For Researchers
For Students
For Professionals
Outreach & Events
About the Lab

Menu

For Researchers
For Students
For Professionals
Outreach & Events
About the Lab

Search

Close

Synthesizing Disparate LiDAR and Satellite Datasets through Deep Learning to Generate Wall-to-Wall Forest Inventories of New England

Sponsor: Maine Agricultural and Forest Experiment Station

Daniel Hayes and Elias Ayrey - University of Maine

Project Title

Project Participants

Project Duration

Project Sponsor

Project Contact Name

Project Contact Email

Project Description

<p class="p1">For two decades Light Detection and Ranging (LiDAR) data has been used to develop spatially-explicit forest inventories. Data derived from LiDAR depict three-dimensional forest canopy structure and are useful for predicting forest attributes such as biomass, stem density, and species. Such enhanced forest inventories (EFIs) are useful for carbon accounting, forest management, and wildlife habitat characterization by allowing practitioners to target specific areas without extensive field work.</p>
<p class="p1">Here in New England, LiDAR data covers nearly the entire geographical extent of the region. However, until now the region’s forest attributes have not been mapped. Developing regional inventories has traditionally been problematic because most regions – including New England – are comprised of a patchwork of datasets acquired with various specifications. These variations in specifications prohibit developing a single set of predictive models for a region. The purpose of this work is to develop a new set of modeling techniques, allowing for EFIs consisting of disparate LiDAR datasets.</p>
<p class="p1">Artificial Intelligence (AI) algorithms were developed to interpret LiDAR data and make forest predictions. After settling on the optimal algorithm, we incorporated satellite spectral, disturbance, and climate data. Our results indicated that this approach dramatically outperformed traditional modeling techniques. We then applied the AI model to the region’s LiDAR, developing 10 m resolution wall-to-wall forest inventory maps of fourteen forest attributes. We assessed error using U.S. federal inventory data and determined that our EFIs did not differ significantly in 33, 25, and 30/38 counties when predicting biomass, percent conifer, and stem density.</p>

Project Type - select all applicable

Applied Research Project
Faculty Research Project
Industry Outreach Project
Public Service Project
Student Project

Project Applications - select all applicable

Arctic Ecosystems and Permafrost Landscapes
Carbon Cycle
Climate Change
Conservation
Forestry
Project-Based Learning
Remote Sensing Applications
Terrestrial Biosphere Modeling
Terrestrial Ecosystem
Tourism

Project Technologies - select all applicable

GIS
Hyperspectral
Lidar
Machine Learning
Multispectral
Piloted Aircraft
Remote Sensing
Statistical Modeling
UAV

Featured Image

http://wheatlandlab.org/wp-content/uploads/2020/05/AGB_Elias.png

Additional Project Images

Project Video URL - if any

Project URL - if any

Applications:

Climate Change, Conservation, Forestry, Remote Sensing Applications, Terrestrial Ecosystem

Technologies:

GIS, Lidar, Machine Learning, Multispectral, Remote Sensing, Statistical Modeling

Contact:

Daniel Hayes

daniel.j.hayes@maine.edu

uploads

Recent News

UMaine & NASA to map carbon in forests!

Planes, UAVs, and AI to count seabirds in coastal Maine

New lidR book now available online!

WPI Institute on Project-Based Learning – Summer 2020

Upcoming Events

Getting Started with QGIS

Spectroscopy of plants – What light spectra can tell us about functional, taxonomic, and phylogenetic plant biodiversity

Leveraging High Resolution Forest Inventory and Satellites to Predict Fire Damage Severity at the Micro-Stand Level

Moving Beyond Enhanced Forest Inventory (EFI): Accelerating the Digitalization of the Forest Value-Chain

Current Projects

Forest Disturbance Detection and Aboveground Biomass Modeling Using Moderate-Resolution, Time-Series Satellite Imagery

Synthesizing Disparate LiDAR and Satellite Datasets through Deep Learning to Generate Wall-to-Wall Forest Inventories of New England

Airborne Hyperspectral Data Application in Health Stress Detection of Blueberry Fields and Ash Trees

The Effects of Climate Change on Forest Ecosystem Phenology and its Impacts on Tourism in Maine

About

The Lab
Our People
Calendar
Contact us

Follow Us

Twitter Youtube Instagram

Supporting the geospatial education, research, outreach, and innovation needs of students, forest industry, and natural resource partners in Maine since 2013

Copyright 2021 All Rights Reserved

Insert/edit link

Enter the destination URL

URL

Link Text

Open link in a new tab

Or link to existing content

Search

No search term specified. Showing recent items. Search or use up and down arrow keys to select an item.