Variation in Onset of Leaf Unfolding and Wood Formation in a Central African Tropical Tree Species

A diversity of phenological strategies has been reported for tropical tree species. Defoliation and seasonal dormancy of cambial activity inform us on how trees cope with water stress during the dry season, or maximize the use of resources during the rainy season. Here, we study the matching between leaf phenology (unfolding and shedding) and cambial activity for Prioria balsamifera, a key timber species in the Democratic Republic of Congo. In particular, we (i) evaluated the seasonality of cambial activity and synchrony of phenology among trees in response to climate and (ii) identified the seasonality of leaf phenology and its relation with cambial phenology. The study was conducted in the Luki Man and Biosphere Reserve, located in the Mayombe forest at the southern margin of the Congo Basin. Historic defoliation data were collected every ten days using weekly crown observations whereas recent observations involved time-lapse cameras. Cambial pinning was performed on ten trees during 20 months and radius dendrometers were installed on three trees during 13 months. Tree rings were measured on cores from 13 trees and growth synchrony was evaluated. We found that P. balsamifera defoliates annually with a peak observed at the end of the dry season and the beginning of the rainy season. The new leaves unfolded shortly after shedding of the old leaves. The peak defoliation dates varied across years from September 12 to November 14 and the fraction of number of trees that defoliated at a given time was found to be negatively correlated with annual rainfall and temperature; during the dry season, when precipitation and temperatures are the lowest. Wood formation (radial growth), was found to be highly seasonal, with cambial dormancy occurring during the dry season and growth starting at the beginning of the rainy season. Individual ring-width series did not cross date well. The within species variability of leaf phenology and cambial rhythms provides indication about resistance of the population against climatic changes.

Characterizing and forecasting the responses of tropical forest leaf phenology to El Nino by machine learning algorithms

Climate change and global warming have serious adverse impacts on tropical forests. In particular, climate change may induce changes in leaf phenology. However, in tropical dry forests where tree diversity is high, species responses to climate change differ. The objective of this research is to analyze the impact of climate variability on the leaf phenology in Thailand’s tropical forests. Machine learning approaches were applied to model how leaf phenology in dry dipterocarp forest in Thailand responds to climate variability and El Niño. First, we used a Self-Organizing Map (SOM) to cluster mature leaf phenology at the species level. Then, leaf phenology patterns in each group along with litterfall phenology and climate data were analyzed according to their response time. After that, a Long Short-Term Memory neural network (LSTM) was used to create model to predict leaf phenology in dry dipterocarp forest. The SOM-based clustering was able to classify 92.24% of the individual trees. The result of mapping the clustering data with lag time analysis revealed that each cluster has a different lag time depending on the timing and amount of rainfall. Incorporating the time lags improved the performance of the litterfall prediction model, reducing the average root mean square percent error (RMSPE) from 14.35% to 12.06%. This study should help researchers understand how each species responds to climate change. The litterfall prediction model will be useful for managing dry dipterocarp forest especially with regards to forest fires.

Identifying Leaf Phenology of Deciduous Broadleaf Forests from PhenoCam Images Using a Convolutional Neural Network Regression Method

Vegetation phenology plays a key role in influencing ecosystem processes and biosphere-atmosphere feedbacks. Digital cameras such as PhenoCam that monitor vegetation canopies in near real-time provide continuous images that record phenological and environmental changes. There is a need to develop methods for automated and effective detection of vegetation dynamics from PhenoCam images. Here we developed a method to predict leaf phenology of deciduous broadleaf forests from individual PhenoCam images using deep learning approaches. We tested four convolutional neural network regression (CNNR) networks on their ability to predict vegetation growing dates based on PhenoCam images at 56 sites in North America. In the one-site experiment, the predicted phenology dated to after the leaf-out events agree well with the observed data, with a coefficient of determination (R2) of nearly 0.999, a root mean square error (RMSE) of up to 3.7 days, and a mean absolute error (MAE) of up to 2.1 days. The method developed achieved lower accuracies in the all-site experiment than in the one-site experiment, and the achieved R2 was 0.843, RMSE was 25.2 days, and MAE was 9.3 days in the all-site experiment. The model accuracy increased when the deep networks used the region of interest images rather than the entire images as inputs. Compared to the existing methods that rely on time series of PhenoCam images for studying leaf phenology, we found that the deep learning method is a feasible solution to identify leaf phenology of deciduous broadleaf forests from individual PhenoCam images.