Deep learning of DEM image texture for landform classification in the Shandong area, China

doi:10.1007/s11707-021-0884-y

Front. Earth Sci.

2022, Vol. 16

Issue (2) : 352-367 https://doi.org/10.1007/s11707-021-0884-y

REVIEW ARTICLE

Deep learning of DEM image texture for landform classification in the Shandong area, China

Yuexue XU¹, Hongchun ZHU¹(

), Changyu HU¹, Haiying LIU², Yu CHENG¹

¹. College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao 266590, China
². College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China

Download: PDF(3824 KB)
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Landforms are an important element of natural geographical environment, and textures are the research basis for the spatial differentiation, evolution features, and analysis rules of the landform. Using the regional difference of texture to describe the spatial distribution pattern of macro landform features is helpful to the landform classification and identification. Digital elevation model (DEM) image texture, which gives full expression to texture difference, is key data source to reflect the surface features and landform classification. Following the texture analysis, landform features analysis is assistant to different landforms classification, even in landform boundary. With the increasing accuracy requirement of landform information acquisition in geomorphic thematic mapping, hierarchical landform classification has become the focus and difficulty in research. Recently, the pattern recognition represented by Convolutional Neural Network has made great achievements in landform research, whose multichannel feature fusion structure satisfies the network structure of different landform classification. In this paper, DEM image texture was taken as the data source, and gray level co-occurrence matrix was applied to extract texture measures. Owing to the similarity of similar landform and the difference of different landform in a certain scale, a comprehensive texture factor reflecting landform features was proposed, and the spatial distribution pattern of landform features was systematically analyzed. On this basis, the coupling relationship between texture and landform type was explored. Thus, the deep learning method of Convolutional Neural Network is used to train the texture features, and the second-class landform classification is carried out through softmax. The classification results in small relief and mid-relief low mountains, overall accuracy are 84.35% and 69.95% respectively, while kappa coefficient are 0.72 and 0.40 respectively, were compared to that of traditional unsupervised landform classification results, and the superiority of Convolutional Neural Network classification was verified, it approximately improved 6% in overall accuracy and 0.4 in kappa coefficient.

Keywords DEM image texture comprehensive texture factor texture spatial pattern features Convolutional Neural Network landform classification

Corresponding Author(s): Hongchun ZHU

About author:

Tongcan Cui and Yizhe Hou contributed equally to this work.

Online First Date: 13 July 2021 Issue Date: 26 August 2022

Cite this article:

Yuexue XU,Hongchun ZHU,Changyu HU, et al. Deep learning of DEM image texture for landform classification in the Shandong area, China[J]. Front. Earth Sci., 2022, 16(2): 352-367.

URL:

https://academic.hep.com.cn/fesci/EN/10.1007/s11707-021-0884-y
https://academic.hep.com.cn/fesci/EN/Y2022/V16/I2/352

1	J Ahmed, H Ahmed (2019). Assessing performance of convolutional features for terrain classification using remote sensing data. In: 2019 2nd International Conference on Communication, Computing and Digital systems (C-CODE). IEEE, 2019: 178–183 https://doi.org/DOI: doi:10.1109/C-CODE.2019.8680969
2	K E Arrell, P F Fisher, N J Tate, L Bastin (2007). A fuzzy c-means classification of elevation derivatives to extract the morphometric classification of landforms in Snowdonia, Wales. Comput Geosci, 33(10): 1366–1381 https://doi.org/10.1016/j.cageo.2007.05.005
3	L E Band (1986). Topographic partition of watersheds with digital elevation models. Water Resour Res, 22(1): 15–24 https://doi.org/10.1029/WR022i001p00015
4	S Basu, S Mukhopadhyay, M Karki, R DiBiano, S Ganguly, R Nemani, S Gayaka (2018). Deep neural networks for texture classification––A theoretical analysis. Neural Netw, 97: 173–182 https://doi.org/10.1016/j.neunet.2017.10.001 pmid: 29126070
5	P K Bricher, A Lucieer, J Shaw, A Terauds, D M Bergstrom (2013). Mapping sub-antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling. PLoS One, 8(8): e72093 https://doi.org/10.1371/journal.pone.0072093 pmid: 23940805
6	P Bugnicourt, S Guitet, V F Santos, L Blanc, E D Sotta, N Barbier, P Couteron (2018). Using textural analysis for regional landform and landscape mapping, Eastern Guiana Shield. Geomorphology, 317: 23–44 https://doi.org/10.1016/j.geomorph.2018.03.017
7	N Chen (2020). Spectra method for revealing relations between slope and possible sunshine duration in China. Earth Sci Inform, 13(3): 695–707 https://doi.org/10.1007/s12145-020-00456-7
8	N Chen, G A Tang, D S Guo, C C Chen (2014a). Influence of DEM orientation on the error of slope calculation. Earth Sci Inform, 7(4): 277–285 https://doi.org/10.1007/s12145-014-0154-6
9	W T Chen, X J Li, Y X Wang, G Chen, S W Liu (2014b). Forested landslide detection using LiDAR data and the random forest algorithm: a case study of the Three Gorges, China. Remote Sens Environ, 152: 291–301 https://doi.org/10.1016/j.rse.2014.07.004
10	Y S Chen, L Zhu, P Ghamisi, X P Jia, G Y Li, L Tang (2017). Hyperspectral images classification with Gabor filtering and convolutional neural network. IEEE Geosci Remote Sens Lett, 14(12): 2355–2359 https://doi.org/10.1109/LGRS.2017.2764915
11	W M Cheng, C H Zhou (2014). Methodology on hierarchical classification of multi-scale digital geomorphology. Prog Geogr, 33(1): 23–33
12	R G Congalton (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ, 37(1): 35–46 https://doi.org/10.1016/0034-4257(91)90048-B
13	J De Reu, J Bourgeois, M Bats, A Zwertvaegher, V Gelorini, P De Smedt, W Chu, M Antrop, P De Maeyer, P Finke, M Van Meirvenne, J Verniers, P Crombé (2013). Application of the topographic position index to heterogeneous landscapes. Geomorphology, 186: 39–49 https://doi.org/10.1016/j.geomorph.2012.12.015
14	H Ding, J M Na, X L Huang, G A Tang, K Liu (2018). Stability analysis unit and spatial distribution pattern of the terrain texture in the northern Shaanxi Loess Plateau. J Mt Sci, 15(3): 577–589 https://doi.org/10.1007/s11629-017-4551-4
15	L Drăguţ, T Blaschke (2006). Automated classification of landform elements using object-based image analysis. Geomorphology, 81(3–4): 330–344 https://doi.org/10.1016/j.geomorph.2006.04.013
16	L Du, X You, K Li, L Q Meng, G Cheng, L Y Xiong, G X Wang (2019). Multi-modal deep learning for landform recognition. ISPRS J Photogramm Remote Sens, 158: 63–75 https://doi.org/10.1016/j.isprsjprs.2019.09.018
17	C Eisank, L Drăguţ, T Blaschke (2011). A generic procedure for semantics-oriented landform classification using object-based image analysis. Geomorphometry, 2011: 125–128
18	S E Franklin, O S Ahmed (2017). Object-based wetland characterization using RADARSAT-2 quad-polarimetric SAR data, Landsat-8 OLI imagery, and airborne LiDAR-derived geomorphometric variables. Photogramm Eng Remote Sensing, 83(1): 27–36 https://doi.org/10.14358/PERS.83.1.27
19	J D Fu, G C Zhang, L Wang, N Xia (2018). Geomorphology classification of Shandong Province based on digital elevation model in the 1 Arc-second format of shuttle radar topography mission data. IOP Conf Ser Earth Environ Sci, 108(3): 032025 https://doi.org/10.1088/1755-1315/108/3/032025
20	G Guvenc, A Akyuz, C H Açikel (2011). Health belief model scale for cervical cancer and Pap smear test: psychometric testing. J Adv Nurs, 67(2): 428–437 https://doi.org/10.1111/j.1365-2648.2010.05450.x pmid: 20946564
21	J N Halls, M A Frishman, A D Hawkes (2018). An automated model to classify barrier island geomorphology using lidar data and change analysis (1998–2014). Remote Sens, 10(7): 1109 https://doi.org/10.3390/rs10071109
22	R M Haralick, K Shanmugam, I H Dinstein (1973). Textural features for image classification. IEEE Trans Syst Man Cybern, SMC-3(6): 610–621 https://doi.org/10.1109/TSMC.1973.4309314
23	M N Ikechukwu, E Ebinne, U Idorenyin, N I Raphael (2017). Accuracy assessment and comparative analysis of IDW, spline and kriging in spatial interpolation of landform (Topography): an experimental study. J Geogr Inf Syst, 9(3): 354–371 https://doi.org/10.4236/jgis.2017.93022
24	J Iwahashi, R J Pike (2007). Automated classifications of topography from DEMs by an unsupervised nested-means algorithm and a three-part geometric signature. Geomorphology, 86(3-4): 409–440 https://doi.org/10.1016/j.geomorph.2006.09.012
25	H F Kaiser (1958). The varimax criterion for analytic rotation in factor analysis. Psychometrika, 23(3): 187–200 https://doi.org/10.1007/BF02289233
26	N Kussul, M Lavreniuk, S Skakun, A Shelestov (2017). Deep learning classification of land cover and crop types using remote sensing data. IEEE Geosci Remote Sens Lett, 14(5): 778–782 https://doi.org/10.1109/LGRS.2017.2681128
27	S J Li, L Y Xiong, G A Tang, J Strobl (2020). Deep learning-based approach for landform classification from integrated data sources of digital elevation model and imagery. Geomorphology, 354: 107045 https://doi.org/10.1016/j.geomorph.2020.107045
28	Y Li, Y Zhou, X Lei, P L Li, C X Liang (2019). Simulation of quantitative relationship between positive and negative topographic factors of loess based on catchment unit. J Arid Land Res Env, 33(07): 78–84 (in Chinese) https://doi.org/10.13448/j.cnki.jalre.2019.201
29	K Liu, G A Tang, S Jiang (2013). Research on the classification of terrain texture from DEMs based on BP neural network. Geomorphometry: 1–4
30	E Maggiori, Y Tarabalka, G Charpiat, P Alliez (2017). Convolutional neural networks for large-scale remote-sensing image classification. IEEE Trans Geosci Remote Sens, 55(2): 645–657 https://doi.org/10.1109/TGRS.2016.2612821
31	M K Mao (1993). A study on regional structure of landforms in Shandong Province. Sci Geogr Sin, 13(1): 26–33 https://doi.org/10.13249/j.cnki.sgs.1993.01.002
32	B M Meneses, R Reis, M J Vale, R Saraiva (2015). Land use and land cover changes in Zêzere watershed (Portugal)––water quality implications. Sci Total Environ, 527-528: 439–447 https://doi.org/10.1016/j.scitotenv.2015.04.092 pmid: 25981942
33	M R Mezaal, B Pradhan (2018). An improved algorithm for identifying shallow and deep-seated landslides in dense tropical forest from airborne laser scanning data. Catena, 167: 147–159 https://doi.org/10.1016/j.catena.2018.04.038
34	M Mokarram, G Roshan, S Negahban (2015). Landform classification using topography position index (case study: salt dome of Korsia-Darab plain, Iran). Model Earth Syst Environ, 1(4): 40 https://doi.org/10.1007/s40808-015-0055-9
35	D Napitupulu, J A Kadar, R K Jati (2017). Validity testing of technology acceptance model based on factor analysis approach. Indonesian J Electrical Eng Comput Sci, 5(3): 697–704 https://doi.org/10.11591/ijeecs.v5.i3.pp697-704
36	A Piloyan, M Konečný (2017). Semi-automated classification of landform elements in Armenia based on SRTM DEM using k-means unsupervised classification. Quaest Geogr, 36(1): 93–103 https://doi.org/10.1515/quageo-2017-0007
37	O D A Prima, A Echigo, R Yokoyama, T Yoshida (2006). Supervised landform classification of Northeast Honshu from DEM-derived thematic maps. Geomorphology, 78(3–4): 373–386 https://doi.org/10.1016/j.geomorph.2006.02.005
38	A Puissant, J Hirsch, C Weber (2005). The utility of texture analysis to improve per-pixel classification for high to very high spatial resolution imagery. Int J Remote Sens, 26(4): 733–745 https://doi.org/10.1080/01431160512331316838
39	P Roy Chowdhury, B Deshmukh, A K Goswami, S S Prasad (2011). Neural network based dunal landform mapping from multispectral images using texture features. IEEE J Sel Top Appl Earth Obs Remote Sens, 4(1): 171–184 https://doi.org/10.1109/JSTARS.2010.2062491
40	S S Rwanga, J M Ndambuki (2017). Accuracy assessment of land use/land cover classification using remote sensing and GIS. Int J Geosci, 8(04): 611–622 https://doi.org/10.4236/ijg.2017.84033
41	N Sahu, G P Obireddy, N Kumar, M S S Nagaraju, R A J E E V Srivastava, S K Singhm (2014). Characterization of landforms and land use/land cover in basaltic terrain using IRS-P6 LISS-IV and Cartosat-1 DEM data: a case study. Agropedology (Nagpur), 24(2): 166–178
42	A Sharma (2010). Integrating terrain and vegetation indices for identifying potential soil erosion risk area. Geo Spat Inf Sci, 13(3): 201–209 https://doi.org/10.1007/s11806-010-0342-6
43	B H Shi (2013). Influence of the hydrologic and geomorphic conditions upon the location of settlements in the Jiaodong Peninsula. Huaxia Archaeol, 04: 34–45 https://doi.org/10.16143/j.cnki.1001-9928.2013.04.008
44	S Shumack, P Hesse, W Farebrother (2020). Deep learning for dune pattern mapping with the AW3D30 global surface model. Earth Surf Process Landf, 45(11): 2417–2431 https://doi.org/10.1002/esp.4888
45	M Story, R G Congalton (1986). Accuracy assessment: a user’s perspective. Photogramm Eng Remote Sensing, 52(3): 397–399 https://doi.org/10.1016/0031-0182(86)90068-4
46	G A Tang, X O Song, F Y Li, Y Zhang, L Y Xiong (2015). Slope spectrum critical area and its spatial variation in the loess plateau of China. J Geogr Sci, 25(12): 1452–1466 https://doi.org/10.1007/s11442-015-1245-0
47	T Ungureanu, G O Iancu, M Pintilei, M M Chicoș (2017). Spatial distribution and geochemistry of heavy metals in soils: a case study from the NE area of Vaslui county, Romania. J Geochem Explor, 176: 20–32 https://doi.org/10.1016/j.gexplo.2016.08.012
48	M Volpi, D Tuia, F Bovolo, M Kanevski, L Bruzzone (2013). Supervised change detection in VHR images using contextual information and support vector machines. Int J Appl Earth Obs Geoinf, 20: 77–85 https://doi.org/10.1016/j.jag.2011.10.013
49	C Z Wang, G A Tang, S Yuan, J W Sun, K Liu (2015). A method for identifying the lunar morphology based on texture from DEMs. Journal of Geo-Information Science, 17(1): 45–53 https://doi.org/10.3724/SP.J.1047.2015.00045
50	M Wieczorek, P Migoń (2014). Automatic relief classification versus expert and field based landform classification for the medium-altitude mountain range, the Sudetes, SW Poland. Geomorphology, 206: 133–146 https://doi.org/10.1016/j.geomorph.2013.10.005
51	K Wongsuphasawat, D Smilkov, J Wexler, J Wilson, D Mané, D Fritz, D Krishnan, F B Viégas, M Wattenberg (2018). Visualizing dataflow graphs of deep learning models in tensorflow. IEEE Trans Vis Comput Graph, 24(1): 1–12 https://doi.org/10.1109/TVCG.2017.2744878 pmid: 28866562
52	J X Xu, B Y Li, X P Yang, L P Zhou, C X Shi, S Gao, X M Zheng, K N Xiong, B Q Zhu, Y P Wang, L M Zhou (2009). Recent progress in geomorphology and quaternary geology in China and some perspectives. Acta Geogr Sin, 64(11): 1375–1393
53	R Zhao, W M Cheng, J P Liu, C Dong, R H Yu, H M Yin (2019a). Accurate division of geomorphological types in China. Sci Surv Mapp, 44(06): 248–255 https://doi.org/10.16251/j.cnki.1009-2307.2019.06.037
54	W D Zhao, S S Li, A Li, B Zhang, Y Li (2019b). Hyperspectral images classification with convolutional neural network and textural feature using limited training samples. Remote Sens Lett, 10(5): 449–458 https://doi.org/10.1080/2150704X.2019.1569274
55	W F Zhao, L Y Xiong, H Ding, G A Tang (2017). Automatic recognition of loess landforms using Random Forest method. J Mt Sci, 14(5): 885–897 https://doi.org/10.1007/s11629-016-4320-9
56	H Zhi, J Siwabessy, S L Nichol, B P Brooke (2014). Predictive mapping of seabed substrata using high-resolution multibeam sonar data: a case study from a shelf with complex geomorphology. Mar Geol, 357: 37–52 https://doi.org/10.1016/j.margeo.2014.07.012
57	C H Zhou, W M Cheng, J K Qian, B Y Li, B P Zhang (2009). Research on the classification system of digital land geomorphology of 1:1000000 in China. J Geo-Infor Sci, 11(06): 707–724 https://doi.org/10.3724/SP.J.1047.2009.00707
58	H C Zhu, Y X Xu, Y Cheng, H Y Liu, Y P Zhao (2019). Landform classification based on optimal texture feature extraction from DEM data in Shandong Hilly Area, China. Front Earth Sci, 13(3): 641–655 https://doi.org/10.1007/s11707-019-0751-2
59	H C Zhu, Y P Zhao, H Y Liu (2018a). Scale characters analysis for gully structure in the watersheds of loess landforms based on digital elevation models. Front Earth Sci, 12(2): 431–443 https://doi.org/10.1007/s11707-018-0696-x
60	H C Zhu, Y P Zhao, Y X Xu, H Y Liu (2018b). Hierarchy structure characteristics analysis for the China Loess watersheds based on gully node calibration. J Mt Sci, 15(12): 2637–2650 https://doi.org/10.1007/s11629-018-5000-8

[1]	Hongchun ZHU, Yuexue XU, Yu CHENG, Haiying LIU, Yipeng ZHAO. Landform classification based on optimal texture feature extraction from DEM data in Shandong Hilly Area, China[J]. Front. Earth Sci., 2019, 13(3): 641-655.

Viewed

Full text

Abstract

Cited

Shared

Discussed