Abstract
Remote sensing shallow water depth inversion is to automatically predict the water depth value of 0–30 m based on the extraction of the significative spectral features. For governments, accurate shallow water depth inversion in real time is crucial to provide important scientific data for shipping safety, marine engineering and military marine. Recent research in machine learning have shown the dominance on shallow water depth inversion. However, previous methods based on machine learning basically stacked the single remote sensing depth pixel and failed to invert the continuous spatial relationship properly. In addition, the precision is limited by the simple structure and insufficient parameter training of classic artificial neural network (ANN). To remedy these issues, we proposed a spatial-aware neural network (SAN-Net) for shallow water depth inversion. The SAN-Net mainly consists of a spatial-aware feature extraction block (SAB) and a fully connected with dropout feature mapping sub-network (FCDN). The SAB consisting of two convolutional pooling operations can capture the spatial features of the neighborhood and improve the feature expression of shallow water depth inversion. The FCDN is constructed to integrate highly abstract features output from the SAB. Finally, the MSE loss with a regularization term is utilized to constrain the training process. Experiment results on the proposed Shallow Water depth Inversion from WorldView-02 in Mischief Reef (SWIW02-MR) dataset demonstrated that the proposed method outperformed several representative machine learning methods.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ai, B., Wen, Z., Wang, Z., et al. (2020). Convolutional neural network to retrieve water depth in marine shallow water area from remote sensing images. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens., 13, 2888–2898. https://doi.org/10.1109/JSTARS.2020.2993731
Allaerts, D., & Meyers, J. (2019). Sensitivity and feedback of wind-farm-induced gravity waves. J Fluid Mechanics, 862, 990–1028. https://doi.org/10.1017/jfm.2018.969
Bai, J., Jiang, H., Li, S., et al. (2019). NHL pathological image classification based on hierarchical local information and GoogLeNet-based representations. BioMed Research International, 2019, 1–13. https://doi.org/10.1155/2019/1065652
Bitonte, R., Livio, F. A., Mazzoli, S., et al. (2021). Frontal accretion vs. foreland plate deformation: Discriminating the style of post-collisional shortening in the Apennines. Journal of Structural Geology, 145(8), 104290. https://doi.org/10.1016/j.jsg.2021.104290
Chandra, B. S., et al. (2019). Robust heartbeat detection from multimodal data via CNN-based generalizable information fusion. IEEE Transactions on Biomedical Engineering, 66(3), 710–717. https://doi.org/10.1109/TBME.2018.2854899
Chen, K. M., Cofer, E. M., Zhou, J., et al. (2019). Selene: a PyTorch-based deep learning library for sequence data. Nature Methods, 16(4), 315. https://doi.org/10.1038/s41592-019-0360-8
Chen, Z., Chen, D., Zhang, Y., et al. (2020). Deep learning for autonomous ship-oriented small ship detection. Safety Science, 130, 104812. https://doi.org/10.1016/j.ssci.2020.104812
Chen, Z. X., & Zheng, G. Z. (2022). A bidirectional context-aware and multi-scale fusion hybrid network for short-term traffic flow prediction. Promet-Traffic & Transportation, 34(3), 407–420. https://doi.org/10.7307/ptt.v34i3.3957
Coffer, M. M., Schaeffer, B. A., Zimmerman, R. C., et al. (2020). Performance across WorldView-2 and RapidEye for reproducible seagrass mapping. Remote Sensing of Environment, 250, 112036. https://doi.org/10.1016/j.rse.2020.112036
Conger, C. L., Hochberg, E. J., Fletcher, C. H., & Atkinson, M. J. (2006). Decorrelating remote sensing color bands from bathymetry in optically shallow waters. IEEE Transactions on Geoscience and Remote Sensing, 44(6), 1655–1660. https://doi.org/10.1109/TGRS.2006.870405
Deng, Y., Zhou, X., Shen, J., et al. (2021). New methods based on back propagation (BP) and radial basis function (RBF) artificial neural networks (ANNs) for predicting the occurrence of haloketones in tap water. Science of the Total Environment, 772(6), 145534. https://doi.org/10.1016/j.scitotenv.2021.145534
Essa, E., Aldesouky, D., Hussein, S. E., et al. (2020). Neuro-fuzzy patch-wise R-CNN for multiple sclerosis segmentation. Medical & Biological Engineering & Computing, 58(5), 2161–2175. https://doi.org/10.1007/s11517-020-02225-6
Eugenio, F., Marcello, J., & Martin, J. (2015). High-resolution maps of bathymetry and benthic habitats in shallow-water environments using multispectral remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 53(7), 3539–3549. https://doi.org/10.1109/TGRS.2014.2377300
Gao, B. C., Montes, M. J., Davis, C. O., et al. (2009). Atmospheric correction algorithms for hyperspectral remote sensing data of land and ocean. Remote Sensing of Environment, 113, S17–S24. https://doi.org/10.1016/j.rse.2007.12.015
Garcia, R. A., Lee, Z., Barnes, B. B., et al. (2020). Benthic classification and IOP retrievals in shallow water environments using MERIS imagery. Remote Sensing of Environment, 249, 112015. https://doi.org/10.1016/j.rse.2020.112015
Guo, D., Niu, Y., & Xie, P. (2019). Speedy and accurate image super-resolution via deeply recursive CNN with skip connection and network in network. IET Image Processing, 13(7), 1201–1209. https://doi.org/10.1049/iet-ipr.2018.5907
Hayakawa, S., & Suzuki, T. (2019). On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces. Neural Networks, 123, 343–361. https://doi.org/10.1016/j.neunet.2019.12.014
Hr, A., Sw, B., Ks, C., et al. (2021). Stable and compact design of Memristive GoogLeNet neural network–ScienceDirect. Neurocomputing, 441, 52–63. https://doi.org/10.1016/j.neucom.2021.01.122
Kanno, A., Tanaka, Y., Shinohara, R., Kurosawa, A., & Sekine, M. (2014). Which spectral bands ofWorldView-2 are useful in remote sensing of water depth? A case study in coral reefs. Marine Geodesy, 37, 283–292. https://doi.org/10.1080/01490419.2014.908794
Koushik, S., & Srinivasa, K. G. (2021). Detection of respiratory diseases from chest X rays using nesterov accelerated adaptive moment estimation. Measurement, 176(4), 109153. https://doi.org/10.1016/j.measurement.2021.109153
Liu, G., Li, S., Song, K., et al. (2021). Remote sensing of CDOM and DOC in alpine lakes across the Qinghai-Tibet Plateau using Sentinel-2A imagery data. Journal of Environmental Management, 286(1), 112231. https://doi.org/10.1016/j.jenvman.2021.112231
Liu, Z. S., & Zhou, Y. (2011). Direct inversion of shallow-water bathymetry from EO-1 hyperspectral remote sensing data. Chinese Optics Letters, 9(6), 060102. https://doi.org/10.3788/COL201109.060102
Moussa, H., Benallal, M. A., Goyet, C., & Lefèvre, N. (2016). Satellite-derived CO2 fugacity in surface seawater of the tropical Atlantic Ocean using a feedforward neural network. International Journal of Remote Sensing, 37(3), 580–598. https://doi.org/10.1080/01431161.2015.1131872
Olson, R. (1996). The kurdish question and chechnya: Turkish And Russian foreign policies since The Gulf War. Middle East Policy, 4(3), 106–118. https://doi.org/10.1111/j.1475-4967.1996.tb00227.x
Poupardin, A., Idier, D., De Michele, M., & Raucoules, D. (2016). Water depth inversion from a single SPOT-5 Dataset. IEEE Transactions on Geoscience and Remote Sensing, 54(4), 2329–2342. https://doi.org/10.1109/TGRS.2015.2499379
Tobler, W. R. (1970). A computer movie simulating urban growth in the Detroit region. Economic Geography, 46, 234–240. https://doi.org/10.2307/143141
Wang, B., Chen, B., Wang, G., et al. (2020). Back propagation (BP) neural network prediction and chaotic characteristics analysis of free falling liquid film fluctuation on corrugated plate wall. Annals of Nuclear Energy, 148(17), 107711. https://doi.org/10.1016/j.anucene.2020.107711
Wei, H. Z., Zhao, Y., Liu, X., et al. (2021). Evolution of paleo-climate and seawater pH from the late Permian to postindustrial periods recorded by boron isotopes and B/Ca in biogenic carbonates. Earth-Science Reviews, 215(3), 103546. https://doi.org/10.1016/j.earscirev.2021.103546
Wu, S., Wang, G., Tang, P., Chen, F., & Shi, L. (2019). Convolution with even-sized kernels and symmetric padding. Advances in Neural Information Processing Systems, 32, 1. https://doi.org/10.48550/arXiv.1903.08385
Xu, D., Zhang, S., Zhang, H., et al. (2021). Convergence of the RMSProp deep learning method with penalty for nonconvex optimization. Neural Networks, 139, 17–23. https://doi.org/10.1016/j.neunet.2021.02.011
Yibeltal, M., Tsunekawa, A., Haregeweyn, N., et al. (2019). Analysis of long-term gully dynamics in different agro-ecology settings. CATENA, 179, 160–174. https://doi.org/10.1016/j.catena.2019.04.013
Yongming, L., et al. (2021). A downscaled bathymetric mapping approach combining multitemporal Landsat-8 and high spatial resolution imagery: Demonstrations from clear to turbid waters. ISPRS Journal of Photogrammetry and Remote Sensing, 180(2021), 65–81. https://doi.org/10.1016/j.isprsjprs.2021.07.015
Zajac, B. K., Scheiper, S., Zehner, R., et al. (2020). Brother-brother or father-son? How a dropout of AmelX may facilitate the elucidation of a familial relationship. International Journal of Legal Medicine, 134(4), 1305–1310. https://doi.org/10.1007/s00414-019-02084-3
Zheng, G. Z., Chen, F., & Shen, Y. L. (2017). Detecting the water depth of the South China Sea reef area from WorldView-2 satellite imagery. Earth Science Informatics, 10(3), 331–337. https://doi.org/10.1007/s12145-017-0299-1
Zheng, G., Hua, W., Qiu, Z., et al. (2020). Detecting water depth from remotely sensed imagery based on ELM and GA-ELM. Journal of the Indian Society of Remote Sensing, 49, 1–11. https://doi.org/10.1007/s12524-020-01270-w
Funding
The research was financially supported by the National Natural Science Foundation of China (Grant Nos. 42130309 and 41972066).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Authors have no conflict of interest to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Guizhou, Z., Zhixing, C., Mengxiao, W. et al. A Spatial-Aware Neural Network for Inversion of Shallow Water Depth from WorldView-02 High-Spectral-Resolution Imagery. J Indian Soc Remote Sens 51, 1923–1936 (2023). https://doi.org/10.1007/s12524-023-01732-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12524-023-01732-x