Towards sustainable forest management strategies with MOEAs

Philipp Back*, Antti Suominen, Pekka Malo, Olli Tahvonen, Julian Blank, Kalyanmoy Deb

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Sustainable forest management is a crucial element in combating climate change, plastic pollution, and other unsolved challenges of the 21st century. Forests not only produce wood - a renewable resource that is increasingly replacing fossil-based materials - but also preserve biodiversity and store massive amounts of carbon. Thus, a truly optimal forest policy has to balance profit-oriented logging with ecological and societal interests, and should thus be solved as a multi-objective optimization problem. Economic forest research, however, has largely focused on profit maximization. Recent publications still scalarize the problem a priori by assigning weights to objectives. In this paper, we formulate a multi-objective forest management problem where profit, carbon storage, and biodiversity are maximized. We obtain Pareto-efficient forest management strategies by utilizing three state-of-the-art Multi-Objective Evolutionary Algorithms (MOEAs), and by incorporating domain-specific knowledge through customized evolutionary operators. An analysis of Pareto-efficient strategies and their harvesting schedules in the design space clearly shows the benefits of the proposed approach. Unlike many EMO application studies, we demonstrate how a systematic post-optimality trade-off analysis can be applied to choose a single preferred solution. Our pioneering work on sustainable forest management explores an entirely new application area for MOEAs with great societal impact.
Original languageEnglish
Title of host publicationProceedings of the 2020 Genetic and Evolutionary Computation Conference
PublisherACM
Pages1046-1054
Number of pages9
ISBN (Electronic)9781450371285
ISBN (Print)9781450371285
DOIs
Publication statusPublished - 25 Jun 2020
MoE publication typeA4 Article in a conference publication
EventGenetic and Evolutionary Computation Conference - Cancun, Mexico
Duration: 8 Jul 202012 Jul 2020

Conference

ConferenceGenetic and Evolutionary Computation Conference
Abbreviated titleGECCO
CountryMexico
CityCancun
Period08/07/202012/07/2020

Keywords

  • Economic forest research
  • optimal forest management
  • multi-objective optimization
  • NSGA-II
  • NSGA-III
  • MOEA/D

Fingerprint

Dive into the research topics of 'Towards sustainable forest management strategies with MOEAs'. Together they form a unique fingerprint.

Cite this