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

Observational Learning01:12

Observational Learning

356
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
356
Prediction Intervals01:03

Prediction Intervals

2.4K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
2.4K
Maxwell-Boltzmann Distribution: Problem Solving01:20

Maxwell-Boltzmann Distribution: Problem Solving

1.8K
Individual molecules in a gas move in random directions, but a gas containing numerous molecules has a predictable distribution of molecular speeds, which is known as the Maxwell-Boltzmann distribution, f(v).
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
1.8K
Predicting Reaction Outcomes02:24

Predicting Reaction Outcomes

8.7K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
8.7K
Neural Regulation01:37

Neural Regulation

40.4K
Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.
40.4K
Neural Control of Respiration01:18

Neural Control of Respiration

3.2K
The neural regulation of respiration is a meticulously coordinated process primarily controlled by the respiratory centers located within the brainstem. These centers, composed of specialized neurons, transmit nerve impulses that control the contraction and relaxation of our respiratory muscles.
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
3.2K

You might also read

Related Articles

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

Sort by
Same author

Volatile methylsiloxanes in a textile dyeing and printing industrial park: Source profiles, ambient distributions and SOA formation potential.

Journal of hazardous materials·2026
Same author

Design and characterization of a novel vehicle-mounted dual-reactor smog chamber for controlled and real-world atmospheric process simulations.

Journal of environmental sciences (China)·2026
Same author

Priority control strategies derived from updated measurement of VOCs source profiles for plastic product industry.

Environment international·2026
Same author

Assessment of environmental and health impacts during 3D printing of candidate polymeric materials for space additive manufacturing.

Journal of hazardous materials·2025
Same author

High-quality narrow black phosphorus nanoribbons with nearly atomically smooth edges and well-defined edge orientation.

Nature materials·2025
Same author

Advancing Atmospheric Detection of Weakly Absorbing Reactive Trace Gases Using the FY-3E/HIRAS-II TIR Sounder on a Dawn-Dusk Orbit.

Environmental science & technology letters·2025

Related Experiment Videos

Optimized neural network for daily-scale ozone prediction based on transfer learning.

Wei Ma1, Zibing Yuan1, Alexis K H Lau2

  • 1School of Environment and Energy, South China University of Technology, Guangzhou 510006, China.

The Science of the Total Environment
|March 6, 2022
PubMed
Summary

A new Transfer Learning-Long Short-Term Memory (TL-LSTM) model improves daily ozone (O3) pollution forecasting. This machine learning approach enhances prediction accuracy, crucial for managing air quality in urban environments.

Keywords:
Hong KongL2 regularizationLong short-term memoryOzone pollutionTransfer learning

Related Experiment Videos

Area of Science:

  • Atmospheric Chemistry and Physics
  • Environmental Science and Engineering
  • Artificial Intelligence and Machine Learning

Background:

  • Tropospheric ozone (O3) pollution is a significant environmental concern, particularly in China, necessitating accurate forecasting for effective mitigation.
  • Existing machine learning models for O3 prediction show limitations in accuracy, especially for daily levels.
  • Accurate O3 forecasting is essential for implementing effective pollution control strategies and reducing peak O3 concentrations.

Purpose of the Study:

  • To develop and evaluate a novel Transfer Learning-Long Short-Term Memory (TL-LSTM) model for improved daily O3 concentration prediction.
  • To assess the model's performance in Hong Kong, considering meteorological and pollutant concentration data.
  • To identify key meteorological factors influencing O3 prediction accuracy.

Main Methods:

  • A novel TL-LSTM model was developed by coupling Long Short-Term Memory (LSTM) neural networks with transfer learning.
  • Meteorological data and pollutant concentrations were used as input features for the model.
  • L2 regularization was employed to enhance model generalization and prevent overfitting.

Main Results:

  • The TL-LSTM model significantly improved O3 prediction accuracy, increasing the coefficient of determination (R²) from 0.684 to 0.783 and reducing mean square error (MSE) from 1.36 × 10⁻² to 1.05 × 10⁻² compared to baseline models.
  • Model performance showed seasonal variations, with the highest accuracy in summer, though peak O3 levels were under-predicted due to limited high-pollution event data.
  • Sobol analysis identified wind speed as the most sensitive factor affecting O3 prediction, attributed to land-sea breeze effects on pollutant trapping and O3 formation.

Conclusions:

  • The TL-LSTM model demonstrates superior performance in predicting daily O3 concentrations in Hong Kong, offering a significant advancement over existing methods.
  • The model's effectiveness highlights the potential of transfer learning in enhancing air pollution forecasting.
  • The TL-LSTM approach can be adapted for O3 pollution forecasting and management in other regions susceptible to photochemical smog.