High-resolution landscape-scale biomass mapping using a spatiotemporal
patchwork of LiDAR coverages
- URL: http://arxiv.org/abs/2205.08530v1
- Date: Tue, 17 May 2022 17:53:50 GMT
- Title: High-resolution landscape-scale biomass mapping using a spatiotemporal
patchwork of LiDAR coverages
- Authors: Lucas K. Johnson (1), Michael J. Mahoney (1), Eddie Bevilacqua (1),
Stephen V. Stehman (1), Grant Domke (2), Colin M. Beier (1) ((1) State
University of New York College of Environmental Science and Forestry, (2)
USDA Forest Service)
- Abstract summary: Estimating forest aboveground biomass at fine scales has become increasingly important for greenhouse gas estimation.
Here we address common obstacles including selection of training data, the investigation of regional or coverage specific bias and error, and map patterns at multiple scales.
Our model was overall accurate (% RMSE 13-33%), had very low bias (MBE $leq$ $pm$5 Mg ha$-1$), explained most field-observed variation.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Estimating forest aboveground biomass at fine spatial scales has become
increasingly important for greenhouse gas estimation, monitoring, and
verification efforts to mitigate climate change. Airborne LiDAR continues to be
a valuable source of remote sensing data for estimating aboveground biomass.
However airborne LiDAR collections may take place at local or regional scales
covering irregular, non-contiguous footprints, resulting in a 'patchwork' of
different landscape segments at different points in time. Here we addressed
common obstacles including selection of training data, the investigation of
regional or coverage specific patterns in bias and error, and map agreement,
and model-based precision assessments at multiple scales.
Three machine learning algorithms and an ensemble model were trained using
field inventory data (FIA), airborne LiDAR, and topographic, climatic and
cadastral geodata. Using strict selection criteria, 801 FIA plots were selected
with co-located point clouds drawn from a patchwork of 17 leaf-off LiDAR
coverages 2014-2019). Our ensemble model created 30m AGB prediction surfaces
within a predictor-defined area of applicability (98% of LiDAR coverage) and
resulting AGB predictions were compared with FIA plot-level and areal estimates
at multiple scales of aggregation. Our model was overall accurate (% RMSE
13-33%), had very low bias (MBE $\leq$ $\pm$5 Mg ha$^{-1}$), explained most
field-observed variation (R$^2$ 0.74-0.93), produced estimates that were both
largely consistent with FIA's aggregate summaries (86% of estimates within 95%
CI), as well as precise when aggregated to arbitrary small-areas (mean
bootstrap standard error 0.37 Mg ha$^{-1}$). We share practical solutions to
challenges faced when using spatiotemporal patchworks of LiDAR to meet growing
needs for biomass prediction and mapping, and applications in carbon accounting
and ecosystem stewardship.
Related papers
- A Data-Driven Supervised Machine Learning Approach to Estimating Global
Ambient Air Pollution Concentrations With Associated Prediction Intervals [0.0]
We have developed a scalable, data-driven, supervised machine learning framework to impute missing temporal and spatial measurements.
This model is designed to impute missing temporal and spatial measurements, thereby generating a comprehensive dataset for pollutants including NO$, O$_3$, PM$_10$, PM$_2.5$, and SO$.
The model's performance across various geographical locations is examined, providing insights and recommendations for strategic placement of future monitoring stations.
arXiv Detail & Related papers (2024-02-15T11:09:22Z) - Observation-Guided Meteorological Field Downscaling at Station Scale: A
Benchmark and a New Method [66.80344502790231]
We extend meteorological downscaling to arbitrary scattered station scales and establish a new benchmark and dataset.
Inspired by data assimilation techniques, we integrate observational data into the downscaling process, providing multi-scale observational priors.
Our proposed method outperforms other specially designed baseline models on multiple surface variables.
arXiv Detail & Related papers (2024-01-22T14:02:56Z) - A Hybrid Deep Learning-based Approach for Optimal Genotype by
Environment Selection [8.084449311613517]
We used a dataset comprising 93,028 training records to forecast yields for 10,337 test records, covering 159 locations over 13 years (2003-2015)
This dataset included details on 5,838 distinct genotypes and daily weather data for a 214-day growing season, enabling comprehensive analysis.
We developed two novel convolutional neural network (CNN) architectures: the CNN-DNN model, combining CNN and fully-connected networks, and the CNN-LSTM-DNN model, with an added LSTM layer for weather variables.
arXiv Detail & Related papers (2023-09-22T17:31:47Z) - 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) - A Meta-Learning Approach to Predicting Performance and Data Requirements [163.4412093478316]
We propose an approach to estimate the number of samples required for a model to reach a target performance.
We find that the power law, the de facto principle to estimate model performance, leads to large error when using a small dataset.
We introduce a novel piecewise power law (PPL) that handles the two data differently.
arXiv Detail & Related papers (2023-03-02T21:48:22Z) - Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global
Weather Forecast [91.9372563527801]
We present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast.
For the first time, an AI-based method outperforms state-of-the-art numerical weather prediction (NWP) methods in terms of accuracy.
Pangu-Weather supports a wide range of downstream forecast scenarios, including extreme weather forecast and large-member ensemble forecast in real-time.
arXiv Detail & Related papers (2022-11-03T17:19:43Z) - Jalisco's multiclass land cover analysis and classification using a
novel lightweight convnet with real-world multispectral and relief data [51.715517570634994]
We present our novel lightweight (only 89k parameters) Convolution Neural Network (ConvNet) to make LC classification and analysis.
In this work, we combine three real-world open data sources to obtain 13 channels.
Our embedded analysis anticipates the limited performance in some classes and gives us the opportunity to group the most similar.
arXiv Detail & Related papers (2022-01-26T14:58:51Z) - Predicting Vegetation Stratum Occupancy from Airborne LiDAR Data with
Deep Learning [4.129847064263057]
We propose a new deep learning-based method for estimating the occupancy of vegetation from airborne 3D LiDAR point clouds.
Our model predictsized occupancy maps for three vegetation strata corresponding to lower, medium, and higher cover.
arXiv Detail & Related papers (2022-01-20T08:30:27Z) - 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) - EarthNet2021: A novel large-scale dataset and challenge for forecasting
localized climate impacts [12.795776149170978]
Large Earth observation datasets now enable us to create machine learning models capable of translating coarse weather information into high-resolution Earth surface forecasts.
We define high-resolution Earth surface forecasting as video prediction of satellite imagery conditional on mesoscale weather forecasts.
We introduce EarthNet 2021, a new curated dataset containing target-temporal Sentinel 2 satellite imagery at 20 m resolution, matched with high-resolution topography and mesoscale (1.28 km) weather variables.
arXiv Detail & Related papers (2020-12-11T11:21:00Z)
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.