Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

The Tree of Life - Bacteria, Archaea, Eukaryotes02:40

The Tree of Life - Bacteria, Archaea, Eukaryotes

38.3K
The “tree of life” describes the evolution of life and the evolutionary relationships between organisms. The root of the tree is the common ancestor to all life on Earth. All other species radiate from this point, much like the branches of a tree. The numerous tips of these branches on the tree of life represent every living, or extant, species. Extinct species, which are species that no longer exist, can be found towards the center of the tree. Currently, these organisms, both...
38.3K
ortho–para-Directing Activators: –CH3, –OH, –⁠NH2, –OCH301:11

ortho–para-Directing Activators: –CH3, –OH, –⁠NH2, –OCH3

7.4K
All ortho–para directors, excluding halogens, are activating groups. These groups donate electrons to the ring, making the ring carbons electron-rich. Consequently, the reactivity of the aromatic ring towards electrophilic substitution increases. For instance, the nitration of anisole is about 10,000 times faster than the nitration of benzene. The electron-donating effect of the methoxy group in anisole activates the ortho and para positions on the ring and stabilizes the corresponding...
7.4K
Nuclear Fusion02:45

Nuclear Fusion

33.8K
The process of converting very light nuclei into heavier nuclei is also accompanied by the conversion of mass into large amounts of energy, a process called fusion. The principal source of energy in the sun is a net fusion reaction in which four hydrogen nuclei fuse and ultimately produce one helium nucleus and two positrons.
A helium nucleus has a mass that is 0.7% less than that of four hydrogen nuclei; this lost mass is converted into energy during the fusion. This reaction produces about...
33.8K
What is a Species?01:17

What is a Species?

49.7K
Overview
49.7K
Keystone Species01:39

Keystone Species

24.6K
Measures of species biodiversity, such as richness (i.e., the number of species present) and evenness (i.e., their relative abundance), describe an ecological community’s structure. Many factors affect community structure, including abiotic factors (e.g., sunlight and nutrients), disturbances (e.g., fire or flood), species interactions (e.g., predation or competition), and chance events (e.g., foreign species invasion). Certain species—such as keystone species—also play a...
24.6K
Survival Tree01:19

Survival Tree

418
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
418

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Predicting wheat yield and grain quality with UAV multispectral imagery and deep learning.

Frontiers in plant science·2026
Same author

Wheat spike and spikelet detection and counting from high-resolution digital imagery using YOLO with Oriented Bounding Boxes.

Scientific reports·2026
Same author

Revisiting Underwater Image Enhancement for Object Detection: A Unified Quality-Detection Evaluation Framework.

Journal of imaging·2026
Same author

Seed Protein Content Estimation with Bench-Top Hyperspectral Imaging and Attentive Convolutional Neural Network Models.

Sensors (Basel, Switzerland)·2025
Same author

Fusion of Visible and Infrared Aerial Images from Uncalibrated Sensors Using Wavelet Decomposition and Deep Learning.

Sensors (Basel, Switzerland)·2025
Same author

Enhancing the potential of phenomic and genomic prediction in winter wheat breeding using high-throughput phenotyping and deep learning.

Frontiers in plant science·2024

Related Experiment Video

Updated: Jan 27, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.5K

Urban Tree Species Classification Using a WorldView-2/3 and LiDAR Data Fusion Approach and Deep Learning.

Sean Hartling1, Vasit Sagan2, Paheding Sidike3

  • 1Department of Earth and Atmospheric Sciences, Saint Louis University, St. Louis, MO 63108, USA. sean.hartling@slu.edu.

Sensors (Basel, Switzerland)
|March 17, 2019
PubMed
Summary

This study shows Dense Convolutional Network (DenseNet) accurately maps urban tree species using fused satellite and LiDAR data. DenseNet outperforms Random Forest and Support Vector Machine, even with limited training samples.

Keywords:
convolutional neural network (CNN)data fusiondeep learningdense convolutional network (DenseNet)random forest (RF)support vector machine (SVM)tree species classification

More Related Videos

Generation of Fluorescent Protein Fusions in Candida Species
09:27

Generation of Fluorescent Protein Fusions in Candida Species

Published on: March 4, 2017

11.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.5K

Related Experiment Videos

Last Updated: Jan 27, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.5K
Generation of Fluorescent Protein Fusions in Candida Species
09:27

Generation of Fluorescent Protein Fusions in Candida Species

Published on: March 4, 2017

11.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.5K

Area of Science:

  • Remote Sensing
  • Urban Ecology
  • Computer Vision

Background:

  • Urban areas present complex challenges for accurate tree species classification due to heterogeneous land cover.
  • High-resolution satellite imagery and LiDAR data, coupled with deep learning, offer new possibilities for detailed urban tree mapping.
  • Knowledge gaps exist regarding the specific contributions of WorldView-3 SWIR bands, PAN band, and LiDAR data, and deep learning's reliance on training data.

Purpose of the Study:

  • To evaluate the efficacy of a Dense Convolutional Network (DenseNet) for identifying dominant individual tree species in complex urban environments.
  • To assess the impact of fusing WorldView-2 VNIR, WorldView-3 SWIR, and LiDAR datasets on classification accuracy.
  • To compare DenseNet's performance against Random Forest (RF) and Support Vector Machine (SVM) classifiers, particularly under limited training data scenarios.

Main Methods:

  • Utilized a data fusion approach combining WorldView-2 VNIR, WorldView-3 SWIR, and LiDAR datasets.
  • Implemented a Dense Convolutional Network (DenseNet) for object detection and scene classification of individual tree species.
  • Compared DenseNet's classification accuracy against Random Forest (RF) and Support Vector Machine (SVM) using varying quantities of training samples.

Main Results:

  • Data fusion, incorporating SWIR, LiDAR, and PAN bands sequentially, improved DenseNet's overall accuracy from 75.9% to 82.6%.
  • DenseNet achieved a significantly higher overall accuracy (82.6%) compared to SVM (51.8%) and RF (52%) for classifying eight dominant tree species.
  • DenseNet demonstrated superior performance over RF and SVM classifiers even when training sample quantities were restricted.

Conclusions:

  • Dense Convolutional Network (DenseNet) is highly effective for urban tree species classification in complex environments.
  • Data fusion of multispectral, SWIR, LiDAR, and PAN data enhances the performance of deep learning models for tree species identification.
  • DenseNet offers a robust solution for urban tree mapping, overcoming limitations of traditional classifiers and small training datasets.