通过基于机器学习的缩放方法,绘制城市一级每日高分辨率颗粒物 (PM2.5) 度的地图
Phuong D M Nguyen1, An H Phan1, Truong X Ngo1
1Faculty of Information Technology, University of Engineering and Technology, Vietnam National University Hanoi, E3 Building, 144 Xuan Thuy Street, Dich Vong Hau Ward, Cau Giay District, Ha Noi, 100000, Vietnam.
Environmental monitoring and assessment
|December 23, 2024
概括
机器学习模型改善了越南的PM2.5空气质量图. CatBoost 2天延迟模型显著提高了空间准确性和可靠性,以更好地监测环境.
科学领域:
- 环境科学 环境科学
- 数据科学数据科学数据科学
- 大气科学 大气科学
背景情况:
- 颗粒物 (PM2.5) 污染对全球健康和环境构成重大风险,特别是在越南.
- 精确,高分辨率监测当地PM2.5水平对于有效的空气质量评估至关重要.
- 越南现有的3公里分辨率PM2.5数据集需要精细化以进行详细的空间变化分析.
研究的目的:
- 研究和比较基于机器学习的缩放方法,以提高越南PM2.5产品的空间分辨率和质量.
- 评估传统机器学习和深度学习模型在缩小PM2.5数据方面的表现.
- 为了验证下调PM2.5地图的实际适用性,超出标准模型评估指标.
主要方法:
- 采用传统的机器学习模型:随机森林,XGBoost,Catboost,支持向量回归 (SVR) 和混合效应模型 (MEM).
- 使用深度学习模型:长期短期记忆 (LSTM),卷积神经网络 (CNN) 和卷积LSTM (ConvLSTM).
- 综合时间因素和经过验证的模型生成地图与现实世界的空间分布相比.
主要成果:
- CatBoost 2天滞后模型表现出卓越的性能,优于其他传统和深度学习方法.
- 与SOTA地图相比,拟议的CatBoost模型实现了57%的相关性增加 (Pearson R) 和RMSE,MRE和MAE的显著减少.
- 生成的每日,每月和每年的平均PM2.5地图准确地捕捉了胡志明市的空间分布和季节性变化.
结论:
- 机器学习,特别是具有时间集成的基于树的模型,如CatBoost,可以显著提高PM2.5的空间分辨率和精度.
- 传统的机器学习模型比深度学习更有效,可以在有限的数据集下进行缩放.
- 增强的PM2.5地图为越南空气质量评估和环境监测提供了更可靠,更准确的工具.
更多相关视频
08:59Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System
Published on: May 22, 2020
5.4K
09:33Visualizing Field Data Collection Procedures of Exposure and Biomarker Assessments for the Household Air Pollution Intervention Network Trial in India
Published on: December 23, 2022
2.2K
相关概念视频
01:23Sampling Plans
1.5K
Sampling is a crucial step in analytical chemistry, allowing researchers to collect representative data from a large population. Common sampling methods include random, judgmental, systematic, stratified, and cluster sampling.
Random sampling is a method where each member of the population has an equal chance of being selected for the sample. It involves selecting individuals randomly, often using random number generators or lottery-type methods. For example, when analyzing the properties of a...
Random sampling is a method where each member of the population has an equal chance of being selected for the sample. It involves selecting individuals randomly, often using random number generators or lottery-type methods. For example, when analyzing the properties of a...
1.5K
01:20Downsampling
872
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
872
01:29Application of Linearization and Approximation
193
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
193