季节性雪中黑碳的全球量化:一个物理和观测限制的机器学习框架
Yang Chen1, Shirui Yan1, Yaliang Hou1
1Key Laboratory for Semi-Arid Climate Change of the Ministry of Education, College of Atmospheric Sciences, Lanzhou University, Lanzhou 730000, China.
一个新的双随机森林模型在季节性雪 (BCS) 数据集中创建了一个全球黑碳,提高了雪变黑和融化预测的准确性. 这有助于人们更好地了解这种关键污染物的气候影响.
科学领域:
- 地球系统科学 地球系统科学
- 气候科学 气候科学
- 环境科学 环境科学
背景情况:
- 季节性雪中的黑碳 (BCS) 通过减少白度和加速融雪,显著影响地球气候.
- 对BCS气候和水文影响的准确量化受到稀缺,高质量的数据的限制.
研究的目的:
- 开发一个新的框架来生成一个全面的全球BCS度数据集.
- 提高BCS估计及其气候影响评估的准确性.
主要方法:
- 引入了双随机森林 (DRF) 框架,整合了物理机制和观测数据.
- 预先训练DRF与地球系统模型模拟,并与全球现场观测微调.
- 在0.5° × 0.625°分辨率下生成了44年 (1981-2024) 的全球月度BCS数据集.
主要成果:
- 与观测相比,DRF数据集显示出高准确度 (R=0.92,NME=31%),表现优于现有方法.
- 该数据集准确地捕捉了季节性BCS变化和长期趋势,包括人为影响.
- 成功复制了由人类活动和自然气候模式的十年变化驱动的日益增长的趋势.
结论:
- 新的DRF框架提供了一个有价值的,高精度的全球BCS数据集.
- 这一数据集可以对BCS诱导的辐射强迫和雪融的归因进行可靠的量化.
- 有助于更好地了解雪的变黑与气候变暖对融雪加速的影响.
更多相关视频
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
09:34A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
Published on: September 25, 2021
相关概念视频
Observational Learning
Global Climate Change
Seasoning of Wood
Achieving equilibrium moisture content is the goal of seasoning; this is the point where the wood's moisture content stabilizes to align with the moisture levels of the surrounding environment. Proper...
Physical and Chemical Properties of Matter
Biological Clocks and Seasonal Responses
Detection of Black Holes
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
