Extracting the sand dune crest lines from satellite images using U-Net deep convolutional neural network
Received date: 2021-01-25
Revised date: 2021-04-13
Online published: 2021-09-23
The evolution process of dune morphology records the history of near-surface wind conditions and environmental evolution， but its characteristic research has been limited by the inefficient and high cost of extracting large-scale dune crest lines. For this reason， this paper builds a U-Net model based on the deep convolutional neural network for batch and high-precision extraction. In order to obtain the best extraction results， the enhancement technology in data preprocessing， random neurons inactivation， batch normalization and transfer learning technology have been applied to the training and parameters updating， making the prediction accuracy of the model higher. The results show that the model and various strategies used in this paper can efficiently and accurately identify the dune crest lines in remote sensing images. In addition， through the application study of the orientation of the dune crest lines extracted from the trained model， we can find the shift of the dune crest lines orientation has a good correspondence with the change of near-surface wind regime， and it is confirmed that the U-Net model can be effectively used in regional dune orientation analysis.
Boyu Gao , Bo Yang , Deguo Zhang . Extracting the sand dune crest lines from satellite images using U-Net deep convolutional neural network[J]. Journal of Desert Research, 2021 , 41(5) : 21 -32 . DOI: 10.7522/j.issn.1000-694X.2021.00042
| 1 | 朱震达，吴正，刘恕，等.中国沙漠概论［M］.北京：科学出版社，1980：10-65. |
| 2 | 董治宝，吕萍.70年来中国风沙地貌学的发展［J］.地理学报，2020，75（3）：509-528. |
| 3 | Pye K，Tsoar H.Aeolian Sand and Sand Dunes［M］.Berlin，Germany：Springer，2009：25-35. |
| 4 | Wasson R J，Hyde R.Factors determining desert dune type［J］.Nature，1983，304：337-339. |
| 5 | Hunter R E，Richmond B M，Alpha T R.Storm-controlled oblique dunes of the Oregon Coast［J］.Geological Society of America Bulletin，1983，94（12）：1450-1465. |
| 6 | Rubin D M，Hunter R E.Bedform alignment in directionally varying flows［J］.Science，1987，237：276-278. |
| 7 | Werner B T，Kocurek G.Bed-form dynamics：does the tail wag the dog？［J］.Geology，1997，25（9）：771-774. |
| 8 | Fenton L K，Michaels T I，Beyer A R，et al.Inverse maximum gross bedform-normal transport 1：how to determine a dune-constructing wind regime using only imagery［J］.Icarus，2014，230：5-14. |
| 9 | Telfer M W，Fyfe R M，Lewin S.Automated mapping of linear dunefield morphometric parameters from remotely-sensed data［J］.Aeolian Research，2015，19：215-224. |
| 10 | Scuderi L.The fingerprint of linear dunes［J］.Aeolian Research，2019，39：1-12. |
| 11 | 蒋缠文，董治宝，文青.基于MATLAB平台的遥感影像沙丘脊线提取与地貌格局表征参数计算［J］.中国沙漠，2013，33（6）：1636-1642. |
| 12 | LeCun Y，Bengio Y，Hinton G.Deep learning［J］.Nature，2015，521：436-444. |
| 13 | 柳潜.基于深度学习的遥感图像场景分类研究［D］.北京：北京邮电大学，2019. |
| 14 | Ma N，Wang C X，Sun L，et al.Cloud detection based on convolutional neural network using different bands information for Landsat 8 OLI［J］.Journal of Remote Sening & GIS，2019，8（1）：259. |
| 15 | 陈冠宇，安凯，李向.基于卷积神经网络的不良地质体识别与分类［J］.地质科技情报，2016，35（1）：205-211. |
| 16 | 张玉玺，刘洋，张浩然，等.基于深度学习的多属性盐丘自动识别方法［J］.石油地球物理勘探，2020，55（3）：475-483. |
| 17 | 段艳廷，郑晓东，胡莲莲，等.基于3D半密度卷积神经网络的断裂检测［J］.地球物理学进展，2019，34（6）：2256-2261. |
| 18 | Wu X M，Geng Z C，Shi Y Z，et al.Building realistic structure models to train convolutional neural networks for seismic structural interpretation［J］.Geophysics，2019，85（4）：1-48. |
| 19 | Wu X M，Shi Y Z，Fomel S，et al.FaultNet3D：predicting fault probabilities，strikes，and dips with a single convolutional neural network［J］.IEEE Transactions on Geoscience and Remote Sensing，2019，57（11）：1-18. |
| 20 | Zhang Y，Wang G，Li M C，et al.Automated classification analysis of geological structures based on images data and deep learning model［J］.Applied Sciences，2018，8（12）：2493. |
| 21 | Soroush M，Mehrtash A，Khazraee E，et al.Deep learning in archaeological remote sensing：automated qanat detection in the Kurdistan region of Iraq［J］.Remote Sensing，2020，12（3）：500. |
| 22 | Long J，Shelhamer E，Darrell T.Fully convolutional networks for semantic segmentation［EB/OL］.arXiv：1411.4038v2，2014. |
| 23 | Ronneberger O，Fischer P，Brox T.U-Net：convolutional networks for biomedical image segmentation［EB/OL］.arXiv：，2015. |
| 24 | Dolz J，Ayed I B，Desrosiers C.Dense multi-path U-Net for Ischemic Stroke Lesion segmentation in multiple image modalities［EB/OL］.arXiv：，2018. |
| 25 | Li X M，Chen H，Qi X J，et al.H-DenseU-Net：Hybrid densely connected U-Net for Liver and Tumor segmentation from CT volumes［J］.IEEE Transactions on Medical Imaging，2017，37（12）：2663-2674. |
| 26 | Inoue H.Data augmentation by pairing samples for images classification［EB/OL］.arXiv：1801.02929v2，2018. |
| 27 | Ma J.Segmentation Loss Odyssey［EB/OL］.arXiv：，2020. |
| 28 | Roder S.An overview of gradient descent optimization algorithms［EB/OL］.arXiv：1609.04747v2，2016. |
| 29 | Kingma D P，Ba J.Adam：a method for stochastic optimization［EB/OL］.arXiv：1412.6980v9，2014. |
| 30 | Nwankpa C，Ljomah W，Gachagan A，et al.Activation functions：comparison of trends in practice and research for deep learning［EB/OL］.arXiv：，2018. |
| 31 | Loffe S，Szegedy C.Batch normalization：accelerating deep network training by reducing internal covariate shift［EB/OL］.arXiv：1502.03167v3，2015. |
| 32 | Glorot X，Bengio Y.Understanding the difficulty of training deep feedforward neural networks［J］.Journal of Machine Learning Research，2010，9：249-256. |
| 33 | Srivastava N，Hinton G，Krizhevsky A，et al.Dropout：a simple way to prevent neural networks from overfitting［J］.Journal of Machine Learning Research，2014，15：1929-1958. |
| 34 | Tan C Q，Sun F C，Tao K，et al.A survey on deep transfer learning［EB/OL］.arXiv：，2018. |
| 35 | Fryberger S G.Dune forms and wind regimes，a study of global sand seas［J］.United States Geological Survey Professional Paper，1979，1052：137-140. |
| 36 | Gao X，Narteau C，Rozier O，et al.Phase diagrams of dune shape and orientation depending on sand availability［J］.Scientific Reports，2015，5（1）：14677. |
| 37 | Lucas A，Rodriguez S，Narteau C，et al.Growth mechanisms and dune orientation on Titan［J］.Geophysical Research Letters，2015，41（17）：6093-6100. |
| 38 | Courrech du Pont S，Narteau C，Gao X.Two modes for dune orientation［J］.Geology，2014，42（9）：743-746. |
| 39 | 许炯心，李炳元，杨小平，等.中国地貌与第四纪研究的近今进展与未来展望［J］.地理学报，2009，64（11）：1375-1393. |
| 40 | 杨小平，梁鹏，张德国，等.中国东部沙漠/沙地全新世地层序列及其古环境［J］.中国科学：地球科学，2019，49（8）：129-143. |
| 41 | Lancaster N，Kocurek G，Singhvi A K，et al.Late Pleistocene and Holocene dune activity and wind regimes in the western Sahara Desert of Mauritania［J］.Geology，2002，30（11）：991-994. |
/
| 〈 |
|
〉 |