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

Global and regional patterns of soil metal(loid) mobility and associated risks.

Nature communications·2025
Same author

Improved classification of soil As contamination at continental scale: Resolving class imbalances using machine learning approach.

Chemosphere·2024
Same author

The initial stages of cement hydration at the molecular level.

Nature communications·2024
Same author

Influence of CaO on Physical and Environmental Properties of Granulated Copper Slag: Melting Behavior, Grindability and Leaching Behavior.

International journal of environmental research and public health·2022
Same author

Concrete Strength Prediction Using Different Machine Learning Processes: Effect of Slag, Fly Ash and Superplasticizer.

Materials (Basel, Switzerland)·2022
Same author

Hydration and Mechanical Properties of Blended Cement with Copper Slag Pretreated by Thermochemical Modification.

Materials (Basel, Switzerland)·2022

Related Experiment Video

Updated: Jun 25, 2025

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

16.2K

A Deep Learning Approach for Chromium Detection and Characterization from Soil Hyperspectral Data.

Chundi Ma1, Xinhang Xu1, Min Zhou1

  • 1School of Resources and Safety Engineering, Central South University, Changsha 410083, China.

Toxics
|May 24, 2024
PubMed
Summary

A novel deep neural network (DNN) model accurately predicts soil chromium (Cr) levels using hyperspectral data. This efficient method offers a faster, more cost-effective alternative to traditional lab analyses for environmental monitoring.

Keywords:
chromiumdeep learningsensitive bandssoil hyperspectral

More Related Videos

Two-Dimensional Visualization and Quantification of Labile, Inorganic Plant Nutrients and Contaminants in Soil
12:03

Two-Dimensional Visualization and Quantification of Labile, Inorganic Plant Nutrients and Contaminants in Soil

Published on: September 1, 2020

6.1K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K

Related Experiment Videos

Last Updated: Jun 25, 2025

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

16.2K
Two-Dimensional Visualization and Quantification of Labile, Inorganic Plant Nutrients and Contaminants in Soil
12:03

Two-Dimensional Visualization and Quantification of Labile, Inorganic Plant Nutrients and Contaminants in Soil

Published on: September 1, 2020

6.1K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K

Area of Science:

  • Environmental Science
  • Soil Science
  • Data Science

Background:

  • High chromium (Cr) levels in soil present significant environmental and human health risks.
  • Traditional laboratory methods for Cr analysis are costly and time-consuming, necessitating efficient alternatives.

Purpose of the Study:

  • To develop a highly accurate and generalizable deep neural network (DNN) model for predicting soil Cr content using hyperspectral data.
  • To identify key hyperspectral bands and soil properties influencing Cr detection.

Main Methods:

  • Applied a deep neural network (DNN) approach to the Land Use and Cover Area frame Survey (LUCAS) dataset.
  • Optimized spectral preprocessing techniques and DNN hyperparameters for Cr detection.
  • Utilized permutation importance and local interpretable model-agnostic explanations (LIME) to identify sensitive hyperspectral bands.

Main Results:

  • The optimal DNN model achieved a strong predictive performance for soil Cr detection, with a correlation coefficient of 0.79 on the testing set.
  • Identified four critical hyperspectral bands (400-439, 1364-1422, 1862-1934, and 2158-2499 nm) highly sensitive to Cr.
  • Found soil iron oxide and clay mineral content to be significant factors influencing soil Cr levels.

Conclusions:

  • The study presents a feasible and rapid method for determining soil Cr content from hyperspectral data.
  • The developed DNN model demonstrates good generalizability and accuracy for Cr detection.
  • This approach holds potential for future large-scale soil Cr monitoring applications.