Deep Learning Based 3D Point Cloud Regression for Estimating Forest
Biomass
- URL: http://arxiv.org/abs/2112.11335v2
- Date: Wed, 22 Dec 2021 09:35:55 GMT
- Title: Deep Learning Based 3D Point Cloud Regression for Estimating Forest
Biomass
- Authors: Stefan Oehmcke, Lei Li, Jaime Revenga, Thomas Nord-Larsen, Katerina
Trepekli, Fabian Gieseke, Christian Igel
- Abstract summary: Knowledge of forest biomass stocks and their development is important for implementing effective climate change mitigation measures.
Remote sensing using airborne LiDAR can be used to measure vegetation biomass at large scale.
We present deep learning systems for predicting wood volume, above-ground biomass (AGB), and subsequently carbon directly from 3D LiDAR point cloud data.
- Score: 15.956463815168034
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Knowledge of forest biomass stocks and their development is important for
implementing effective climate change mitigation measures. It is needed for
studying the processes driving af-, re-, and deforestation and is a
prerequisite for carbon-accounting. Remote sensing using airborne LiDAR can be
used to measure vegetation biomass at large scale. We present deep learning
systems for predicting wood volume, above-ground biomass (AGB), and
subsequently carbon directly from 3D LiDAR point cloud data. We devise
different neural network architectures for point cloud regression and evaluate
them on remote sensing data of areas for which AGB estimates have been obtained
from field measurements in a national forest inventory. Our adaptation of
Minkowski convolutional neural networks for regression gave the best results.
The deep neural networks produced significantly more accurate wood volume, AGB,
and carbon estimates compared to state-of-the-art approaches operating on basic
statistics of the point clouds, and we expect this finding to have a strong
impact on LiDAR-based analyses of terrestrial ecosystem dynamics.
Related papers
- Fine-tuning of Geospatial Foundation Models for Aboveground Biomass Estimation [2.3429628556845405]
Fine-tuning of a geospatial foundation model to estimate above-ground biomass has comparable performance to a U-Net trained from scratch.
We also explore the transfer-learning capabilities of the models by fine-tuning on satellite imagery with sparse labels from different eco-regions in Brazil.
arXiv Detail & Related papers (2024-06-28T12:54:10Z) - A Survey of Label-Efficient Deep Learning for 3D Point Clouds [109.07889215814589]
This paper presents the first comprehensive survey of label-efficient learning of point clouds.
We propose a taxonomy that organizes label-efficient learning methods based on the data prerequisites provided by different types of labels.
For each approach, we outline the problem setup and provide an extensive literature review that showcases relevant progress and challenges.
arXiv Detail & Related papers (2023-05-31T12:54:51Z) - Vision Transformers, a new approach for high-resolution and large-scale
mapping of canopy heights [50.52704854147297]
We present a new vision transformer (ViT) model optimized with a classification (discrete) and a continuous loss function.
This model achieves better accuracy than previously used convolutional based approaches (ConvNets) optimized with only a continuous loss function.
arXiv Detail & Related papers (2023-04-22T22:39:03Z) - Mapping historical forest biomass for stock-change assessments at parcel
to landscape scales [0.0]
Map products can help identify where, when, and how forest carbon stocks are changing as a result of both anthropogenic and natural drivers alike.
These products can thus serve as inputs to a wide range of applications including stock-change assessments, monitoring reporting, and verification frameworks.
arXiv Detail & Related papers (2023-04-05T17:55:00Z) - Classification of Single Tree Decay Stages from Combined Airborne LiDAR
Data and CIR Imagery [1.4589991363650008]
This study, for the first time, automatically categorizing individual trees (Norway spruce) into five decay stages.
Three different Machine Learning methods - 3D point cloud-based deep learning (KPConv), Convolutional Neural Network (CNN), and Random Forest (RF)
All models achieved promising results, reaching overall accuracy (OA) of up to 88.8%, 88.4% and 85.9% for KPConv, CNN and RF, respectively.
arXiv Detail & Related papers (2023-01-04T22:20:16Z) - Hyperspectral and LiDAR data for the prediction via machine learning of
tree species, volume and biomass: a possible contribution for updating forest
management plans [0.3848364262836075]
This work intends to lay the foundations for identifying the prevailing forest types and the delineation of forest units in the Autonomous Province of Trento (PAT)
Data from LiDAR and hyperspectral surveys of 2014 made available by PAT were acquired and processed.
arXiv Detail & Related papers (2022-09-30T06:06:25Z) - Neuroevolution-based Classifiers for Deforestation Detection in Tropical
Forests [62.997667081978825]
Millions of hectares of tropical forests are lost every year due to deforestation or degradation.
Monitoring and deforestation detection programs are in use, in addition to public policies for the prevention and punishment of criminals.
This paper proposes the use of pattern classifiers based on neuroevolution technique (NEAT) in tropical forest deforestation detection tasks.
arXiv Detail & Related papers (2022-08-23T16:04:12Z) - Measuring the Carbon Intensity of AI in Cloud Instances [91.28501520271972]
We provide a framework for measuring software carbon intensity, and propose to measure operational carbon emissions.
We evaluate a suite of approaches for reducing emissions on the Microsoft Azure cloud compute platform.
arXiv Detail & Related papers (2022-06-10T17:04:04Z) - Information fusion approach for biomass estimation in a plateau
mountainous forest using a synergistic system comprising UAS-based digital
camera and LiDAR [9.944631732226657]
The objective of this study was to quantify the aboveground biomass (AGB) of a plateau mountainous forest reserve.
We utilized digital aerial photogrammetry (DAP), which has the unique advantages of speed, high spatial resolution, and low cost.
Based on the CHM and spectral attributes obtained from multispectral images, we estimated and mapped the AGB of the region of interest with considerable cost efficiency.
arXiv Detail & Related papers (2022-04-14T04:04:59Z) - Deep Learning Based Cloud Cover Parameterization for ICON [55.49957005291674]
We train NN based cloud cover parameterizations with coarse-grained data based on realistic regional and global ICON simulations.
Globally trained NNs can reproduce sub-grid scale cloud cover of the regional simulation.
We identify an overemphasis on specific humidity and cloud ice as the reason why our column-based NN cannot perfectly generalize from the global to the regional coarse-grained data.
arXiv Detail & Related papers (2021-12-21T16:10:45Z) - Country-wide Retrieval of Forest Structure From Optical and SAR
Satellite Imagery With Bayesian Deep Learning [74.94436509364554]
We propose a Bayesian deep learning approach to densely estimate forest structure variables at country-scale with 10-meter resolution.
Our method jointly transforms Sentinel-2 optical images and Sentinel-1 synthetic aperture radar images into maps of five different forest structure variables.
We train and test our model on reference data from 41 airborne laser scanning missions across Norway.
arXiv Detail & Related papers (2021-11-25T16:21:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.