|
|
|
|
|
|
Forest Stock Volume Estimation Model Using Textural and Topographic Factors of Landsat8 OLI |
YANG Liu1,2, FENG Zhong-ke1*, YUE De-peng1, SUN Jin-hua3 |
1. Beijing Key Laboratory of Precision Forestry, Beijing Forestry University, Beijing 100083, China
2. College of Tourism and Planning, Pingdingshan University, Pingdingshan 467002, China
3. College of Geoscience and Surveying Engineering, China University of Mining and Techology, Beijing 100083, China |
|
|
Abstract Forest stock volume (FSV) is an important factor in the investigation of the forest stand and the main indicator to evaluate forest. The traditional methods of forest stock volume measurement are time-consuming and low efficiency. In remote sensing multiple linear regression method the accuracy is low and it is difficult to achieve accurate forestry requirements. As a self-improvement and automatic method which using lots of training data, machine learning can approach any nonlinear system model to improve prediction accuracy. Take into account spectral factor, texture factor, topographical factors in study area JIUFENG forest. BP-FSV,LSSVM-FSV and RF-FSV multi-spectral forest volume estimation models were established using BP neural network (BP), least squares support vector machine (LSSVM), random forest (RF) method in machine learning. Ground-angle gauge plots measured data, forest resource in subcompartment inventory data for management, forest sub-compartment map, model in conjunction Landsat8 OLI multispectral remote sensing data of sub-forest types were used for forest volume inversion. Programming in Matlab 2014a realization, BP-FSV Model of BP neural network and LSSVM least squares support vector mechanism LSSVM-FSV model were compared and analyzed based on R2 and RMSE. The results showed that: the p value tested between the predicted values from BP-FSV, LSSVM-FSV and RF-FSV model and observed values is less than 0.05. It indicates that there is no significant differences between the predicted and observed values of forest stock volume, It shows that the predicted results with the models are ideal, and it is feasible to predict forest stock volume by the models. The model established can improve the forecasting precision of forest stock volume through inversion combining with image spectral, textural, and terrain factor. RF-FSV model in coniferous forest, broad-leaved forest and mixed forest have shown a strong predictive ability, higher than BP -FSV model, which is above or close to LSSVM-FSV model. the RF-FSV model training and predicting accuracy are the highest among the three models, RF-FSV model in the training phase R2 and RMSE is 0.839 and 13.953 3 in coniferous forest, in broad-leaved forest is 0.924 and 7.634 1, for mixed forest 0.902 and 12.153 9. In the prediction stage R2 and RMSE in coniferous forests is 0.816 and 15.630 1, in broad-leaved forest 0.913 and 4.890 2, in mixed forest 0.865 and 9.344 1, it can provide a new method for forest stock volume prediction with better prospects.
|
Received: 2016-03-13
Accepted: 2016-07-24
|
|
Corresponding Authors:
FENG Zhong-ke
E-mail: fengzhongke@126.com
|
|
[1] ZHANG Chao, PENG Dao-li, TU Yun-yan, et al(张 超,彭道黎,涂云燕,等). Journal of Beijing Forestry University(北京林业大学学报),2013, 35(3): 11.
[2] Abdullahi S, Kugler F, Pretzsch H. Remote Sensing of Environment, 2016, 174: 197.
[3] Thiel C, Schmullius C. Remote Sensing of Environment, 2016, 173: 258.
[4] WANG Yue-ting,ZHANG Xiao-li,YANG Hui-qiao, et al(王月婷,张晓丽,杨慧乔, 等). Journal of Zhejiang A&F University(浙江农林大学学报), 2015, 32(3): 384.
[5] WANG Jia,SONG Shan-yun,LIU Xia, et al(王 佳,宋珊芸,刘 霞, 等). Transactions of the Chinese Society of Agricultural Machinery(农业机械学报), 2014, 45(5): 216.
[6] TU Yun-yan,PENG Dao-li(涂云燕,彭道黎). Journal of Central South Forestry University(中南林业科技大学学报), 2012, 32(3): 49.
[7] LIU Jun,BI Hua-xing,ZHU Peng-lin, et al(刘 俊,毕华兴,朱沛林, 等). Transactions of the Chinese Society of Agricultural Machinery(农业机械学报), 2014, 45(7).
[8] Ziegler A, Koenig I R. Wiley Interdisciplinary Reviews-Data Mining and Knowledge Discovery, 2014, 4(1): 55.
[9] Su C, Ju S, Liu Y, et al. Intelligent Data Analysis, 2015, 19(6): 1409.
[10] Baasch D M, Fischer J W, Hygnstrom S E, et al. Environmental Management, 2010, 46(5): 725.
[11] Yang L, Yang S, Li S, et al. Knowledge-Based Systems, 2015, 79: 80.
[12] LIU Ya-dong,CUI Ri-xian(刘亚东,崔日鲜). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015,35(12): 3480.
[13] XIAO Jin-cheng,OU Wei-xin,FU Hai-yue(肖锦成,欧维新,符海月). Acta Ecologica Sinica(生态学报), 2013(23): 7496.
[14] Li S, Harner E J, Adjeroh D A. BMC Bioinformatics, 2011, 12(450). |
[1] |
LI Sheng-fang1,2, JIA Min-zhi1, DONG Da-ming2,3*. Fast Measurement of Sugar in Fruits Using Near Infrared Spectroscopy Combined with Random Forest Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(06): 1766-1771. |
[2] |
ZHANG Yan-jun, ZHANG Fang-cao, FU Xing-hu*, XU Jin-rui. Raman Spectra Based on QPSO-MLSSVM Algorithm to Detect the Content of Four Components Blent Oil[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(05): 1437-1443. |
[3] |
SUN Tong, LIU Jin, GAN Lan-ping, WU Yi-qing, LIU Mu-hua*. Detection of Dimethoate Content with Laser Induced Breakdown Spectroscopy Combined with LSSVM and Internal Standard Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(04): 1251-1255. |
[4] |
CHEN Xi-ai1,2,3, WU Xue1, ZHANG Song1, WANG Ling1. Study of Plant Growth Regulators Detection Technology Based on Terahertz Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(03): 665-669. |
[5] |
FU Cai-li1, LI Ying1, CHEN Li-fan1, WANG Shao-yun1, WANG Wu2*. Rapid Detection of Lotus Seed Powder Based on Near Infrared Spectrum Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(02): 424-429. |
[6] |
XU Li-peng1, 2, GE Liang-quan1*, DENG Xiao-qin2, CHEN Li2, ZHAO Qiang2, LI Bin2, WANG Liang2. Research of Carborne γ-Ray Energe Spectrum Radiation Dose Rate Based on FFT-BP Network Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(02): 590-594. |
[7] |
LIU Yan-de, XIAO Huai-chun, SUN Xu-dong, WU Ming-ming, YE Ling-yu, HAN Ru-bing, ZHU Dan-ning, HAO Yong. Researching of Non-Destructive Detection for Citrus Greening Based on Confocal Micro-Raman[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(01): 111-116. |
[8] |
MA Yue1, JIANG Qi-gang1*, MENG Zhi-guo1, 2, LIU Hua-xin1. Black Soil Organic Matter Content Estimation Using Hybrid Selection Method Based on RF and GABPSO[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(01): 181-187. |
[9] |
Lü Meng1, HU Ying-tian1, GAO Ya1, WANG Xiao-ping2*. Novel Spectral COD Measurement Method Based on Identification of Water Samples[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(12): 3797-3802. |
[10] |
ZHANG Yan-jun, HE Bao-dan, FU Xing-hu*, XU Jin-rui, ZHOU Kun-peng. Raman Spectra Combined with PSO-LSSVM Algorithm for Detecting the Components in Ternary Blended Edible Oil[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(08): 2440-2445. |
[11] |
LI Yue-sheng1, LU Wei-ye1, ZHAO Jing-bo2, 3, FENG Guo-xing1, WEI Dong-ming2, LU Ji-dong2, 3, YAO Shun-chun2, 3*, LU Zhi-min2, 3. Detection of Caloric Value of Coal Using Laser-Induced Breakdown Spectroscopy Combined with BP Neural Networks[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(08): 2575-2579. |
[12] |
LIU Yan-de,MA Kui-rong, SUN Xu-dong, HAN Ru-bing, ZHU Dan-ning, WU Ming-ming, YE Ling-yu. The Fruits Soluble Solids Content Detection Online Using Universal Mathematical Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(07): 2177-2183. |
[13] |
SONG Kun-lin, ZHANG Chu, PENG Ji-yu, YE Lan-han, LIU Fei*, HE Yong. Determination of Caffeine Content in Coffee Beans Based on Laser Induced Breakdown Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(07): 2199-2204. |
[14] |
JIANG Chun-lei1,2, ZHANG Shu-qing1*, ZHANG Ce3, LI Hua-peng1, DING Xiao-hui1,2 . Modeling and Predicting of MODIS Leaf Area Index Time Series Based on a Hybrid SARIMA and BP Neural Network Method [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(01): 189-193. |
[15] |
ZHANG Yi1, 2, CHEN Guo-qing1, 2*, ZHU Chun1, 2, ZHU Zhuo-wei1, 2, XU Rui-yu1, 2 . Soft Measurement of the Purity of the Synthetic Edible Pigment Powder Using Fluorescence Spectroscopy Combined with SVM [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(12): 3978-3985. |
|
|
|
|