A Geostationary Satellite Precipitation Estimation Machine Learning Model With Dynamic Sample Balancing for Fengyun-4B

地球静止轨道 遥感 降水 计算机科学 卫星 地球静止运行环境卫星 样品(材料) 机器学习 天气预报 人工智能 大气模式 气象学 估计 估计理论 数据建模 环境科学 时间序列 全球定位系统 定量降水量估算
作者
Hanna Sai,Yanhui Xie,Husi Letu,Mengyuan Cui,Shanhu Bao,Na Xu,Xia Li,Jinbiao Zhu,Wen Feng Qiu,Jiancheng Shi,Dabin Ji
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:64: 1-18
标识
DOI:10.1109/tgrs.2026.3681960
摘要

High-precision, real-time precipitation estimation is critical for improving the accuracy of meteorological forecasting and disaster warnings. However, mainstream satellite remote sensing inversion techniques are often limited by their reliance on cloud-top information. Additionally, estimation accuracy is further constrained by the severe category imbalance in precipitation samples and the widespread use of low-spatial-resolution reanalysis data, making it difficult for existing products to meet the practical application requirements. To address these challenges, this study proposes a high-precision real-time precipitation inversion algorithm named GSPE-DML, which is based on the Fengyun-4B (FY-4B) satellite and machine learning. The algorithm is designed with two core innovations. First, it incorporates high-resolution (3 km) CMA-BJ v2.0 reanalysis data to replace conventional low-resolution datasets such as ERA5, thereby capturing more detailed information on the sub-cloud vertical atmospheric structure. Second, a real-time dynamic sample balance mechanism is introduced, which adaptively adjusts category weights during model training to effectively mitigate the precipitation sample imbalance problem. A comparative analysis conducted across different temporal scales indicates that the performance of GSPE-DML is better than that of real-time precipitation products such as FY4B-QPE, APCP, and GSMAP-NRT across several key metrics. On the hourly scale, in particular, GSPE-DML maintained a Heidke Skill Score (HSS) above 0.52 and achieved a correlation coefficient of 0.45 with ground observations. Notably, its false alarm rate (FAR) was significantly lower than that of the GSMAP-NRT product across all four quarters. A case study of Typhoon "Doksuri" further validated the robustness of the algorithm. The inversion results showed minimal deviation (–0.01) from ground observations and high consistency in spatial patterns, successfully reconstructing the intense precipitation band near the typhoon's eyewall and the weak precipitation structure within its outer spiral rainbands.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
洋子完成签到,获得积分10
2秒前
2秒前
岁杪望舒发布了新的文献求助10
2秒前
Zz完成签到,获得积分10
5秒前
5秒前
洋子发布了新的文献求助10
5秒前
氯化钠完成签到,获得积分10
5秒前
时时完成签到,获得积分20
6秒前
6秒前
荼蘼发布了新的文献求助10
6秒前
6秒前
7秒前
自觉海冬完成签到,获得积分10
8秒前
8秒前
SSY完成签到,获得积分10
9秒前
吴邪完成签到,获得积分10
10秒前
111发布了新的文献求助10
10秒前
悍劲芭比单挑孔子完成签到,获得积分10
10秒前
10秒前
10秒前
研友_nxwbrL完成签到,获得积分10
11秒前
tutu发布了新的文献求助10
11秒前
AA发布了新的文献求助10
11秒前
感性的雅容完成签到 ,获得积分10
11秒前
乐乐的应助被陶醉的谷秋采纳,获得30
11秒前
lianxin发布了新的文献求助10
12秒前
kaelin完成签到,获得积分10
12秒前
13秒前
14秒前
proudzhu完成签到,获得积分10
14秒前
15秒前
英姑的应助被LIU采纳,获得10
15秒前
15秒前
16秒前
16秒前
16秒前
Chichien发布了新的文献求助10
17秒前
18秒前
荼蘼发布了新的文献求助10
18秒前
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
Resource Recovery Handbook 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8175157
求助须知:如何正确求助?哪些是违规求助? 9566975
关于积分的说明 21789458
捐赠科研通 7769647
什么是DOI,文献DOI怎么找? 3431836
关于科研通互助平台的介绍 2556078
邀请新用户注册赠送积分活动 2477241