收稿：2017-05-19，
录用：2017-10-31，
纸质出版：2019-01
移动端阅览
竹林是中国亚热带地区特殊而重要的森林资源，现有方法难以实现全国范围竹林时空分布信息快速准确提取。针对此问题，本研究利用2003年、2008年、2014年MODIS NDVI、反射率产品数据和省域Landsat分类数据，提出了基于决策树结合混合像元分解的全国竹林信息提取方法。首先，通过最大似然法获取中国林地分布信息；然后，在林地信息的基础上，构建决策树模型提取中国竹林分布信息；最后，采用线性最小二乘法混合像元分解得到中国竹林丰度图，并计算竹林面积。研究结果表明：(1)最大似然法提取的3个时期中国林地信息的生产者与用户精度均在90%以上，Kappa系数均值为0.93，为竹林信息提取奠定了基础。(2)C5.0算法构建的决策树模型能够很好的提取中国竹林时空分布信息，3个时期竹林分类精度均在80%左右。(3)在混合像元分解的基础上，统计得到的全国各省竹林估算面积与清查面积具有较高的相关性，
R
2
分别为0.98、0.97和0.95，RMSE范围为3.92万—9.58万ha，说明估算得到全国竹林面积与实际情况较为吻合。本研究所提出基于MODIS遥感数据运用C5.0算法决策树结合混合像元分解的方法，实现了全国竹林时空分布信息的准确提取，为全国竹林资源信息动态监测及管理提供了技术手段和数据支撑。
A bamboo forest is a special and important forest resource that is distributed in subtropics of China. However
present methods cannot quickly and accurately extract spatiotemporal distribution information of a bamboo forest at the national scale. This study presents a method for extracting bamboo forest information in China by combining decision tree and linear spectral unmixing methods using MODIS NDVI
reflectance product
and provincial Landsat classification data in 2003
2008
and 2014. The steps are as follows: First
forest information was extracted based on the maximum likelihood method; second
a decision tree model was constructed to extract bamboo forest distribution information based on a forest information map; finally
the linear spectral unmixing method was applied to obtain the abundance map of a bamboo forest in China
and the bamboo forest area was calculated. The main experimental results are as follows: (1) The forest information in China was extracted through the maximum likelihood method. The accuracy of a producer and a user was higher than 90%
and the Kappa coefficient was 0.93
thereby establishing the extraction of bamboo forest information. (2) The decision tree constructed by using a C5.0 algorithm satisfactorily extracted the bamboo forest spatiotemporal distribution information in China
with an average classification accuracy of 80%. (3) The estimated bamboo forest area of each province in China was highly correlated with the observations
with the
R
2
values of 0.98
0.97
and 0.95
correspondingly. The RMSE ranged from 3.92×10
4
to 9.58×10
4
ha
thus indicating that the estimated bamboo forest area was essentially consistent with the actual situation. In this study
the C5.0 algorithm decision tree
which is based on the MODIS remote sensing data
combined with the mixed pixel decomposition presents accurate extraction of bamboo forest spatiotemporal distribution information in China. This method provides the technical approach and data support for the dynamic monitoring and management of bamboo forest resources.
Adams J B, Sabol D E, Kapos V, Almeida Filho R, Roberts D A, Smith M O and Gillespie A R. 1995. Classification of multispectral images based on fractions of endmembers: application to land-cover change in the Brazilian Amazon. Remote Sensing of Environment, 52(2): 137–154
Chao C M, Yu Y W, Cheng B W and Kuo Y L. 2014. Construction the model on the breast cancer survival analysis use support vector machine, logistic regression and decision tree. Journal of Medical Systems, 38(10): 106
杜华强, 周国模, 葛宏立, 赵宪文, 崔林丽. 2008. 基于TM数据提取竹林遥感信息的方法. 东北林业大学学报, 36(3): 35–38
Du H Q, Zhou G M, Ge H L, Zhao X W and Cui L L. 2008. Bamboo information extraction based on Landsat TM data. Journal of Northeast Forestry University, 36(3): 35–38 (
Duan H J, Deng Z D, Deng F F and Wang D Q. 2016. Assessment of groundwater potential based on multicriteria decision making model and decision tree algorithms. Mathematical Problems in Engineering, 2016: 2064575
范渭亮, 杜华强, 周国模, 徐小军, 崔瑞蕊, 董德进. 2010. 模拟真实场景的混合像元分解. 遥感学报, 14(6): 1250–1265
Fan W L, Du H Q, Zhou G M, Xu X J, Cui R R and Dong D J. 2010. Spectral mixture analysis method based on the simulation of real scenario. Journal of Remote Sensing, 14(6): 1250–1265 (
高国龙, 杜华强, 韩凝, 徐小军, 孙少波, 李雪建. 2016. 基于特征优选的面向对象毛竹林分布信息提取. 林业科学, 52(9): 77–85
Gao G L, Du H Q, Han N, Xu X J, Sun S B and Li X J. 2016. Mapping of Moso bamboo forest using object-based approach based on the optimal features. Scientia Silvae Sinicae, 52(9): 77–85 (
Griffiths P, Kuemmerle T, Baumann M, Radeloff V C, Abrudan I V, Lieskovsky J, Munteanu C, Ostapowicz K and Hostert P. 2014. Forest disturbances, forest recovery, and changes in forest types across the Carpathian ecoregion from 1985 to 2010 based on Landsat image composites. Remote Sensing of Environment, 151: 72–88
Han N, Du H Q, Zhou G M, Sun X Y, Ge H L and Xu X J. 2014. Object-based classification using SPOT-5 imagery for Moso bamboo forest mapping. International Journal of Remote Sensing, 35(3): 1126–1142
Han N, Du H Q, Zhou G M, Xu X J, Ge H L, Liu L J, Gao G L and Sun S B. 2015. Exploring the synergistic use of multi-scale image object metrics for land-use/land-cover mapping using an object-based approach. International Journal of Remote Sensing, 36(13): 3544–3562
Klein I, Gessner U and Kuenzer C. 2012. Regional land cover mapping and change detection in Central Asia using MODIS time-series. Applied Geography, 35(1/2): 219–234
李俊祥, 达良俊, 王玉洁, 宋永昌. 2005. 基于NOAA-AVHRR数据的中国东部地区植被遥感分类研究. 植物生态学报, 29(3): 436–443
Li J X, Da L J, Wang Y J and Song Y C. 2005. Vegetation classification of east China using multi-temporal NOAA-AVHRR data. Acta Phytoecologica Sinica, 29(3): 436–443 (
Li M N, Li C C, Jiang H, Fang C Y, Yang J, Zhu Z L, Shi L, Liu S R and Gong P. 2016. Tracking bamboo dynamics in Zhejiang, China, using time-series of Landsat data from 1990 to 2014. International Journal of Remote Sensing, 37(7): 1714–1729
李明诗, 彭世揆, 周林, 马以秀. 2006. 基于ASTER数据的决策树自动构建及分类研究. 国土资源遥感, 18(3): 33–36
Li M S, Peng S K, Zhou L and Ma Y X. 2006. A study of automated construction and classification of decision tree classifiers based on aster remotely sensed datasets. Remote Sensing for Land and Resources, 18(3): 33–36 (
Lu M, Pebesma E, Sanchez A and Verbesselt J. 2016. Spatio-temporal change detection from multidimensional arrays: detecting deforestation from MODIS time series. ISPRS Journal of Photogrammetry and Remote Sensing, 117: 227–236
乔艳雯, 臧淑英, 那晓东. 2013. 基于决策树方法的淡水沼泽湿地信息提取——以扎龙湿地为例. 中国农学通报, 29(8): 169–174
Qiao Y W, Zang S Y and Na X D. 2013. The information extraction of freshwater marsh wetland based on the decision tree method: taking Zhalong wetland as an example. Chinese Agricultural Science Bulletin, 29(8): 169–174 (
Quinlan J R. 1993. C4.5: Programs for Machine Learning. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.
Shang Z Z, Zhou G M, Du H Q, Xu X J, Shi Y J, Lü Y L, Zhou Y F and Gu C Y. 2013. Moso bamboo forest extraction and aboveground carbon storage estimation based on multi-source remotely sensed images. International Journal of Remote Sensing, 34(15): 5351–5368
Stagakis S, Vanikiotis T and Sykioti O. 2016. Estimating forest species abundance through linear unmixing of CHRIS/PROBA imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 119: 79–89
孙少波. 2016. 亚热带典型森林冠层参数及碳储量定量估算研究. 杭州: 浙江农林大学
Sun S B. 2016. Retrieval of Canopy Parameters and Estimation of Aboveground Carbon Storage for Typical Types of Subtropical Forest Using Remote Sensing data. Hangzhou: Zhejiang A&F University
孙晓艳. 2014. 面向对象的毛竹林分布遥感信息提取及调查因子估算. 杭州: 浙江农林大学
Sun X Y. 2014. Object-Based Extraction of Moso Bamboo Forest and Estimation of Moso Bamboo Inventory Factors. Hangzhou: Zhejiang A&F University
孙晓艳, 杜华强, 韩凝, 葛宏立, 谷成燕. 2013. 面向对象多尺度分割的SPOT 5影像毛竹林专题信息提取. 林业科学, 49(10): 80–87
Sun X Y, Du H Q, Han N, Ge H L and Gu C Y. 2013. Multi-scale segmentation, object-based extraction of moso bamboo forest from SPOT5 imagery. Scientia Silvae Sinicae, 49(10): 80–87 (
Ture M, Tokatli F and Kurt I. 2009. Using Kaplan–Meier analysis together with decision tree methods (C&RT, CHAID, QUEST, C4.5 and ID3) in determining recurrence-free survival of breast cancer patients. Expert Systems with Applications, 36(2): 2017–2026
王聪, 杜华强, 周国模, 徐小军, 孙少波, 高国龙. 2015. 基于几何光学模型的毛竹林郁闭度无人机遥感定量反演. 应用生态学报, 26(5): 1501–1509
Wang C, Du H Q, Zhou G M, Xu X J, Sun S B and Gao G L. 2015. Retrieval of crown closure of moso bamboo forest using unmanned aerial vehicle (UAV) remotely sensed imagery based on geometric-optical model. Chinese Journal of Applied Ecology, 26(5): 1501–1509 (
徐小军, 杜华强, 周国模, 董德进, 范渭亮, 崔瑞蕊. 2011. Erf-BP混合像元分解及在森林遥感信息提取中应用. 林业科学, 47(2): 30–38
Xu X J, Du H Q, Zhou G M, Dong D J, Fan W L and Cui R R. 2011. Spectral mixture analysis based on Erf-BP model and applied in extracting forest information. Scientia Silvae Sinicae, 47(2): 30–38 (
颜梅春, 张友静, 鲍艳松. 2004. 基于灰度共生矩阵法的IKONOS影像中竹林信息提取. 遥感信息, 15(2): 31–34
Yan M C, Zhang Y J and Bao Y S. 2004. Deriving bamboos from IKONOS image by texture information. Remote Sensing Information, 15(2): 31–34 (
Yang G, Shen H F, Zhang L P, He Z Y and Li X H. 2015. A moving weighted harmonic analysis method for reconstructing high-quality SPOT vegetation NDVI time-series data. IEEE Transactions on Geoscience and Remote Sensing, 53(11): 6008–6021
赵英时. 2013. 遥感应用分析原理与方法. 2版. 北京: 科学出版社
Zhao Y S. 2013. Analysis Principle and Method of Remote Sensing Applications. 2nd ed. Beijing: Science Press
周国模, 姜培坤, 杜华强, 施拥军. 2017. 竹林生态系统碳汇计测与增汇技术. 北京: 科学出版社
Zhou G M, Jiang P K, Du H Q and Shi Y J. 2017. Technology for the Measurement and Enhancement of Carbon Sinks in Bamboo Forest Ecosystems. Beijing: Science Press
相关作者
相关机构
京公网安备11010802024621
