Related items
Showing items related by metadata.
-
ArticleCoupling machine learning and forest simulations to promote the applicability of long-term forest projections under climate change perspectives
XV World Forestry Congress, 2-6 May 2022
2022Also available in:
No results found.Projecting forest dynamics is the foundation for sound decision support in adaptive forest management. However, due to their complexity, many forest modeling techniques addressing global changes in terrestrial ecosystems are limited to scientific applications. Integrating conventional research and artificial intelligence technologies has the potential to bridge research and practical use. In this study, we propose a Machine Learning (ML) framework that facilitates the implementation of long-term forest projections under climate change scenarios. Our approach combines ML and forest simulations based on process-based models to project forest dynamics. The goal is to leverage the complementary strength of process-based and state-of-the-art ML models to improve predictions at a reduced computational cost. We use environmental data and periodic field measurements at a national scale to train ML models to predict forest growth. By integrating process-based simulations we investigate how the additional variables can improve the prediction accuracy. The proposed hybrid ML framework identifies forest dynamics processes and drivers across spatial and temporal scales, contributing at many levels to the climate change adaptation: from increasing awareness of the climate-induced hazards to enhancing education and assisting in sustainable natural resource management and planning. Keywords: adaptive forest management, climate change, forest growth modelling, machine learning ID: 3623078 -
ArticleNew findings on loblolly pine plantations from long-term experimental field studies
XV World Forestry Congress, 2-6 May 2022
2022Also available in:
No results found.Pine plantations in the southern US have been among the most intensively managed forests in the world. Their productivity has been enhanced by intensive silvicultural treatments over the past 60 years, and our knowledge about their treatment response has been expanded through long-term large-scale experimental studies. The analysis of nine long-term loblolly pine (Pinus taeda L.) field trials resulted in several new findings. For loblolly pine in the southern US, there exist maximum productivity and maximum response to silvicultural practices. The maximum response was inversely proportional to the base site quality. The maximum stand basal area (BA) and maximum stand density index (SDI) were redefined for individual stands. The average maximum stand BA and maximum SDI were 46.2 m2 ha-1 and 1002 tph, respectively, and both showed significant variation (30.2– 61.7 m2 ha-1 and 600–1410 tph, respectively). Stand aboveground net primary production (ANPP) generally increased with increasing site quality, due to increased stand foliage biomass in the early stage, and mainly due to increased growth efficiency in the late stages of stand development. More intensive silvicultural treatments increased foliage biomass, thus increased ANPP at early ages; thereafter silvicultural intensity did not affect foliage biomass, ANPP, and growth efficiency. The trend of early age increases in both foliage biomass and ANPP resulting from increased planting density did not hold true with stand development. Keywords: pine plantation; maximum stand density index; maximum stand basal area; maximum response; intensive management ID: 3606017 -
DocumentManaging taxonomic and functional diversity is the key to sustain aboveground biomass and soil microbial diversity: A synthesis from long-term forest restoration of southern China
XV World Forestry Congress, 2-6 May 2022
2022Also available in:
No results found.Exploring the biodiversity-ecosystem functioning relationship is one of the central goals of ecological research. Restoration is essential for supporting key ecosystem functions such as aboveground biomass production and managing soil microbial diversity. However, the relative importance of functional versus taxonomic diversity in explaining aboveground biomass and soil microbial diversity during restoration is poorly understood. Here, we used a trait-based approach to test for the importance of multiple plant diversity attributes in regulating aboveground biomass and soil microbial diversity in four 30- years-old restored subtropical forests in southern China. High-throughput Illumina sequencing was applied for detecting fungal and bacterial diversity. We show that both taxonomic and functional diversities are significant and positive regulators of aboveground biomass; however, functional diversity (FD) was more important than taxonomic diversity (TD) in controlling aboveground biomass. FD had the strongest direct effect on aboveground biomass compared with TD, soil properties, and community weighted mean (CWM) traits. Our results further indicate that leaf and root morphological traits and traits related to the nutrient content in plant tissues showed acquisitive resource use strategy which influenced aboveground biomass. In contrast to aboveground biomass, taxonomic diversity explained more of the soil microbial diversity than the FD and soil properties. Prediction of fungal richness was better than that of bacterial richness. In addition, root traits explained more variation of soil microbes than the leaf traits. Our results suggest that both TD and FD play a role in shaping aboveground biomass and soil microbial diversity; but FD is more important in supporting aboveground biomass while TD for belowground microbial diversity. These results imply that enhancing TD and FD is important to restoring and managing degraded forest landscapes. Key words: Biodiversity-Ecosystem functions; soil microbial diversity, taxonomic diversity, functional diversity, forest restoration ID: 3486373
Users also downloaded
Showing related downloaded files
No results found.