Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress)

Toward a Next Generation Particle Precipitation Model: Mesoscale Prediction Through Machine Learning (a Case Study and Framework for Progress)
复制标题

迈向下一代粒子沉淀模型:通过机器学习进行中尺度预测(案例研究和进展框架)

DOI:
10.1029/2020sw002684
复制
发表时间:
2020
期刊:
影响因子:
3.7
通讯作者:
S. Skone
S. Skone
中科院分区:
地球科学1区
文献类型:
--
作者:
R. McGranaghan;Jack L. Ziegler;T. Bloch;S. Hatch;E. Camporeale;K. Lynch;M. Owens;J. Gjerloev;Binzheng Zhang;S. Skone

文献摘要

参考文献

被引文献

相似文献

我们通过一个新的数据库和使用机器学习(ML)工具来提高从磁层到电离层的电子粒子沉淀的建模能力,以从这些数据中获得实用性。我们编制、整理、分析并提供了一个新的、功能更强大的粒子降水数据数据库,其中包括51个卫星年的国防气象卫星计划(DMSP)观测数据,这些观测数据与太阳风和地磁活动数据在时间上一致。新的总电子能量通量粒子降水临近预报模型是一个名为PrecipNet的神经网络,它利用ML方法提供的增强的表达能力,适当地利用来自太阳风和地磁活动的各种信息,更重要的是,它们的时间历史。通过对组织参数和目标电子能量通量观测的更有效表征,与目前最先进的模式椭圆变化、评估、跟踪、强度和在线近预报(OVATION Prime)相比,PrecipNet将误差降低了约50%,更好地捕捉了极光通量的动态变化,并为其能够重建中尺度现象提供了证据。我们创建并应用了空间天气模型评估的新框架,该框架将之前来自整个日地研究界的指导推向高潮。研究方法和结果代表了空间天气研究的“新前沿”,处于传统和数据科学驱动发现的交叉点,并为未来的努力奠定了基础。
We advance the modeling capability of electron particle precipitation from the magnetosphere to the ionosphere through a new database and use of machine learning (ML) tools to gain utility from those data. We have compiled, curated, analyzed, and made available a new and more capable database of particle precipitation data that includes 51 satellite years of Defense Meteorological Satellite Program (DMSP) observations temporally aligned with solar wind and geomagnetic activity data. The new total electron energy flux particle precipitation nowcast model, a neural network called PrecipNet, takes advantage of increased expressive power afforded by ML approaches to appropriately utilize diverse information from the solar wind and geomagnetic activity and, importantly, their time histories. With a more capable representation of the organizing parameters and the target electron energy flux observations, PrecipNet achieves a >50% reduction in errors from a current state‐of‐the‐art model oval variation, assessment, tracking, intensity, and online nowcasting (OVATION Prime), better captures the dynamic changes of the auroral flux, and provides evidence that it can capably reconstruct mesoscale phenomena. We create and apply a new framework for space weather model evaluation that culminates previous guidance from across the solar‐terrestrial research community. The research approach and results are representative of the “new frontier” of space weather research at the intersection of traditional and data science‐driven discovery and provides a foundation for future efforts.
使用空间天气建模框架的扰动输入集合建模
DOI: 10.1029/2018sw002000
发表时间: 2018
期刊: Space Weather
影响因子: 3.7
作者:
Morley, S. K.;Welling, D. T.;Woodroffe, J. R.
通讯作者: Woodroffe, J. R.
DOI: 10.1029/2018sw002067
发表时间: 2018-12
期刊: Space Weather
影响因子: --
作者:
M. Liemohn;J. McCollough;V. Jordanova;C. Ngwira;Steven K. Morley;C. Cid;W. Tobiska;P. Wintoft
通讯作者: M. Liemohn;J. McCollough;V. Jordanova;C. Ngwira;Steven K. Morley;C. Cid;W. Tobiska;P. Wintoft
太阳风驱动的地球磁层中地磁和等离子体时滞的调查
DOI: 10.1016/j.jastp.2020.105376
发表时间: 2020
影响因子: 1.9
作者:
Borovsky, Joseph E.
通讯作者: Borovsky, Joseph E.
DOI: 10.1029/2018sw002127
发表时间: 2019
期刊: Space Weather
影响因子: 3.7
作者:
Robinson, Robert;Zhang, Yongliang;Garcia‐Sage, Katherine;Fang, Xiaohua;Verkhoglyadova, Olga P.;Ngwira, Chigomezyo;Bingham, Suzy;Kosar, Burcu;Zheng, Yihua;Kaeppler, Stephen
通讯作者: Kaeppler, Stephen
DOI: 10.1038/s41598-018-35091-2
发表时间: 2018-11-22
期刊: Scientific reports
影响因子: 4.6
作者:
Liou K;Sotirelis T;Mitchell EJ
通讯作者: Mitchell EJ