A Novel Large Vision Foundation Model (LVFM)-based Approach for Generating High-Resolution Canopy Height Maps in Plantations for Precision Forestry Management

Accurate, cost-effective monitoring of plantation aboveground biomass (AGB) is crucial for supporting local livelihoods and carbon sequestration initiatives like the China Certified Emission Reduction (CCER) program. High-resolution canopy height maps (CHMs) are essential for this, but standard lidar-based methods are expensive. While deep learning with RGB imagery offers an alternative, accurately extracting canopy height features remains challenging. To address this, we developed a novel model for high-resolution CHM generation using a Large Vision Foundation Model (LVFM). Our model integrates a feature extractor, a self-supervised feature enhancement module to preserve spatial details, and a height estimator. Tested in Beijing's Fangshan District using 1-meter Google Earth imagery, our model outperformed existing methods, including conventional CNNs. It achieved a mean absolute error of 0.09 m, a root mean square error of 0.24 m, and a correlation of 0.78 against lidar-based CHMs. The resulting CHMs enabled over 90% success in individual tree detection, high accuracy in AGB estimation, and effective tracking of plantation growth, demonstrating strong generalization to non-training areas. This approach presents a promising, scalable tool for evaluating carbon sequestration in both plantations and natural forests.

• Publication year

  2025

• Venue

  Unknown venue

• Publication date

  2025-06-25

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  arXiv 2506.20388
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• National tree species mapping using Sentinel-1/2 time series and German National Forest Inventory data

  2024cited by this paper
• Contrasting local and global modeling with machine learning and satellite data: A case study estimating tree canopy height in African savannas

  2024cited by this paper
• Combining Multisource Data and Machine Learning Approaches for Multiscale Estimation of Forest Biomass

  2023cited by this paper
• Global increase in biomass carbon stock dominated by growth of northern young forests over past decade

  2023cited by this paper
• Sub-Meter Tree Height Mapping of California using Aerial Images and LiDAR-Informed U-Net Model

  2023cited by this paper
• Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights

  2023cited by this paper
• DINOv2: Learning Robust Visual Features without Supervision

  2023cited by this paper
• Comparison between three convolutional neural networks for local climate zone classification using Google Earth Images: A case study of the Fujian Delta in China

  2023cited by this paper
• Deep learning enables image-based tree counting, crown segmentation, and height prediction at national scale

  2023cited by this paper
• Monitoring of Monthly Height Growth of Individual Trees in a Subtropical Mixed Plantation Using UAV Data

  2023cited by this paper
• From source to sink – recovery of the carbon balance in young forests

  2023cited by this paper
• Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review

  2023cited by this paper
• Continuous ground monitoring of vegetation optical depth and water content with GPS signals

  2023cited by this paper
• Forestation at the right time with the right species can generate persistent carbon benefits in China

  2023cited by this paper
• TreeFormer: A Semi-Supervised Transformer-Based Framework for Tree Counting From a Single High-Resolution Image

  2023cited by this paper
• SCViT: A Spatial-Channel Feature Preserving Vision Transformer for Remote Sensing Image Scene Classification

  2022cited by this paper
• Forest emissions reduction assessment using airborne LiDAR for biomass estimation

  2022influential reference
• Review of recent progress of emission trading policy in China

  2022cited by this paper
• The first global soil moisture and vegetation optical depth product retrieved from fused SMOS and SMAP L-band observations

  2022cited by this paper
• Limited climate change mitigation potential through forestation of the vast dryland regions

  2022cited by this paper
• MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer

  2022cited by this paper
• GEDI launches a new era of biomass inference from space

  2022cited by this paper
• Depthformer: Multiscale Vision Transformer for Monocular Depth Estimation with Global Local Information Fusion

  2022cited by this paper
• A high-resolution canopy height model of the Earth

  2022cited by this paper
• Automated tree-crown and height detection in a young forest plantation using mask region-based convolutional neural network (Mask R-CNN)

  2021cited by this paper
• Learning Transferable Visual Models From Natural Language Supervision

  2021cited by this paper
• Vision Transformers for Dense Prediction

  2021cited by this paper
• The three major axes of terrestrial ecosystem function

  2021cited by this paper
• Masked Autoencoders Are Scalable Vision Learners

  2021cited by this paper
• fastai: A Layered API for Deep Learning

  2020cited by this paper
• A Survey on Vision Transformer

  2020cited by this paper
• Mapping global forest canopy height through integration of GEDI and Landsat data

  2020influential reference
• lidR: An R package for analysis of Airborne Laser Scanning (ALS) data

  2020cited by this paper
• An unexpectedly large count of trees in the West African Sahara and Sahel

  2020cited by this paper
• It Is Likely That Your Loss Should be a Likelihood

  2020cited by this paper
• Tracking tree growth through satellite soil moisture monitoring: A case study of Pinus halepensis in Spain

  2019cited by this paper
• CARAFE: Content-Aware ReAssembly of FEatures

  2019cited by this paper
• Satellite-observed pantropical carbon dynamics

  2019cited by this paper
• Improvement of the Fmask algorithm for Sentinel-2 images: Separating clouds from bright surfaces based on parallax effects

  2018cited by this paper
• Testing and evaluating different LiDAR-derived canopy height model generation methods for tree height estimation

  2018cited by this paper
• Mapping gains and losses in woody vegetation across global tropical drylands

  2017cited by this paper
• Aboveground Biomass Estimation Using Structure from Motion Approach with Aerial Photographs in a Seasonal Tropical Forest

  2015cited by this paper
• Improving forest aboveground biomass estimation using seasonal Landsat NDVI time-series

  2015cited by this paper
• The national forest inventory in China: history - results - international context

  2015cited by this paper
• A Review of Remote Sensing of Forest Biomass and Biofuel: Options for Small-Area Applications

  2011cited by this paper
• Benchmark map of forest carbon stocks in tropical regions across three continents

  2011cited by this paper
• Assessing multi-temporal Landsat 7 ETM+ images for estimating above-ground biomass in subtropical dry forests of Argentina

  2010cited by this paper
• Plantation forests and biodiversity: oxymoron or opportunity?

  2008cited by this paper
• Mapping the height and above‐ground biomass of a mixed forest using lidar and stereo Ikonos images

  2008cited by this paper
• The potential and challenge of remote sensing‐based biomass estimation

  2006cited by this paper
• Engineering

  1929cited by this paper

• No citing papers are available for this paper.