相关实验视频

Updated: Jun 19, 2026

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression

Published on: November 8, 2019

一个混合深度学习模型用于O₃预测和解释在中国的长江三角洲地区

Lingxia Wu¹, Junlin An¹, Jianjun He²

¹Key Laboratory for Aerosol-Cloud-Precipitation of China Meteorological Administration, Nanjing University of Information Science and Technology, Nanjing, 210044, China.

The Science of the total environment

|November 13, 2025

概括

可解释的人工智能 (XAI) 和层级相关性传播 (LRP) 揭示了臭氧 (O3) 污染的关键驱动因素. 气象因素显著影响O3预测,特别是在光化学活动高峰期间.

科学领域:

环境科学环境科学
人工智能的人工智能
大气化学大气化学

背景情况:

准确的空气质量预测对于公共卫生和环境管理至关重要.
深度学习 (DL) 模型对空气质量预测有希望,但往往缺乏可解释性.
可解释的人工智能 (XAI) 方法,如层级相关性传播 (LRP),是理解DL模型预测所需的.

研究的目的:

将XAI (LRP) 应用于深度学习模型,用于预测臭氧 (O3) 度.
量化不同特征 (网格,气象,污染物) 对O3预测的贡献.
确定影响长江三角洲 (YRD) O3变异性的排放源和运输机制.

主要方法:

开发了一种随机森林校正 (RF校正) 模型,用于为YRD (2020-2023) 生成9公里网格的O3数据.
利用基于注意力的序列对序列 (seq2seq) DL模型,结合网格式O3,WRF气象数据和地面观测,进行24小时,48小时和72小时的O3预测.
应用层级相关性传播 (LRP) 来分析seq2seq模型对O3预测的特征贡献.

主要成果:

seq2seq模型实现了强大的24小时预测性能 (R=0.85测试,R=0.89验证).
LRP分析表明,每年平均有24.6%的格子,38.2%的气象特征和17.0%的污染物特征对O3预测有显著的贡献.
特征贡献在13:00-15:00达到顶峰,与光化学生产和区域运输相关;LRP洞察与潜在来源贡献函数 (PSCF) 和工业区数据保持一致.

结论:

通过XAI (LRP) 增强的深度学习模型,为推动臭氧变化的复杂因素提供了宝贵的见解.
气象因素是O3预测的主要驱动因素,其次是网格和污染物特征.
来自XAI的特征重要性有助于识别排放源和了解O3传输机制,这对于有效的空气质量管理至关重要.

关键词:

基于注意力的seq2seq模型层层相关的传播方法传播方法.臭氧臭氧是什么?臭氧臭氧是什么长江三角洲地区地区长江三角洲地区.

更多相关视频

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Published on: June 13, 2020

相关概念视频

Precipitation Processes

Precipitation Processes

The experimental conditions in a gravimetric analysis should be optimized to maximize the particle size and purity of the obtained precipitate. Ideally, the concentration of the precipitating reagent should be low with effective stirring to maintain low relative supersaturation for the growth of large crystals. In homogeneous precipitation, the precipitant is slowly generated by a chemical reaction in the solution to avoid local reagent excesses. For example, urea decomposes gradually to...

Design Example: Analyzing Capacity Contours for Flood Risk Assessment

Design Example: Analyzing Capacity Contours for Flood Risk Assessment

Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...