A New Model for Predicting Black Soil Nutrient Content by Spectral Parameters
ZHANG Dong-hui, ZHAO Ying-jun, QIN Kai
National Key Laboratory of Remote Sensing Information and Imagery Analyzing Technology, Beijing Research Institute of Uranium Geology, Beijing 100029, China
Abstract:In the field of soil digital mapping, precision agriculture and soil resource investigation, the study of aerial hyperspectral data to provide scientific prediction results by aerial hyperspectral have become the focus of research, especially in the case of black soil rich in nutrients in Northeast China. The data source is CASI-1500 aerial hyperspectral imaging system with a spectral range of 380~1 050 nm, and spatial resolution of 1.5 m. 59 soil samples were collected from the Jiansanjiang area in Heilongjiang, and the contents of organic matter, total nitrogen, total phosphorus and total potassium were obtained. In addition, the eps-regression support vector machine model, BP neural network and PLS1 least square regression model are selected to establish the machine learning model of spectrum and content. A support vector machine (SVM) method is used to extract the total nitrogen, total phosphorus and total potassium in aerial hyperspectral data by evaluating the prediction accuracy of the 3 models. The information of organic matter is retrieved by neural network. The results revealed that the date computed by the spectral statistic, spectral characteristics and spectral values is a kind of effective spectrum of training data, which can reflect the soil comprehensive reflectance situation. The neural network method is the most accurate method for the extraction of organic matter and total potassium. The errors are 1.21% and 0.81% respectively. The accuracy is the highest in the extraction of total nitrogen and total phosphorus information by support vector machines (SVM). The comprehensive accuracy of aerial hyperspectral extraction of soil nutrients was evaluated. The extraction errors of organic matter, total nitrogen, total phosphorus and total potassium were 5.25%, 6.05%, 2.74% and 8.90%, respectively, and the total phosphorus retrieval accuracy was the highest.
Key words:Machine learning; Aerial hyperspectral; Support vector machines; Neural networks; Black soil nutrients
张东辉,赵英俊,秦 凯. 一种新的光谱参量预测黑土养分含量模型[J]. 光谱学与光谱分析, 2018, 38(09): 2932-2936.
ZHANG Dong-hui, ZHAO Ying-jun, QIN Kai. A New Model for Predicting Black Soil Nutrient Content by Spectral Parameters. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(09): 2932-2936.
[1] Liu S, Coyne M S, Grove J H. Applied Soil Ecology, 2017, 120: 121.
[2] ZHENG Guang-hui, JIAO Cai-xia, SHANG Gang, et al(郑光辉,焦彩霞,赏 刚,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(10): 3222.
[3] XUE Li-hong, ZHOU Ding-hao, LI Ying, et al(薛利红,周鼎浩,李 颖,等). Acta Pedologica Sinica Chem.(土壤学报), 2014, 51(5): 993.
[4] SHEN Zhang-quan, YE Ling-bin, SHAN Ying-jie, et al(沈掌泉,叶领宾,单英杰). Acta Pedologica Sinica Chem.(土壤学报), 2014, 51(5): 1011.
[5] Glenn F, Daniel R, Garry O. Field Crops Research, 2010, 116(3): 318.
[6] Liu Tielin, Wei Zhong. Soil Dynamics and Earthquake Engineering, 2017, 99: 137.
[7] Jin Xiuliang, Song Kaishan, Du Jia, et al. Agricultural and Forest Meteorology, 2017, 244: 57.
[8] CAI Yue, SU Hong-jun, LI Qian-nan(蔡 悦,苏红军,李茜楠). Journal of Geo-Information Science(地球信息科学), 2015, 17(8): 986.
[9] Chi-Chin Tsai, Hsing-Wen Liu. Soil Dynamics and Earthquake Engineering, 2017, 102: 124.
[10] GU Hai-yan, YAN Li, LI Hai-tao, et al(顾海燕,闫 利,李海涛,等). Geomatics and Information Science of Wuhan University(武汉大学学报信息科学版), 2016, 41(2): 228.
[11] ZHAO Dan-ping, GU Hai-yan, JIA Ying(赵丹平,顾海燕,贾 莹). Science of Surveying and Mapping(测绘科学), 2016, 41(10): 181.
[12] Jin Xiuliang, Jia Du, Liu Huanjun, et al. Agricultural and Forest Meteorology, 2016, 218: 250.