Optimizing high-dimensional stochastic forestry via reinforcement learning

Tahvonen, Olli; Suominen, Antti; Malo, Pekka; Viitasaari, Lauri; Parkatti, Vesa-Pekka

doi:10.1016/j.jedc.2022.104553

Cited by 9 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RL has found extensive application in the field of forestry. Research endeavors have concentrated on various aspects such as simulated fire fighting [43], forest fire detection [44], optimal harvest modeling [45], and forest management [46], offering crucial insights into these domains. Despite their significant contributions to the efficient preservation and management of forests, these research areas differ significantly in their focus and methodologies.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning for Stand Structure Optimization of Pinus yunnanensis Secondary Forests in Southwest China

Xuan,

Wang,

Chen

2023

Forests

View full text Add to dashboard Cite

Aiming to enhance the efficiency and precision of multi-objective optimization in southwestern secondary growth of Pinus yunnanensis forests, this study integrated spatial and non-spatial structural indicators to establish objective functions and constraints for assessing forest structure. Felling decisions were made using the random selection method (RSM), Q-value method (QVM), and V-map method (VMM). Actions taken to optimize the forest stand structure (FSS) through tree selection were approached as decisions by a reinforcement learning (RL) agent. Leveraging RL’s trial-and-error strategy, we continually refined the agent’s decision-making process, applying it to multi-objective optimization. Simulated felling experiments conducted across circular sample plots (P1–P4) compared RL, Monte Carlo (MC), and particle swarm optimization (PSO) in FSS optimization. Notable enhancements in the values of the objective function (VOFs) were observed across all plots. RL-based strategies exhibited improvements, achieving VOF increases of 17.24%, 44.92%, 34.66%, and 17.10% for P1–P4, respectively, outperforming MC-based (10.73%, 41.54%, 30.39%, and 15.07%, respectively) and PSO-based (14.08%, 37.78%, 26.17%, and 16.23%, respectively) approaches. The hybrid M7 scheme, integrating RL with the RSM, consistently outperformed other schemes across all plots, yielding an average 26.81% increase in VOF compared to the average enhancement of all schemes (17.42%). This study significantly advances the efficacy and precision of multi-objective optimization strategies for Pinus yunnanensis secondary forests, emphasizing RL’s superior optimization performance, particularly when combined with the RSM, highlighting its potential for optimizing sustainable forest management strategies.

show abstract

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning for Stand Structure Optimization of Pinus yunnanensis Secondary Forests in Southwest China

Xuan,

Wang,

Chen

2023

Forests

View full text Add to dashboard Cite

show abstract

Financial Performance

Ahtikoski,

Gong,

Rørstad

et al. 2024

Managing Forest Ecosystems

View full text Add to dashboard Cite

Financial comparisons between rotation forestry (RF) and continuous cover forestry (CCF) are based on simulations in which the growth and yield of trees is estimated using a growth simulator. These often include an optimisation tool to present the maximum value of the objective function (usually the present value of net income). Studies have shown that the profitability of CCF depends on the initial state of a stand, especially the diameter distribution of the trees. The effect of interest discount rate also depends on the initial state. As a rule, it is safe to say that the more the forest structure resembles the target diameter distribution of the trees in CCF (i.e., a forest with heterogeneous structures), the more profitable it is to shift from RF to CCF. The more heterogeneous the tree structure on mineral soil, the higher the applied interest rate, the higher the forest establishment costs (soil preparation and cultivation), and the poorer the growth conditions (site type and temperature sum), the more profitable CCF is. Few studies have been found that focus on peatland forests. Future financial studies should also consider risks associated with wind, harvesting, and insect and fungus damage as well as carbon payments and nontimber benefits

show abstract

Faustmann formula and its use in forest asset valuation: A review and a suggestion

McIntosh,

Zhang

2024

Forest Policy and Economics

View full text Add to dashboard Cite

Optimizing high-dimensional stochastic forestry via reinforcement learning

Cited by 9 publications

References 40 publications

Reinforcement Learning for Stand Structure Optimization of Pinus yunnanensis Secondary Forests in Southwest China

Reinforcement Learning for Stand Structure Optimization of Pinus yunnanensis Secondary Forests in Southwest China

Financial Performance

Faustmann formula and its use in forest asset valuation: A review and a suggestion

Contact Info

Product

Resources

About