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

Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

207
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
207

You might also read

Related Articles

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

Sort by
Same author

Tissue-specific oxidative stress and protective interventions in malathion-induced toxicity in rodent models: A comprehensive review.

Ecotoxicology and environmental safety·2026
Same author

RBFNN-Based PPy/GaN sensor array with wide dynamic range and sub-ppb detection for accurate ammonia identification in human exhaled breath.

Microsystems & nanoengineering·2025
Same author

Systematic Review and Meta-Analysis on Heavy Metals and Trace Elements in Mild Cognitive Impairment.

Biological trace element research·2025
Same author

Real-World Comparative Study of Ultra-Low-Dose Rivaroxaban in Very Elderly Patients with Atrial Fibrillation.

Clinical interventions in aging·2025
Same author

A Hierarchical PSMC-LQR Control Framework for Accurate Quadrotor Trajectory Tracking.

Sensors (Basel, Switzerland)·2025
Same author

Oxygen-Regulated GaN-Based Sensors Fabricated by MOCVD for Switchable Gas Detection: Exhaled Gas Smart Platform for Non-Invasive Disease Detection.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025

Related Experiment Video

Updated: Sep 13, 2025

In Vitro Scratch Assay to Demonstrate Effects of Arsenic on Skin Cell Migration
09:24

In Vitro Scratch Assay to Demonstrate Effects of Arsenic on Skin Cell Migration

Published on: February 23, 2019

23.3K

Predicting arsenic bioaccessibility: A global data-driven machine learning approach and its implication for reducing

Haonan Zhang1, Dan Han1, Maosheng Zhong1

  • 1National Engineering Research Centre of Urban Environmental Pollution Control, Beijing Key Laboratory for Risk Modeling and Remediation of Contaminated Sites, Beijing Municipal Research Institute of Eco-Environmental Protection, Beijing 100037, China.

Journal of Hazardous Materials
|July 29, 2025
PubMed
Summary

Machine learning models accurately predict arsenic bioaccessibility in soils, improving health risk assessments. This approach supports sustainable remediation, reducing soil cleanup volume and emissions.

Keywords:
BioaccessibilityCarbon reductionGlobalMachine learningProbabilistic

More Related Videos

Determination of Inorganic Arsenic in a Wide Range of Food Matrices using Hydride Generation - Atomic Absorption Spectrometry.
08:21

Determination of Inorganic Arsenic in a Wide Range of Food Matrices using Hydride Generation - Atomic Absorption Spectrometry.

Published on: September 1, 2017

15.3K
A Method to Preserve Wetland Roots and Rhizospheres for Elemental Imaging
06:29

A Method to Preserve Wetland Roots and Rhizospheres for Elemental Imaging

Published on: February 15, 2021

3.5K

Related Experiment Videos

Last Updated: Sep 13, 2025

In Vitro Scratch Assay to Demonstrate Effects of Arsenic on Skin Cell Migration
09:24

In Vitro Scratch Assay to Demonstrate Effects of Arsenic on Skin Cell Migration

Published on: February 23, 2019

23.3K
Determination of Inorganic Arsenic in a Wide Range of Food Matrices using Hydride Generation - Atomic Absorption Spectrometry.
08:21

Determination of Inorganic Arsenic in a Wide Range of Food Matrices using Hydride Generation - Atomic Absorption Spectrometry.

Published on: September 1, 2017

15.3K
A Method to Preserve Wetland Roots and Rhizospheres for Elemental Imaging
06:29

A Method to Preserve Wetland Roots and Rhizospheres for Elemental Imaging

Published on: February 15, 2021

3.5K

Area of Science:

  • Environmental Science
  • Geochemistry
  • Toxicology

Background:

  • Arsenic (As) bioaccessibility data are crucial for accurate health risk assessments but direct measurements are costly and time-consuming.
  • Existing predictive models often lack generalizability due to reliance on limited or artificially prepared samples.
  • Current remediation targets based on mean values can be impractically low compared to natural background levels.

Purpose of the Study:

  • To develop and validate a robust machine learning model for predicting arsenic bioaccessibility in field-aged soils.
  • To assess the performance of various machine learning algorithms using a comprehensive global dataset.
  • To evaluate the impact of an ML-informed approach on site remediation strategies and environmental outcomes.

Main Methods:

  • Compiled a global dataset of 1458 arsenic bioaccessibility records in field-aged soils.
  • Evaluated eight machine learning models, including Random Forest (RF).
  • Analyzed the influence of total arsenic (As-T) and soil properties (Fe, Mn, organic carbon, pH) on bioaccessibility.

Main Results:

  • The Random Forest model demonstrated superior performance (R² = 0.86, RMSE = 0.58).
  • Total arsenic explained 73.2% of the variance in gastric bioaccessibility.
  • Significant relationships were found between arsenic bioaccessibility and soil properties like Fe, Mn, organic carbon, and pH.

Conclusions:

  • Machine learning, particularly the RF model, significantly enhances the accuracy of arsenic bioaccessibility prediction.
  • An ML-informed probabilistic risk assessment led to more practical remediation targets and substantial reductions in remediation volume and carbon emissions.
  • This study demonstrates the potential of ML for more accurate environmental risk assessment and sustainable site remediation.