基于GEE云平台和Sentinel⁃2数据的普洱市森林覆盖制图

闫明; 庞勇; 何云玲; 蒙诗栎; 魏巍

doi:10.11873/j.issn.1004-0323.2023.2.0432

閬ユ劅鎶�鏈笌搴旂敤鈥衡�� 2023, Vol. 38 鈥衡�� Issue (2): 432-442.DOI: 10.11873/j.issn.1004-0323.2023.2.0432

鈥� 鏋椾笟閬ユ劅涓撴爮鈥� 涓婁竴绡� 涓嬩竴绡�

鍩轰簬GEE浜戝钩鍙板拰Sentinel鈦�2鏁版嵁鐨勬櫘娲卞競妫灄瑕嗙洊鍒跺浘

闂槑¹(),搴炲媷²(),浣曚簯鐜�³,钂欒瘲鏍�²,榄忓穽⁴

^1.浜戝崡澶у鍥介檯娌虫祦涓庣敓鎬佸畨鍏ㄧ爺绌堕櫌锛屼簯鍗� 鏄嗘槑 650500
^2.涓浗鏋椾笟绉戝鐮旂┒闄㈣祫婧愪俊鎭爺绌舵墍锛屽寳浜� 100091
^3.浜戝崡澶у鍦扮悆绉戝瀛﹂櫌锛屼簯鍗� 鏄嗘槑 650500
^4.浜戝崡鐪佹灄涓氬拰鑽夊師绉戝闄紝浜戝崡鏄嗘槑 650204

鏀剁鏃ユ湡:2022-01-10 淇洖鏃ユ湡:2023-02-18 鍑虹増鏃ユ湡:2023-04-20 鍙戝竷鏃ユ湡:2023-05-29
閫氳浣滆��: 搴炲媷
浣滆�呯畝浠�:闂� 鏄庯紙1997-锛夛紝鐢凤紝娌冲崡鍗楅槼浜猴紝纭曞＋鐮旂┒鐢燂紝涓昏浠庝簨鏋椾笟閬ユ劅鍒嗙被鐮旂┒銆侲?mail锛�a18338191276@163.com
鍩洪噾璧勫姪:
鍥介槻绉戝伐灞�楂樺垎涓撻」鈥滄櫘娲遍珮鍒嗛仴鎰熺湡瀹炴�ф楠岀珯椤圭洰鈥�(21?Y30A02?9001?20/22?6);浜氬お妫灄鎭㈠涓庡彲鎸佺画绠＄悊缃戠粶椤圭洰鈥滈潰鍚戝彲鎸佺画缁忚惀鐨勫尯鍩熸．鏋楄娴嬧��(2018P1?CAF)

Remote Sensing based Land Cover Classification of Pu鈥瞖r City Using GEE Cloud Platform and Sentinel-2 Data

Ming YAN¹(),Yong PANG²(),Yunling HE³,Shili MENG²,Wei WEI⁴

^1.Institute of International Rivers and Eco-Security Security锛孻unnan University锛孠unming 650500锛孋hina
^2.Research Institute of Forest Resources Information Techniques锛孋hinese Academy of Forestry锛孊eijing 100091锛孋hina
^3.School of Earth Sciences锛孻unnan University锛孠unming 650500锛孋hina
^4.Yunnan academy of forestry and grassland锛孠unming 650204锛孋hina

Received:2022-01-10 Revised:2023-02-18 Online:2023-04-20 Published:2023-05-29
Contact: Yong PANG

鎽樿/Abstract

鎽樿锛�

蹇�熷噯纭幏鍙栨．鏋楃殑绌洪棿鍒嗗竷瀵硅瘎浼版．鏋楄祫婧愬拰鐢熸�佺幆澧冪姸鍐靛叿鏈夐噸瑕佺殑鎰忎箟銆備互浜戝崡鐪佹櫘娲卞競涓虹爺绌跺尯锛屽熀浜嶨oogle Earth Engine锛圙EE锛夊钩鍙板拰Sentinel-2褰卞儚鏁版嵁锛岀粨鍚堝疄鍦拌皟鏌ユ暟鎹�佹満杞介仴鎰熸暟鎹強鍦板舰杈呭姪鏁版嵁锛屾彁鍙栧奖鍍忕殑鍏夎氨鐗瑰緛銆佺汗鐞嗙壒寰佷互鍙婂湴褰㈢壒寰侊紝閫氳繃鐗瑰緛绛涢�夛紝寰楀埌閫傚悎妫灄鍒嗙被鐨勬渶浼樼壒寰佹暟鎹泦銆傜粨鍚堢畝鍗曠嚎鎬ч潪杩唬鑱氱被锛圫imple Non-Iterative Clustering锛孲NIC锛夎秴鍍忕礌鍒嗗壊绠楁硶锛屾帰绌朵笉鍚屽垎绫绘柟娉曘�佺壒寰佸彉閲忕瓑鍥犵礌瀵瑰垎绫荤簿搴︾殑褰卞搷銆傜粨鏋滆〃鏄庯細闈㈠悜瀵硅薄鍒嗙被鏂规硶鐨勫垎绫荤簿搴﹁浼樹簬鍩轰簬鍍忓厓鍒嗙被鏂规硶锛屽垎绫绘�讳綋绮惧害涓�88.21锛咃紝Kappa绯绘暟涓�0.87锛屽彲浠ヨ緝涓哄噯纭湴瀵规櫘娲卞競杩涜妫灄瑕嗙洊鍒跺浘銆傞潰鍚戝璞℃柟娉曞彲浠ユ湁鏁堝噺杞烩�滄鐩愮幇璞♀�濓紝鐗瑰緛浼橀�夐伩鍏嶄簡鍐椾綑淇℃伅瀵瑰垎绫荤粨鏋滅殑褰卞搷锛屾湁鏁堟彁楂樹簡鍒嗙被鏁堢巼銆侴EE骞冲彴涓庨潰鍚戝璞℃柟娉曠粨鍚堝彲浠ユ彁渚涘ぇ鍖哄煙銆侀珮绮惧害鐨勬．鏋楄鐩栭仴鎰熷揩閫熷埗鍥俱��

鍏抽敭璇�: 妫灄瑕嗙洊, 闈㈠悜瀵硅薄鍒嗙被, 褰卞儚鍒嗗壊, 鐗瑰緛浼橀��

Abstract:

Quick and accurate access to the spatial distribution of forests is of great significance for assessing the status of forest resources and ecological environment protection.Taking Pu'er City in Yunnan Province as the research area锛� Based on the Google Earth Engine 锛圙EE锛� platform and Sentinel-2 image data锛宑ombined with the field survey data锛� airborne remote sensing data and terrain auxiliary data锛� the spectral features锛� texture features and topographic features were extracted. Through feature screening锛� the optimal feature set suitable for forest classification was obtained.Combining Simple Non-Iterative Clustering 锛圫NIC锛� superpixel segmentation algorithmto explore the influence of different classification methods and characteristic variables on the classification accuracy.The results showed that the classification accuracy of the object-oriented classification method was higher than that of the pixel-based classification method锛� with an overall classification accuracy of 88.21% and the Kappa coefficient of 0.87. which can accurately map the forest cover of Pu 'er City. The object-oriented method can effectively alleviate the 鈥渟alt and pepper phenomenon鈥濓紝 and feature optimization avoids the influence of redundant information on classification results and effectively improves classification efficiency. The combination of GEE platform and object-oriented method can provide large-area锛� high-precision forest cover remote sensing rapid mapping.

Key words: Forest cover, Object-oriented classification, Image segmentation, Feature selection

涓浘鍒嗙被鍙�:

P283.8

闂槑,搴炲媷,浣曚簯鐜�,钂欒瘲鏍�,榄忓穽. 鍩轰簬GEE浜戝钩鍙板拰Sentinel鈦�2鏁版嵁鐨勬櫘娲卞競妫灄瑕嗙洊鍒跺浘[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(2): 432-442.

Ming YAN,Yong PANG,Yunling HE,Shili MENG,Wei WEI. Remote Sensing based Land Cover Classification of Pu鈥瞖r City Using GEE Cloud Platform and Sentinel-2 Data[J]. Remote Sensing Technology and Application, 2023, 38(2): 432-442.

鍙傝�冩枃鐚�

1	ROMIJIN E锛� LANTICAN C B锛� HEROLD M锛� et al. Assessing change in national forest monitoring capacities of 99 tropical countries锛籎锛�. Forest Ecology & Management锛� 2015锛� 352锛�109-123. DOI锛� 10.1016/j.foreco.2015.06.003
2	YAN Wei锛� ZHOU Wen锛� YI Lilong锛� et al. Research progress of remote sensing classification and change monitoring on forest types锛籎锛�. Remote Sensing Technology and Application锛� 2019锛� 34锛�3锛夛細445-454.
2	棰滀紵锛� 鍛ㄩ洴锛� 鏄撳埄榫欙紝绛�. 妫灄绫诲瀷閬ユ劅鍒嗙被鍙婂彉鍖栫洃娴嬬爺绌惰繘灞曪蓟J锛�. 閬ユ劅鎶�鏈笌搴旂敤锛� 2019锛� 34锛�03锛夛細445-454.
3	GUO Ruixia. Research on larch plantation recognition based on multi-source Data锛籇锛�.Xi鈥檃n锛歑i鈥檃n University of Science and Technology锛� 2019.
3	閮憺闇�. 鍩轰簬澶氭簮鏁版嵁鐨勮惤鍙舵澗浜哄伐鏋楄瘑鍒爺绌讹蓟D锛�. 瑗垮畨锛氳タ瀹夌鎶�澶у锛� 2019.
4	GISLASON P O锛� BENEDIKTSSON J A锛� SVEINSSON J R. Random forests for land cover classification锛籎锛�. Pattern Recognition Letters锛�2006锛�27锛�294-300. DOI锛�10.1016/j.patrec. 2005.08.011
5	BREIMAN L. Random forests锛籎锛�. Machine Learning锛� 2001锛� 45锛�1锛夛細 5-32. DOI锛� 10.1023/A锛�1010933404324 .
6	REN Chong. Forest types precise classification and forest resources change monitoring based on medium and high spatial resolution remote sensing images锛籇锛�. Beijing锛欳hinese Academy of Forestry锛� 2016.
6	浠诲啿. 涓珮鍒嗚鲸鐜囬仴鎰熷奖鍍忔．鏋楃被鍨嬬簿缁嗗垎绫讳笌妫灄璧勬簮鍙樺寲鐩戞祴鎶�鏈爺绌讹蓟D锛�. 鍖椾含锛氫腑鍥芥灄涓氱瀛︾爺绌堕櫌锛� 2016.
7	IMMITZER M锛� VUOLO F锛� ATZBERGER C. First experience with Sentinel-2 data for crop and tree species classifications in Central Europe锛籎锛�. Remote Sensing锛� 2016锛� 8锛�3锛夛細166. DOI锛�10.3390/rs8030166
8	WANG Q锛� SHI W锛� LI Z锛� et al. Fusion of Sentinel-2 images锛籎锛�. Remote Sensing of Environment锛�2016锛�187锛�241-252. DOI锛� 10.1016/j.rse.2016.10.030
9	PERSSON M锛� LINDBERG E锛� REESE H. Tree species classification with multi-temporal Sentinel-2 data锛籎锛�. Remote Sen-sing锛�2018锛�10锛�11锛夛細1794. DOI锛�10.3390/rs10111794
10	GRABSKA E锛� FRANTZ D锛� OSTAPOWICZ K. Evaluation of machine learning algorithms for forest stand species mapping using Sentinel-2 imagery and environmental data in the polish carpathians锛籎锛�. Remote Sensing of Environment锛�2020锛� 251锛�112103. DOI锛� 10.1016/j.rse.2020.112103
11	YOU H T锛� HUANG Y W锛� QIN Z G锛� et al.Forest Tree Species Classification based on Sentinel-2 images and auxiliary data锛籎锛�. Forests锛�2022锛�13锛�9锛夛細1416. DOI锛�10.3390/F13091416
12	BENZ U C锛� HOFMANN P锛� WILLHAUCK G锛� et al. Multi-resolution锛� object-oriented fuzzy analysis of remote sensing data for GIS-ready Information锛籎锛�. ISPRS Journal of Photogrammetry and Remote Sensing锛� 2004锛� 58锛�3-4锛夛細239-258. DOI锛�10.1016/j.isprsjprs.2003.10.002
13	CHEN J锛� CHEN J锛� LIAO A P锛� et al. Global land cover mapping at 30 m resolution锛� A POK-based operational approach锛籎锛�. ISPRS Journal of Photogrammetry and Remote Sensing锛� 2015锛� 103锛�7-27. DOI锛� 10.1016/j.isprsjprs.2014.09.002
14	WESSEL M锛� BRANDMEIER M锛� TIEDE D. Evaluation of different machine learning algorithms for scalable classification of tree types and tree species based on Sentinel-2 Data锛籎锛�. Remote Sensing锛�2018锛�10锛�9锛夛細1419. DOI锛�10.3390/rs10091419
15	MAO Lijun锛� LI Mingshi. Integrating Sentinel active and passive data to map land cover in a National Park from GEE platform锛籎锛�. Geomatics and Information Science of Wuhan University锛�2023锛�48锛�5锛夛細756-764.
15	姣涗附鍚涳紝鏉庢槑璇�. GEE鐜涓嬭仈鍚� Sentinel涓昏鍔ㄩ仴鎰熸暟鎹殑鍥藉鍏洯鍦熷湴瑕嗙洊鍒嗙被锛籎锛�. 姝︽眽澶у瀛︽姤锛堜俊鎭瀛︾増锛夛紝2023锛�48锛�5锛夛細756-764.
16	VARIN M锛� CHALGHAF B锛� JOANISSE G. Object-based approach using very high spatial resolution 16-band WorldView-3 and LiDAR data for tree species classification in a broadleaf forest in Quebec锛孋anada锛籎锛�.Remote Sensing锛�2020锛� 12锛�3092锛夛細1-33. DOI锛�10.3390/rs12183092
17	GORELICK N锛� HANCHER M锛� DIXON M锛� et al. Google Earth Engine锛� Planetary-scale geospatial analysis for everyone锛籎锛�. Remote Sensing of Environment锛�2017锛�202锛�18-27.DOI锛� 10.1016/j.rse.2017.06.031
18	CALDER ON-LOOR M锛� HADJIKAKOU M锛� BRYAN M A. High-resolution wall-to-wall land-cover mapping and land change assessment for Australia from 1985 to 2015-science direct锛籎锛�. Remote Sensing of Environment锛�2021锛�252锛�112148. DOI锛� 10.1016/j.rse.2020.112148
19	JIA M M锛� WANG Z M锛� MAO D H锛� et al. Rapid锛� robust锛� and automated mapping of tidal flats in China using time series Sentinel-2 images and Google Earth Engine锛籎锛�. Remote Sensing of Environment锛� 2021锛�255锛�1-2锛夛細112285. DOI锛�10.1016/j.rse.2021.112285
20	XUE Zhaohui锛� QIAN Siyu. Fusion of Landsat-8 and Sentinel-2 data for mangrove phenology information extraction and classification锛籎锛�. National Remote Sensing Bulletin锛�2022锛�26锛�6锛夛細1121-1142.
20	钖涙湞杈夛紝閽辨�濈窘.铻嶅悎Landsat 8涓嶴entinel-2鏁版嵁鐨勭孩鏍戞灄鐗╁�欎俊鎭彁鍙栦笌鍒嗙被锛籎锛�.閬ユ劅瀛︽姤锛�2022锛�26锛�6锛夛細1121-1142.
21	LIU Wande锛� SU Jianrong锛� LI Shuaifeng锛宔t al.Variation of non-structural carbohydrates for the dominant species in a monsoon broad-leaved evergreen forest in Pu鈥檈r锛� Yunnan Province锛籎锛�. Scientia Silvae Sinicae锛�2017锛�53锛�6锛夛細1-9.
21	鍒樹竾寰凤紝鑻忓缓鑽ｏ紝鏉庡竻閿嬶紝绛�.浜戝崡鏅幢瀛ｉ甯哥豢闃斿彾鏋椾富瑕佹爲绉嶉潪缁撴瀯鎬х⒊姘村寲鍚堢墿鍙樺紓鍒嗘瀽锛籎锛�. 鏋椾笟绉戝锛�2017锛�53锛�6锛夛細1-9.
22	SU Junwu锛� LIU Yonggang锛� CHEN Qiang锛� et al. Stand structure of pinus kesiya var. langbianensis plantation in Wanzhangshan Forest Farm锛孻unnan Province锛籎锛�.Journal of West China Forestry Science锛� 2021锛� 50锛�3锛夛細8.鑻忎繆姝︼紝鍒樻案鍒氾紝闄堝己锛� 绛�. 浜戝崡涓囨帉灞辨灄鍦烘�濊寘鏉炬灄鍒嗙粨鏋勭壒寰侊蓟J锛�. 瑗块儴鏋椾笟绉戝锛� 2021锛� 50锛�3锛夛細8.
23	XIONG Haoli锛� ZHOU Xiaocheng锛� WANG Xiaoqin锛� et al. Mapping the spatial distribution of tea plantations with 10 m resolution in Fujian Province using Google Earth Engine锛籎锛�. Journal of Geo-information Science锛�2021锛�23锛�7锛夛細1325-1337.
23	鐔婄殦涓斤紝鍛ㄥ皬鎴愶紝姹皬閽︼紝绛�. 鍩轰簬GEE浜戝钩鍙扮殑绂忓缓鐪�10 m鍒嗚鲸鐜囪尪鍥笓棰樼┖闂村垎甯冨埗鍥撅蓟J锛�. 鍦扮悆淇℃伅绉戝瀛︽姤锛� 2021锛� 23锛�7锛夛細1325-1337.
24	FARR T G锛� ROSEN P A锛� CARO E锛� et al. The shuttle radar topography mission锛籎锛�. Reviews of Geophysics锛� 2007锛� 45锛�2锛夛細361.DOI锛� 10.1029/2005RG000183
25	TUCKER C J. Red and photographic infrared linear combinations for monitoring vegetation锛籎锛�. Remote Sensing and Environment锛� 1979锛� 8锛�2锛夛細127-150. DOI锛� 10.1016/0034-4257锛�79锛�90013-0
26	LOPEZ GARCIA M J锛� CASELLES V. Mapping burns and natural reforestation using thematic mapper data锛籎锛�. Geocarto International锛�1991锛�6锛�1锛夛細31-37.DOI锛�10.1080/10106049 109354290
27	RIKIMARU A. Landsat TM data processing guide for forest canopy density mapping and monitoring model锛籆锛解垾 ITTO Workshop on Utilization of Remote Sensing in Site Assessment and Planning for Rehabilitation of Logged- over Forest锛� Bangkok锛� Thailand锛� 1996锛� 8锛�1-8
28	DATT B. A new reflectance index for remote sensing of chlorophyll content in higher plants锛� Tests using eucalyptus leaves锛籎锛�. Journal of Plant Physiology锛�1999锛�154锛�1锛夛細30-36. DOI锛� 10.1016/S0176-1617锛�99锛�80314-9
29	GITELSON A A锛� KAUFMAN Y J锛� MERZLYAK M N. Use of a green channel in remote sensing of global vegetation from EOS-MODIS锛籎锛�. Remote Sensing of Environment锛� 1996锛� 58锛�3锛夛細289-298. DOI锛� 10.1016/S0034-4257锛�96锛�00072-7
30	DEVENTER V锛� WARD A D锛� GOWDA P H锛� et al. Using thematic mapper data to identify contrasting soil plains and tillage practices锛籎锛�. Photogrammetric Engineering & Remote Sensing锛� 1997锛� 63锛�1锛夛細87-93. DOI锛� 10.1117/12.277087
31	HUETE A R. A Soil-adjusted Vegetation Index 锛圫AVI锛夛蓟J锛�. Remote Sensing of Environment锛� 1988锛� 25锛�3锛夛細37-53.
32	CHEN Zhiqiang锛� CHEN Jianfei. Image recognition analysis and mapping of urban land based on NDBI index method锛籎锛�. Journal of Geo-information Science锛� 2006锛� 8锛�2锛夛細137-140.
32	闄堝織寮猴紝闄堝仴椋�.鍩轰簬NDBI鎸囨暟娉曠殑鍩庨晣鐢ㄥ湴褰卞儚璇嗗埆鍒嗘瀽涓庡埗鍥撅蓟J锛�.鍦扮悆淇℃伅绉戝锛�2006锛�8锛�2锛夛細137-140.
33	XU Hanqiu. A study on information extraction of water body with the Modified Normalized Difference Water Index 锛� MNDWI锛夛蓟J锛�. Journal of Remote Sensing锛�2005锛�9锛�5锛夛細589-595.
33	寰愭兜绉�. 鍒╃敤鏀硅繘鐨勫綊涓�鍖栧樊寮傛按浣撴寚鏁帮紙MNDWI锛夋彁鍙栨按浣撲俊鎭殑鐮旂┒锛籎锛�. 閬ユ劅瀛︽姤锛� 2005锛�9锛�5锛夛細589-595.
34	RADOUX J锛� CHOME G锛� JACQUES D C锛� et al. Sentinel-2鈥檚 potential for sub-pixel landscape feature detection锛籎锛�. Remote Sensing锛� 2016锛� 8锛�6锛夛細488. DOI锛�10.3390/rs8060488
35	GITELSON A A锛� MERZLYAK M N. Remote estimation of Chlorophyll content in higher plant leaves锛籎锛�. International Journal of Remote Sensing锛� 1997锛� 18锛�12锛夛細2691-2697.DOI锛� 10.1080/014311697217558
36	ZHANG Lei锛� GONG Zhaoning锛� WANG Qiwei锛� et al. Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images锛籎锛�. Journal of Remote Sensing锛� 23锛�2锛夛細313-326.寮犵锛� 瀹厗瀹侊紝鐜嬪惎涓猴紝绛�. Sentinel-2褰卞儚澶氱壒寰佷紭閫夌殑榛勬渤涓夎娲叉箍鍦颁俊鎭彁鍙栵蓟J锛�. 閬ユ劅瀛︽姤锛� 2019锛� 23锛�2锛夛細313-326.
37	YUAN Xu. Research on image segmentation method based on super-pexel锛籇锛�. Wuhan锛欻uazhong University of Science and Technology锛� 2019.
37	琚佹棴. 鍩轰簬瓒呭儚绱犵殑鍥惧儚鍒嗗壊鏂规硶鐮旂┒锛籇锛�. 姝︽眽锛氬崕涓鎶�澶у锛� 2019.
38	ACHANTA R锛� SUSSTRUNK S. Superpixels and polygons using Simple Non-iterative Clustering锛籆锛解垾 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017锛�4895-4904.
39	HARALICK R M锛� SHANMUGAM K锛� DINSTEIN I. Textural features for image classification锛籎锛�. Studies in Media and Communication锛� 1973锛� SMC-3锛�6锛夛細610-621. DOI锛� 10.1109/TSMC.1973.4309314
40	STROMANN O锛� NASCETTI A锛� YOUSIF O锛� et al. Dimensionality reduction and feature selection for object-based land cover classification based on Sentinel-1 and Sentinel-2 time series using Google Earth Engine锛籎锛�. Remote Sensing锛� 2019锛� 12锛�1锛夛細76. DOI锛�10.3390/rs12010076
41	FOODY G. Assessing the accuracy of remotely sensed data锛� Principles and practices锛籎锛�. The Photogrammetric Record锛� 2010锛�25锛�130锛夛細204-205. DOI锛�10.1111/j.1477-9730. 2010. 00574_2.x
42	JIA Wen锛� PANG Yong锛� YUE Cairong锛� et al. Mountain forest classification based on AISA Eagle II Hyperspectral data锛籎锛�. Forest Inventory and Planning锛� 2015锛� 40锛�1锛夛細9-14.
42	鑽氭枃锛屽簽鍕囷紝宀冲僵鑽ｏ紝绛�. 鍩轰簬AISA Eagle II鏈鸿浇楂樺厜璋辨暟鎹殑鏅幢甯傚北鍖烘．鏋楀垎绫伙蓟J锛�. 鏋椾笟璋冩煡瑙勫垝锛�2015锛�40锛�1锛夛細9-14.
43	LIU Yijun锛� PANG Yong锛� LIAO Shengxi锛� et al. Merged airborne lidar and hyperspectral data for tree species classification in Puer鈥� s Mountainous area锛籎锛�. Forest Research锛� 2016锛� 29锛�3锛夛細407-412.
43	鍒樻�″悰锛� 搴炲媷锛� 寤栧０鐔欙紝绛�. 鏈鸿浇LiDAR鍜岄珮鍏夎氨铻嶅悎瀹炵幇鏅幢灞卞尯鏍戠鍒嗙被锛籎锛�. 鏋椾笟绉戝鐮旂┒锛� 2016锛� 29锛�3锛夛細407-412.
44	WANG M C锛� LI M J锛� WANG F Y锛� et al. Exploring the optimal feature combination of tree species classification by fusing multi-feature and multi-temporal Sentinel-2 data in Changbai Mountain锛籎锛�.Forests锛�2022锛�13锛�7锛�.DOI锛�10.3390/F13071058
45	SMITH G. Hybrid pixel- and object-based approach to habitat condition monitoring锛籎锛�. Verlag Der sterrchischen Akademie Der Wissenschaften锛�2013锛�2013锛�552-555. DOI锛�10.1553/giscience2013s552

[1]	闄堢拹, 鏉庢椇骞�, 閮濆悰鏄�, 鍛ㄥ厗鍙�, 寮犵闇�, 绋嬪皬寮�, 姹瓭璐�. 鍩轰簬Landsat鏁版嵁鐨勯珮瀵掓箍鍦颁俊鎭彁鍙栨柟娉曠爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(3): 708-717.
[2]	鏉ㄥ缓鍗�,钂嬬幉姊�,娼橀噾姊�. 琚姩寰尝閬ユ劅鍙嶆紨闆按褰撻噺涓嶇‘瀹氭�у洜绱犲垎鏋�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(6): 1274-1284.
[3]	璧靛竻,鏇圭編鑺�,钂嬪厛铦�,闄堣��浜�,闄嗙伅鐩�. 瀹夊窘鐪佸埄杈涘幙骞冲師鍖轰汉宸ユ灄鏍戠鍒嗙被鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(3): 589-598.
[4]	鍒樺��,鑳″績闆�,鏉庢檽褰�,瑕冨厛鏋�. 涓�绉嶅儚绱犱笌瀵硅薄鐩哥粨鍚堢殑鏋楀尯寤虹瓚鐗╄瘑鍒柟娉�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2021, 36(6): 1350-1357.
[5]	璺槬鐕�,闆蜂緷鍑�,鑻忛,榛勯洦鑿�,鍒樻槑鏈�,璐炬槑鏄�. 鍩轰簬闈㈠悜瀵硅薄鈥旀繁搴﹀涔犵殑闂戒笢鍗椾綆娴锋嫈娴峰哺甯﹀湴鍖烘箍鍦板姩鎬侀仴鎰熷垎鏋�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2021, 36(4): 713-727.
[6]	鐜嬫櫒涓�,鐜嬫案鍓�,鐜嬪埄鑺�. 鍩轰簬SAR绾圭悊淇℃伅鐨勫啘浣滅墿璇嗗埆鐮旂┒鈥斺�斾互鍐滃畨鍘夸负渚�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2021, 36(2): 372-380.
[7]	椹吘鑰�,鑲栭箯宄�,寮犲鑹�,椹▉,閮噾閲�. 鍩轰簬鐗瑰緛浼橀�夌殑GF-3鍏ㄦ瀬鍖栨暟鎹Н闆瘑鍒�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2020, 35(6): 1292-1302.
[8]	鏉庡己,鍐痉淇�,鐟氭晱鍚�,浼嶇嚉鍨�,鏉ㄥ巻杈�. 闆嗘垚鐗瑰緛鍒嗛噺鐨勯珮鍒嗕簩鍙峰奖鍍忛槾褰辨娴�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(6): 1252-1260.
[9]	鏉庡摬,寮犳瞾闆�,褰亾榛�. 鍩轰簬楂樺垎浜屽彿閬ユ劅褰卞儚鐨勬爲绉嶅垎绫绘柟娉�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(5): 970-982.
[10]	瀹嬪痉濞�,榄忛潚杩�,寮犳壙鏄�,鏉庡嘲,闊╅濞�,鑼冨厠鐞�. 鍒╃敤RefineNet妯″瀷鎻愬彇鍐皬楹︾妞嶄俊鎭殑鏂规硶[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(4): 720-726.
[11]	寰愬嚒, 寮犻洩绾�, 鐭崇帀绔�. 鍩轰簬婵�鍏夐浄杈惧拰鑸媿褰卞儚鐨勫煄甯傚湴鐗╁垎绫荤爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(2): 253-262.
[12]	钁ｇ珛鏂�. 鍩轰簬鐩存柟鍥句笌鍍忓厓鍒嗚В妯″瀷鐨勬．鏋楄鐩栧害閬ユ劅浼扮畻顎�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2019, 34(1): 136-145.
[13]	姹熶笢锛岄檲甯咃紝涓佹柟瀹囷紝浠樻櫠鑾癸紝閮濊挋钂�. 鍩轰簬闈㈠悜瀵硅薄鐨勯仴鎰熷奖鍍忓垎绫荤爺绌�——浠ユ渤鍖楃渷鏌忎埂鍘夸负渚�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2018, 33(1): 143-150.
[14]	鍛ㄦ檽瀹囷紝闄堝瘜榫�. 鍥涘窛澶х唺鐚爾鎭湴PALSAR鏃跺簭鏁版嵁妫灄瑕嗙洊鍔ㄦ�佺洃娴嬬爺绌额�冾��[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2017, 32(6): 1100-1106.
[15]	鐜嬭嫃鑺革紝瀛欎腑鏄讹紝閮崕涓滐紝鐢崇淮顎嬵��. 鍩轰簬闈㈠悜瀵硅薄鐨勪笢钀ュ競鍩庝埂寤鸿鐢ㄥ湴淇℃伅鎻愬彇顎�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2017, 32(4): 780-786.

鍩轰簬GEE浜戝钩鍙板拰Sentinel鈦�2鏁版嵁鐨勬櫘娲卞競妫灄瑕嗙洊鍒跺浘

Remote Sensing based Land Cover Classification of Pu鈥瞖r City Using GEE Cloud Platform and Sentinel-2 Data

RichHTML

PDF (PC)

鍙鍖�

鎽樿/Abstract

寮曠敤鏈枃

浣跨敤鏈枃

鍙傝�冩枃鐚�

鐩稿叧鏂囩珷 15

缂栬緫鎺ㄨ崘

Metrics

鏈枃璇勪环