Deep Learning Models in Forest Mapping Using Multitemporal SAR and Optical Satellite Data

Shaojia Ge, Hong Gu, Weimin Su, Jaan Praks, Anne Lonnqvist, Oleg Antropov

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

In this study, we evaluate the potential of deep learning models in predicting forest tree height in boreal forest zone using ESA Sentinel-1 and Sentinel-2 images. The performance of studied deep learning models is compared to several popular conventional machine learning approaches. The study area is located near Hyytiala forestry station in Finland, and represents a conifer-dominated mixed boreal forestland. Improved predictions were obtained when using combined optical and SAR data for all studied models. Our results indicate that UNet based models can achieve better accuracy in predicting forest tree heights (RMSE of 1.90m, mathrm{R}{2} of 0.69), compared to traditional parametric and machine learning models with RMSE range of 2.27-2.41m and mathrm{R}{2} range of 0.50-0.56 when satellite optical and radar data are combined.

Original languageEnglish
Title of host publicationIGARSS 2022
Subtitle of host publication2022 IEEE International Geoscience and Remote Sensing Symposium
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages5688-5691
ISBN (Electronic)978-1-6654-2792-0, 978-1-6654-2791-3
ISBN (Print)978-1-6654-2793-7
DOIs
Publication statusPublished - 28 Sept 2022
MoE publication typeA4 Article in a conference publication
Event2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022 - Kuala Lumpur, Malaysia
Duration: 17 Jul 202222 Jul 2022

Publication series

SeriesIEEE International Geoscience and Remote Sensing Symposium Proceedings
Volume2022-July
ISSN2153-6996

Conference

Conference2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022
Country/TerritoryMalaysia
CityKuala Lumpur
Period17/07/2222/07/22

Keywords

  • boreal
  • deep learning
  • forest height
  • forest management
  • Sentinel-1
  • Sentinel-2
  • synthetic aperture radar

Fingerprint

Dive into the research topics of 'Deep Learning Models in Forest Mapping Using Multitemporal SAR and Optical Satellite Data'. Together they form a unique fingerprint.

Cite this