Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Response Surface Methodology01:16

Response Surface Methodology

609
Response Surface Methodology (RSM) is a collection of statistical and mathematical techniques used to develop, improve, and optimize processes. It is particularly valuable when many input variables or factors potentially influence a response variable.
The process of RSM involves several key steps:
609

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Interplay Between Exfoliation and Functionalization Strategies for Group VI Layered Transition Metal Dichalcogenide Dispersions.

Nanomaterials (Basel, Switzerland)·2026
Same author

Artificial intelligence algorithm to predict the requirement of neonatal endotracheal intubation within 3 h: application for clinical practice.

Frontiers in medicine·2026
Same author

Advances in air quality modeling through artificial intelligence, machine learning, and deep learning: A comprehensive review.

The Science of the total environment·2026
Same author

Impacts of uncertainties in Chinese NH<sub>3</sub> emissions on PM<sub>2.5</sub> concentrations over mainland China and downwind regions.

Environmental pollution (Barking, Essex : 1987)·2025
Same author

Using multi-satellite observations to constrain ammonia emissions and unlock their potential over open water.

Scientific reports·2025
Same author

Potential impact of vehicle electrification on greenhouse gases and criteria pollutants in 2035: A scenario-based well-to-wheel analysis for New York City, Los Angeles, Chicago, and Houston using GREET-MOVES integration.

Environmental pollution (Barking, Essex : 1987)·2025

相关实验视频

Updated: Jan 17, 2026

Modeling and Simulations of Olfactory Drug Delivery with Passive and Active Controls of Nasally Inhaled Pharmaceutical Aerosols
15:04

Modeling and Simulations of Olfactory Drug Delivery with Passive and Active Controls of Nasally Inhaled Pharmaceutical Aerosols

Published on: May 20, 2016

11.4K

使用深度学习模拟CMAQ:通过使用EQUATES数据集在CONUS上模拟表面NO2,O3和PM2.5的比较研究.

Mahsa Payami1, Yunsoo Choi1, Sagun Gopal Kayastha1

  • 1Department of Earth and Atmospheric Sciences, University of Houston, Houston, TX, 77004, United States of America.

The Science of the total environment
|September 14, 2025
PubMed
概括

我们开发了快速的2D CNN模拟器,以准确预测美国各地的每日空气质量 (NO2,O3,PM2.5). 这种深度学习方法与传统模型相比,大大加快了空气质量评估.

关键词:
这就是CMAQQ.深度学习是一种深度学习.均等地表示等于.一个模拟器模拟器.NO ((2)) 的情况.十三) 的情况.在PM{2.5) 中,

更多相关视频

Calibrated Passive Sampling - Multi-plot Field Measurements of NH3 Emissions with a Combination of Dynamic Tube Method and Passive Samplers
10:29

Calibrated Passive Sampling - Multi-plot Field Measurements of NH3 Emissions with a Combination of Dynamic Tube Method and Passive Samplers

Published on: March 21, 2016

12.8K
Automated, High-resolution Mobile Collection System for the Nitrogen Isotopic Analysis of NOx
07:14

Automated, High-resolution Mobile Collection System for the Nitrogen Isotopic Analysis of NOx

Published on: December 20, 2016

12.1K

相关实验视频

Last Updated: Jan 17, 2026

Modeling and Simulations of Olfactory Drug Delivery with Passive and Active Controls of Nasally Inhaled Pharmaceutical Aerosols
15:04

Modeling and Simulations of Olfactory Drug Delivery with Passive and Active Controls of Nasally Inhaled Pharmaceutical Aerosols

Published on: May 20, 2016

11.4K
Calibrated Passive Sampling - Multi-plot Field Measurements of NH3 Emissions with a Combination of Dynamic Tube Method and Passive Samplers
10:29

Calibrated Passive Sampling - Multi-plot Field Measurements of NH3 Emissions with a Combination of Dynamic Tube Method and Passive Samplers

Published on: March 21, 2016

12.8K
Automated, High-resolution Mobile Collection System for the Nitrogen Isotopic Analysis of NOx
07:14

Automated, High-resolution Mobile Collection System for the Nitrogen Isotopic Analysis of NOx

Published on: December 20, 2016

12.1K

科学领域:

  • 环境科学 环境科学
  • 计算机科学 计算机科学
  • 大气化学 大气化学

背景情况:

  • 空气质量建模对于公共卫生和环境监测至关重要.
  • 传统的化学运输模型 (CTM) 是计算密集型的,限制了它们用于快速评估的应用.
  • 开发高效的模拟器对于更快的空气质量预测至关重要.

研究的目的:

  • 开发和验证基于二维卷积神经网络 (CNN) 的模拟器,用于预测每日平均 NO2,O3 和 PM2.5.5 的表面度.
  • 通过使用现实数据,对这些模拟器的性能与已建立的CTM (CMAQ) 进行评估.
  • 与传统建模相比,评估深度学习方法的计算效率.

主要方法:

  • 使用U-Net架构为2D CNN模拟器.
  • 输入数据包括来自美国环保署EQUATES数据集的气象,排放和陆地表面数据.
  • CMAQ模型的输出作为培训和验证的目标数据.
  • 使用一致性指数 (IOA) 和时空分析评估模拟器性能.

主要成果:

  • 模拟器与CMAQ模拟实现了很高的一致性 (NO2的IOA高达0.95,O3的0.88,PM2.5的0.85).
  • 在各种条件和排放模式中表现出一致的时空准确性.
  • 与CPU-GPU设置上的CMAQ相比,实现了显著的加快速度 (NO2模拟的1064倍)

结论:

  • 深度学习模拟器为空气质量评估提供了一个计算效率高的替代方案,其准确性与CTM相比较.
  • 2D方法显示了O3和PM2.5等复杂物种的局限性,这表明3D模拟器的潜在好处.
  • 这项技术可以为政策和研究提供更快,更容易获得的空气质量预测.