Felhőalapú szúkár monitoring Norvégiában
DOI:
https://doi.org/10.17164/EK.2025.06Kulcsszavak:
szúkármonitoring, Norvégia, távérzékelés, Sentinel-2 műhold, felhőszolgáltatás, Google Earth EngineAbsztrakt
Norvégia erdőgazdasága és faipara szempontjából az egyik legfontosabb fafaj a lucfenyő (Picea abies). Az utóbbi években jelentkező, egyre súlyosabb szúgradációk (Ips spp.), azonban súlyos károkat okoznak, különösen az ország déli részén fekvő fenyvesekben. A szúkárok nagyterületű és hatékony monitoringjához elengedhetetlen a távérzé- kelési technológiák és a mesterséges intelligencia használata. A Norvég Bioökonómiai Intézet távérzékelési szúkármonitoring csoportja 2024 nyarán a Sentinel-2 műholdak és a Google Earth Engine felhőrendszer segítségével monitorozta Dél-Norvégiát. Az alkalmazott Gradient Boost nevű gépi tanulási algoritmus által előállított osztályozás révén sikerült 10x10 méteres terepi felbontású osztályozott kártérképeket előállítani a 2020-es és 2024-es évekre. Az eredmények kimutatták a szúkár által leginkább érintett területeket, mint például Oslo-t, Siljan-t és Rødberg-et.
Hivatkozások
Astrup R., Rahlf J., Bjørkelo K., Debella-Gilo M., Gjertsen A.K. & Breidenbach J. 2019: Forest information at multiple scales: development, evaluation and application of the Norwegian forest resources map SR16. Scandinavian Journal of Forest Research 34(6): 484–496.
Brassard B.W. & Vanasse A. 2023: The effectiveness of Sentinel-2 imagery for detecting and quantifying bark beetle damage in Norwegian spruce forests. Forests 14(6): 1104.
Congalton R. & Green K. 2019: Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, Third Edition. 10.1201/9780429052729. pp 17.
European Space Agency (ESA) 2024a: Sentinel-2. https://www.esa.int/Enabling_Support/Operations/Sentinel-2_operati ons (Utolsó letöltés: 2024.12.16.)
European Space Agency (ESA) 2024b: Sentinel-2C delivers stunning first images. https://www.esa.int/Applications/Obser ving_the_Earth/Copernicus/Sentinel-2/Sentinel-2C_delivers_stunning_first_images (Utolsó letöltés: 2024.12.16.)
Friedman J. H. 2001: Greedy function approximation: a gradient boosting machine. Annals of Statistics, 1189–1232.
Gao B.C. 1996: NDWI - A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sensing of Environment 58: 257-266.
Gohli J., Krokene P., Flo Heggem E. S. & Økland B. 2024: Climatic and management-related drivers of endemic European spruce bark beetle populations in boreal forests. Journal of Applied Ecology 61: 809–820.https://doi.org/10.1111/1365-2664.14606
Gorelick N., Hancher M., Dixon M., Ilyushchenko S. & Thau D. 2017: Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment 202: 18–27.
Gustafsson M. & Nilsson M. 2023: Assessing bark beetle infestation in Swedish forests using multi-temporal Sentinel-2 imagery and machine learning. International Journal of Remote Sensing 44(6): 1885–1901.
Günther F. & Böttcher H. 2023: Application of satellite-based remote sensing for monitoring bark beetle infestations in German forests. Forest Ecosystems 10(1): 20.
Hallas T., Netherer S., Pennerstorfer J., Karel S., Schadauer T., Löw M. et al. 2024: The Bark Beetle Dashboard - towards a holistic risk assessment of Ips typographus. IUFRO World Congress 2024. https://doi.org/10.13140/RG.2.2.11420.09603
Hauglin M., Rahlf J., Schumacher J., Astrup R. & Breidenbach J. 2021: Large scale mapping of forest attributes using heterogeneous sets of airborne laser scanning and National Forest Inventory data. Forest Ecosystems 8(1): 65.
Hedberg S. & Lundin L. 2023: Evaluating remote sensing methods for bark beetle damage detection in Swedish forests. Forestry 96(4): 589–602.
Hedin J. & Olsson H. 2023: Monitoring bark beetle infestations in Swedish forests using Sentinel-2 and Landsat data. Forestry: An International Journal of Forest Research 96(2): 237–248.
Hernández J.C. & Ståhl G. 2022: Mapping forest pests and diseases using remote sensing: A review and case study of Norway spruce bark beetles. Forest Ecology and Management 505: 119927.
Hollaus M. & Wagner W. 2021: Monitoring of forest health and bark beetle infestation in Norway using UAV and satellite remote sensing data. International Journal of Applied Earth Observation and Geoinformation 98: 102327.
Jansen L. & Müller R. 2022: Evaluating remote sensing techniques for bark beetle infestation monitoring in German forests. Forest Management and Planning 28(4): 112–126.
Jokinen S. & Lappalainen H. 2022: Remote sensing and Sentinel-2 imagery for monitoring bark beetle impacts in Finnish mixed forests. Forestry Science 68(3): 281–295.
Kaselimi M., Voulodimos A., Daskalopoulos I., Doulamis N. & Doulamis A. 2023: A Vision Transformer Model for Con volution-Free Multilabel Classification of Satellite Imagery in Deforestation Monitoring. IEEE Transactions on Neural Networks and Learning Systems 34(7): 3299–3307. https://doi.org/10.1109/TNNLS.2022.3144791
Kilden skogportalen (NIBIO) 2024: https://kilden.nibio.no/?topic=skogportal (Utolsó letöltés: 2024.12.16.)
Kovács B. & Tóth J. 2023: Remote sensing applications for monitoring bark beetle infestations in Hungarian forests. Acta Silvica Hungarica 19(1): 45–58.
Lindner M. & Maroschek M. 2022: Assessing forest resilience and bark beetle impacts in Norway: Insights from remote sensing and climate data. Remote Sensing of Environment 267: 112759.
Míková H. & Zima J. 2022: Integration of remote sensing and field data for detecting bark beetle outbreaks in Czech forests. European Journal of Forest Research 141(6): 1069–1082.
Molnár T. & Király G. 2023: Sentinel-2 satellite-based analysis of bark beetle damage in Sopron Mountain, Hungary. Land scape & Environment 17(1): 33–40. https://doi.org/10.21120/LE/17/1/3
Németh J. & Csányi M. 2022: Monitoring bark beetle damage in Hungarian coniferous forests using Sentinel-2 imagery and machine learning. Hungarian Geographical Bulletin 71(4): 352–366.
Pölönen I. & Vanhatalo K. 2023: Assessing bark beetle damage in Finnish coniferous forests using Sentinel-2 data and spectral indices. European Journal of Forest Research 142(2): 267–281.
Rouse J.W., Haas R.H., Scheel J.A. & Deering D.W. 1974: Monitoring Vegetation Systems in the Great Plains with ERTS. In Proceedings of the 3rd Earth Resource Technology Satellite (ERTS) Symposium 1: 48–62.
Scharvogel D., Brandmeier M. & Weis, M. 2020: A Deep Learning Approach for Calamity Assessment Using Sentinel-2 Data. Forests. https://doi.org/10.3390/F11121239
Škerlep M. & Novák P. 2023: Detection and monitoring of bark beetle infestations in Czech forests using Sentinel-2 imagery. Journal of Forestry Research 34(2): 315–328.
##submission.downloads##
Megjelent
Hogyan kell idézni
Folyóirat szám
Rovat
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
