4.01.02 - Growth models for tree and stand simulation

UNIT NOTICEBOARD

2023-01-16

Artificial Intelligence and Ecosystems Management

Palencia, Spain; 17-21 April 2023.

Ecosystem management under changing conditions needs new tools to insight and forecast forest dynamic and management. Artificial intelligence is a game changer in forest management. Artificial intelligence (AI) encompasses a wide range of techniques and frameworks dating back to the mid twenty century. The use of AI in forestry is relatively new, especially when compared to the early adoption of AI in other fields. The irruption of AI spins researchers and practitioners to unfold the analysis of complex big data. Narrow AI, defined as an AI system that is specified to perform a limited task, is commonly applied in biometry (e.g., analysis of forest structure with 3D point cloud data) but no so common in other ecosystem management domains. Currently, adequate AI algorithms can be efficiently prototyped due to plenty of publicly available databases, open-source libraries and the accessibility to computing platforms.

IMPORTANT DATES
- Start of abstract submission: 16 January 2023
- Start of registration: 16 January 2023
- End of abstract submission: 10 February 2023
- Acceptance of communications: 3 March 2023
- End of early-bird registration: 10 March 2023
- Side events: 17 April 2023
- Conference: 18-20 April 2023
- Field trip: 21 April 2023

Details:  https://eventos.uva.es/92504/detail/artificial-intelligence-and-ecosystems-management.html

View all entries

Coordinator:

Felipe Bravo, Spain

Deputies:

Albert Ciceu, Austria

Mathieu Fortin, Canada

Woongsoon Jang, Canada

Daesung Lee, Finland

Tammam Suliman, Austria

About Unit

Unit 4.01.02 is principally concerned with the theoretical, mathematical, statistical and computational aspects of growth and yield model development, specification, calibration, verification, simulation, computerization and application/deployment. Model forms include those developed for tropical, temperate and boreal forest types and cover the entire range of stand structural complexity. For example, these include individual-tree distance-dependent and distance-independent models, stand-level diameter distribution models and average stand-level models. Incorporating the impact of anthropogenic influences, such as thinning, forest fertilization, tree improvement, drainage, and climate change, on tree and stand growth through model refinement and adaptation is an evolving issue within this unit. Additionally, in response to the paradigmic shift towards value-based management occurring in many forest regions, a renewed focus on model development for predicting a wider range of management-relevant yield-based metrics including implicit and explicit measures of end-product potential and value continues. Facilitating, enabling and engaging in local, regional, national and global knowledge exchange activities through virtual and non-virtual-based workshops, conferences, presentations, on-site demonstrations, and publications, are important primary goals of this Unit.

 


State of Knowledge

  • Analytics for quantifying the impact of anthropogenic influences on growth and yield through model refinement and adaptation
  • Adapting to the paradigmic shift towards stand-level value-based management objectives via modelling innovations and modification including the development of prediction models for forecasting both volumetric-based and end-product-based outcome metrics
  • Linking and reconciling tree-level, size-class and stand-level models to ensure analytical consistency and predictive equivalence
  • Provision of solutions arising from the challenges of modelling of complex stand-types (see outputs)