广西师范大学学报（自然科学版） ›› 2026, Vol. 44 ›› Issue (1): 227-236.doi: 10.16088/j.issn.1001-6600.2025012201

• 生态环境科学研究 • 上一篇    

基于地形数据优化随机森林解译的准确度

何文敏1,2,3, 刘宣园1,2,3, 周岐海1,2,3, 张明霞1,2,3*   

  1. 1.珍稀濒危动植物生态和环境保护教育部重点实验室(广西师范大学), 广西 桂林 541006;
    2.广西珍稀濒危动物生态学重点实验室(广西师范大学), 广西 桂林 541006;
    3.崇左白头叶猴野外科学观测研究站, 广西 崇左 532204
  • 收稿日期:2025-01-22 修回日期:2025-04-17 出版日期:2026-01-05 发布日期:2026-01-26
  • 通讯作者: 张明霞(1981—), 女, 云南临沧人, 广西师范大学副教授, 博士。E-mail: zhangnn2003@126.com
  • 基金资助:
    国家自然科学基金(32260329)

Optimizing Accuracy of Random Forest Interpretation Based on Terrain Data

HE Wenmin1,2,3, LIU Xuanyuan1,2,3, ZHOU Qihai1,2,3, ZHANG Mingxia1,2,3 *   

  1. 1. Key Laboratory of Ecology of Rare and Endangered Species and Environmental Protection (Guangxi Normal University), Ministry of Education, Guilin Guangxi 541006, China;
    2. Guangxi Key Laboratory of Rare and Endangered Animal Ecology (Guangxi Normal University), Guilin Guangxi 541006, China;
    3. The Chongzuo White-headed Langur Field Observation and Research Station of Guangxi, Chongzuo Guangxi 532204, China
  • Received:2025-01-22 Revised:2025-04-17 Online:2026-01-05 Published:2026-01-26

PDF (PC)

0

摘要： 土地利用数据可以为很多科研工作提供重要基础,遥感影像作为主要数据来源,广泛应用于土地利用的制图。为了提高遥感影像分类的准确度,往往需要结合多源数据对影像进行解译。广西喀斯特地区地形复杂,近年来大量扩张的人工林与天然林难以区分,给遥感影像的解译带来困难。本文基于随机森林算法,对广西崇左地区的遥感影像进行土地利用分类解译。研究设计2组实验:第1组实验仅使用遥感影像数据进行分类,第2组实验在遥感影像的基础上加入海拔和坡度数据作为辅助变量。实验结果显示,仅使用遥感影像的分类准确度为0.849,而加入海拔和坡度数据后,总体准确度提升至0.961。这一改进提高了天然林、人工林和农田等土地利用类型的区分度,在喀斯特这一类崎岖地貌中尤为实用。本文研究为土地利用监测提供更好的解决方案。

关键词: 喀斯特地貌, 遥感影像解译, 地形因子, 土地利用

Abstract: Land use data can provide important basis for many scientific researches, and remote sensing images are widely used as data source for land use type interpretation. In order to improve the accuracy of remote sensing image classification, it is necessary to involve some other digital information. The terrain in the karst area of Guangxi is complex, together with quick expansion of plantation in recent years, which brings difficulties to the interpretation of remote sensing images. Based on the random forest algorithm, this study conducted land use interpretation of remote sensing images in Chongzuo, Guangxi. Two classification procedures were run: the first one only used remote sensing image data for classification, and altitude and slope data were added in the second procedure. Results show that the classification accuracy of using remote sensing images alone is 0.849, and after adding altitude and slope data, the overall accuracy improved to 0.961. The discrimination among land use types such as natural forests, artificial forests and farmland is largely increased, which is particularly useful in rugged landforms such as karst. This research provides a better solution for land use montoring.

Key words: karst landform, remote sensing image interpretation, terrain factor, land use

中图分类号:  TP18; TP751; P237

[1] HOMER C, HUANG C Q, YANG L M, et al. Development of a 2001 national land-cover database for the United States[J]. Photogrammetric Engineering & Remote Sensing, 2004, 70(7): 829-840. DOI: 10.14358/pers.70.7.829.
[2] FOODY G M. Status of land cover classification accuracy assessment[J]. Remote Sensing of Environment, 2002, 80(1): 185-201. DOI: 10.1016/S0034-4257(01)00295-4.
[3] HANSEN M C, DEFRIES R S, TOWNSHEND J R G, et al. Global land cover classification at 1 km spatial resolution using a classification tree approach[J]. International Journal of Remote Sensing, 2000, 21(6/7): 1331-1364. DOI: 10.1080/014311600210209.
[4] FRIEDL M A, MCIVER D K, HODGES J C F, et al. Global land cover mapping from MODIS: algorithms and early results[J]. Remote Sensing of Environment, 2002, 83(1/2): 287-302. DOI: 10.1016/S0034-4257(02)00078-0.
[5] WULDER M A, WHITE J C, GOWARD S N, et al. Landsat continuity: Issues and opportunities for land cover monitoring[J]. Remote Sensing of Environment, 2008, 112(3): 955-969. DOI: 10.1016/j.rse.2007.07.004.
[6] LOVELAND T R, REED B C, BROWN J F, et al. International journal of remote sensing[J]. Remote Sensing of Environment, 2000, 21(6): 1303-1330. DOI: 10.1080/014311600210191.
[7] ZHU Z, WOODCOCK C E. Continuous change detection and classification of land cover using all available Landsat data[J]. Remote Sensing of Environment, 2014, 144: 152-171. DOI: 10.1016/j.rse.2014.01.011.
[8] 薛洋, 曾庆科, 夏海英, 等. 基于卷积神经网络超分辨率重建的遥感图像融合[J]. 广西师范大学学报(自然科学版), 2018, 36(2): 33-41. DOI: 10.16088/j.issn.1001-6600.2018.02.005.
[9] ZHENG Y, CHENG L L, WANG J Q, et al. Spatial conflict of land use based on “element-pattern-effect”: Logical main lines and coordination paths[J]. Journal of Natural Resources, 2025, 40(2): 316. DOI: 10.31497/zrzyxb.20250203.
[10] BURKHARD B, KROLL F, NEDKOV S, et al. Mapping ecosystem service supply, demand and budgets[J]. Ecological Indicators, 2012, 21: 17-29. DOI: 10.1016/j.ecolind.2011.06.019.
[11] GUIDICI D, CLARK M. One-dimensional convolutional neural network land-cover classification of multi-seasonal hyperspectral imagery in the San francisco bay area, California[J]. Remote Sensing, 2017, 9(6): 629. DOI: 10.3390/rs9060629.
[12] WESSELS K J, REYERS B, VAN JAARSVELD A S, et al. Identification of potential conflict areas between land transformation and biodiversity conservation in north-eastern South Africa[J]. Agriculture, Ecosystems & Environment, 2003, 95(1): 157-178. DOI: 10.1016/S0167-8809(02)00102-0.
[13] JIN S, DEWITZ J, HOMER C, Et al. Completion of the 2006 national land cover database for the conterminous united states[J]. Photogrammetric Engineering & Remote Sensing, 2011, 77(9): 858-864.
[14] 罗艳华, 李平星, 肖伟烨, 等. 土地利用转型的生态环境效应研究进展与展望[J]. 生态科学, 2024, 43(6): 220-231. DOI: 10.14108/j.cnki.1008-8873.2024.06.024.
[15] LI Y, WU H, ZHU L Q, et al. Identification of ecosystem service degradation risks in Zhengzhou based on multi-scenario simulation of land use changes[J]. Journal of Natural Resources, 2025, 40(2): 493. DOI: 10.31497/zrzyxb.20250213.
[16] 黄子豪, 杜华强, 李雪建, 等. 土地利用/覆盖变化及其对森林碳收支影响研究综述[J]. 遥感学报, 2025, 25(1): 49-69. DOI: 10.11834/jrs.20233169.
[17] TOPALOĞLU R H, SERTEL E, MUSAOĞLU N. Assessment of classification accuracies of sentinel-2 and landsat-8 data for land cover/use mapping[J]. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, XLI-B8: 1055-1059. DOI: 10.5194/isprsarchives-xli-b8-1055-2016.
[18] KHATAMI R, MOUNTRAKIS G, STEHMAN S V. A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: General guidelines for practitioners and future research[J]. Remote Sensing of Environment, 2016, 177: 89-100. DOI: 10.1016/j.rse.2016.02.028.
[19] GÓMEZ C, WHITE J C, WULDER M A. Optical remotely sensed time series data for land cover classification: a review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 116: 55-72. DOI: 10.1016/j.isprsjprs.2016.03.008.
[20] DURO D C, FRANKLIN S E, DUBÉ M G. A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery[J]. Remote Sensing of Environment, 2012, 118: 259-272. DOI: 10.1016/j.rse.2011.11.020.
[21] XIA J S, DALLA MURA M, CHANUSSOT J, et al. Random subspace ensembles for hyperspectral image classification with extended morphological attribute profiles[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(9): 4768-4786. DOI: 10.1109/TGRS.2015.2409195.
[22] CHEN Y B, DOU P, YANG X J. Improving land use/cover classification with a multiple classifier system using AdaBoost integration technique[J]. Remote Sensing, 2017, 9(10): 1055. DOI: 10.3390/rs9101055.
[23] LIU S C, DU K C, ZHENG Y J, et al. Remote sensing change detection technology in the Era of artificial intelligence: Inheritance, development and challenges[J]. National Remote Sensing Bulletin, 2023, 27(9): 1975-1987. DOI: 10.11834/jrs.20222199.
[24] 周明. 高精度卫星遥感影像在工程测绘中的应用与挑战[J]. Engineering Technology and Quality Management, 2025, 3(1): 63-65. DOI: 10.61369/ETQM.9091.
[25] 张国宾, 韩如雪, 张健秀. 高分辨率遥感影像解译方法探讨[J]. 科技创新导报, 2018, 15(13): 77-78. DOI: 10.16660/j.cnki.1674-098X.2018.13.077.
[26] 周培诚, 程塨, 姚西文, 等. 高分辨率遥感影像解译中的机器学习范式[J]. 遥感学报, 2021, 25(1): 182-197.
[27] 曹恒硕, 丁宁, 钱建军, 等. 多源高分辨率卫星遥感海岸线数据集[J]. 计算机与数字工程, 2025, 53(1): 202-208. DOI: 10. 3969/j.issn.1672-9722.2025.01.037.
[28] 肖丹, 安裕伦, 熊康宁. 3S技术支持下喀斯特景观解译与格局研究: 以贵州省清镇市为例[C]//现代地理科学与贵州社会经济. 贵州财经学院经济与管理学院, 贵州师范大学地理与生物科学学院, 贵州师范大学中国南方喀斯特研究院, 2009: 87-92.
[29] 金伟, 余著成, 徐全, 等. 1991—2021年江山仙霞岭省级自然保护区土地覆被动态变化遥感监测[J]. 自然保护地, 2024, 4(4): 84-93. DOI: 10.12335/2096-8981.2023120701.
[30] GUAN H Y, LI J, CHAPMAN M, et al. Integration of orthoimagery and lidar data for object-based urban thematic mapping using random forests[J]. International Journal of Remote Sensing, 2013, 34(14): 5166-5186. DOI: 10.1080/01431161.2013.788261.
[31] BELGIU M, DRĂGU L. Random forest in remote sensing: a review of applications and future directions[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 114: 24-31. DOI: 10.1016/j.isprsjprs.2016.01.011.
[32] GISLASON P O, BENEDIKTSSON J A, SVEINSSON J R. Random Forests for land cover classification[J]. Pattern Recognition Letters, 2006, 27(4): 294-300. DOI: 10.1016/j.patrec.2005.08.011.
[33] BRUZZONE L, CONESE C, MASELLI F, et al. Multisource classification of complex rural areas by statistical and neural-network approaches[J]. Photogrammetric Engineering and Remote Sensing, 1997, 63(5): 523-533.
[34] 刘志洋, 尹慧杰, 李明渊, 等. 利用多源遥感数据的中国三大经济带代表区域经济发展分析[J/OL]. 武汉大学学报(信息科学版): 1-17[2025-06-11]. https://doi.org/10.13203/j.whugis20240233.
[35] 潘耀忠, 李强子, 张锦水, 等. 主要农作物面积多维多尺度立体统计遥感调查技术研究进展[J]. 北京师范大学学报(自然科学版), 2025, 61(1): 118-25. DOI: 10.12202/j.0476-0301.2024188.
[36] GAHEGAN M, FLACK J. A Model to support the integration of image understanding techniques within a GIS[J]. Photogrammetric Engineering & Remote Sensing, 1996, 62(5): 483-90. DOI: 0099-1112/96/6205-483$3.00/0.
[37] FAHSI A, TSEGAYE T, TADESSE W, et al. Incorporation of digital elevation models with Landsat-TM data to improve land cover classification accuracy[J]. Forest Ecology and Management, 2000, 128(1/2): 57-64. DOI: 10.1016/S0378-1127(99)00272-8.
[38] 朱星磊, 安裕伦, 黄祖宏, 等. 喀斯特地区遥感影像解译新算法: 支持向量机算法[J]. 中国岩溶, 2011, 30(2): 222-226. DOI: 10.3969/j.issn.1001-4810.2011.02.016.
[39] 赵银军, 曾兰, 何忠, 等. 基于多源遥感影像的喀斯特地貌景观解译及格局研究[J]. 水土保持研究, 2017, 24(4): 158-162. DOI: 10.13869/j.cnki.rswc.2017.04.026.
[40] 刘宣园, 管超毅, 张明霞, 等. 保护区缓解耕地扩张对喀斯特森林景观破碎化的影响研究[J]. 广西师范大学学报(自然科学版), 2023, 41(6): 202-210. DOI: 10.16088/j.issn.1001-6600.2022101701.
[41] 廖超明, 韦媛媛, 唐丹, 等. 喀斯特地区土地利用冲突识别与影响机制[J]. 水土保持研究, 2025, 32(1): 358-367. DOI: 10.13869/j.cnki.rswc.2025.01.028.
[42] 陈知明, 张江, 邱汉清, 等. 基于密集连接的高分辨率遥感图像分类[J]. 广西师范大学学报(自然科学版), 2022, 40(3): 88-94. DOI: 10.16088/j.issn.1001-6600.2021071503.
[43] LI Q, YUE Y M, LIU S Y, et al. Beyond tree cover: Characterizing Southern China’s forests using deep learning[J]. Remote Sensing in Ecology and Conservation, 2023, 9(1): 17-32. DOI: 10.1002/rse2.292.
[44] BREIMAN L. Bagging predictors[J]. Machine Learning, 1996, 24(2): 123-140. DOI: 10.1007/BF00058655.
[45] DIETTERICH T G. An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization[J]. Machine Learning, 2000, 40(2): 139-157. DOI: 10.1023/A:1007607513941.
[46] BREIMAN L. Random Forests[J]. Machine Learning, 2001, 45: 5-32. DOI: 10.1023/A:1010933404324.
[47] RODRIGUEZ-GALIANO V F, GHIMIRE B, ROGAN J, et al. An assessment of the effectiveness of a random forest classifier for land-cover classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 67: 93-104. DOI: 10.1016/j.isprsjprs.2011.11.002.
[48] KAMBHAM S P, BHARATHI D. Deep learning based image fusion applied on landsat-8 archival data using UVCGAN[C] //2023 Innovations in Power and Advanced Computing Technologies (i-PACT). December 8-10, 2023, Kuala Lumpur, Malaysia. IEEE, 2023: 1-6. DOI: 10.1109/i-PACT58649.2023.10434448.
[49] SINGHAL S, JAMES L, G A R V, et al. Cloud detection from AWiFS imagery using deep learning[C]//2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing (MIGARS). January 27-29, 2023, Hyderabad, India. IEEE, 2023: 1-4. DOI: 10.1109/MIGARS57353.2023.10064610.
[50] WU H R, GENG J, JIANG W. Multidomain constrained translation network for change detection in heterogeneous remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5616916. DOI: 10.1109/TGRS.2024.3381196.
[51] KUSSUL N, LAVRENIUK M, SKAKUN S, et al. Deep learning classification of land cover and crop types using remote sensing data[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(5): 778-782. DOI: 10.1109/LGRS.2017.2681128.
[52] THANH NOI P, KAPPAS M. Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using sentinel-2 imagery[J]. Sensors, 2017, 18(1): 18. DOI: 10.3390/s18010018.
[53] 江涛. 遥感影像解译标志库的建立和应用[J]. 地理空间信息, 2010, 8(5): 31-33. DOI: 10.3969/j.issn.1672-4623.2010.05.011.
[1] 张晓瑞, 陈雨, 王振波. 江淮地区城市土地利用演变对景观格局与生态系统服务价值的影响[J]. 广西师范大学学报（自然科学版）, 2026, 44(1): 199-214.
[2] 王军广, 王鹏, 赵志忠, 唐薇, 赵泽阳, 李燕. 海南岛东部地区土地利用方式对土壤有机碳含量的影响[J]. 广西师范大学学报（自然科学版）, 2023, 41(5): 171-179.
[3] 朱婧, 刘鼎, 王珊, 黄祚水, 梁建宏. 土壤养分及其化学计量特征对微生物碳利用效率的影响机制[J]. 广西师范大学学报（自然科学版）, 2022, 40(5): 376-387.
[4] 郜红娟, 韩会庆, 罗绪强, 李金艳, 陈梦玲, 张新鼎. 贵州土地利用变化对淡水生态系统服务的影响[J]. 广西师范大学学报（自然科学版）, 2020, 38(1): 157-163.
[5] 李贤江, 石淑芹, 蔡为民, 曹玉青. 基于CA-Markov模型的天津滨海新区土地利用变化模拟[J]. 广西师范大学学报（自然科学版）, 2018, 36(3): 133-143.
[6] 何东艳, 华璀, 卢远. 漓江流域土地利用生态风险评价[J]. 广西师范大学学报（自然科学版）, 2012, 30(4): 172-178.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 刘晓娟, 林璐, 胡郁葱, 潘雷. 站点周边用地类型对地铁乘车满意度影响研究[J]. 广西师范大学学报（自然科学版）, 2025, 43(6): 1 -12 .
[2] 韩华彬, 高丙朋, 蔡鑫, 孙凯. 基于HO-CNN-BiLSTM-Transformer模型的风机叶片结冰故障诊断[J]. 广西师范大学学报（自然科学版）, 2025, 43(6): 13 -28 .
[3] 陈建国, 梁恩华, 宋学伟, 覃章荣. 基于OCT图像三维重建的人眼房水动力学LBM模拟[J]. 广西师范大学学报（自然科学版）, 2025, 43(6): 29 -41 .
[4] 李好, 何冰. 凹槽结构表面液滴弹跳行为研究[J]. 广西师范大学学报（自然科学版）, 2025, 43(6): 42 -53 .
[5] 田晟, 赵凯龙, 苗佳霖. 基于改进YOLO11n模型的自动驾驶道路交通检测算法研究[J]. 广西师范大学学报（自然科学版）, 2026, 44(1): 1 -9 .
[6] 黄艳国, 肖洁, 吴水清. 基于D2STGNN的双向高效多尺度交通流预测[J]. 广西师范大学学报（自然科学版）, 2026, 44(1): 10 -22 .
[7] 刘志豪, 李自立, 苏珉. 智能通信与无人机结合的YOLOv8电动车骑行者头盔佩戴检测方法[J]. 广西师范大学学报（自然科学版）, 2026, 44(1): 23 -32 .
[8] 张竹露, 李华强, 刘洋, 许立雄. 基于Bi-LSTM特征融合和FT-FSL的非侵入式负荷辨识[J]. 广西师范大学学报（自然科学版）, 2026, 44(1): 33 -44 .
[9] 王涛, 黎远松, 石睿, 陈慧宁, 侯宪庆. MGDE-UNet:轻量化光伏电池缺陷分割模型[J]. 广西师范大学学报（自然科学版）, 2026, 44(1): 45 -55 .
[10] 黄文杰, 罗维平, 陈镇南, 彭志祥, 丁梓豪. 基于YOLO11的轻量化PCB缺陷检测算法研究[J]. 广西师范大学学报（自然科学版）, 2026, 44(1): 56 -67 .
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发