Improving near real-time precipitation estimation using a U-Net convolutional neural network and geographical information

被引:65
|
作者
Sadeghi, Mojtaba [1 ]
Phu Nguyen [1 ]
Hsu, Kuolin [1 ]
Sorooshian, Soroosh [1 ,2 ]
机构
[1] Univ Calif Irvine, Dept Civil & Environm Engn, Henry Samueli Sch Engn, Ctr Hydrometeorol & Remote Sensing CHRS, Irvine, CA 92697 USA
[2] Univ Calif Irvine, Dept Earth Syst Sci, 3200 Croul Hall, Irvine, CA 92697 USA
基金
美国海洋和大气管理局;
关键词
Infrared information; Precipitation estimation; Deep learning; Convolutional neural networks; RAIN-GAUGE; GLOBAL PRECIPITATION; PASSIVE MICROWAVE; DATA SETS; SATELLITE; RADAR; CLOUD; PRODUCT; CLASSIFICATION; COMBINATION;
D O I
10.1016/j.envsoft.2020.104856
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Reliable near real-time precipitation estimates are essential for monitoring and managing of natural disasters such as floods. Quality of inputs and capability of the retrieval algorithm are two important aspects for developing satellite-based precipitation datasets. Most retrieval algorithms utilize infrared (IR) information as their input due to its fine spatiotemporal resolution and near-instantaneous availability. However, their sole reliance on IR information limits their capability to learn different mechanisms of precipitation during training, resulting in less accurate estimates. Moreover, recent advances in the field of machine learning offer attractive opportunities to improve the precipitation retrieval algorithms. This study investigates the effectiveness of adding geographical information (i.e. latitude and longitude) to IR information and the application of a U-Net-based convolutional neural network for improving the accuracy of retrieval algorithms. This research suggests that applying an appropriate CNN architecture on geographical and IR information provides an opportunity to improve the satellite-based precipitation products.
引用
收藏
页数:14
相关论文
共 50 条
  • [21] Microaneurysms segmentation with a U-Net based on recurrent residual convolutional neural network
    Kou, Caixia
    Li, Wei
    Liang, Wei
    Yu, Zekuan
    Hao, Jianchen
    JOURNAL OF MEDICAL IMAGING, 2019, 6 (02)
  • [22] Deep Learning Based Automatic Liver Volume Estimation and Segmentation via U-net Convolutional Neural Network
    Marlatt, B.
    Pettit, R.
    Havelka, J.
    Corr, S. J.
    Rana, A.
    AMERICAN JOURNAL OF TRANSPLANTATION, 2021, 21 : 797 - 797
  • [23] Coverage Estimation of Wireless Network Using Attention U-Net
    Lyu, Feibi
    Cheng, Xinzhou
    Xu, Lexi
    Liu, Liang
    Qiao, Jinjian
    Zhi, Lu
    Di, Zixiang
    Xiao, Tian
    Cheng, Chen
    2022 IEEE INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS, TRUSTCOM, 2022, : 1255 - 1260
  • [24] End-to-End Automated Iris Segmentation Framework Using U-Net Convolutional Neural Network
    Chai, Tong-Yuen
    Goi, Bok-Min
    Hong, Ye-Yi
    INFORMATION SCIENCE AND APPLICATIONS, 2020, 621 : 259 - 267
  • [25] Automatic Detection of Post-Operative Clips in Mammography Using a U-Net Convolutional Neural Network
    Schnitzler, Tician
    Ruppert, Carlotta
    Hejduk, Patryk
    Borkowski, Karol
    Kajuter, Jonas
    Rossi, Cristina
    Ciritsis, Alexander
    Landsmann, Anna
    Zaytoun, Hasan
    Boss, Andreas
    Schindera, Sebastian
    Burn, Felice
    JOURNAL OF IMAGING, 2024, 10 (06)
  • [26] Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network
    Guo, Yanan
    Cao, Xiaoqun
    Liu, Bainian
    Gao, Mei
    SYMMETRY-BASEL, 2020, 12 (06):
  • [27] Binarization of Printed Wiring Board Images with Scratches Using Convolutional Neural Network with U-Net Structure
    Hayakawa S.
    Kurihara T.
    Seimitsu Kogaku Kaishi/Journal of the Japan Society for Precision Engineering, 2022, 88 (02): : 181 - 187
  • [28] Infrared Precipitation Estimation Using Convolutional Neural Network
    Wang, Cunguang
    Xu, Jing
    Tang, Guoqiang
    Yang, Yi
    Hong, Yang
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (12): : 8612 - 8625
  • [29] REAL-TIME DENOISING AND DEREVERBERATION WTIH TINY RECURRENT U-NET
    Choi, Hyeong-Seok
    Park, Sungjin
    Lee, Jie Hwan
    Heo, Hoon
    Jeon, Dongsuk
    Lee, Kyogu
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 5789 - 5793
  • [30] Investigation of the applicability of the convolutional neural network U-Net to a problem of segmentation of aircraft images
    Gavrilov, D. A.
    COMPUTER OPTICS, 2021, 45 (04) : 575 - +