Innovative Techniques to Produce New Data
A forest measurement method based on maps of 2D lidar and sparse laser scanning data, which enables accurate forest information using more affordable mapping devices, for example by harvester measurements.
Vezeteu et al. 2026. Direct 3D mapping with a 2D LiDAR using sparse reference maps.
The benefits of the thinning density assistant were mainly to help less experienced forest machine operators with their work productivity. It also increases the quality of fellings and enables documenting tree-level information from the data collected by the harvester.
Pohjala et al. 2025. Effects of a mobile LiDAR-based thinning density assistant (TDA) system on harvester operator performance.
Extensive survey of AI methods for identifying tree species from laser scanning data. Point-based deep learning methods performed the most effectively among those examined.
Taher et al. 2026. Multispectral airborne laser scanning for tree species classification: A benchmark of machine learning and deep learning algorithms.
Agile Knowledge Creation from Forest Data
A statistical method that found the oldest forests from remote sensing data more reliably than before. The challenge has been that old trees stop growing vertically, making them undetectable by methods that estimate age by crown height.
Toivonen et al. 2025. Combining tree-boosting and mixed effects models improves the performance of remote-sensing based forest age predictions.
A solution for better detection of old-growth forests using remote sensing: classification using laser scanning and satellite images showed that the accuracy of classification was improved by using larger experimental plots than currently used.
Räty, J. et al. 2025. Mapping old-growth forests using airborne lidar data and satellite images: How do plot size and rarity affect accuracy?
A new model for predicting average growth in relation to age for the growth measurement data of the national forest inventory. It enables the simulation of different logging options, which illustrates the connection between the sustainability of forest use and logging.
Mehtätalo et al. 2024. A new growth curve and fit to the National Forest Inventory data of Finland – ScienceDirect..
Smart decision support for human action in space and time
In continuous cover forestry, pine regeneration after cuttings remains weak considering timber production, especially under dense overstory. A thick humus layer and dense moss and herb cover reduced seedling establishment.
Peltola, P. et al. 2025. Natural regeneration and development of Scots pine seedlings in continuous cover forestry in northern Finland – ScienceDirect.
Analysis of spruce bark beetle attacks, where hotspots were found especially in mature spruce stands in the vicinity of previous damage. Knowledge of potential locations helps in risk assessment and forest management planning.
Pulgarin et al. 2025. Assessing the impacts of forest stand structure and landscape on the formation of Ips typographus damage hotspots in Finland | Forestry: An International Journal of Forest Research | Oxford Academic.
This paper presents how data-flow-based model linking can be used to build flexible, modular, and efficient simulation software for decision-making in forest management.
Lempinen et al. 2025. A lightweight dataflow-based software framework for building forest simulators – ScienceDirect.
Gameful Forest Interaction for Meaningful Experiences
and Practices
12 different ways in which interactive technology might support forest-related experiences that are joyful for humans.
Altarriba Bertran et al 2025. How Can Interactive Technology Help Us to Experience Joy With(in) the Forest? Towards a Taxonomy of Tech for Joyful Human-Forest Interactions.
This co-design study on companion robots for the wild resulted in a comprehensive design space that can be leveraged by designers and researchers in creating companion robots for the wild.
Ahmed et al 2025. Co-Designing Companion Robots for the Wild: Ideating Towards a Design Space.
Analysis of gamification dynamics and interactions best suited for different crowdsourcing tasks in a forest setting. Gamification approaches influence the type and quality of crowdsourced data, as well as the user experience.
Nummenmaa, T. et al 2025. Employing Gamified Crowdsourced Close-Range Sensing in the Pursuit of a Digital Twin of the Earth.