Sentinel-1 and Sentinel-2 data for predicting forest stand variables in GEE: A case study of timber plantations in northern Spain

Aim of study: In this study we developed machine learning models for estimating five forest stand variables, including total over bark volume, number of trees per hectare, dominant height, basal area and aboveground biomass, from remote sensing data and ancillary variables in forest plantations of Eucalyptus globulus Labill, Pinus pinaster Aiton and Pinus radiata D. Don. Area of study: The study was conducted in northern Spain (Autonomous Communities of Asturias, Cantabria, Basque Country and Galicia) where plantations of the species of interest are mainly concentrated due to the high productivity of forest stands in these areas. Material and methods: We used ground-truth data from Spanish National Forest Inventory plots, two sources of remote sensing data and images from the Sentinel-1 constellation (radar) and from the Sentinel-2 constellation (optical) combined with terrain and climate data. We used the Google Earth Engine platform using Random Forest algorithm with 10-fold cross-validation to obtain forest stand variables, including density, size and yield variables. Main results: Evaluation of the model accuracy and variable importance in estimating forest variables showed that the total volume models performed best, yielding R² values between 0.39 and 0.45 for the different tree species. Optical bands were very important in all cases, while radar bands were less important. Research highlights: The use of synthetic aperture radar, although promising, is limited in platforms like GEE, especially for complex terrains where shadowing and angles affect the image quality. The research contributions include the automation of preprocessing steps, and the findings highlight the need to develop more robust, adaptable models using AI and new radar sensors.

• Publication year

  2025

• Venue

  Forest Systems

• Publication date

  2025-11-27

• Fields of study

  Not labeled

• Identifiers
  DOI 10.5424/fs/2025343-20986
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Estimating Forest Variables for Major Commercial Timber Plantations in Northern Spain Using Sentinel-2 and Ancillary Data

  2024influential reference
• Evaluation of Correction Algorithms for Sentinel-2 Images Implemented in Google Earth Engine for Use in Land Cover Classification in Northern Spain

  2024influential reference
• Biomass Change Estimated by TanDEM-X Interferometry and GEDI in a Tanzanian Forest

  2024cited by this paper
• A Review of Forest Height Inversion by PolInSAR: Theory, Advances, and Perspectives

  2023cited by this paper
• Synergistic use of Sentinel-1, Sentinel-2, and Landsat 8 in predicting forest variables

  2023cited by this paper
• Mapping tropical forest aboveground biomass using airborne SAR tomography

  2023cited by this paper
• Mapping forest site quality at national level

  2022influential reference
• Forest Applications

  2021cited by this paper
• Sentinel-1 SAR Backscatter Analysis Ready Data Preparation in Google Earth Engine

  2021cited by this paper
• Volume 34

  2020cited by this paper
• SAR-enhanced mapping of live fuel moisture content

  2020cited by this paper
• Volume 34 Issue (3)

  2020cited by this paper
• Comparison of Sentinel-2 and Landsat 8 imagery for forest variable prediction in boreal region

  2019cited by this paper
• Integration of National Forest Inventory and Nationwide Airborne Laser Scanning Data to Improve Forest Yield Predictions in North-Western Spain

  2019cited by this paper
• Spatial prediction of basal area and volume in Eucalyptus stands using Landsat TM data: an assessment of prediction methods

  2018cited by this paper
• Significance of dual polarimetric synthetic aperture radar in biomass retrieval: An attempt on Sentinel-1

  2018cited by this paper
• Large Scale Mapping of Forests and Land Cover with Synthetic Aperture Radar Data

  2014cited by this paper
• Using RADARSAT-2 polarimetric and ENVISAT-ASAR dual-polarization data for estimating soil moisture over agricultural fields

  2012cited by this paper
• Soil Moisture Limitations on Monitoring Boreal Forest Regrowth Using Spaceborne L-Band SAR Data

  2011cited by this paper
• Research for Information Extraction Based on Wrapper Model Algorithm

  2010influential reference
• The potential and challenge of remote sensing‐based biomass estimation

  2006cited by this paper
• Atlas climático digital de la Península Ibérica: metodología y aplicaciones en bioclimatología y geobotánica

  2005cited by this paper
• Modern Regression Methods

  1996influential reference
• Relating forest biomass to SAR data

  1992cited by this paper

• No citing papers are available for this paper.