基于自注意力变换网络的多源空间数据融合方法在变电站汛情降水预报中的应用

doi:10.13474/j.cnki.11-2246.2025.0217

摘要/Abstract

摘要： 随着近年来极端天气事件的频率和规模不断增加,利用先进技术提升测绘和地理信息系统的精度与效率,从而提高户外露天常规输变电子站电力系统的抗灾能力显得尤为重要。本文提出了一种基于自注意力变换网络的多源空间数据融合方法,用于提升对复杂地理环境和自然资源变化的监测与预测能力。该方法将连续气象雷达回波数据表示为时空序列,利用自注意力机制编码器捕捉长期时间依赖关系,并整合多尺度卷积提取短期时间依赖关系;此外,在变换网络中引入图注意力网络,以深入分析不同空间变量之间的关系。为验证该模型的有效性,基于2019—2022年某地区的降水数据与遥感数据进行试验,并与传统的卷积神经网络、基准U-Net和长短时记忆网络进行对比。结果表明,该方法在测量精度和数据融合能力上优于传统模型,特别是在地理信息系统构建、工程测量、矿山测量、地籍测绘和海洋测绘等领域具有广泛的应用潜力。

关键词: 雷达回波外推, 降水预报, 长短期记忆, 注意力

Abstract: With the increasing frequency and scale of extreme weather events in recent years, it is particularly important to utilize advanced technologies to enhance the accuracy and efficiency of mapping and geographic information systems, so as to improve the resilience of power systems in outdoor open-air conventional transmission and substation substations. In this paper, a multi-source spatial data fusion method based on self-attentive transform network is proposed for enhancing the monitoring and prediction capability of changes in complex geographic environments and natural resources. The method represents continuous weather radar echo data as a spatio-temporal sequence, captures long term time dependencies using a self-attentive mechanism encoder, and integrates multi-scale convolution to extract short term time dependencies. In addition, a graph attention network is introduced into the transformation network to deeply analyze the relationship between different spatial variables. To verify the effectiveness of the model, this paper conducts experiments based on precipitation data and remote sensing data from 2019 to 2022 in a region, and compares it with traditional convolutional neural networks, benchmark U-Net and long-short term memory networks. The experimental results show that the method is superior to the traditional model in terms of measurement accuracy and data fusion ability, especially in the fields of GIS construction, engineering survey, mine survey, cadastral mapping and ocean survey and mapping, etc., which has a wide application potential.

Key words: radar echo extrapolation, precipitation forecast, long-short term memory, attention

中图分类号:

P208

原辉, 俞华, 孟晓凯, 范晶晶, 李劲松. 基于自注意力变换网络的多源空间数据融合方法在变电站汛情降水预报中的应用[J]. 测绘通报, 2025, 0(2): 96-100,107.

YUAN Hui, YU Hua, MENG Xiaokai, FAN Jingjing, LI Jinsong. Application of multi-source spatial data fusion method based on self-attentive transform network in flood and precipitation forecasting at substation[J]. Bulletin of Surveying and Mapping, 2025, 0(2): 96-100,107.

参考文献

[1] 曲巧娜,吴炜.多种模式降水预报的稳定性特征研究[J].气象,2024,50(4):420-433.
[2] 李振轩,黄敏儿,高飞,等.基于U-Net、U-Net++和Attention-U-Net网络的遥感影像水体提取[J].测绘通报,2024(8):26-30.
[3] 杜明斌,曹云昌,王晓峰,等.北斗卫星导航系统在数值天气中的应用[J].测绘通报,2024(7):178-181.
[4] 程安坤,王敏,孟欣,等.采用北斗PPP-B2b服务的大气可降水量反演及香港暴雨过程分析[J].测绘通报,2024(2):118-123.
[5] HE Guangxin,QU Haifeng,LUO Jingjia,et al.An long short-term memory model with multi-scale context fusion and attention for radar echo extrapolation[J].Remote Sensing,2024,16:376.
[6] 马志峰,张浩,刘劼.基于深度学习的短临降水预报综述[J].计算机工程与科学,2023,45(10):1731-1753.
[7] BOWLER N E H,PIERCE C E,SEED A.Development of a precipitation nowcasting algorithm based upon optical flow techniques[J].Journal of Hydrology,2004,288(1/2):74-91.
[8] WOO W C,WONG W K.Operational application of optical flow techniques to radar-based rainfall nowcasting[J].Atmosphere,2017,8(3):48.
[9] AYZEL G,HEISTERMANN M,WINTERRATH T.Optical flow models as an open benchmark for radar-based precipitation nowcasting (rainymotion v0.1)[J].Geoscientific Model Development,2019,12(4):1387-1402.
[10] SAMAD A,BHAGYANIDHI,GAUTAM V,et al.An approach for rainfall prediction using long short term memory neural network[C]//Proceedings of the 5th International Conference on Computing Communication and Automation (ICCCA).Greater Noida:IEEE,2020.
[11] 方巍,庞林,王楠,等.人工智能在短临降水预报中应用研究综述[J].南京信息工程大学学报(自然科学版),2020,12(4):406-420.
[12] ADERYANI F R,JAMSHID MOUSAVI S,JAFARI F.Short-term rainfall forecasting using machine learning-based approaches of PSO-SVR,LSTM and CNN[J].Journal of Hydrology,2022,614:128463.
[13] AMINI A,DOLATSHAHI M,KERACHIAN R.Adaptive precipitation nowcasting using deep learning and ensemble modeling[J].Journal of Hydrology,2022,612:128197.
[14] 齐丹宁,胡政军,赵尚民.山西省西山煤田长时间序列NDVI时空变化趋势及对气候响应[J].测绘通报,2021(9):98-102.
[15] HU Yuan,CHEN Lei,WANG Zhibin,et al.Towards a more realistic and detailed deep-learning-based radar echo extrapolation method[J].Remote Sensing,2021,14(1):24.
[16] YIN Jian,GAO Zhiqiu,HAN Wei.Application of a radar echo extrapolation-based deep learning method in strong convection nowcasting[J].Earth and Space Science,2021,8(8):e01621.
[17] 陈生,黄启桥,谭金凯,等.基于多尺度特征深度学习的短临降水预报[J].热带气象学报,2023,39(6):799-806.
[18] SHI X,GAO Z,LAUSEN L,et al.Deep learning for precipitation nowcasting:a benchmark and a new model[M]// Advances in Neural Information Processing Systems.Long Beach:[s.n.],2017.
[19] WANG Y,GAO Z,LONG M,et al.Predrnn++:towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning [C]//Proceedings of the 35th International Conference on Machine Learning.Stockhol￣msmässan:[s.n.],2018.