The Earth's future carbon balance and regional source-sink dynamics are inextricably linked to plant photosynthesis. Vegetation greenness is widely used to estimate photosynthesis at coarse spatial and temporal scales, however, the capacity of green leaves to take up carbon may change throughout the season. Photosynthetic capacity is largely determined by the maximum rate of RuBP carboxylation (Vcmax) and regeneration (Jmax). Vcmax and Jmax vary seasonally and in response to plant stress. Hyperspectral remote sensing of plant physiological parameters has revealed strong relationships between leaf spectra and Vcmax and Jmax, but the degree to which hyperspectral imaging can detect temporal variation in these key determinants of photosynthetic capacity remains unknown. To address this issue, we studied two genotypes of hybrid poplar (Populus spp.) during hot conditions to compare and contrast interactions between leaf size, Vcmax, Jmax and warmer temperatures. We measured Vcmax and Jmax with standard gas exchange techniques over a 10-week period and compared indices obtained from fresh-leaf reflectance spectroscopy (λ=350–2500 nm) and partial least squares regression (PLSR) models.
Results/Conclusions
We found that the PLSR models were robust despite dynamic temporal variation in Vcmax and Jmax throughout the study period. Drought-induced temporal variation in plant stress only modestly reduced PLSR model predictive capacity. Hyperspectral indices were well-correlated to changes in photosynthetic capacity. Notably, the most commonly used remotely sensed metric for greenness (Normalized Difference Vegetation Index: NDVI) was strongly correlated with changes in Vcmax and Jmax throughout the study period. Our results suggest that hyperspectral estimation of plant physiological traits using PLSR is relatively robust to temporal variation. Additionally, widely-used hyperspectral indices such as NDVI may be sufficient to detect temporal changes in photosynthetic capacity in contexts similar to those studied here. More generally, our results highlight the potential of hyperspectral remote sensing methods to detect dynamic temporal variations in Vcmax and Jmax related to seasonality and plant stress, thereby aiding improved estimates of plant productivity and associated carbon budget.