ICESat-2与Sentinel-2数据融合的深度学习浅滩水深测量

doi:10.13474/j.cnki.11-2246.2023.0198

测绘通报 ›› 2023, Vol. 0 ›› Issue (7): 39-43.doi: 10.13474/j.cnki.11-2246.2023.0198

ICESat-2与Sentinel-2数据融合的深度学习浅滩水深测量

钟静¹, 孙杰¹, 赖祖龙¹, 谌一夫²

1. 中国地质大学(武汉)地理与信息工程学院, 湖北武汉 430074;
2. 中国地质大学(武汉)计算机学院, 湖北武汉 430074

收稿日期:2022-11-22 出版日期:2023-07-25 发布日期:2023-08-08
通讯作者: 孙杰。E-mail:jiesun@cug.edu.cn
作者简介:钟静(1997-),女,硕士生,主要研究方向为海洋遥感。E-mail:jingzhong@cug.edu.cn
基金资助:
国家自然科学基金(42171373)

A deep learning method for nearshore bathymetry with ICESat-2 and Sentinel-2 datasets

ZHONG Jing¹, SUN Jie¹, LAI Zulong¹, SHEN Yifu²

1. School of Geography and Information Engineering, China University of Geosciences (Wuhan), Wuhan 430074, China;
2. School of computing, China University of Geosciences (Wuhan), Wuhan 430074, China

Received:2022-11-22 Online:2023-07-25 Published:2023-08-08

摘要/Abstract

摘要： 目前卫星测深(SDB)被广泛应用于近海岸水深测量,然而常用的经验模型较简单,无法适用于各类复杂浅滩环境。为突破传统方法的局限性,本文提出一种ICESat-2与Sentinel-2数据融合的深度学习浅滩水深测量方法。以美国密西西比州猫岛(CI)、巴克岛(BI)为研究区,利用ICESat-2提取先验水深点,再基于Sentinel-2数据训练一维卷积神经网络(1-DCNN)以获取研究区水深图;同时采用波段比值模型(BR)、随机森林(RF)和多层感知器(MLP)作为对比方法进行精度定量分析发现,本文方法在CI、BI测得水深的均方根误差和决定系数分别为0.20 m、0.94和0.95 m、0.95,精度验证优于其他方法,因此该方法提高了水深反演精度。

关键词: 卫星测深, ICESat-2, Sentinel-2, 深度学习, 机器学习

Abstract: Currently, satellite-derived bathymetry (SDB) is widely used for nearshore bathymetry. However, the commonly used empirical models are too simple to be applied to various complex shore environments. To break through the limitations of traditional methods, this paper proposes a deep learning method for nearshore bathymetry with ICESat-2 and Sentinel-2 datasets. Cat Islands (CI) and Buck Island (BI) are used as the study areas. ICESat-2 is used to extract a priori bathymetry points, and then a one dimensional convolutional neural network(1DCNN) is trained on the Sentinel-2 data to obtain a bathymetry map of the study area. band ratio (BR), random forest (RF) and multilayer perceptron (MLP) are also used as comparison methods. Through quantitative analysis of accuracy, the root mean square error and coefficient of determination of water depth measured by the proposed method in CI and BI are 0.20 m, 0.94 and 0.95 m, 0.95, respectively, which verify the accuracy better than other comparative methods and improved the accuracy of water depth inversion.

Key words: satellite-derived bathymetry, ICESat-2, Sentinel-2, deep learning, machine learning

中图分类号:

P237

钟静, 孙杰, 赖祖龙, 谌一夫. ICESat-2与Sentinel-2数据融合的深度学习浅滩水深测量[J]. 测绘通报, 2023, 0(7): 39-43.

ZHONG Jing, SUN Jie, LAI Zulong, SHEN Yifu. A deep learning method for nearshore bathymetry with ICESat-2 and Sentinel-2 datasets[J]. Bulletin of Surveying and Mapping, 2023, 0(7): 39-43.

参考文献

[1] SIMARRO G,CALVETE D,PLOMARITIS T A,et al. The influence of camera calibration on nearshore bathymetry estimation from UAV videos[J]. Remote Sensing,2021,13(1):150.
[2] 彭认灿,董箭,贾帅东,等. 数字水深模型建模技术研究进展与展望[J]. 测绘学报,2022,51(7):1575-1587.
[3] ALBRIGHT A,GLENNIE C. Nearshore bathymetry from fusion of Sentinel-2 and ICESat-2 observations[J]. IEEE Geoscience and Remote Sensing Letters,2021,18(5):900-904.
[4] SU H,LIU H,WANG L,et al. Geographically adaptive inversion model for improving bathymetric retrieval from satellite multispectral imagery[J]. IEEE transactions on Geoscience and Remote Sensing,2013,52(1):465-476.
[5] 赵建虎,欧阳永忠,王爱学. 海底地形测量技术现状及发展趋势[J]. 测绘学报,2017,46(10):1786-1794.
[6] 黄荣永,余克服,王英辉,等. 珊瑚礁遥感研究进展[J]. 遥感学报,2019,23(6):1091-1112.
[7] KANNO A,KOIBUCHI Y,ISOBE M. Statistical combination of spatial interpolation and multispectral remote sensing for shallow water bathymetry[J]. IEEE Geoscience and Remote Sensing Letters,2010,8(1):64-67.
[8] ZHANG X,CHEN Y,LE Y,et al. Nearshore bathymetry based on ICESat-2 and multispectral images:comparison between Sentinel-2,Landsat-8,and Testing Gaofen-2[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2022,15:2449-2462.
[9] KERR J M,PURKIS S. An algorithm for optically-deriving water depth from multispectral imagery in coral reef landscapes in the absence of ground-truth data[J]. Remote Sensing of Environment,2018,210:307-324.
[10] PARRISH C E,MAGRUDER L A,NEUENSCHWANDER A L,et al. Validation of ICESat-2 atlas bathymetry and analysis of ATLAS's bathymetric mapping performance[J]. Remote Sensing,2019,11(14):1634.
[11] MCGILL M,MARKUS T,SCOTT V S,et al. The multiple altimeter beam experimental LiDAR (MABEL):an airborne simulator for the ICESat-2 mission[J]. Journal of Atmospheric and Oceanic Technology,2013,30(2):345-352.
[12] TONION F,PIROTTI F,FAINA G,et al. A machine learning approach to multispectral satellite derived bathymetry[J]. ISPRS Annals of the Photogrammetry,Remote Sensing and Spatial Information Sciences,2020,3:565-570.
[13] 刘瑾璐. 顾及底质类型的光学浅海水深遥感反演研究[D]. 南京:南京信息工程大学,2022.
[14] STUMPF R P,HOLDERIED K,SINCLAIR M. Determination of water depth with high-resolution satellite imagery over variable bottom types[J]. Limnology and Oceanography,2003,48(1):547-556.
[15] PAN Zhigang,GLENNIE C,LEGLEITER C,et al. Estimation of water depths and turbidity from hyperspectral imagery using support vector regression[J]. IEEE Geoscience and Remote Sensing Letters,2015,12(10):2165-2169.
[16] LAI W,LEE Z,WANG J,et al. A portable algorithm to retrieve bottom depth of optically shallow waters from top-of-atmosphere measurements[J]. Journal of Remote Sensing,2022:1-16.
[17] ZHANG Jiashu,KEREKES J,CSATHO B,et al. A clustering approach for detection of ground in micropulse photon-counting LiDAR altimeter data[C]//Proceedings of 2014 IEEE Geoscience and Remote Sensing Symposium. Quebec City,QC,Canada:IEEE,2014:177-180.
[18] LE Zhongping,HU Chuanmin,ARNONE R,et al. Impact of sub-pixel variations on ocean color remote sensing products[J]. Optics Express,2012,20(19):20844-20854.
[19] DUBEY A K,JAIN V. Comparative study of convolution neural network's ReLU and leaky-relu activation functions[M]//Applications of Computing,Automation and Wireless Systems in Electrical Engineering. Singapore:Springer,2019:873-880.

ICESat-2与Sentinel-2数据融合的深度学习浅滩水深测量

A deep learning method for nearshore bathymetry with ICESat-2 and Sentinel-2 datasets

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	胡荣明, 李鑫, 竞霞, 武建强, 魏青博. YOLOv7在探地雷达B-Scan图像解译中的应用[J]. 测绘通报, 2023, 0(8): 29-33.
[2]	周宝定, 谢沛瑶, 郭文浩, 毛庆洲. 基于激光点云灰度图像的隧道渗水病害检测[J]. 测绘通报, 2023, 0(8): 34-39,90.
[3]	欧阳许童, 张璇, 李维庆, 刘娟, 刘卓圣. 基于Sentinel-2和Landsat卫星时序数据的耕地撂荒识别[J]. 测绘通报, 2023, 0(8): 57-62.
[4]	张戬, 高雅. 深度学习遥感影像解译技术在耕地保护中的应用[J]. 测绘通报, 2023, 0(8): 142-145.
[5]	杨盈, 邱芹军, 谢忠, 田苗, 郑诗语, 郑帅. 人在回路学习增强的地理命名实体识别[J]. 测绘通报, 2023, 0(8): 155-160,177.
[6]	李鹏, 周虹利, 林是聪, 王厚杰, 李振洪. 海洋塑料垃圾卫星遥感探测方法[J]. 测绘通报, 2023, 0(6): 20-26.
[7]	刘明月, 郑浩, 陈星彤, 杨晓芜, 宋敬茹, 张永彬, 满卫东. GEE支持下联合植被物候特征与机器学习的入侵植物互花米草提取[J]. 测绘通报, 2023, 0(6): 36-43.
[8]	王冬梅, 吴勇锋, 石一凡, 梁文广, 王轶虹, 潘思远. 利用Sentinel-2遥感影像分析水葫芦时空分布规律[J]. 测绘通报, 2023, 0(6): 44-49.
[9]	奥勇, 李红丽, 张文娟, 秦梦. 基于XGBoost算法的近紫外通道地表反射率模拟[J]. 测绘通报, 2023, 0(6): 68-74,103.
[10]	沈鑫甦, 嵇灵. 面向遥感地类变化检测的U型深度学习神经网络改进方法[J]. 测绘通报, 2023, 0(6): 93-97,103.
[11]	陈桥驿, 闫宇飞, 黄永芳. 融合面向对象和深度置信网络的农村建筑物信息提取[J]. 测绘通报, 2023, 0(6): 134-137.
[12]	王丽梅, 王延正. 基于高分辨率遥感影像的建筑物提取[J]. 测绘通报, 2023, 0(6): 180-183.
[13]	李心媛, 贺智, 楼桉君, 肖曼. 双线性图卷积网络的环南海地区湿地遥感分类[J]. 测绘通报, 2023, 0(5): 44-50.
[14]	王子赫, 康彦彦, 王敏京. ICESat-2与多源光学影像的潮滩地形反演方法[J]. 测绘通报, 2023, 0(5): 51-55,61.
[15]	蔡军, 温日强, 江伟, 严娇, 卢丽娟. 传统村落航拍图像中民族建筑识别的DeepLabV3+改进算法[J]. 测绘通报, 2023, 0(4): 49-53.