改进的表面 NO2 检索:中国 (2018-2023) 双层机器学习模型构建和时空特征分析 (2018-2023)
Wei Wang1, Bingqian Li1, Biyan Chen1
1School of Geosciences and Info-Physics, Central South University, Changsha, China.
Journal of environmental management
|April 29, 2025
概括
这项研究开发了一种新的双层机器学习 (DLML) 模型,通过考虑其垂直结构来准确估计表面的二氧化 (NO2) 水平. DLML模型显著提高了中国各地的NO2监测准确度.
科学领域:
- 大气化学和物理大气化学和物理
- 环境监测 环境监测
- 机器学习应用 机器学习应用
背景情况:
- 表面二氧化 (SNO2) 是一种具有重大健康和环境影响的关键空气污染物.
- 现有的SNO2检索模型不充分考虑NO2的垂直结构,导致不准确.
- 传统的机器学习模型与SNO2和热层NO2柱 (XNO2) 复杂的时空动态作斗争.
研究的目的:
- 通过整合NO2垂直分层特征和时空变化机制,提高SNO2水平逆转的准确性.
- 开发和验证一种新的双层机器学习 (DLML) 框架,用于估计中国各地的SNO2水平.
- 分析2018年至2023年中国SNO2水平的时间和空间变化模式.
主要方法:
- 开发一个双层机器学习 (DLML) 框架,利用光梯度增强机 (LGBM) 和极端随机森林 (ERF).
- 将NO2垂直分层和时空变化机制纳入DLML模型.
- 在2018-2023年期间,中国各地的SNO2水平估计.
主要成果:
- 在空间时空交叉验证中,DLML模型表现出卓越的性能,在空间时空交叉验证中R2为0.87,比传统模型提高10%.
- 平均绝对误差 (MAE) 和根平均平方误差 (RMSE) 分别降至大约4.24μg/m3和5.79μg/m3.
- 从中部/东部沿海地区到周边地区,SNO2水平呈现下降趋势,与世卫组织空气质量指南保持一致;观察到U形时间变化,冬季 (一月,十二月) 达到峰值,夏季 (六月至八月) 达到最低.
结论:
- DLML框架有效地整合了NO2的垂直结构和时空动态,以准确地估计SNO2.
- 冬季气象条件显著影响SNO2的变化,区域经济和工业活动导致武汉和长江三角洲等地区的升水平.
- 该研究提供了一种可靠的SNO2监测方法,这对于了解和减轻空气污染影响至关重要.
相关概念视频
Fineness of Cement
112
The fineness of cement directly influences the rate of hydration, as the hydration begins at the surface of the cement particles. In addition to hydration, the fineness of cement is vital for various properties of concrete including workability, gypsum requirement, and long-term behavior. The fineness of cement is represented in terms of the specific surface of cement which is typically measured in square meters per kilogram, with several methods available for this determination.
Direct...
Direct...
112
Surface Tension and Surface Energy
1.3K
When a paint brush is immersed in water, the bristles wave freely inside the water. When it is taken out, the bristles stick together. The reason behind this effect is surface tension.
Consider a beaker filled with liquid. The bulk molecules in the liquid experience equal attractive forces on all sides with the surrounding molecules. However, the surface molecules experience a net attractive force downward due to the bulk molecules. The surface of the liquid behaves like a stretched membrane,...
Consider a beaker filled with liquid. The bulk molecules in the liquid experience equal attractive forces on all sides with the surrounding molecules. However, the surface molecules experience a net attractive force downward due to the bulk molecules. The surface of the liquid behaves like a stretched membrane,...
1.3K
Shape and Texture of Coarse Aggregate
175
Aggregate shape is classified based on the relative sharpness or roundness of the edges and corners. This classification includes categories like rounded, angular, elongated, and flaky, each with specific characteristics. Rounded aggregates, fully shaped by attrition, are typical of river or seashore gravel, while angular aggregates, such as crushed rock, have well-defined edges. Aggregates that are elongated and flaky are less desirable, as they can reduce the workability and strength of...
175


