|
|
|
|
|
|
Horizon Classification in Soil Profile Using Imaging Spectroscopy |
ZHENG Guang-hui1,2, JIAO Cai-xia2, SHANGGUAN Chen-xi2, WU Wen-qian2, LIU Yi3, HONG Chang-qiao2,4 |
1. Collaborative Innovation Center on Forecast and Evaluation of Meteologicla Disasters (CIC-FEMD), Nanjing University of Information Science & Technology, Nanjing 210044, China
2. School of Geographic Sciences, Nanjing University of Information Science & Technology, Nanjing 210044, China
3. School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China
4. School of Geographic and Oceanographic Sciences, Nanjing University, Nanjing 210023,China |
|
|
Abstract The soil profile is one of the core topics in pedogenesis research, but traditional pedological observations of soil profiles rely on the use of visible light and a toolbox that has not changed in the past decades. The imaging spectroscopy can provide high-resolution spatial and spectral soil profile information, which gives continuous depth functions of soil properties and compensates for the large gap between the sampling depths of reflectance spectroscopy. The objective of this study is to analyze the classification of soil horizon in a profile by investigating the spectral data of imaging spectroscopy collected in the laboratory. The support vector machine (SVM) method was used to classify the spectral data, and the feasibility and influence factors of the imaging spectroscopy for classification were studied. Firstly, the morphological characteristics of the average spectral curves of each horizon in sample profile were analyzed qualitatively. Secondly, depth dynamic and scatter plot of principal components were qualitatively analyzed to explain the feasibility of horizon classification using profile imaging spectroscopy. Finally, One thousand times computations were carried out to reduce the classification error by partitioning random dataset and building prediction model. The prediction results can quantificationally testify the feasibility and the influence factors were discussed by the percentage of wrong classification in prediction results. The results indicated that the four average spectral curves in sample profile differed and reflected the variation in depth derived from pedogenic processes. The principal components of the imaging spectral data showed the continuous change in the depth direction of the soil profile and the grouping feature in scatter plot, which proved that imaging spectroscopy reflected the difference between the genetic horizons and can be used for the horizon classification. The average accuracy of classification prediction reached 93.08%. Moreover, it was found that the sample with similar scattering distribution and locating transition region were classified in wrong classes easily. This study provides a theoretical basis for horizon classification, and proves that imaging spectroscopy is a potential technology for mapping soil profile.
|
Received: 2018-01-09
Accepted: 2018-05-22
|
|
|
[1] Hartemink A E, Minasny B. Geoderma, 2014, 230-231: 305.
[2] Viscarra Rossel R A, Brus D J, Lobsey C, et al. Geoderma, 2016, 265: 152.
[3] Stockmann U, Minasny B, McBratney A B. Geoderma, 2014, 216: 48.
[4] Demattê J A M, Terra F D S. Geoderma, 2014, 217-218: 190.
[5] Fajardo M, McBratney A, Whelan B. Geoderma, 2016, 263: 244.
[6] Weindorf D C, Zhu Y, McDaniel P, et al. Geoderma, 2012, 189-190: 268.
[7] Gomez C, Oltra-Carrió R, Bacha S, et al. Remote Sens. Environ., 2015, 164: 1.
[8] Franceschini M H D, Demattê J A M, Terra F D S, et al. Int. J. Appl. Earth Obs. and Geoinformation, 2015, 38: 358.
[9] Steffens M, Buddenbaum H. Geoderma, 2013, 195-196: 122.
[10] LI Shuo, WANG Shan-qin, SHI Zhou(李 硕, 汪善勤, 史 舟). Acta Pedol. Sin.(土壤学报), 2015, 52(5): 1014.
[11] Zheng Guanghui, RYU Dongryeol, Jiao Caixia, et al. Pedosphere, 2016, 26(1): 130.
[12] HONG Chang-qiao, ZHENG Guang-hui, CHEN Chang-chun(洪长桥, 郑光辉, 陈昌春). Acta Pedol. Sin.(土壤学报), 2016, 53(5): 1120. |
[1] |
LI Xin-quan1, 2,ZHANG Jun-qiang1, 3*,WU Cong-jun1,MA Jian1, 2,LU Tian-jiao1, 2,YANG Bin3. Optical Design of Airborne Large Field of View Wide Band Polarization Spectral Imaging System Based on PSIM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 250-257. |
[2] |
QI Chen, YU Tao*, ZHANG Zhou-feng, ZHONG Jing-jing, LIU Yu-yang, WANG Xue-ji, HU Bing-liang. Design and Research of a Compact Polarization Spectral Imaging Method Based on Double Gaussian[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(07): 2082-2089. |
[3] |
LI Hu1, 2, 3, LIU Xue-feng1, 3*, YAO Xu-ri4, 5*, ZHAI Guang-jie1, 3. Block Compressed Sensing Computed-Tomography Imaging Spectrometry[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(02): 348-355. |
[4] |
XU Lu1, CHEN Yi-yun1, 2, 3*, HONG Yong-sheng1, WEI Yu1, GUO Long4, Marc Linderman5. Estimation of Soil Organic Carbon Content by Imaging Spectroscopy With Soil Roughness[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2788-2794. |
[5] |
GUO Wei1, QIAO Hong-bo1, ZHAO Heng-qian2,3*, ZHANG Juan-juan1, PEI Peng-cheng1, LIU Ze-long2,3. Cotton Aphid Damage Monitoring Using UAV Hyperspectral Data Based on Derivative of Ratio Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(05): 1543-1550. |
[6] |
CAO Xiao-feng1, 2, 3, YU Ke-qiang1, 2, 3, ZHAO Yan-ru1, 2, 3*, ZHANG Hai-hui1, 2, 3*. Current Status of High-Throughput Plant Phenotyping for Abiotic Stress by Imaging Spectroscopy: A REVIEW[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(11): 3365-3372. |
[7] |
JIAO Cai-xia1, ZHENG Guang-hui1*, XIE Xian-li2, CUI Xue-feng3, SHANG Gang1. Prediction of Soil Organic Matter Using Visible-Short Near-Infrared Imaging Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(10): 3277-3281. |
[8] |
LI Ming, QIN Kai*, ZHAO Ning-bo, TIAN Feng, ZHAO Ying-jun. Study on the Relationship Between Black Soil Emissivity Spectrum and Total Potassium Content Based on TASI Thermal Infrared Data[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(09): 2862-2868. |
[9] |
LIU Jia-nan1, 2*, CUI Ji-cheng1, YIN Lu1, 2, SUN Ci1, CHEN Jian-jun1, 2, ZHANG Rui1, 2, LIU Jian-li1, 2. Analysis and Design of Pre-Imaging System of Integral Field Imaging Spectrometer Based on Lenslet Array[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(10): 3269-3272. |
[10] |
ZHAO Shou-jiang1, YANG Bin1, JIAO Jian-nan2, YANG Peng1, WU Tai-xia3*, WANG Xue-qi1, YAN Lei1*. Using a Polarization Method to Reduce the Vegetation Inversion Error Caused by Strong or Weak Reflection Intensity[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(10): 3315-3320. |
[11] |
HAO Li-hua1,2, LU Xiao-dong2, WANG Ming-quan1,2. Research on a Novel Static Imaging Spectrometer[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(09): 2971-2975. |
[12] |
ZHANG Quan1, 2, HUANG Shu-hua1*, TIAN Yu-ze1, 2, LU Yue-lin1, 2, ZHAO Min-jie1, ZHOU Hai-jin1, ZHAO Xin1, WANG Yu1, SI Fu-qi1. Noise Analysis and Processing Method of Environment Monitoring Instrument[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(09): 2976-2981. |
[13] |
LIU Xiang-lei1,2, LIU Yang-yang1*, FANG Yu1, PEI Lin-lin1, Lü Qun-bo1. Optical Design of Large Relief Large Relative Apertureand High Resolution Modified Dyson Imaging Spectrometer[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(12): 3908-3912. |
[14] |
GAO Jian-hua1,2, LIANG Jing-qiu1, Lü Jin-guang1*, LIANG Zhong-zhu1, QIN Yu-xin1, WANG Wei-biao1. A Stepped Mirror Based Temporally and Spatially Modulated Imaging Fourier Transform Spectrometer: Principle and Data Processing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(12): 3932-3939. |
[15] |
LI Shi-wei1,2, WANG Zhao-ba1,2, ZHANG Rui1,2,WANG Zhi-bin1,2,3. Spectral Measurements Based on Difference Frequency Modulation of Two PEMs Modulators[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37(09): 2966-2973. |
|
|
|
|