Assessing the potential of synthetic and ex situ airborne laser scanning and ground plot data to train forest biomass models

Airborne laser scanning data are increasingly used to predict forest biomass over large areas. Biomass information cannot be derived directly from airborne laser scanning data; therefore, field measurements of forest plots are required to build regression models. We tested whether simulated laser sc...

Full description

Saved in:
Bibliographic Details
Main Authors: Schäfer, Jannika (Author) , Winiwarter, Lukas (Author) , Weiser, Hannah (Author) , Novotný, Jan (Author) , Höfle, Bernhard (Author) , Schmidtlein, Sebastian (Author) , Henniger, Hans (Author) , Krok, Grzegorz (Author) , Stereńczak, Krzysztof (Author) , Faßnacht, Fabian Ewald (Author)
Format: Article (Journal)
Language:English
Published: Oktober 2024
Edition:Online veröffentlicht: 4. Dezember 2023
In: Forestry
Year: 2023, Volume: 97, Issue: 4, Pages: 512-530
ISSN:1464-3626
DOI:10.1093/forestry/cpad061
Online Access:Verlag, kostenfrei, Volltext: https://doi.org/10.1093/forestry/cpad061
Get full text
Author Notes:Jannika Schäfer, Lukas Winiwarter, Hannah Weiser, Jan Novotný, Bernhard Höfle, Sebastian Schmidtlein, Hans Henniger, Grzegorz Krok, Krzysztof Stereńczak and Fabian Ewald Fassnacht

MARC

LEADER 00000caa a2200000 c 4500
001 1879044749
003 DE-627
005 20250516151355.0
007 cr uuu---uuuuu
008 240126s2024 xx |||||o 00| ||eng c
024 7 |a 10.1093/forestry/cpad061  |2 doi 
035 |a (DE-627)1879044749 
035 |a (DE-599)KXP1879044749 
035 |a (OCoLC)1425207516 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 61  |2 sdnb 
100 1 |a Schäfer, Jannika  |e VerfasserIn  |0 (DE-588)1317313690  |0 (DE-627)1879045591  |4 aut 
245 1 0 |a Assessing the potential of synthetic and ex situ airborne laser scanning and ground plot data to train forest biomass models  |c Jannika Schäfer, Lukas Winiwarter, Hannah Weiser, Jan Novotný, Bernhard Höfle, Sebastian Schmidtlein, Hans Henniger, Grzegorz Krok, Krzysztof Stereńczak and Fabian Ewald Fassnacht 
250 |a Online veröffentlicht: 4. Dezember 2023 
264 1 |c Oktober 2024 
300 |b Illustrationen 
300 |a 19 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 16.05.2025 
520 |a Airborne laser scanning data are increasingly used to predict forest biomass over large areas. Biomass information cannot be derived directly from airborne laser scanning data; therefore, field measurements of forest plots are required to build regression models. We tested whether simulated laser scanning data of virtual forest plots could be used to train biomass models and thereby reduce the amount of field measurements required. We compared the performance of models that were trained with (i) simulated data only, (ii) a combination of simulated and real data, (iii) real data collected from different study sites, and (iv) real data collected from the same study site the model was applied to. We additionally investigated whether using a subset of the simulated data instead of using all simulated data improved model performance. The best matching subset of the simulated data was sampled by selecting the simulated forest plot with the highest correlation of the return height distribution profile for each real forest plot. For comparison, a randomly selected subset was evaluated. Models were tested on four forest sites located in Poland, the Czech Republic, and Canada. Model performance was assessed by root mean squared error (RMSE), squared Pearson correlation coefficient (r$^{2}$), and mean error (ME) of observed and predicted biomass. We found that models trained solely with simulated data did not achieve the accuracy of models trained with real data (RMSE increase of 52-122 %, r$^{2}$ decrease of 4-18 %). However, model performance improved when only a subset of the simulated data was used (RMSE increase of 21-118 %, r$^{2}$ decrease of 5-14 % compared to the real data model), albeit differences in model performance when using the best matching subset compared to using a randomly selected subset were small. Using simulated data for model training always resulted in a strong underprediction of biomass. Extending sparse real training datasets with simulated data decreased RMSE and increased r$^{2}$, as long as no more than 12-346 real training samples were available, depending on the study site. For three of the four study sites, models trained with real data collected from other sites outperformed models trained with simulated data and RMSE and r$^{2}$ were similar to models trained with data from the respective sites. Our results indicate that simulated data cannot yet replace real data but they can be helpful in some sites to extend training datasets when only a limited amount of real data is available. 
700 1 |a Winiwarter, Lukas  |d 1994-  |e VerfasserIn  |0 (DE-588)1198882808  |0 (DE-627)1681036118  |4 aut 
700 1 |a Weiser, Hannah  |e VerfasserIn  |0 (DE-588)1244932566  |0 (DE-627)1776004736  |4 aut 
700 1 |a Novotný, Jan  |e VerfasserIn  |4 aut 
700 1 |a Höfle, Bernhard  |e VerfasserIn  |0 (DE-588)1019895403  |0 (DE-627)691049297  |0 (DE-576)358986753  |4 aut 
700 1 |8 1\p  |a Schmidtlein, Sebastian  |d 1965-  |e VerfasserIn  |0 (DE-588)1329182723  |0 (DE-627)1888412399  |4 aut 
700 1 |a Henniger, Hans  |e VerfasserIn  |4 aut 
700 1 |a Krok, Grzegorz  |e VerfasserIn  |4 aut 
700 1 |a Stereńczak, Krzysztof  |e VerfasserIn  |4 aut 
700 1 |a Faßnacht, Fabian Ewald  |e VerfasserIn  |0 (DE-588)1049994310  |0 (DE-627)78310944X  |0 (DE-576)402425588  |4 aut 
773 0 8 |i Enthalten in  |t Forestry  |d Oxford : Oxford Univ. Press, 1927  |g 97(2023), 4 vom: Okt., Seite 512-530  |h Online-Ressource  |w (DE-627)266016146  |w (DE-600)1466705-8  |w (DE-576)074960059  |x 1464-3626  |7 nnas  |a Assessing the potential of synthetic and ex situ airborne laser scanning and ground plot data to train forest biomass models 
773 1 8 |g volume:97  |g year:2023  |g number:4  |g month:10  |g pages:512-530  |g extent:19  |a Assessing the potential of synthetic and ex situ airborne laser scanning and ground plot data to train forest biomass models 
856 4 0 |u https://doi.org/10.1093/forestry/cpad061  |x Verlag  |x Resolving-System  |z kostenfrei  |3 Volltext 
883 |8 1\p  |a cgwrk  |d 20250301  |q DE-101  |u https://d-nb.info/provenance/plan#cgwrk 
951 |a AR 
992 |a 20240126 
993 |a Article 
994 |a 2024 
998 |g 1019895403  |a Höfle, Bernhard  |m 1019895403:Höfle, Bernhard  |d 120000  |d 120700  |e 120000PH1019895403  |e 120700PH1019895403  |k 0/120000/  |k 1/120000/120700/  |p 5 
998 |g 1244932566  |a Weiser, Hannah  |m 1244932566:Weiser, Hannah  |d 120000  |d 120700  |e 120000PW1244932566  |e 120700PW1244932566  |k 0/120000/  |k 1/120000/120700/  |p 3 
998 |g 1198882808  |a Winiwarter, Lukas  |m 1198882808:Winiwarter, Lukas  |d 120000  |e 120000PW1198882808  |k 0/120000/  |p 2 
999 |a KXP-PPN1879044749  |e 4467967354 
BIB |a Y 
SER |a journal 
JSO |a {"relHost":[{"title":[{"title":"Forestry","title_sort":"Forestry"}],"id":{"issn":["1464-3626"],"zdb":["1466705-8"],"eki":["266016146"]},"note":["Fortsetzung der Druck-Ausgabe","Gesehen am 14. Januar 2025"],"disp":"Assessing the potential of synthetic and ex situ airborne laser scanning and ground plot data to train forest biomass modelsForestry","name":{"displayForm":["Institute of Chartered Foresters"]},"physDesc":[{"extent":"Online-Ressource"}],"part":{"year":"2023","extent":"19","pages":"512-530","text":"97(2023), 4 vom: Okt., Seite 512-530","volume":"97","issue":"4"},"type":{"bibl":"periodical","media":"Online-Ressource"},"origin":[{"publisher":"Oxford Univ. Press","dateIssuedDisp":"1927-","publisherPlace":"Oxford","dateIssuedKey":"1927"}],"language":["eng"],"pubHistory":["1.1927 -"],"recId":"266016146"}],"physDesc":[{"extent":"19 S.","noteIll":"Illustrationen"}],"person":[{"role":"aut","display":"Schäfer, Jannika","given":"Jannika","roleDisplay":"VerfasserIn","family":"Schäfer"},{"roleDisplay":"VerfasserIn","family":"Winiwarter","display":"Winiwarter, Lukas","role":"aut","given":"Lukas"},{"given":"Hannah","role":"aut","display":"Weiser, Hannah","roleDisplay":"VerfasserIn","family":"Weiser"},{"family":"Novotný","roleDisplay":"VerfasserIn","given":"Jan","role":"aut","display":"Novotný, Jan"},{"given":"Bernhard","role":"aut","display":"Höfle, Bernhard","roleDisplay":"VerfasserIn","family":"Höfle"},{"roleDisplay":"VerfasserIn","family":"Schmidtlein","given":"Sebastian","display":"Schmidtlein, Sebastian","role":"aut"},{"display":"Henniger, Hans","role":"aut","given":"Hans","roleDisplay":"VerfasserIn","family":"Henniger"},{"roleDisplay":"VerfasserIn","family":"Krok","display":"Krok, Grzegorz","role":"aut","given":"Grzegorz"},{"given":"Krzysztof","role":"aut","display":"Stereńczak, Krzysztof","roleDisplay":"VerfasserIn","family":"Stereńczak"},{"display":"Faßnacht, Fabian Ewald","role":"aut","given":"Fabian Ewald","family":"Faßnacht","roleDisplay":"VerfasserIn"}],"name":{"displayForm":["Jannika Schäfer, Lukas Winiwarter, Hannah Weiser, Jan Novotný, Bernhard Höfle, Sebastian Schmidtlein, Hans Henniger, Grzegorz Krok, Krzysztof Stereńczak and Fabian Ewald Fassnacht"]},"type":{"media":"Online-Ressource","bibl":"article-journal"},"origin":[{"editionNo":"4","edition":"Online veröffentlicht: 4. Dezember 2023","dateIssuedKey":"2024","dateIssuedDisp":"Oktober 2024"}],"language":["eng"],"note":["Gesehen am 16.05.2025"],"recId":"1879044749","id":{"eki":["1879044749"],"doi":["10.1093/forestry/cpad061"]},"title":[{"title_sort":"Assessing the potential of synthetic and ex situ airborne laser scanning and ground plot data to train forest biomass models","title":"Assessing the potential of synthetic and ex situ airborne laser scanning and ground plot data to train forest biomass models"}]} 
SRT |a SCHAEFERJAASSESSINGT2024