Forest productivity is influenced by various factors, including biodiversity, environmental factors, functional traits, and forest types. However, the relative importance of these factors in determining the productivity of subtropical forests in southern China remains controversial. In this study, we analyzed a dataset of 24 forest plots from four subtropical forest types in the Nanling Mountains with the main goal of identifying and quantifying the relative contribution of the main driving factors of forest productivity in these forests. Generalized linear regression and structural equation modeling were used to examine the relationship between forest biomass productivity (aboveground, belowground and total), biodiversity (taxonomic diversity, phylogenetic diversity and functional diversity), and environmental variables (i.e., physiography and climate). The results indicated that both environmental factors and biodiversity played pivotal roles in explaining the biomass productivity of the Nanling subtropical forests. Environmental factors had the greatest influence on total productivity, while the impacts of different types of biodiversity on various productivity components (aboveground and belowground) varied notably. Taxonomic diversity showed the strongest positive effect on the aboveground and belowground biomass productivity. However, phylogenetic and functional diversity had negative effects on productivity. Furthermore, these relationships also exhibited variations when considering different altitude gradients, with low altitudes generally leading to negative biodiversity–productivity correlations. We contextualized our results regarding the three state-of-the-art theories about biodiversity–productivity relationships (selection probability, niche complementarity, and biomass ratio) and concluded that both selection probability and niche complementarity are the driving mechanisms of productivity in the subtropical forests of the Nanling Mountains. This study offers valuable insights into the functioning and biodiversity mechanisms of subtropical forest ecosystems in southern China.

Climate change might entail significant alterations in future forest productivity, profitability and management. In this work, we estimated the financial profitability (Soil Expectation Value, SEV) of a set of radiata pine plantations in the northwest of Spain under climate change. We optimized silvicultural interventions using a differentiable approach and projected future productivity using a machine learning model basing on the climatic predictions of 11 Global Climate Models (GCMs) and two Representative Concentration Pathways (RCPs). The forecasted mean SEV for future climate was lower than current SEV (∼22% lower for RCP 4.5 and ∼29% for RCP 6.0, with interest rate = 3%). The dispersion of the future SEV distribution was very high, alternatively forecasting increases and decreases in profitability under climate change depending on the chosen GCM. Silvicultural optimization considering future productivity projections effectively mitigated the potential economic losses due to climate change; however, its ability to perform this mitigation was strongly dependent on interest rates. We conclude that the financial profitability of radiata pine plantations in this region might be significantly reduced under climate change, though further research is necessary for clearing the uncertainties regarding the high dispersion of profitability projections.

1. In recent years, Representation Learning (RL), a subdiscipline of artificial intelligence, has proved a valuable resource in many research fields for mapping abstract categories into numeric scales as a means to boost varied quantitative modeling tasks. Despite the up-and-coming advantages that RL could imply for managing categorical data in ecological modeling, applications in ecology are still lacking. In this study, we proposed a new method for applying RL to forest ecology, labeled TreeSp2Vec, for developing tree species numeric representations (embeddings).2. Our approach entailed a supervised species classification of individual trees using as input a set of phytocentric (morphometrics and composition) and geocentric (climate, soil, and physiography) variables derived from National Forest Inventory data and environmental cartography. Species classification was carried out using deep neural networks with several fully connected layers, an intermediate embedding layer of up to 32 dimensions, and an output layer with softmax activations.3. Among the tested neural network architectures, a multi-layer perceptron with two hidden layers of 1024 units and an embedding layer of 16 units provided the best apparent and test classification performances (Matthew’s Correlation Coefficient = 0.89). Additionally, the developed latent representations (W), or embeddings, were evaluated intrinsically by estimating their correlations with supplementary species descriptors that were not included in the training dataset. The evaluation analysis revealed some significant associations that proved the generality of the embedding model. For instance, some latent dimensions (e.g., W6 and W16) helped differentiate species general features, such as conifers vs. broad-leaved species, while other dimensions (e.g., W2 and W5) were related to forest ecosystem characteristics such as competition intensity (relative spacing index) and biodiversity (Simpson index).4. We concluded that the developed embeddings provided accurate and generalizable numeric representations of the considered tree species, which can be used as a ground for further cutting-edge forest ecology modeling approaches. Moreover, our approach is easily extendable to other ecological research areas, opening a new range of artificial intelligence applications in ecology.

Understanding the spatial variations of forest features and their underlying drivers is crucial for managing and preserving forest ecosystems. Remote sensing techniques, due to their vast spatial coverage, are proving an essential tool for mapping and analyzing the complex spatial patterns of forests characteristics. In the current study, we use high-resolution Gaofen 1 satellite imagery to map features, such as biomass, biodiversity, and habitat type, of the subtropical forests in the Nanling area, a major biodiversity hot spot in the south of China; for subsequently analyzing the association between forest features and environmental drivers. We based our modeling approach on a semi-supervised fully convolutional neural network consisting of a ResNet architecture and a masking and aggregation module for computing predictions for forest survey plots of varied sizes. The fitted convolutional models yielded very high performance statistics, with test R2 values above 0.90 for basal area, aboveground biomass and Shannon diversity index regressions, slightly lower values for the regression of species richness (R2=0.83), and average test classification accuracy of forest types of 0.89, with lower performance for infrequent forest types, such as dwarf forests. The association analysis between predicted maps of forest features and environmental drivers revealed significant correlations being the strongest drivers the altitude, nitrogen content and climate variables, such as mean annual precipitation and temperature. Altitude was strongly associated with dwarf forests and high basal area and high aboveground biomass locations. Basal area and aboveground biomass were also positively influenced by annual rainfall and soil nitrogen and carbon, and negatively by temperature and radiation variables. Species richness was associated with high nitrogen and carbon contents, while the Shannon diversity index showed overall mild correlations with most drivers, with no remarkable patterns. We concluded that our semi-supervised convolutional approach using Gaofen 1 imagery proved useful for modeling the spatial distribution of the subtropical forests in Nanling; however, more research and data collection is necessary to improve the performance of species richness modeling and segmentation of infrequent forest types. Moreover, the strong associations found between climate, and predicted maps of biomass and forest types, provided key insights into the potential repercussions of climate change on Nanling forests.