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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

40
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
40

You might also read

Related Articles

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

Sort by
Same author

Lateral stability control of distributed drive electric vehicles via controllable-region analysis and adaptive torque distribution.

ISA transactions·2026
Same author

Sensitive detection of aflatoxin B1 using a dual-mode fluorescent aptasensor based on cascade signal amplification.

The Analyst·2026
Same author

Development and external validation of a parsimonious lactate-to-diastolic blood pressure ratio model for 28-day mortality risk stratification in septic shock: a retrospective two-cohort study.

Frontiers in medicine·2026
Same author

Diosgenin alleviates radiation nephropathy by suppressing renal mTORC1 signalling with concomitant effects on the gut and liver.

Cellular signalling·2026
Same author

Breaking the Fixed Output: Harnessing Photonic Reabsorption and Photothermal Effects for Tunable NIR Waveguiding in a Flexible Organic Crystal.

Angewandte Chemie (International ed. in English)·2026
Same author

Interpretable machine learning model for predicting kidney failure among CAKUT children in multicenter large-scale study.

NPJ digital medicine·2026

Related Experiment Video

Updated: Jun 5, 2025

An Anaerobic Biosensor Assay for the Detection of Mercury and Cadmium
09:33

An Anaerobic Biosensor Assay for the Detection of Mercury and Cadmium

Published on: December 17, 2018

10.1K

Modeling the global ocean distribution of dissolved cadmium based on machine learning-SHAP algorithm.

Ziyuan Jiang1, Enhui Liao1, Ziang Li1

  • 1Key Laboratory of Polar Ecosystem and Climate Change, Ministry of Education, School of Oceanography, Shanghai Jiao Tong University, Shanghai 200030, China.

The Science of the Total Environment
|December 13, 2024
PubMed
Summary

Machine learning reconstructed a global dissolved cadmium (dCd) dataset, revealing its distribution is influenced by biological processes and water mass mixing. This improves understanding of marine element cycling and the cadmium-phosphate relationship.

Keywords:
Dissolved cadmiumMachine learningShapley additive explanations

More Related Videos

An Ultra-clean Multilayer Apparatus for Collecting Size Fractionated Marine Plankton and Suspended Particles
09:01

An Ultra-clean Multilayer Apparatus for Collecting Size Fractionated Marine Plankton and Suspended Particles

Published on: April 19, 2018

8.8K
Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.1K

Related Experiment Videos

Last Updated: Jun 5, 2025

An Anaerobic Biosensor Assay for the Detection of Mercury and Cadmium
09:33

An Anaerobic Biosensor Assay for the Detection of Mercury and Cadmium

Published on: December 17, 2018

10.1K
An Ultra-clean Multilayer Apparatus for Collecting Size Fractionated Marine Plankton and Suspended Particles
09:01

An Ultra-clean Multilayer Apparatus for Collecting Size Fractionated Marine Plankton and Suspended Particles

Published on: April 19, 2018

8.8K
Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon
09:44

Use of Principal Components for Scaling Up Topographic Models to Map Soil Redistribution and Soil Organic Carbon

Published on: October 16, 2018

10.1K

Area of Science:

  • Marine Biogeochemistry
  • Oceanography
  • Machine Learning Applications in Environmental Science

Background:

  • Cadmium (Cd) is a vital trace metal in oceans, essential at low concentrations but toxic at high levels, affecting marine ecosystems and phytoplankton.
  • Dissolved cadmium (dCd) distribution is linked to phosphate (PO4), but the underlying mechanisms and spatial patterns are not fully understood.
  • Current observational data limits comprehensive analysis of dCd spatial distribution and cycling.

Purpose of the Study:

  • To reconstruct a global dataset of dissolved cadmium (dCd) using advanced machine learning methods.
  • To improve the accuracy and comprehensiveness of dCd cycling analyses.
  • To explore factors influencing dCd distribution and the Cd-PO4 relationship.

Main Methods:

  • Comparison of five machine learning algorithms (random forest, artificial neural network, support vector machine, Lasso regression, k-nearest neighbors).
  • Application of the best-performing random forest model to reconstruct a global dCd dataset.
  • Utilized SHapley Additive exPlanations (SHAP) to analyze factors driving dCd distribution and Cd-PO4 variations.

Main Results:

  • The random forest model achieved high performance (Rsq=0.99, RMSE=0.035 nmol kg⁻¹), reducing bias by 25% compared to previous studies.
  • dCd variability is influenced by surface biological processes, deep-sea mineralization, and seawater stratification.
  • Cd-PO4 relationship variations are linked to biological fractionation in high-nutrient, low-chlorophyll (HNLC) regions and water mass mixing.

Conclusions:

  • Machine learning offers a powerful tool for oceanographic research, enabling global-scale analysis of element cycling.
  • The study provides new insights into the drivers of Cd cycling and the Cd-PO4 relationship in the ocean.
  • Over 80% of particles contributing to Cd and PO4 regeneration occur in HNLC regions.