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

Atomic Nuclei: Types of Nuclear Relaxation01:28

Atomic Nuclei: Types of Nuclear Relaxation

239
Nuclear relaxation restores the equilibrium population imbalance and can occur via spin–lattice or spin–spin mechanisms, which are first-order exponential decay processes.
In spin–lattice or longitudinal relaxation, the excited spins exchange energy with the surrounding lattice as they return to the lower energy level. Among several mechanisms that contribute to spin–lattice relaxation, magnetic dipolar interactions are significant. Here, the excited nucleus transfers...
239
Atomic Nuclei: Nuclear Relaxation Processes01:23

Atomic Nuclei: Nuclear Relaxation Processes

603
In the absence of an external magnetic field, nuclear spin states are degenerate and randomly oriented. When a magnetic field is applied, the spins begin to precess and orient themselves along (lower energy) or against (higher energy) the direction of the field. At equilibrium, a slight excess population of spins exists in the lower energy state. Because the direction of the magnetic field is fixed as the z-axis,  the precessing magnetic moments are randomly oriented around the z-axis.
603
Nuclear Power02:36

Nuclear Power

7.7K
Controlled nuclear fission reactions are used to generate electricity. Any nuclear reactor that produces power via the fission of uranium or plutonium by bombardment with neutrons has six components: nuclear fuel consisting of fissionable material, a nuclear moderator, a neutron source, control rods, reactor coolant, and a shield and containment system.
Nuclear Fuels
Nuclear fuel consists of a fissile isotope, such as uranium-235, which must be present in sufficient quantity to provide a...
7.7K
Random Error01:04

Random Error

799
Random or indeterminate errors originate from various uncontrollable variables, such as variations in environmental conditions, instrument imperfections, or the inherent variability of the phenomena being measured. Usually, these errors cannot be predicted, estimated, or characterized because their direction and magnitude often vary in magnitude and direction even during consecutive measurements. As a result, they are difficult to eliminate. However, the aggregate effect of these errors can be...
799
Nuclear Transmutation03:20

Nuclear Transmutation

17.4K
Nuclear transmutation is the conversion of one nuclide into another. It can occur by the radioactive decay of a nucleus, or the reaction of a nucleus with another particle. The first manmade nucleus was produced in Ernest Rutherford’s laboratory in 1919 by a transmutation reaction, the bombardment of one type of nuclei with other nuclei or with neutrons. Rutherford bombarded nitrogen-14 atoms with high-speed α particles from a natural radioactive isotope of radium and observed...
17.4K
Atomic Nuclei: Nuclear Spin State Population Distribution01:14

Atomic Nuclei: Nuclear Spin State Population Distribution

918
Near absolute zero temperatures, in the presence of a magnetic field, the majority of nuclei prefer the lower energy spin-up state to the higher energy spin-down state. As temperatures increase, the energy from thermal collisions distributes the spins more equally between the two states. The Boltzmann distribution equation gives the ratio of the number of spins predicted in the spin −½ (N−) and spin +½ (N+) states.
918

You might also read

Related Articles

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

Sort by
Same author

Double Network Physical Crosslinked Hydrogel for Healing Skin Wounds: New Formulation Based on Polysaccharides and Zn<sup>2</sup>.

International journal of molecular sciences·2023
Same author

Inhibition of <i>Cronobacter sakazakii</i> Biofilm Formation and Expression of Virulence Factors by Coenzyme Q<sub>0</sub>.

Foodborne pathogens and disease·2023
Same author

Highly Efficient Photosensitizers with Molecular Vibrational Torsion for Cancer Photodynamic Therapy.

ACS central science·2023
Same author

Stability and ecological risk assessment of nickel (Ni) in phytoremediation-derived biochar.

The Science of the total environment·2023
Same author

Trends of hospitalisation for patients with liver cirrhosis in Ningxia, China: a cross-sectional study.

BMJ open·2023
Same author

Crystal Sponge Behavior in a Two-Dimensional Rare-Earth Hybrid Coordinate Polymer.

Inorganic chemistry·2023

Related Experiment Video

Updated: May 29, 2025

Laser-heating and Radiance Spectrometry for the Study of Nuclear Materials in Conditions Simulating a Nuclear Power Plant Accident
09:18

Laser-heating and Radiance Spectrometry for the Study of Nuclear Materials in Conditions Simulating a Nuclear Power Plant Accident

Published on: December 14, 2017

10.3K

Source term inversion of nuclear accident with random release durations based on machine learning.

Wendong Yang1, Yifei Wu1, Wenbao Jia1

  • 1Department of Nuclear Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China.

Journal of Hazardous Materials
|February 4, 2025
PubMed
Summary

A new machine learning model using a long short-term memory (LSTM) neural network accurately estimates radioactive nuclide release rates and durations during nuclear accidents. This advanced source term inversion method reduces reliance on prior data, improving emergency response capabilities.

Keywords:
LSTMNuclear accidentsSource term inversion

More Related Videos

Visualization of Low-Level Gamma Radiation Sources Using a Low-Cost, High-Sensitivity, Omnidirectional Compton Camera
06:28

Visualization of Low-Level Gamma Radiation Sources Using a Low-Cost, High-Sensitivity, Omnidirectional Compton Camera

Published on: January 30, 2020

12.4K
Automated 90Sr Separation and Preconcentration in a Lab-on-Valve System at Ppq Level
08:53

Automated 90Sr Separation and Preconcentration in a Lab-on-Valve System at Ppq Level

Published on: June 6, 2018

7.9K

Related Experiment Videos

Last Updated: May 29, 2025

Laser-heating and Radiance Spectrometry for the Study of Nuclear Materials in Conditions Simulating a Nuclear Power Plant Accident
09:18

Laser-heating and Radiance Spectrometry for the Study of Nuclear Materials in Conditions Simulating a Nuclear Power Plant Accident

Published on: December 14, 2017

10.3K
Visualization of Low-Level Gamma Radiation Sources Using a Low-Cost, High-Sensitivity, Omnidirectional Compton Camera
06:28

Visualization of Low-Level Gamma Radiation Sources Using a Low-Cost, High-Sensitivity, Omnidirectional Compton Camera

Published on: January 30, 2020

12.4K
Automated 90Sr Separation and Preconcentration in a Lab-on-Valve System at Ppq Level
08:53

Automated 90Sr Separation and Preconcentration in a Lab-on-Valve System at Ppq Level

Published on: June 6, 2018

7.9K

Area of Science:

  • Nuclear Engineering
  • Environmental Science
  • Data Science

Background:

  • Nuclear accidents release harmful radioactive nuclides, necessitating accurate environmental and health impact assessments.
  • Traditional source term inversion methods struggle with prior information dependence and scenario adaptability.
  • Machine learning offers a promising approach to overcome these limitations in nuclear accident consequence assessment.

Purpose of the Study:

  • To develop and validate a novel source term inversion model using a long short-term memory (LSTM) neural network.
  • To accurately determine radioactive nuclide release rates and durations during nuclear accidents, even with unknown release times.
  • To enhance emergency decision-making by providing reliable data for nuclear accident consequence assessment.

Main Methods:

  • A long short-term memory (LSTM) neural network was employed for source term inversion.
  • The model was optimized using the Optuna algorithm for improved performance.
  • Testing involved a nuclear accident scenario with varying nuclides (Kr-88, Te-132, I-131) and meteorological conditions.

Main Results:

  • The LSTM model achieved a Mean Absolute Percentage Error (MAPE) below 20% for release duration prediction (1-120 min).
  • MAPEs for Kr-88, Te-132, and I-131 release rates were 19.68%, 10.83%, and 28.63% respectively (1-30 min duration).
  • Gamma dose rate is the most critical input, with release duration showing the highest sensitivity; the model demonstrates robustness against meteorological variations.

Conclusions:

  • The proposed LSTM-based source term inversion model effectively estimates release rates and durations with reduced prior information dependence.
  • The model's accuracy and robustness make it a valuable tool for supporting emergency response and decision-making following nuclear accidents.
  • Further validation across diverse accident scenarios and meteorological conditions is recommended to fully establish its operational utility.