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

You might also read

Related Articles

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

Sort by
Same author

Design, synthesis, and activity study of heterocyclic derivatives as JAK inhibitors.

Medicinal chemistry research : an international journal for rapid communications on design and mechanisms of action of biologically active agents·2026
Same author

The Airway Epithelial Barrier in Childhood Asthma: A Central Player in Glucocorticoid Therapy, Resistance, and Severe Asthma.

Pediatric discovery·2026
Same author

Effects of microbial fertilizers on photosynthetic characteristics and enzyme activities of oil sunflower under combined saline-alkali stress.

Scientific reports·2026
Same author

Identification of genes differentially expressed in granulosa cells from women with high vs. low ovarian responsiveness.

Frontiers in reproductive health·2026
Same author

Macrophage-Specific SPP1 Contributes to Pressure Overload-Induced Cardiac Dysfunction and Maladaptive Remodeling.

JACC. Basic to translational science·2026
Same author

A novel metal-free sling approach for benign prostatic hyperplasia: early results of the Progator procedure with high ejaculatory preservation.

Translational andrology and urology·2026

Related Experiment Video

Updated: Nov 2, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.8K

Deep learning based regression for optically inactive inland water quality parameter estimation using airborne

Chao Niu1, Kun Tan2, Xiuping Jia3

  • 1Key Laboratory of Geographic Information Science (Ministry of Education), East China Normal University, Shanghai, 200241, China.

Environmental Pollution (Barking, Essex : 1987)
|June 13, 2021
PubMed
Summary

Deep learning models accurately estimate optically inactive water quality parameters using airborne hyperspectral data. The patch-based deep neural network regression (patch_DNNR) model shows superior prediction accuracy for inland water monitoring.

Keywords:
Airborne hyperspectral imageryDeep learning based regressionOptically inactive water quality parameters

More Related Videos

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.1K
RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

16.5K

Related Experiment Videos

Last Updated: Nov 2, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.8K
Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy
07:13

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

4.1K
RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
11:37

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

16.5K

Area of Science:

  • Environmental Science
  • Remote Sensing
  • Data Science

Background:

  • Airborne hyperspectral remote sensing offers high spatial and spectral resolution for inland water quality monitoring.
  • Estimating optically inactive water quality parameters (e.g., CODmn, TN, TP) is challenging with traditional models, especially in polluted waters.
  • Existing models struggle with accuracy for parameters like permanganate index (CODmn), total nitrogen (TN), and total phosphorus (TP).

Purpose of the Study:

  • To develop and evaluate deep learning models for estimating optically inactive inland water quality parameters.
  • To compare the performance of pixel-based and patch-based deep neural network regression models against traditional methods.
  • To generate thematic maps for water quality assessment and pollution source analysis.

Main Methods:

  • Collected 60 water samples from the Guanhe River for simultaneous airborne data acquisition.
  • Developed and applied two deep learning models: pixel-based deep neural network regression (pixel_DNNR) and patch-based deep neural network regression (patch_DNNR).
  • Compared deep learning models with Partial Least Squares Regression (PLSR) and Support Vector Regression (SVR).

Main Results:

  • Deep learning models, particularly patch_DNNR, significantly outperformed PLSR and SVR in accuracy.
  • The patch_DNNR model achieved prediction accuracy (Rp² > 0.6, RPD > 1.6) for all tested optically inactive parameters.
  • Thematic maps visualized water quality and identified pollution sources, demonstrating the models' practical application.

Conclusions:

  • Deep learning models excel at feature extraction and understanding high-dimensional hyperspectral data.
  • The patch_DNNR model provides a novel and accurate approach for estimating optically inactive inland water quality parameters.
  • This research offers a new pathway for effective inland water quality monitoring, especially in challenging environments.