Black Soil Organic Matter Content Estimation Using Hybrid Selection Method Based on RF and GABPSO
MA Yue1, JIANG Qi-gang1*, MENG Zhi-guo1, 2, LIU Hua-xin1
1. College of Geo-Exploration Science and Technology, Jilin University, Changchun 130026, China
2. Key Laboratory of Planetary Sciences, Chinese Academy of Sciences, Shanghai 200030, China
Abstract：To solve the problem of high-dimensional variables and characteristic wavelengths selection on soil organic matter content estimation using hyperspectral data, a hybrid feature selection method that combined random forest and self-adaptive searching method was proposed. In this hybrid method, random forest was employed to select spectral variables as the preliminary optimal dataset, which had great importance in the modeling process. The wrapper approach which combined genetic algorithm and binary particle swarm optimization was used as the self-adaptive searching algorithm to further search variables in the preliminary dataset. As for the prediction model, random forest was picked on because of the strong robustness and the excellent performance of dealing with high-dimensional variables. In this paper, the soil samples collected in the typical black soil region were used as the research object, and the Vis-NIR spectral data of the soil obtained from ASD spectrometer and the organic matter content through chemical analysis were used as the data sources. Following reflectance transformation and spectral resampling, the proposed hybrid selection method was employed to extract the characteristic spectral regions that were used as the input data for random forest. The prediction accuracy was compared with the results from random forest algorithm with the spectral datasets which were respectively extracted by no-selected method, only random forest method and only self-adaptive searching method. The results showed that using random forest model with the characteristic wavelengths extracted by proposed method obtained the highest predicted accuracy, in which the R2, RMSE and the RPD were 0.838, 0.54% and 2.534, respectively. Moreover, the proposed method was more efficient to selected features than other approaches. It can be concluded that the hybrid feature selection method and random forest algorithm can be effectively applied to black soil organic matter content estimation using hyperspectral data and it also provides a reference for solving the problem of variables selection and modeling on other types of soil organic matter content estimation.
Key words：Hyperspectral; Black soil organic matter content; Genetic algorithm; Binary particle swarm optimization; Random forest
马 玥，姜琦刚，孟治国，刘骅欣. 基于RF-GABPSO混合选择算法的黑土有机质含量估测研究[J]. 光谱学与光谱分析, 2018, 38(01): 181-187.
MA Yue, JIANG Qi-gang, MENG Zhi-guo, LIU Hua-xin. Black Soil Organic Matter Content Estimation Using Hybrid Selection Method Based on RF and GABPSO. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(01): 181-187.
[1] Ahmed Z, Iqbal J. European Journal of Remote Sensing, 2014, 47(1): 557.
[2] Ma Fei, Du Changwen, Zhou Jianmin. Soil Science Society of America Journal, 2016, 80(1): 238.
[3] JI Wen-jun，SHI Zhou, ZHOU Qing, et al(纪文君, 史 舟, 周 清). Journal of Infrared and Millimeter Waves(红外与毫米波学报), 2012, 31(3): 277.
[4] Wang Junjie, Gui Lijuan, Gao Wenxiu, et al. Geoderma, 2014, 216(4): 1.
[5] Fassnacht F E, Neumann C, Forster M, et al. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6): 2547.
[6] Viscarra Rossel R A, Behrens T. Geoderma, 2010, 158(1-2): 46.
[7] Jin Xiuliang, Du Jia, Liu Huanjun, et al. Agricultural and Forest Meteorology, 2016, 218-219: 250.
[8] Mouazen A M, Kuang B, De Baerdemaeker J, et al. Geoderma, 2010, 158(1-2): 23
[9] YANG Ai-xia, DING Jian-li, LI Yan-hong, et al (杨爱霞, 丁建丽, 李艳红，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(3): 691.
[10] XIAO Yan, JIANG Qi-gang, WANG Bin, et al(肖 艳, 姜琦刚, 王 斌，等). Transactions of the Chinese Society of Agricultural Engineering (农业工程学报), 2016, 32(4): 211.
[11] Rodriguez-Galiano V F, Chica-Olmo M, Abarca-Hernandez F, et al. Remote Sensing of Environment, 2012, 121(138): 93.
[12] Beijma S V, Comber A, Lamb A. Remote Sensing of Environment, 2014, 149: 118.
