Heikki Astola, Annika Kangas, Francesco Minunno, Matti Mõttus. (2026). Emulating a forest growth and productivity model with deep learning. Silva Fennica vol. 60 no. 1 article id 25012. https://doi.org/10.14214/sf.25012

Keywords: carbon balance; simulation; machine learning; climate scenarios; digital twins; forest variables; time series prediction

Highlights: Emulating the operation of analytical forest growth models is feasible using state-of-the-art machine learning methods; Long term prediction of forest growth and carbon balance variables were produced with low bias accumulation when compared to the reference model; The methods tested offer means for long time span simulations of large areas with a high spatial resolution.

Abstract | Full text in HTML | Full text in PDF | Author Info

We studied the possibility of replacing a complex forest growth and productivity model with a deep learning model with sufficient accuracy. We used three different neural network architectures for emulating the prediction task of the PREBASSO (Mäkelä 1997; Minunno et al. 2016) forest growth model: 1) Recurrent Neural Network (RNN) Encoder-decoder network, 2) RNN encoder network, and 3) Transformer encoder network. The PREBASSO forest growth model was used to produce 25-year predictions for forest variables: tree height, stem diameter, basal area, and the carbon balance variables: net primary production (NPP), gross primary production per tree layer (GPP), net ecosystem exchange (NEE) and gross growth (GGR) to train the machine learning models. The Finnish Forest Centre provided the data for 29 619 field inventory plots in continental Finland that were used as the initial state of the forest sites to be simulated. Climate data downloaded from Copernicus Climate Data Store were used to provide realistic climate scenarios. We emphasized the importance of low bias in long term predictions and set the goal for the emulator prediction relative bias to be within ±2%. The RNN encoder model produced the best results with the mean of the yearly bias values within the specified ±2% limit over the 25-year prediction period. The study shows that emulating the operation of analytical forest growth models is feasible using state-of-the-art machine learning methods and indicates the potential of using such emulators for producing long time span simulations for e.g. digital twins.

Astola, VTT Technical Research Centre of Finland, Tekniikantie 1, 02150 Espoo, Finland https://orcid.org/0000-0003-4989-9910 E-mail: heikki.astola@gmail.com
Kangas, Natural Resources Institute Finland (Luke), Bioeconomy and Environment, Yliopistokatu 6, 80100 Joensuu, Finland https://orcid.org/0000-0002-8637-5668 E-mail: annika.kangas@luke.fi
Minunno, Yucatrote, Rua António Gavina L49, 8600-214 Luz, Lagos, Portugal https://orcid.org/0000-0002-7658-6402 E-mail: francesco.minunno@helsinki.fi
Mõttus, VTT Technical Research Centre of Finland, Tekniikantie 1, 02150 Espoo, Finland https://orcid.org/0000-0002-2745-1966 E-mail: Matti.Mottus@vtt.fi

Click this link to register to Silva Fennica.

If you are a registered user, log in to save your selected articles for later access.

Contents alert

Your selected articles

Follow @SilvaFennica