基于人工神经网络的高分五号高光谱影像悬浮泥沙浓度反演方法
作者:
作者单位:

1.华东师范大学 上海市多维度信息处理重点实验室,上海 200241;2.北京跟踪与通信技术研究所,北京 100094;3.华东师范大学 空间信息与定位导航上海高校工程研究中心,上海 200241;4.华东师范大学 纳光电集成与先进装备教育部工程研究中心,上海 200241;5.南通智能感知研究院,江苏 南通 226000

作者简介:

通讯作者:

中图分类号:

TN215

基金项目:


A neural networks based method for suspended sediment concentration retrieval from GF-5 hyperspectral images
Author:
Affiliation:

1.Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai 200241, China;2.Beijing Tracking and communication Technology Institute, Beijing 100094, China;3.Engineering Center of SHMEC for Space Information and GNSS, Shanghai 200241, China;4.Engineering Research Center of Nanophotonics & Advanced Instrument, Ministry of Education, East China Normal University, Shanghai 200241, China;5.Nantong Academy of Intelligent Sensing, Nantong 226000, China

Fund Project:

Supported by the National Natural Science Foundation of China (61975056, 61901173), the Shanghai Natural Science Foundation (19ZR1416000), the Science and Technology Commission of Shanghai Municipality (20440713100, 19511120100, 18DZ2270800)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    悬浮泥沙浓度是水体监测中极为重要的指标。本论文基于神经网络具有弥补传统经验算法固有误差的潜力,设计并开发了基于人工神经网络的神经网络校正器来对经验反演结果进行二次校正。为了防止在小数据集的情况下出现过拟合问题,采用了特殊设计的正则化项。基于高分五号高光谱遥感数据以及在长江口和沿海水域同时收集的悬浮泥沙浓度实地测量结果,研究了4种基线经验模型,并评估了使用神经网络校正器后的精度。在每个基线模型上都测试了神经网络校正器模型的两个典型应用,包括基线模型校正和时间校正。在这两种应用中,结果均表明,经校正的D''Sa模型具有最高的准确性。通过使用基线模型校正,均方根误差从0.1495 g/L降低至0.1436 g/L,平均绝对百分比误差从0.7821降低至0.7580,决定系数从0.6805升高至0.6926。实施时间校正后,平均绝对百分比误差从0.8657降低至0.7817,决定系数从0.6688升高至0.7155。最后,基于神经网络校正器校正后精度最高的模型处理了整幅高分五号高光谱图像。本论文结果为各种经验反演算法提供了一种通用的二次校正方法,以最大程度地减少基线模型的固有误差,并且保证了反演精度。

    Abstract:

    The suspended sediment concentration (SSC) is an extremely important property for water monitoring. Since machine learning technology has been successfully applied in many domains, we combined the strengths of empirical algorithms and the artificial neural network (ANN) to further improve remote sensing retrieval results. In this study, the neural network calibrator (NNC) based on ANN was proposed to secondarily correct the empirical coarse results from empirical algorithms and generate fine results. A specialized regularization term has been employed in order to prevent overfitting problem in case of the small dataset. Based on the Gaofen-5 (GF-5) hyperspectral remote sensing data and the concurrently collected SSC field measurements in the Yangtze estuarine and coastal waters, we systematically investigated 4 empirical baseline models and evaluated the improvement of accuracy after the calibration of NNC. Two typical applications of NNC models consisting baseline model calibration and temporal calibration have been tested on each baseline models. In both applications, results showed that the calibrated D’Sa model is of highest accuracy. By employing the baseline model calibration, the root mean square error (RMSE) decreased from 0.1495 g/L to 0.1436 g/L, the mean absolute percentage error (MAPE) decreased from 0.7821 to 0.7580 and the coefficient of determination (R2) increased from 0.6805 to 0.6926. After implementation of the temporal calibration, MAPE decreased from 0.8657 to 0.7817 and R2 increased from 0.6688 to 0.7155. Finally, the entire GF-5 hyperspectral images on target date were processed using the NNC calibrated model with the highest accuracy. Our work provides a universal double calibration method to minimize the inherent errors of the baseline models and a moderate improvement of accuracy can be achieved.

    参考文献
    相似文献
    引证文献
引用本文

刘一鸣,张磊,周梅,梁建,王妍,孙力,李庆利.基于人工神经网络的高分五号高光谱影像悬浮泥沙浓度反演方法[J].红外与毫米波学报,2022,41(1):323~336]. LIU Yi-Ming, ZHANG Lei, ZHOU Mei, LIANG Jian, WANG Yan, SUN Li, LI Qing-Li. A neural networks based method for suspended sediment concentration retrieval from GF-5 hyperspectral images[J]. J. Infrared Millim. Waves,2022,41(1):323~336.]

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-01-18
  • 最后修改日期:2021-09-06
  • 录用日期:2021-06-01
  • 在线发布日期: 2021-09-05
  • 出版日期: