枝干增多;用空气温度和代表物候过程的绝对绿度指数(2G_RB)做线性回归分析,得到回归系数(R2)为0.60(p<0.001)。说明在城市绿地生态系统中,空气温度是决定植被物候过程的主要驱动因素,随着植被物候变化,叶片的凋落导致的裸露土壤的增多以及随时间变化的色素含量和其比例的变化将影响PRI和LUE的关系;采用植被生长模型(logistic曲线),拟合时间与2G_RB,得到曲率变化最快的点,确定为秋季植被落叶期的初日,即第290天。在0.5 h和日时间尺度上,PRI都可以捕捉LUE的变化。但是日尺度上不同物候期,PRI和LUE的关系发生了急剧的变化。在秋季植被正常生长期,PRI和LUE之间的关系最密切(R2=0.70,p<0.001)。当土壤温度大于15℃、光合有效辐射(PAR)大于300μmol·m^(–2)·s^(–1)以及饱和水汽压差(VPD)大于700 Pa的情况下,PRI能够更好地预测LUE。基于通量塔尺度上时空尺度相匹配,利用半经验的核驱动二向反射分布函数模型得到的高光谱PRI和通量观测得到的LUE在不同环境条件下的关系以及考虑到在植被的不同物候期对PRI和LUE的关系的优化,将会更加准确地估算城市绿地生态系统的LUE。

Aims Light-use efficiency （LUE） is one of critical parameters in the terrestrial ecosystem production studies. Accurate determination of LUE is very important for LUE models to simulate gross primary productivity （GPP） at regional and global scales. We used eddy covariance technique measurement and tower-based, multi-angular spec- tro-radiometer observations in autumn 2012 to explore the relationship between bidirectional reflectance distribu- tion function （BRDF） corrected photochemical reflectance index （PRI） and LUE in different phenology and envi- ronment conditions in urban green-land ecosystems. Methods Using the eddy covariance technique, we estimated the temporal changes in GPP during the autumn 2012 over Beijing Olympic Forest Park. LUE was calculated as the ratio of GPP to the difference between in- coming photosynthetically active radiation （PAR） and PAR reflected from the canopy. Daily PR/values were av- eraged from the BRDF using semi-empirical kernel driven models. The absolute greenness index （2G_RB） was made by webcam at a constant view zenith and view azimuth angle at solar noon. The logistic function was usedto fit the time series of the greenness index. The onset of phonological stages was defined as the point when the curvature reached its maximum value. Important findings Webcamera-observed greenness index （2G_RB） showed a decreasing trend. There was a highly significant relationship between 2G_RB and air temperature （R2 = 0.60, p 〈 0.001）. This demonstrates that air temperature is the main driving factor to determine the phenology. PR/estimated from multi-angle hy- per-spectrum can estimate LUE in urban green-land ecosystems in vigorous photosynthetic period. The correlation was the strongest （R2 = 0.70, p 〈 0.001） in the peak photosynthetic period. PR/relates better to LUE under high temperature （〉15 ℃） with high vapour pressure deficit （VPD） （〉700 Pa） and high PAR （〉300 μmol·m^-2·s^-1）. The LUE was up-scaled to landscape/regional scales based on these relationships and phenology. It can also be used for the estimation of GPP of urban green-land with high accuracy.