基于机器学习和多光谱遥感的银川平原土壤盐分预测

doi:10.12118/j.issn.1000-6060.2022.277

摘要/Abstract

摘要：

快速获取区域土壤盐渍化程度信息，对于盐渍化治理与生态环境保护具有重要意义。以银川平原为研究区，以盐分影响因子和盐分指数分别作为输入参数，建立支持向量机（SVM），BP神经网络（BPNN）和贝叶斯神经网络（BNN）3种土壤盐分预测模型，选取最佳模型进行研究区不同深度的土壤盐渍化预测。结果表明：（1） 0~20 cm土壤盐分预测模型中基于影响因子变量组的BNN模型效果最佳，决定系数（R²）为0.618，均方根误差（RMSE）为2.986;20~40 cm土壤盐分预测模型中基于盐分指数变量组的BNN模型效果最佳，R²为0.651，RMSE为1.947;综合对比下，BNN模型的预测效果最好，可用于研究区土壤盐渍化预测。（2）银川平原主要是以非盐渍化和轻度盐渍化为主，0~20 cm土壤重度盐渍化及盐土共占总面积的11.59%，20~40 cm土壤重度盐渍化及盐土共占总面积的7.04%，20~40 cm土壤盐渍化程度较0~20 cm土壤盐渍化轻。

关键词: 机器学习, 土壤盐分预测, 贝叶斯神经网络, 银川平原

Abstract:

Soil salinization can hinder agricultural development. In this study, the degree of regional soil salinization was obtained to provide a theoretical reference for improving agricultural land quality. Using Yinchuan Plain of China as the study area with a grid size of 5 km×5 km, the soil salinity data of 166 sampling points at different depths were obtained. Combined with the Landsat 8 OLI image corresponding to the sampling time, the salt influence factor and salt index were used as input parameters, respectively, and soil salinity at field sampling points was used as output layer parameters. Support vector machine, back propagation neural network, and Bayesian neural network (BNN) were established as soil salinity inversion models. The determination coefficient and root mean square error of the different models were compared to screen the best model. Finally, soil salinization inversion at different depths was performed in the study area. The following results were obtained: (1) In the 0-20 cm soil salinity inversion model, the BNN model based on the influence factor variable group of salinization was the best, with a coefficient of determination (R²) and root mean square error (RMSE) of 0.618 and 2.986, respectively; the best inversion result of 20-40 cm soil salinity was the BNN model based on the salt index variable group (R²=0.651; RMSE=1.947); the comparative analysis of the modeling and verification effects of different variables of the selected algorithms revealed that the BNN model was the best inversion model with a better fitting degree than the other two models, and the introduction of a neural network had certain advantages in the model construction. (2) Non-salinized and mildly salinized soils were the main soil types in Yinchuan Plain. Soil salinization showed a low trend in the south and a high trend in the north. The 20-40 cm soil salinization was found to be lighter than the 0-20 cm soil salinization.

Key words: machine learning, soil salinity prediction, Bayesian neural network, Yinchuan Plain

魏慧敏, 贾科利, 张旭, 张俊华. 基于机器学习和多光谱遥感的银川平原土壤盐分预测[J]. 干旱区地理, 2023, 46(1): 103-114.

WEI Huimin, JIA Keli, ZHANG Xu, ZHANG Junhua. Prediction of soil salinity based on machine learning and multispectral remote sensing in Yinchuan Plain[J]. Arid Land Geography, 2023, 46(1): 103-114.

图/表 10

图1

表1

表2

盐分指数计算公式"

盐分指数	计算公式	参考文献
SI-T	100(Red-NIR)	刘旭辉等^[19]
NDSI	(Red-NIR)/(Red+NIR)	Amal等^[20]
S1	Blue/Red	Sahana等^[21]
S2	(Blue-Red)/(Blue+Red)	Nguyen等^[22]
S3	(Green×Red)/Blue	Nguyen等^[22]
S4	$B l u e × R e d$	樊彦国等^[23]
S5	(Blue×Red)/Green	孙亚楠等^[24]
S6	(Red×NIR)/Green	孙亚楠等^[24]
SI1	$G r e e n × R e d$	樊彦国等^[23]
SI2	$G r e e n 2 + R e d 2 + N I R 2$	樊彦国等^[23]
SI3	$G r e e n 2 + R e d 2$	赵巧珍等^[25]

表2

表3

图2

表4

表5

图3

图4

表6

参考文献 42

[1]	杨真, 王宝山. 中国盐渍土资源现状及改良利用对策[J]. 山东农业科学, 2015, 47(4): 125-130.
	[Yang Zhen, Wang Baoshan. Present status of saline soil resources and countermeasures for improvement and utilization in China[J]. Shandong Agricultural Sciences, 2015, 47(4): 125-130.]
[2]	翁永玲, 戚浩平, 方洪宾, 等. 基于PLSR方法的青海茶卡-共和盆地土壤盐分高光谱遥感反演[J]. 土壤学报, 2010, 47(6): 1255-1263.
	[Weng Yongling, Qi Haoping, Fang Hongbin, et al. PLSR-based hyperspectral remote sensing retrieval of soil salinity of Chaka-Gonghe Basin in Qinghai Province[J]. Acta Pedologica Sinica, 2010, 47(6): 1255-1263.]
[3]	王爽, 丁建丽, 王璐, 等. 基于地表光谱建模的区域土壤盐渍化遥感监测研究[J]. 干旱区地理, 2016, 39(1): 190-198.
	[Wang Shuang, Ding Jianli, Wang Lu, et al. Remote sensing monitoring of soil salinization based on surface spectral modeling[J]. Arid Land Geography, 2016, 39(1): 190-198.]
[4]	El-Horiny M M. Mapping and monitoring of soil salinization using remote sensing and regression techniques: A case study in the Bahariya depression, western desert, Egypt[C]// 2019 IEEE International Geoscience and Remote Sensing Symposium. Yokohama: Institute of Electrical and Electronic Engineers, 2019.
[5]	陈红艳, 赵庚星, 陈敬春, 等. 基于改进植被指数的黄河口区盐渍土盐分遥感反演[J]. 农业工程学报, 2015, 31(5): 107-114.
	[Chen Hongyan, Zhao Gengxing, Chen Jingchun, et al. Remote sensing inversion of saline soil salinity based on modified vegetation index in estuary area of Yellow River[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(5): 107-114.]
[6]	徐红涛, 陈春波, 郑宏伟, 等. 集成建模变量优选和参数学习的SVR盐渍化监测[J]. 遥感技术与应用, 2021, 36(1): 176-186.
	[Xu Hongtao, Chen Chunbo, Zheng Hongwei, et al. SVR salinization monitoring based on integrated feature subset selection and model parameter learning[J]. Remote Sensing Technology and Application, 2021, 36(1): 176-186.]
[7]	姜红, 玉素甫江·如素力, 热伊莱·卡得尔, 等. 基于神经网络模型的干旱区绿洲土壤盐渍化评价分析[J]. 地球信息科学学报, 2017, 19(7): 983-993. doi: 10.3724/SP.J.1047.2017.00983
	[Jiang Hong, Rusuli Yusufujiang, Kadeer Reyilai, et al. Evaluation and analysis of soil salinization in the arid zones based on neural network model[J]. Journal of Geo-information Science, 2017, 19(7): 983-993.] doi: 10.3724/SP.J.1047.2017.00983
[8]	马国林, 丁建丽, 韩礼敬, 等. 基于变量优选与机器学习的干旱区湿地土壤盐渍化数字制图[J]. 农业工程学报, 2020, 36(19): 124-131.
	[Ma Guolin, Ding Jianli, Han Lijing, et al. Digital mapping of soil salinization in arid area wetland based on variable optimized selection and machine learning[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(19): 124-131.]
[9]	杨厚翔, 雷国平, 徐秋, 等. 基于危险度与风险格局的土地盐碱化监测区优先级评价[J]. 农业工程学报, 2019, 35(7): 238-246.
	[Yang Houxiang, Lei Guoping, Xu Qiu, et al. Priority evaluation of land salinization monitoring area based on danger degree and risk pattern[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(7): 238-246.]
[10]	刘全明, 成秋明, 王学, 等. 河套灌区土壤盐渍化微波雷达反演[J]. 农业工程学报, 2016, 32(16): 109-114.
	[Liu Quanming, Cheng Qiuming, Wang Xue, et al. Soil salinity inversion in Hetao irrigation district using microwave radar[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(16): 109-114.]
[11]	杨练兵, 郑宏伟, 罗格平, 等. 基于遗传算法优化BP神经网络的土壤盐渍化反演[J]. 地理与地理信息科学, 2021, 37(2): 12-21, 37.
	[Yang Lianbing, Zheng Hongwei, Luo Geping, et al. Retrieval of soil salinity content based on BP neural network optimized by genetic algorithm[J]. Geography and Geo-information Science, 2021, 37(2): 12-21, 37.]
[12]	章龙管, 刘绥美, 李开富, 等. 基于故障树与贝叶斯网络的地铁盾构施工风险预测[J]. 现代隧道技术, 2021, 58(5): 21-29, 55.
	[Zhang Longguan, Liu Suimei, Li Kaifu, et al. Prediction of shield construction risks in subway tunneling based on fault tree and Bayesian network[J]. Modern Tunneling Technology, 2021, 58(5): 21-29, 55.]
[13]	毕春光, 王金龙, 胡楠, 等. 基于贝叶斯神经网络的玉米病害预警模型[J]. 吉林农业大学学报, 2021, 43(2): 189-195.
	[Bi Chunguang, Wang Jinlong, Hu Nan, et al. A Bayesian neural network-based early warning model for maize diseases[J]. Journal of Jilin Agricultural University, 2021, 43(2): 189-195.]
[14]	靳晓辉, 樊玉苗, 段浩, 等. 银川平原地下水位对黄河流域水量统一调度的时空响应分析[J]. 水资源与水工程学报, 2021, 32(4): 45-51.
	[Jin Xiaohui, Fan Yumiao, Duan Hao, et al. Temporal and spatial response of groundwater depth in Yinchuan Plain to the integrated water regulation of the Yellow River[J]. Journal of Water Resources and Water Engineering, 2021, 32(4): 45-51.]
[15]	曹肖奕, 丁建丽, 葛翔宇, 等. 基于不同卫星光谱模拟的土壤电导率估算研究[J]. 干旱区地理, 2020, 43(1): 172-181.
	[Cao Xiaoyi, Ding Jianli, Ge Xiangyu, et al. Estimation of soil conductivity based on spectral simulation of different satellites[J]. Arid Land Geography, 2020, 43(1): 172-181.]
[16]	贾萍萍, 尚天浩, 张俊华, 等. 利用多源光谱信息反演宁夏银北地区干湿季土壤含盐量[J]. 农业工程学报, 2020, 36(17): 125-134.
	[Jia Pingping, Shang Tianhao, Zhang Junhua, et al. Inversion of soil salinity in dry and wet seasons based on multi-source spectral data in Yinbei area of Ningxia, China[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(17): 125-134.]
[17]	武丹, 贾科利, 张晓东, 等. 基于异质SVM神经网络的土壤盐渍化灾害预测模型[J]. 水文地质工程地质, 2018, 45(5): 143-149, 157.
	[Wu Dan, Jia Keli, Zhang Xiaodong, et al. Soil salinization disaster prediction model based on heterogeneous SVM neural network[J]. Hydrogeology & Engineering Geology, 2018, 45(5): 143-149, 157.]
[18]	张智韬, 魏广飞, 姚志华, 等. 基于无人机多光谱遥感的土壤含盐量反演模型研究[J]. 农业机械学报, 2019, 50(12): 151-160.
	[Zhang Zhitao, Wei Guangfei, Yao Zhihua, et al. Soil salt inversion model based on UAV multispectral remote sensing[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(12): 151-160.]
[19]	刘旭辉, 白云岗, 柴仲平, 等. 基于多光谱遥感的典型绿洲棉田春季土壤盐分反演及验证[J]. 干旱区地理, 2022, 45(4): 1165-1175.
	[Liu Xuhui, Bai Yungang, Cai Zhongping, et al. Inversion and validation of soil salinity based on multispectral remote sensing in typical oasis cotton field in spring[J]. Arid Land Geography, 2022, 45(4): 1165-1175.]
[20]	Amal A, Lalit K, Youself Y A. Assessing soil salinity using soil salinity and vegetation indices derived from IKONOS high-spatial resolution imageries: Applications in a date palm dominated region[J]. Geoderma, 2014, 230- 231(7): 1-8.
[21]	Sahana M, Rehman S, Patel P P, et al. Assessing the degree of soil salinity in the Indian Sundarban Biosphere Reserve using measured soil electrical conductivity and remote sensing data-derived salinity indices[J]. Arabian Journal of Geosciences, 2020, 13(24): 1289, doi: s12517-020-06310-w.
[22]	Nguyen K A, Liou Y A, Tran H P, et al. Soil salinity assessment by using near-infrared channel and vegetation soil salinity index derived from Landsat 8 OLI data: A case study in the Tra Vinh Province, Mekong Delta, Vietnam[J]. Progress in Earth and Planetary Science, 2020, 7(1): 1-16. doi: 10.1186/s40645-019-0311-0
[23]	樊彦国, 张维康, 刘敬一. 基于植被指数-盐分指数特征空间的黄河三角洲盐渍化遥感监测研究[J]. 山东农业科学, 2016, 48(5): 137-141.
	[Fan Yanguo, Zhang Weikang, Liu Jingyi. Remote sensing monitoring model of soil salinization in the Yellow River Delta Zone based on vegetation index-salt index feature space[J]. Shandong Agricultural Sciences, 2016, 48(5): 137-141.]
[24]	孙亚楠, 李仙岳, 史海滨, 等. 基于多源数据融合的盐分遥感反演与季节差异性研究[J]. 农业机械学报, 2020, 51(6): 169-180.
	[Sun Ya’nan, Li Xianyue, Shi Haibin, et al. Remote sensing inversion of soil salinity and seasonal difference analysis based on multi-source data fusion[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(6): 169-180.]
[25]	赵巧珍, 丁建丽, 韩礼敬, 等. MODIS和Landsat时空融合影像在土壤盐渍化监测中的适用性研究——以渭干河-库车河三角洲绿洲为例[J]. 干旱区地理, 2022, 45(4): 1155-1164.
	[Zhao Qiaozhen, Ding Jianli, Han Lijing, et al. Exploring the application of MODIS and Landsat spatiotemporal fusion images in soil salinization: A case of Weigan River-Kuqa River Delta Oasis[J]. Arid Land Geography, 2022, 45(4): 1155-1164.]
[26]	赖宁, 李新国, 阿斯耶姆·图尔迪, 等. 开都河流域下游绿洲土壤盐渍化时空变化及其成因分析[J]. 干旱区资源与环境, 2013, 27(12): 66-73.
	[Lai Ning, Li Xinguo, Tuerdi Asiyemu, et al. Analysis of tempo-spatial dynamic change and the cause of soil salinization in the oasis of the lower reaches of Kaidu River Basin[J]. Journal of Arid Land Resources and Environment, 2013, 27(12): 66-73.]
[27]	庄庆威, 吴世新, 杨怡, 等. 近10年新疆不同程度盐渍化耕地的时空变化特征[J]. 中国科学院大学学报, 2021, 38(3): 341-349. doi: 10.7523/j.issn.2095-6134.2021.03.007
	[Zhuang Qingwei, Wu Shixin, Yang Yi, et al. Spatiotemporal characteristics of different degrees of salinized cultivated land in Xinjiang in the recent ten years[J]. Journal of University of Chinese Academy of Sciences, 2021, 38(3): 341-349.] doi: 10.7523/j.issn.2095-6134.2021.03.007
[28]	庄大方, 刘纪远. 中国土地利用程度的区域分异模型研究[J]. 自然资源学报, 1997, 12(2): 10-16.
	[Zhuang Dafang, Liu Jiyuan. Study on the model of regional differentiation of land use degree in China[J]. Journal of Natural Resources, 1997, 12(2): 10-16.]
[29]	汪海燕, 黎建辉, 杨风雷. 支持向量机理论及算法研究综述[J]. 计算机应用研究, 2014, 31(5): 1281-1286.
	[Wang Haiyan, Li Jianhui, Yang Fenglei. Overview of support vector machine analysis and algorithm[J]. Application Research of Computers, 2014, 31(5): 1281-1286.]
[30]	杨淑娥, 黄礼. 基于BP神经网络的上市公司财务预警模型[J]. 系统工程理论与实践, 2005, 25(1): 12-18, 26. doi: 10.12011/1000-6788(2005)1-12
	[Yang Shu’e, Huang Li. Financial crisis warning model based on BP neural network[J]. Systems Engineering-Theory & Practice, 2005, 25(1): 12-18, 26.] doi: 10.12011/1000-6788(2005)1-12
[31]	赵亚琴. 基于模糊神经网络的火灾识别算法[J]. 计算机仿真, 2015, 32(2): 369-373.
	[Zhao Yaqin. Forest fire recognition algorithm based on fuzzy neural network[J]. Computer Simulation, 2015, 32(2): 369-373.]
[32]	宿嘉颖. 贝叶斯深度网络的不确定性分析[D]. 哈尔滨: 哈尔滨工业大学, 2020.
	[Su Jiaying. Uncertainty analysis of Bayesian deep network[D]. Harbin:Harbin Institute of Technology, 2020.]
[33]	孙发友, 蒙祖强. 一种设备状态监测的贝叶斯正则化BP神经网络[J]. 网络安全技术与应用, 2019(10): 48-53.
	[Sun Fayou, Meng Zuqiang. A Bayesian regularized BP neural network for equipment condition monitoring[J]. Network Security Technology & Application, 2019(10): 48-53.]
[34]	王子涵, 杨秀芝, 段现银, 等. 基于贝叶斯神经网络的机床热误差建模[J]. 制造技术与机床, 2022(1): 141-145.
	[Wang Zihan, Yang Xiuzhi, Duan Xianyin, et al. Research on the thermal error modeling of machine tool based on Bayesian neural network[J]. Manufacturing Technology & Machine Tool, 2022(1): 141-145.]
[35]	杨思存, 车宗贤, 王成宝, 等. 甘肃沿黄灌区土壤盐渍化特征及其成因[J]. 干旱区研究, 2014, 31(1): 57-64.
	[Yang Sicun, Che Zongxian, Wang Chengbao, et al. Soil salinization and its causes in the irrigated areas along the Yellow River in Gansu Province[J]. Arid Zone Research, 2014, 31(1): 57-64.]
[36]	苏春利, 纪倩楠, 陶彦臻, 等. 河套灌区西部土壤盐渍化分异特征及其主控因素[J]. 干旱区研究, 2022, 39(3): 916-923.
	[Su Chunli, Ji Qiannan, Tao Yanzhen, et al. Differentiation characteristics and factors of soil salinization in the west of Hetao Irrigation Area[J]. Arid Zone Research, 2022, 39(3): 916-923.]
[37]	刘继龙, 刘璐, 马孝义, 等. 不同尺度不同土层土壤盐分的空间变异性研究[J]. 应用基础与工程科学学报, 2018, 26(2): 305-312.
	[Liu Jilong, Liu Lu, Ma Xiaoyi, et al. Spatial variability of soil salt in different soil layers at different scales[J]. Journal of Basic Science and Engineering, 2018, 26(2): 305-312.]
[38]	边慧芹, 王雪梅. 基于多光谱影像的干旱区绿洲耕层土壤盐分估算[J]. 干旱区资源与环境, 2022, 36(5): 110-118.
	[Bian Huiqin, Wang Xuemei. Estimation of soil salinity in cultivated layers of oasis in arid areas based on multispectral images[J]. Journal of Arid Land Resources and Environment, 2022, 36(5): 110-118.]
[39]	何宝忠, 丁建丽, 刘博华, 等. 渭库绿洲土壤盐渍化时空变化特征[J]. 林业科学, 2019, 55(9): 185-196.
	[He Baozhong, Ding Jianli, Liu Bohua, et al. Spatiotemporal variation of soil salinization in Weigan-Kuqa River Delta Oasis[J]. Scientia Silvae Sinicae, 2019, 55(9): 185-196.]
[40]	陈俊英, 姚志华, 张智韬, 等. 大田葵花土壤含盐量无人机遥感反演研究[J]. 农业机械学报, 2020, 51(7): 178-191.
	[Chen Junying, Yao Zhihua, Zhang Zhitao, et al. UAV remote sensing inversion of soil salinity in field of sunflower[J]. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(7): 178-191.]
[41]	王明宽, 莫宏伟, 陈红艳. 基于多光谱影像反演土壤盐分的建模方法研究[J]. 土壤通报, 2016, 47(5): 1036-1041.
	[Wang Mingkuan, Mo Hongwei, Chen Hongyan. Study on model method of inversion of soil salt based on multispectral image[J]. Chinese Journal of Soil Science, 2016, 47(5): 1036-1041.]
[42]	杨宁, 崔文轩, 张智韬, 等. 无人机多光谱遥感反演不同深度土壤盐分[J]. 农业工程学报, 2020, 36(22): 13-21.
	[Yang Ning, Cui Wenxuan, Zhang Zhitao, et al. Soil salinity at different depths using improved spectral index with UAV multispectral remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(22): 13-21.]

深度/cm	程度	含盐量/g·kg^-1	样本数	含盐量均值 /g·kg^-1	含盐量最大值 /g·kg^-1	含盐量最小值 /g·kg^-1	变异系数 /%	总样本变异系数/%
0~20	非盐渍化	<1	75	0.510	0.983	0.097	41.295	172.327
	轻度盐渍化	1~2	32	1.522	1.946	1.058	18.823
	中度盐渍化	2~4	20	2.819	3.667	2.003	20.119
	重度盐渍化	4~6	12	4.734	5.803	4.122	11.538
	盐土	>6	27	15.104	43.725	6.676	59.548
20~40	非盐渍化	<1	101	0.566	0.997	0.308	30.428	132.278
	轻度盐渍化	1~2	34	1.471	1.979	1.020	17.701
	中度盐渍化	2~4	23	2.674	3.752	2.015	19.605
	重度盐渍化	4~6	4	4.387	5.276	4.038	13.545
	盐土	>6	4	9.872	17.929	6.274	55.894

变量类型	参数名称	描述
环境变量	土壤pH	土壤酸碱性
	土壤含水率/%	土壤绝对含水量
	高程/m	地区的海拔高度
	增强植被指数	农作物长势和营养信息
	水体指数	地区水体信息
	地表温度/℃	地区土壤温度
	地下水埋深/m	地区潜水的埋藏深度
	地下水矿化度/g·L^-1	区域潜水中可溶性盐类的质量
人为活动变量	土地利用强度	土地资源的利用效率
	人口密度/人·km^-2	每平方千米的人口平均数
	生产总值/元	生产活动的最终成果

参数类型	参数	与0~20 cm土壤相关系数（r₁）	与20~40 cm土壤相关系数（r₂）
盐渍化影响因子	土壤pH	0.034	0.030
	土壤含水率	0.103	0.102
	高程	-0.253^**	-0.114
	土地利用强度	-0.403^**	-0.255^**
	增强植被指数	-0.580^**	-0.311^**
	水体指数	0.511^**	0.271^**
	地表温度	-0.445^**	-0.119^**
	地下水埋深	-0.477^**	-0.204^**
	地下水矿化度	0.768^**	0.254^**
	人口密度	-0.023	0.048
	生产总值	-0.173^*	-0.025
盐分指数	S1	0.492^**	0.402^**
	S2	0.480^**	0.388^**
	S3	-0.230^**	-0.054
	S4	0.049	0.210^**
	S5	0.067	0.229^**
	S6	-0.309^**	-0.093
	SI1	-0.032	0.136
	SI2	-0.130^*	0.069
	SI3	-0.043	0.127^*
	NDSI	0.325^**	0.204^**
	SI-T	0.347^**	0.182^*

变量组	模型类别	建模集（n=110）		验证集（n=56）
变量组	模型类别	R²	RMSE	R²	RSME
影响因子组（0~20 cm）	SVM	0.766	3.397	0.542	3.266
	BPNN	0.773	2.638	0.608	3.081
	BNN	0.797	2.751	0.618	2.986
盐分指数组（0~20 cm）	SVM	0.319	5.945	0.213	4.155
	BPNN	0.311	5.878	0.206	4.405
	BNN	0.336	5.715	0.250	3.890
影响因子组（20~40 cm）	SVM	0.368	1.327	0.221	2.401
	BPNN	0.314	1.353	0.331	2.221
	BNN	0.425	1.076	0.486	2.026
盐分指数组（20~40 cm）	SVM	0.440	1.032	0.436	2.079
	BPNN	0.348	1.086	0.545	2.033
	BNN	0.442	1.006	0.651	1.947

深度/cm	盐渍化程度	实测插值像元数	预测和实测插值相同等级个数	相同率/%
0~20	非盐渍化	3922460	3221641	82.13
	轻度盐渍化	1925470	1409137	73.18
	中度盐渍化	779011	648843	83.29
	重度盐渍化	764161	602002	78.78
	盐土	507095	434657	85.72
20~40	非盐渍化	4279527	3613169	84.43
	轻度盐渍化	2413166	2046062	84.79
	中度盐渍化	722601	538546	74.53
	重度盐渍化	311423	274697	88.21
	盐土	171493	144933	84.51