基于Sentinel-2时序数据的新疆焉耆盆地农作物遥感识别与评估

doi:10.12118/j.issn.1000－6060.2023.262

干旱区地理 ›› 2024, Vol. 47 ›› Issue (4): 672-683.doi: 10.12118/j.issn.1000－6060.2023.262

基于Sentinel-2时序数据的新疆焉耆盆地农作物遥感识别与评估

张旭辉¹(), 玉素甫江·如素力¹^,²(), 仇忠丽¹, 亚夏尔·艾斯克尔¹, 阿卜杜热合曼·吾斯曼¹

1.新疆师范大学地理科学与旅游学院流域信息集成与生态安全实验室，新疆乌鲁木齐 830054
2.新疆干旱区湖泊环境与资源重点实验室，新疆乌鲁木齐 830054

收稿日期:2023-06-06 修回日期:2023-07-24 出版日期:2024-04-25 发布日期:2024-05-17
通讯作者: 玉素甫江·如素力（1975-），男，博士，教授，主要从事流域水文与生态环境遥感研究. E-mail: Yusupjan@xjnu.edu.cn
作者简介:张旭辉（1997-），男，硕士研究生，主要从事空间信息分析与应用研究. E-mail: philamour@163.com
基金资助:
国家自然科学基金项目(U1703341);国家自然科学基金项目(41764003);自治区科技创新基地建设计划项目(2020D04039)

Remote sensing identification and assessment of crops in the Yanqi Basin, Xinjiang, China based on Sentinel-2 time series data

ZHANG Xuhui¹(), Yusufujiang RUSULI¹^,²(), QIU Zhongli¹, Yaxiaer AISIKEER¹, Abudureheman WUSIMAN¹

1. Watershed Information Integration and Ecological Security Laboratory, College of Geographic Science and Tourism, Xinjiang Normal University, Urumqi 830054, Xinjiang, China
2. Key Laboratory of Lake Environment and Resources in the Arid Zone of Xinjiang, Urumqi 830054, Xinjiang, China

Received:2023-06-06 Revised:2023-07-24 Published:2024-04-25 Online:2024-05-17

摘要/Abstract

摘要：

为及时准确地获取干旱区农作物种植信息，研究借助PIE-Engine Studio平台，以新疆焉耆盆地为研究区，基于2022年Sentinel-2影像和1948个野外定位采样数据提取农作物生育期内14种植被指数，使用See5.0决策树、随机森林（Random forest，RF）和多元回归（Multiple regression，MR）模型优选特征参数，结合支持向量机（Support vector machine，SVM）算法构建5种分类模型和5种样方分割方案进行农作物种植信息提取，通过目视解译和混淆矩阵对比分析分类结果，确定最佳分类方案。结果表明：（1）所有分类模型的总体精度（OA）和Kappa系数均在92.20%和0.9037以上，说明在PIE平台中使用SVM算法提取农作物信息是可行的。（2） SVM-有红边的OA和Kappa系数均值为93.77%和0.9236，比SVM-无红边方法提高了0.96%和0.0120。（3）相比于SVM-有红边方法，植被指数的引入提高了SVM-RF、SVM-MR和SVM-See5.0的OA和Kappa系数。（4） 5种分类模型的OA和Kappa系数均值的大小关系为：SVM-RF>SVM-MR>SVM-See5.0>SVM-有红边>SVM-无红边，表明红边波段和植被指数的加入显著提高了农作物识别的精度，其中SVM-RF（8:2）为最佳分类模型，OA和Kappa系数分别为98.72%和0.9866。研究结果可为准确快速获取大尺度干旱区农作物信息提供新的思路和参考依据。

关键词: 农作物, Sentinel-2, 支持向量机, PIE-Engine Studio, 焉耆盆地

Abstract:

To obtain timely and accurate information about crop cultivation in arid zones, this study used the PIE-Engine Studio platform to extract 14 vegetation indices in the Yanqi Basin, Xinjiang, China based on 2022 Sentinel-2 images and 1948 field location sampling data during the crop reproduction period. Crop planting information was extracted using the See5.0 decision tree, random forest (RF), and multiple regression (MR) models to select feature parameters. Each model was combined with support vector machine (SVM) algorithms to construct five classification models and five sample segmentation schemes. The best classification scheme was determined by visual interpretation and confusion matrix comparison. The results are as follows: (1) The overall accuracy (OA) and Kappa coefficients of all classification models are above 92.20% and 0.9037, respectively, indicating that it is feasible to extract crop information using the SVM algorithm in the PIE platform. (2) The mean OA and Kappa coefficients of SVM-with-red-edge are 93.77% and 0.9236, which are 0.96% and 0.0120, respectively. (3) The introduction of vegetation index improved the OA and Kappa coefficients of SVM-RF, SVM-MR, and SVM-See5.0 compared with the SVM-with-red-edge method. (4) The mean OA and Kappa coefficient relationships for the five classification models were SVM-RF>SVM-MR>SVM-See5.0>SVM-with-red-edge>SVM-without-red-edge, showing that the inclusion of the red-edge band and vegetation index significantly improved the accuracy of crop identification, with SVM-RF (8:2) being the best classification model with OA and Kappa coefficients of 98.72% and 0.9866, respectively. These results provide new ideas and references for accurate and rapid access to large-scale arid zone crop information.

Key words: crop, Sentinel-2, support vector machines, PIE-Engine Studio, Yanqi Basin

张旭辉, 玉素甫江·如素力, 仇忠丽, 亚夏尔·艾斯克尔, 阿卜杜热合曼·吾斯曼. 基于Sentinel-2时序数据的新疆焉耆盆地农作物遥感识别与评估[J]. 干旱区地理, 2024, 47(4): 672-683.

ZHANG Xuhui, Yusufujiang RUSULI, QIU Zhongli, Yaxiaer AISIKEER, Abudureheman WUSIMAN. Remote sensing identification and assessment of crops in the Yanqi Basin, Xinjiang, China based on Sentinel-2 time series data[J]. Arid Land Geography, 2024, 47(4): 672-683.

图/表 10

图1

表1

表2

表3

植被指数计算公式"

序号	植被指数	计算公式
1	NDVI	$(B 8 - B 4) / (B 8 + B 4)$
2	NDVI₇₀₅	$(B 5 - B 4) / (B 5 + B 4)$
3	NDVI₇₄₀	$(B 6 - B 4) / (B 6 + B 4)$
4	NDVI₇₈₃	$(B 7 - B 4) / (B 7 + B 4)$
5	GI	$B 3 / B 4$
6	VIgreen	$(B 3 - B 4) / (B 3 + B 4)$
7	GNDVI	$(B 8 - B 3) / (B 8 + B 3)$
8	RDVI	$(B 8 - B 4) / B 8 + B 4$
9	TVI	$0.5 [120 B 8 - B 3 - 200 (B 4 - B 3)]$
10	EVI	$G (B 8 - B 4 B 8 + C 1 × B 4 - C 2 × B 2 + L)$
11	SRI	$B 8 / B 4$
12	MSR	$[(B 8 / B 4) - 1] / [(B 8 / B 4) 0.5 + 1]$
13	MCARI	$[B 8 - B 4 - 0.2 B 8 - B 3] × (B 8 / B 4)$
14	TCARI	$3 [B 8 - B 4 - 0.2 B 8 - B 3 × B 8 / B 4]$

表3

表4

图2

图3

图4

图5

图6

参考文献 32

[1]	唐华俊, 吴文斌, 杨鹏, 等. 农作物空间格局遥感监测研究进展[J]. 中国农业科学, 2010, 43(14): 2879-2888.
	[Tang Huajun, Wu Wenbin, Yang Peng, et al. Recent progresses in monitoring crop spatial patterns by using remote sensing technologies[J]. Scientia Agricultura Sinica, 2010, 43(14): 2879-2888. ]
[2]	陈亚宁, 李玉朋, 李稚, 等. 全球气候变化对干旱区影响分析[J]. 地球科学进展, 2022, 37(2): 111-119. doi: 10.11867/j.issn.1001-8166.2022.006
	[Chen Yaning, Li Yupeng, Li Zhi, et al. Analysis of the impact of global climate change on dryland areas[J]. Advances in Earth Science, 2022, 37(2): 111-119. ] doi: 10.11867/j.issn.1001-8166.2022.006
[3]	刘珍环, 杨鹏, 吴文斌, 等. 近30年中国农作物种植结构时空变化分析[J]. 地理学报, 2016, 71(5): 840-851. doi: 10.11821/dlxb201605012
	[Liu Zhenhuan, Yang Peng, Wu Wenbin, et al. Spatio-temporal changes in Chinese crop patterns over the past three decades[J]. Acta Geographica Sinica, 2016, 71(5): 840-851. ] doi: 10.11821/dlxb201605012
[4]	胡琼, 吴文斌, 宋茜, 等. 农作物种植结构遥感提取研究进展[J]. 中国农业科学, 2015, 48(10): 1900-1914. doi: 10.3864/j.issn.0578-1752.2015.10.004
	[Hu Qiong, Wu Wenbin, Song Qian, et al. Recent progresses in research of crop patterns mapping by using remote sensing[J]. Scientia Agricultura Sinica, 2015, 48(10): 1900-1914. ] doi: 10.3864/j.issn.0578-1752.2015.10.004
[5]	杨雪峰. 使用高分遥感影像获取塔里木河胡杨高度信息[J]. 遥感技术与应用, 2021, 36(5): 1199-1208.
	[Yang Xuefeng. Estimation height of Populus euphratica in Tarim River using VHR satellite images[J]. Remote Sensing Technology and Application, 2021, 36(5): 1199-1208. ]
[6]	梁继, 郑镇炜, 夏诗婷, 等. 高分六号红边特征的农作物识别与评估[J]. 遥感学报, 2020, 24(10): 1168-1179.
	[Liang Ji, Zheng Zhenwei, Xia Shiting, et al. Crop recognition and evaluation using red edge features of GF-6 satellite[J]. Journal of Remote Sensing, 2020, 24(10): 1168-1179. ]
[7]	Jia K, Wu B F, Li Q Z. Crop classification using HJ satellite multispectral data in the North China Plain[J]. Journal of Applied Remote Sensing, 2013, 7(1): 73576, doi: 10.1117/1.JRS.7.073576.
[8]	美合日阿依·莫一丁, 买买提·沙吾提, 李金朝, 基于Sentinel-2时间序列数据及物候特征的棉花种植区提取[J]. 干旱区地理, 2022, 45(6): 1847-1859.
	[Moyiding Meiheriayi, Shawuti Maimaiti, Li Jinzhao. Extraction of cotton planting area based on Sentinel-2 time series data and phenological characteristics[J]. Arid Land Geography, 2022, 45(6): 1847-1859. ]
[9]	Liangzhi Y, Stanley W, Ulrike W S. Generating plausible crop distribution maps for Sub-Saharan Africa using a spatially disaggregated data fusion and optimization approach[J]. Agricultural Systems, 2008, 99(2): 126-140.
[10]	Chad M, Navin R, Jonathan A F. Farming the planet: 2. Geographic distribution of crop areas, yields, physiological types, and net primary production in the year 2000[J]. Global Biogeochemical Cycles, 2008, 22(1): 1-19.
[11]	Reichstein M, Camps V G, Stevens B, et al. Deep learning and process understanding for data-driven Earth system science[J]. Nature, 2019, 566(7743): 195-204.
[12]	许晴, 张锦水, 张凤, 等. 深度学习农作物分类的弱样本适用性[J]. 遥感学报, 2022, 26(7): 1395-1409.
	[Xu Qing, Zhang Jinshui, Zhang Feng, et al. Applicability of weak samples to deep learning crop classification[J]. Journal of Remote Sensing, 2022, 26(7): 1395-1409. ]
[13]	贾银江, 姜涛, 苏中滨, 等. 基于改进SVM算法的典型作物分类方法研究[J]. 东北农业大学学报, 2020, 51(7): 77-85.
	[Jia Yinjiang, Jiang Tao, Su Zhongbin, et al. Study on classification method of typical crops based on improved SVM algorithm[J]. Journal of Northeast Agricultural University, 2020, 51(7): 77-85. ]
[14]	梁习卉子, 陈兵旗, 李民赞, 等. 基于HOG特征和SVM的棉花行数动态计数方法[J]. 农业工程学报, 2020, 36(15): 173-181.
	[Liang Xihuizi, Chen Bingqi, Li Minzan, et al. Method for dynamic counting of cotton rows based on HOG feature and SVM[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(15): 173-181. ]
[15]	边增淦, 王文, 江渊. 黑河流域中游地区作物种植结构的遥感提取[J]. 地球信息科学学报, 2019, 21(10): 1629-1641. doi: 10.12082/dqxxkx.2019.190183
	[Bian Zenggan, Wang Wen, Jiang Yuan. Remote sensing of cropping structure in the middle reaches of the Heihe River Basin[J]. Journal of Geoinformation Science, 2019, 21(10): 1629-1641. ]
[16]	田鑫, 何海, 金双彦, 等. 基于遥感影像的张掖灌区作物种植结构提取研究[J]. 中国农村水利水电, 2022(8): 206-212, 217.
	[Tian Xin, He Hai, Jin Shuangyan, et al. Crop planting structure extraction in Zhangye irrigation area based on remote sensing images[J]. China Rural Water and Hydropower, 2022(8): 206-212, 217. ]
[17]	郭其乐, 李军玲, 郭鹏. 基于作物双时相遥感特征的花生种植区提取[J]. 应用气象学报, 2022, 33(2): 218-230.
	[Guo Qile, Li Junling, Guo Peng. Extraction of peanut planting area based on dual-temporal remote sensing features of crops[J]. Journal of Applied Meteorological Science, 2022, 33(2): 218-230. ]
[18]	付东杰, 肖寒, 苏奋振, 等. 遥感云计算平台发展及地球科学应用[J]. 遥感学报, 2021, 25(1): 220-230.
	[Fu Dongjie, Xiao Han, Su Fenzhen, et al. Remote sensing cloud computing platform development and Earth science application[J]. Journal of Remote Sensing, 2021, 25(1): 220-230. ]
[19]	刘通, 任鸿瑞. GEE平台下利用物候特征进行面向对象的水稻种植分布提取[J]. 农业工程学报, 2022, 38(12): 189-196.
	[Liu Tong, Ren Hongrui. Object-oriented extraction of paddy rice planting areas using phenological features from the GEE platform[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(12): 189-196. ]
[20]	潘力, 夏浩铭, 王瑞萌, 等. 基于Google Earth Engine的淮河流域越冬作物种植面积制图[J]. 农业工程学报, 2021, 37(18): 211-218.
	[Pan Li, Xia Haoming, Wang Ruimeng, et al. Mapping of the winter crop planting areas in Huaihe River Basin based on Google Earth Engine[J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(18): 211-218. ]
[21]	姜伊兰, 陈保旺, 黄玉芳, 等. 基于Google Earth Engine和NDVI时序差异指数的作物种植区提取[J]. 地球信息科学学报, 2021, 23(5): 938-947. doi: 10.12082/dqxxkx.2021.200291
	[Jiang Yilan, Chen Baowang, Huang Yufang, et al. Crop planting area extraction based on Google Earth Engine and NDVI time series difference index[J]. Journal of Geoinformation Science, 2021, 23(5): 938-947. ]
[22]	程伟, 钱晓明, 李世卫, 等. 时空遥感云计算平台PIE-Engine Studio的研究与应用[J]. 遥感学报, 2022, 26(2): 335-347.
	[Cheng Wei, Qian Xiaoming, Li Shiwei, et al. Research and application of PIE-Engine Studio for spatiotemporal remote sensing cloud computing platform[J]. Journal of Remote Sensing, 2022, 26(2): 335-347. ]
[23]	田颖, 陈卓奇, 惠凤鸣, 等. 欧空局哨兵卫星Sentinel-2A/B数据特征及应用前景分析[J]. 北京师范大学学报(自然科学版), 2019, 55(1): 57-65.
	[Tian Ying, Chen Zhuoqi, Hui Fengming, et al. ESA Sentinel-2A/B satellite: Characteristics and applications[J]. Journal of Beijing Normal University (Natural Science Edition), 2019, 55(1): 57-65. ]
[24]	齐红超, 祁元, 徐瑱. 基于C5.0决策树算法的西北干旱区土地覆盖分类研究——以甘肃省武威市为例[J]. 遥感技术与应用, 2009, 24(5): 648-653, 553.
	[Qi Hongchao, Qi Yuan, Xu Zhen. The study of the northwest arid zone land-cover classification cased on C5.0 decision tree algorithm at Wuwei City, Gansu Province[J]. Remote Sensing Technology and Application, 2009, 24(5): 648-653, 553. ]
[25]	许晴, 张锦水, 张凤, 等. 深度学习农作物分类的弱样本适用性[J]. 遥感学报, 2022, 26(7): 1395-1409.
	[Xu Qing, Zhang Jinshui, Zhang Feng, et al. Applicability of weak samples to deep learning crop classification[J]. Journal of Remote Sensing, 2022, 26(7): 1395-1409. ]
[26]	张善红, 白红英, 齐贵增, 等. 基于多元线性回归模型和Anusplin的秦巴山区≥10 ℃积温空间模拟比较[J]. 水土保持研究, 2022, 29(1): 184-189, 196.
	[Zhang Shanhong, Bai Hongying, Qi Guizeng, et al. Spatial simulation of active accumulated temperature ≥10 ℃ in Qinling-Daba Mountains based on Anusplin and multiple linear regression model[J]. Research of Soil and Water Conservation, 2022, 29(1): 184-189, 196. ]
[27]	Giorgos M, Jungho I, Caesar O. Support vector machines in remote sensing: A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2010, 66(3): 247-259.
[28]	黄双燕, 杨辽, 陈曦, 等. 机器学习法的干旱区典型农作物分类[J]. 光谱学与光谱分析, 2018, 38(10): 3169-3176.
	[Huang Shuangyan, Yang Liao, Chen Xi, et al. Study of typical arid crops classification based on machine learning[J]. Spectroscopy and Spectral Analysis, 2018, 38(10): 3169-3176. ]
[29]	牛乾坤, 刘浏, 黄冠华, 等. 基于GEE和机器学习的河套灌区复杂种植结构识别[J]. 农业工程学报, 2022, 38(6): 165-174.
	[Niu Qiankun, Liu Liu, Huang Guanhua, et al. Extraction of complex crop structure in the Hetao Irrigation District of Inner Mongolia using GEE and machine learning[J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(6): 165-174. ]
[30]	谷祥辉, 张英, 桑会勇, 等. 基于哨兵2时间序列组合植被指数的作物分类研究[J]. 遥感技术与应用, 2020, 35(3): 702-711.
	[Gu Xianghui, Zhang Ying, Sang Huiyong, et al. Research on crop classification method based on Sentinel-2 time series combined vegetation index[J]. Remote Sensing Technology and Application, 2020, 35(3): 702-711. ]
[31]	郭交, 朱琳, 靳标. 基于Sentinel-1和Sentinel-2数据融合的农作物分类[J]. 农业机械学报, 2018, 49(4): 192-198.
	[Guo Jiao, Zhu Lin, Jin Biao. Crop classification based on data fusion of Sentinel-1 and Sentinel-2[J]. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(4): 192-198. ]
[32]	薛朝辉, 钱思羽. 融合Landsat 8与Sentinel-2数据的红树林物候信息提取与分类[J]. 遥感学报, 2022, 26(6): 1121-1142.
	[Xue Zhaohui, Qian Siyu. Fusion of Landsat 8 and Sentinel-2 data for mangrove phenology information extraction and classification[J]. Journal of Remote Sensing, 2022, 26(6): 1121-1142. ]

序号	传感器类型及产品序号	影像获取时间（年-月-日）	光谱波段	空间分辨率/m	云量/%
1	S2_L2A_45TUG_20220304	2022-03-04	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10、20	<10
2	S2_L2A_45TUG_20220403	2022-04-03	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10、20	<10
3	S2_L2A_45TUG_20220503	2022-05-03	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10、20	<10
4	S2_L2A_45TUG_20220605	2022-06-05	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10、20	<10
5	S2_L2A_45TUG_20220705	2022-07-05	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10、20	<10
6	S2_L2A_45TUG_20220804	2022-08-04	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10、20	<10
7	S2_L2A_45TUG_20220903	2022-09-03	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10、20	<10
8	S2_L2A_45TUG_20221003	2022-10-03	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10、20	<10
9	S2_L2A_45TUG_20221102	2022-11-02	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10、20	<10

分类模型	特征参数	波段数目	样本分割方案
SVM-无红边	B2、B3、B4、B8、B8a、B11、B12	7	5:5、6:4、7:3、8:2、9:1
SVM-有红边	B2、B3、B4、B5、B6、B7、B8、B8a、B11、B12	10	5:5、6:4、7:3、 8:2、9:1
SVM-See5.0	B8、EVI、B5、B6、TVI、B7、TCARI、NDVI₇₀₅、GI、B3、B2、VIgreen、B4、NDVI₇₄₀、NDWI、RNDVI、NDVI、NDVI₇₈₃、MCARI、B11、B8a、SRI	22	5:5、6:4、7:3、 8:2、9:1
SVM-RF	B8、NDVI₇₀₅、B3、B6、TVI、B11、B2、B4、EVI、B7、MCARI、RNDVI、B8a、VIgreen、GI、B5、NDVI₇₄₀、TCARI、GNDVI、NDWI	20	5:5、6:4、7:3、8:2、9:1
SVM-MR	MCARI、NDVI、TCARI、SRI、TVI、VIgreen、NDVI₇₈₃、MSR、B5、B4、B8a、EVI	12	5:5、6:4、7:3、8:2、9:1

基于Sentinel-2时序数据的新疆焉耆盆地农作物遥感识别与评估

Remote sensing identification and assessment of crops in the Yanqi Basin, Xinjiang, China based on Sentinel-2 time series data

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 32

相关文章 6

Metrics

本文评价

推荐阅读 0

样本类别	样本总数	5:5		6:4		7:3		8:2		9:1
样本类别	样本总数	训练数	检验数	训练数	检验数	训练数	检验数	训练数	检验数	训练数	检验数
番茄	190	95	95	114	76	133	57	152	38	171	19
甘草	70	35	35	42	28	49	21	56	14	63	7
葵花	180	90	90	108	72	126	54	144	36	162	18
辣椒	289	145	144	173	116	202	87	231	58	260	29
芦苇	120	60	60	72	48	84	36	96	24	108	12
棉花	125	63	62	75	50	88	37	100	25	113	12
葡萄	190	95	95	114	76	133	57	152	38	171	19
果林	70	35	35	42	28	49	21	56	14	63	7
水稻	180	90	90	108	72	126	54	144	36	162	18
甜菜	289	145	144	173	116	202	87	231	58	260	29
小麦	120	60	60	72	48	84	36	96	24	108	12
玉米	125	63	62	75	50	88	37	100	25	113	12

[1]	杨一飞, 杨鹏年, 汪昌树, 寇鑫, 谭翻, 徐杰, 王翠. 新疆焉耆盆地农田耗水有效性评价[J]. 干旱区地理, 2023, 46(5): 730-741.
[2]	姜磊鹏,丁建丽,包青岭,葛翔宇,刘景明,王瑾杰. 低空遥感结合卫星影像的河道流量反演[J]. 干旱区地理, 2023, 46(3): 385-396.
[3]	王杰, 龙爱华, 杨广, 邓晓雅, 张沛, 海洋, 李扬. 近25 a来新疆农作物水足迹与经济增长的空间关系分析[J]. 干旱区地理, 2019, 42(3): 526-533.
[4]	张华, 王敏. 基于纹理特征与LSSVM的青土湖地物提取[J]. 干旱区地理, 2018, 41(4): 802-808.
[5]	陈莉. 基于PCA-GASVM的晋陕甘宁地区生态环境评价[J]. 干旱区地理, 2015, 38(6): 1262-1269.
[6]	李东，周可法，孙卫东，王金林，于浩，刘慧. BP神经网络和SVM在矿山环境评价中的应用分析[J]. 干旱区地理, 2015, 38(1): 128-134.