Project: ForestMap
The overall objective of the project is to develop and evaluate a new methodology to produce forest maps across the globe, to advance the societal values of forest use. The forest maps will be produced using crowdsourced data from smartphones and remote sensing data from space- and airborne systems in an AI framework.
Project information
Project name
ForestMap: The next generation of forest maps – adapting a Nordic success story across the globe
Project manager
Johan Fransson
Other project members
Jörgen Wallerman and Mats Nilsson, Swedish University of Agricultural Sciences, Sweden
Anton Holmström, Katam Technologies, Sweden
Cem Ünsalan, Yeditepe University, Turkey
Elif Sertel, Istanbul Technical University, Turkey
Jari Salo, University of Helsinki, Finland
Shafiullah Soomro, Linnaeus University
Jorge Lazo, AI Sweden
Dag Björnberg, Softwerk, Sweden
Participating organizations
Linnaeus University, Swedish University of Agricultural Sciences, Katam Technologies, AI Sweden and Softwerk, Sweden; Yeditepe University and Istanbul Technical University, Turkey; University of Helsinki, Finland
Financier
Vinnova, Swedish Energy Agency, Formas, EU Horizon 2020
Timetable
1 Jan 2022–31 Dec 2024
Subject
Forestry and wood technology (Department of Forestry and Wood Technology, Faculty of Technology)
Website
Katam.se/company/collaborations/forestmap
More about the project
From the positive experience with open forest map data in Sweden and Finland, it’s clear that offering the same solution world-wide would revolutionize forest management and business across the globe. The management of forest in the Nordic countries can of course be improved, but the fastest solution for climate change mitigation is to offer all other countries some of the opportunities that the forestry sector in Sweden and Finland have benefitted from during the initial digitalization age.
In this project, we will develop a new, hierarchical, flexible decision-making system for efficient forest mapping, utilizing a broad scale of remote sensing data sources, where hierarchical levels consist of remote sensing data with different resolutions. Here, we will use modern AI methods to form a new hierarchical system. The developed system will then be backed up by results from traditional computer vision methods such as texture analysis, saliency, and probabilistic object representation.
The power and strength in the research project are that we can use forest data and forest maps of Sweden and Finland as test beds to benchmark the methodology to be developed in the project. We strongly believe that the project largely will contribute to mitigate climate change, strengthen biodiversity and other societal values, and create new business models through the development of a new methodology for the next generation of forest maps. Our vision is to adapt the Nordic success story of open forest map data across the globe, benefiting from innovative AI technology and integrated use of remote sensing and field data.
The project is part of the research in the Forest Management , Forestry, Wood and Building Technologies and Linnaeus University Centre for Data Intensive Sciences and Applications (DISA) research groups, the collaboration The Bridge, and the Linnaeus Knowledge Environment Green Sustainable Development.
