Alwin A. Hardenbol, Hans Ole Ørka, Terje Gobakken, Joel Kostensalo. (2026). Optimising rare tree species detection for large-area mapping: a case study on European aspen (Populus tremula). Silva Fennica vol. 60 no. 3 article id 26012. https://doi.org/10.14214/sf.26012

Keywords: Bayesian statistics; biodiversity conservation; base rate problem; broadleaves; individual tree map; model transferability

Highlights: Balancing false discovery and false negative rates improves rare tree species detection; Preferring volume- over count-based approaches makes ecological sense for rare tree species; We detected 70% of aspen volume and classified this volume with 31% false discovery rate and 54% false negative rate; Base rates of rare tree species have been overlooked in remote sensing literature.

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

Some locally rare tree species – like European aspen (Populus tremula L.) – contribute disproportionately to forest biodiversity, making their accurate monitoring important for conservation. However, most remote sensing studies of rare tree species ignore their low prevalence/base rate, necessary for model transferability. We aimed to assess European aspen classification under realistic landscape prevalence and find methods to improve classification performance. Across 253 plots from field data in Våler, Norway we detected and segmented 5455 living trees, including 55 European aspens (ca. 1% prevalence), from high-density airborne laser scanning (ALS) data merged with multispectral aerial imagery. Individual segments were then classified as European aspen or non-aspen using random forest and synthetic minority oversampling (SMOTE). We evaluated classification based on tree counts and summed tree volumes. To underpin the importance of prevalence consideration and compare our results, we also re-analysed published Fennoscandian European aspen classification studies. Contrary to a perfect balance, we found an optimal SMOTE-ratio at ca. 0.07 (European aspen–non-aspen ratio). Our count-based classification achieved 32% (16–52) false discovery rate (FDR) and 73% (60–83) false negative rate (FNR), whereas volume-based classification achieved 31% (11–51) FDR and 54% (38–71) FNR. Re-analysed studies averaged 66% FDR and 33% FNR at a 1% prevalence. Our results demonstrate that rare tree species classification benefits from optimising majority–minority ratios and, given the ecological value of larger trees, volume-based approaches are warranted. Finally, we urge reporting landscape prevalence and adjust classification metrics to reflect these to enable transferability to real-world applications in rare tree species classification.

Hardenbol, Natural Resources Institute Finland (Luke), Natural Resources Unit, Yliopistokatu 6B, FI-80100 Joensuu, Finland https://orcid.org/0000-0002-0615-505X E-mail: alwin.hardenbol@luke.fi
Ørka, Norwegian University of Life Sciences (NMBU), Faculty of Environmental Sciences and Natural Resource Management, P.O. Box 5003, NO-1432 Ås, Norway https://orcid.org/0000-0002-7492-8608 E-mail: hans-ole.orka@nmbu.no
Gobakken, Norwegian University of Life Sciences (NMBU), Faculty of Environmental Sciences and Natural Resource Management, P.O. Box 5003, NO-1432 Ås, Norway https://orcid.org/0000-0001-5534-049X E-mail: terje.gobakken@nmbu.no
Kostensalo, Natural Resources Institute Finland (Luke), Natural Resources Unit, Yliopistokatu 6B, FI-80100 Joensuu, Finland https://orcid.org/0000-0001-9883-1256 E-mail: joel.kostensalo@luke.fi

article id 321, category Research article

Jori Uusitalo, Anne Puustelli, Veli-Pekka Kivinen, Tapio Nummi, Bikas K. Sinha. (2006). Bayesian estimation of diameter distribution during harvesting. Silva Fennica vol. 40 no. 4 article id 321. https://doi.org/10.14214/sf.321

Keywords: diameter distribution; Bayesian statistics; tree harvesting

Abstract | View details | Full text in PDF | Author Info

This research aims to combine two different data sets with Bayesian statistics in order to predict the diameter distribution of trees at harvest. The parameters of prior distribution are derived from the forest management plans supplemented by additional ocular information. We derive the parameters for the sample data from the first trees harvested, and then create the posterior distribution within the Bayesian framework. We apply the standard normal distribution to construct diameter (dbh) distributions, although many other theoretical distributions have been proved better with dbh data available. The methodology developed is then tested on nine mature spruce (Picea abies) dominated stands, on which the normal distribution seems to work well in mature spruce stands. The tests indicate that prediction of diameter distribution for the whole stand based on the first trees harvested is not wise, since it tends to give inaccurate predictions. Combining the first trees harvested with prior information seems to increase the reliability of predictions.

Uusitalo, The Finnish Forest Research Institute, Parkano unit, FI-39700 Parkano, Finland E-mail: jori.uusitalo@metla.fi
Puustelli, University of Tampere, Department of Mathematics, Statistics and Philosophy, FI-33014 University of Tampere, Finland E-mail: ap@nn.fi
Kivinen, University of Helsinki, Department of Forest Resource Management, Box 27, FI-00014 University of Helsinki, Finland E-mail: vpk@nn.fi
Nummi, University of Tampere, Department of Mathematics, Statistics and Philosophy, FI-33014 University of Tampere, Finland E-mail: tn@nn.fi
Sinha, Stat-Math Division, Indian Statistical Institute, 203 B.T. Road, Kolkata - 700 108, India E-mail: bks@nn.in

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
Send to email

Korhonen L., Ali-Sisto D. et al. (2015) Tropical forest canopy cover estimation using sa.. Silva Fennica vol. 49 no. 5 article id 1405 (remove) | Edit comment

Follow @SilvaFennica