基于可解释机器学习模型的高寒草地土壤盐渍化反演

doi:10.12118/j.issn.1000－6060.2025.411

干旱区地理 ›› 2026, Vol. 49 ›› Issue (3): 549-558.doi: 10.12118/j.issn.1000－6060.2025.411 cstr: 32274.14.ALG2025411

基于可解释机器学习模型的高寒草地土壤盐渍化反演

杨明新¹^,²^,³^,⁴(), 宁晓春², 杨刘生², 张亚飞², 石明明², 康彦斌², 黄青东智², 王守兴², 周华坤³()

1.青海师范大学地理科学学院，青海西宁 810008
2.中国地质调查局西宁自然资源综合调查中心，青海西宁 810021
3.中国科学院西北高原生物研究所青海省寒区恢复生态学重点实验室，青海西宁 810008
4.自然资源要素耦合过程与效应重点实验室，北京 100055

收稿日期:2025-07-15 修回日期:2025-09-09 出版日期:2026-03-25 发布日期:2026-03-24
通讯作者: 周华坤（1974-），男，博士，研究员，主要从事高寒草地恢复生态学研究. E-mail: hkzhou@nwipb.cas.cn
作者简介:杨明新（1990-），男，博士研究生，主要从事寒区资源生态观测与监测评价研究. E-mail: ymxin@bjfu.edu.cn
基金资助:
中国地质调查局自然资源综合调查指挥中心科技创新基金(KC20240013);中国地质调查项目(DD20242555);自然资源部自然资源要素耦合过程与效应重点实验室开放课题(2024KFKT009)

Inversion of soil salinization in alpine grasslands based on explainable machine learning models

YANG Mingxin¹^,²^,³^,⁴(), NING Xiaochun², YANG Liusheng², ZHANG Yafei², SHI Mingming², KANG Yanbin², HUANGQING Dongzhi², WANG Shouxing², ZHOU Huakun³()

1. College of Geographic Sciences, Qinghai Normal University, Xining 810008, Qinghai, China
2. Xining Natural Resources Comprehensive Survey Center, China Geological Survey, Xining 810021, Qinghai, China
3. Key Laboratory of Restoration Ecology for Cold Regions Laboratory in Qinghai, Northwest of Plateau Biology, Chinese Academy of Sciences, Xining 810008, Qinghai, China
4. Key Laboratory of Coupling Processes and Effects of Natural Resource Elements, Beijing 100055, China

Received:2025-07-15 Revised:2025-09-09 Published:2026-03-25 Online:2026-03-24

摘要/Abstract

摘要：

草地土壤盐渍化不仅加剧草地植被退化，影响草地生态功能发挥，同时制约退化草地生态保护修复。在黄河源高寒草地土壤盐渍化发育地区，通过地面网格采样，结合哨兵2号（Sentinel-2）光谱指数，构建了基于特征筛选的可解释机器学习盐渍化反演模型，揭示了盐渍化模型的影响因素，并监测了区域盐渍化的空间分布特征。结果表明：（1）基于逐步回归（STEP）特征筛选结合随机森林模型（RF）构建的盐渍化反演模型精度最优，决定系数（R²）为0.64，均方根误差（RMSE）为0.76 g·kg^-1。（2）基于沙普利加性解释（SHAP）对最优模型分析表明，9个特征变量中归一化水体指数（NDWI）对本研究模型贡献度最高，且与土壤盐渍化呈正相关。（3）监测表明，研究区47.13%区域为轻度盐渍化，33.19%区域为中度盐渍化，而重度盐渍化和盐土在研究区发育较少且主要沿河流及沟谷地带分布。通过探索不同方法组合的可解释盐渍化监测模型，为黄河流域生态保护和高质量发展提供科学依据和技术支撑。

关键词: 盐渍化, 机器学习, SHAP, 高寒草地, 黄河源

Abstract:

Soil salinization in grasslands exacerbates the degradation of grassland vegetation, which affects the performance of grassland ecological functions, restricting the ecological protection and restoration of degraded grasslands. In this study, we constructed an explainable machine-learning salinity inversion model based on feature screening by ground grid sampling combined with Sentinel-2 spectral index in the salinity development area of alpine grassland at the Yellow River source of China, revealed the influencing factors of the salinity model, and monitored the spatial distribution characteristics of regional salinity. The results showed that: (1) The salinity inversion model based on stepwise regression characteristic screening combined with a random forest model resulted in the best accuracy, with a coefficient of determination of 0.64 and a root mean squared error of 0.76 g·kg^-1. (2) Shapley additive explanations analysis of the optimal model determined that among the nine feature variables, the normalized difference water index contributed most significantly to the model and showed a positive correlation with soil salinization. (3) Monitoring revealed that 47.13% of the study area exhibited mild salinization, whereas 33.19% exhibited moderate salinization. Less prevalent severe salinization and saline soils were primarily distributed along rivers and valleys. This study contributes to the exploration of interpretable salinization-monitoring models and provides a scientific basis and technical support for ecological conservation and high-quality development in the Yellow River Basin.

Key words: salinization, machine learning, SHAP, alpine grassland, the Yellow River source

杨明新, 宁晓春, 杨刘生, 张亚飞, 石明明, 康彦斌, 黄青东智, 王守兴, 周华坤. 基于可解释机器学习模型的高寒草地土壤盐渍化反演[J]. 干旱区地理, 2026, 49(3): 549-558.

YANG Mingxin, NING Xiaochun, YANG Liusheng, ZHANG Yafei, SHI Mingming, KANG Yanbin, HUANGQING Dongzhi, WANG Shouxing, ZHOU Huakun. Inversion of soil salinization in alpine grasslands based on explainable machine learning models[J]. Arid Land Geography, 2026, 49(3): 549-558.

图/表 7

图1

表1

表2

图2

图3

图4

图5

参考文献 40

[1]	Butcher K, Wick A F, Desutter T, et al. Soil salinity: A threat to global food security[J]. Agronomy Journal, 2016, 108(6): 2189-2200. doi: 10.2134/agronj2016.06.0368
[2]	李建国, 濮励杰, 朱明, 等. 土壤盐渍化研究现状及未来研究热点[J]. 地理学报, 2012, 67(9): 1233-1245.
	[Li Jianguo, Pu Lijie, Zhu Ming, et al. The present situstion and hot issues in the salt-affected soil research[J]. Acta Geographica Science, 2012, 67(9): 1233-1245.]
[3]	杨劲松, 姚荣江, 王相平, 等. 中国盐渍土研究: 历程、现状与展望[J]. 土壤学报, 2022, 59(1): 10-27.
	[Yang Jinsong, Yao Rongjiang, Wang Xiangping, et al. Research on salt-affected soils in China: History, status quo and prospect[J]. Acta Pedologica Science, 2022, 59(1): 10-27.]
[4]	Li J G, Pu L J, Han M F, et al. Soil salinization research in China: Advances and prospects[J]. Journal of Geographical Sciences, 2014, 24(5): 943-960. doi: 10.1007/s11442-014-1130-2
[5]	吴秀泉, 乌兰图雅, 张萨日郎, 等. 中国干旱区草地土壤盐渍化研究可视化分析[J]. 内蒙古师范大学学报(自然科学版), 2024, 53(2): 120-128.
	[Wu Xiuquan, Ulan Tuya, Zhang Saerilang, et al. Visualization analysis on grassland soil salinization in arid regions of China[J]. Journal of Inner Mongolia Normal University (Natural Science Edition), 2024, 53(2): 120-128.]
[6]	Cao C Y, Tao S, Cui Z B, et al. Response of soil properties and microbial communities to increasing salinization in the meadow grassland of northeast China[J]. Microbial Ecology, 2021, 82(3): 722-735. doi: 10.1007/s00248-021-01695-x pmid: 33511437
[7]	Yang L, Zhao G J, Mu X M, et al. Integrated assessments of land degradation on the Qinghai-Xizang Plateau[J]. Ecological Indicators, 2023, 147: 109945, doi: 10.1007/s00248-021-01695-x.
[8]	赵起越, 夏夜, 邹本东. 土壤盐渍化成因危害及恢复[J]. 农业与技术, 2022, 42(11): 115-119.
	[Zhao Qiyue, Xia Ye, Zou Bendong. Soil salinization causes and hazards and restoration[J]. Agriculture and Technology, 2022, 42(11): 115-119.]
[9]	陈振宇, 赵禹, 白金, 等. 干旱绿洲区包气带土壤盐分分布特征及运移机制——以新疆焉耆盆地为例[J]. 地质论评, 2024, 70(5): 1857-1872.
	[Chen Zhenyu, Zhao Yu, Bai Jin, et al. Distribution characteristics and migration mechanism of soil salt in the aeration zone of arid oasis areas: A case study of the Yanqi Basin, Xinjiang[J]. Geological Review, 2024, 70(5): 1857-1872.]
[10]	Metternicht G I, Zinck J A. Remote sensing of soil salinity: Potentials and constraints[J]. Remote Sensing of Environment, 2003, 85(1): 1-20. doi: 10.1016/S0034-4257(02)00188-8
[11]	王敬哲, 丁建丽, 葛翔宇, 等. 基于星地传感技术的土壤盐渍化监测进展与展望[J]. 遥感学报, 2024, 28(9): 2187-2208.
	[Wang Jingzhe, Ding Jianli, Ge Xiangyu, et al. Monitoring soil salinization on the basis of remote sensing and proximal soil sensing: Progress and prospective[J]. National Remote Sensing Bulletin, 2024, 28(9): 2187-2208.] doi: 10.11834/jrs.20233164
[12]	Abuelgasim A, Ammad R. Mapping soil salinity in arid and semi-arid regions using Landsat 8 OLI satellite data[J]. Remote Sensing Applications, 2019, 13: 415-425.
[13]	郭佳丽, 马勇刚, 潘恒, 等. 艾比湖春夏季土壤盐渍化卫星监测对比分析[J]. 干旱区地理, 2025, 48(12): 2143-2157. doi: 10.12118/j.issn.1000-6060.2025.044
	[Guo Jiali, Ma Yonggang, Pan Heng, et al. Comparative analysis of satellite monitoring of soil salinization in Ebinur Lake during spring and summer[J]. Arid Land Geography, 2025, 48(12): 2143-2157.] doi: 10.12118/j.issn.1000-6060.2025.044
[14]	李星佑, 张飞, 王筝. 土壤盐渍化遥感监测模型构建方法现状与发展趋势[J]. 自然资源遥感, 2022, 34(4): 11-21.
	[Li Xingyou, Zhang Fei, Wang Zheng. Present situation and development trend in building remote sensing monitoring models of soil salinization[J]. Remote Sensing for Natural Resources, 2022, 34(4): 11-21.]
[15]	田义超, 郑丹琳, 张强, 等. 基于国产资源一号02D卫星和机器学习算法的钦州湾滨海土壤盐分反演[J]. 中国环境科学, 2024, 44(1): 371-385.
	[Tian Yichao, Zheng Danlin, Zhang Qiang, et al. Inversion of coastal soil salinity in Qinzhou Bay based on domestic ZY1-02D satellite and machine learning algorithm[J]. China Environmental Science, 2024, 44(1): 371-385.]
[16]	Jia P P, Zhang J H, Liang Y N, et al. The inversion of arid-coastal cultivated soil salinity using explainable machine learning and Sentinel-2[J]. Ecological Indicators, 2024, 166: 112364, doi: 10.1016/j.ecolind.2024.112364.
[17]	王飞, 杨胜天, 丁建丽, 等. 环境敏感变量优选及机器学习算法预测绿洲土壤盐分[J]. 农业工程学报, 2018, 34(22): 102-110.
	[Wang Fei, Yang Shengtian, Ding Jianli, et al. Environment sensitive variable optimization and machine learning algorithm using in soil salt predictionat oasis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(22): 102-110.]
[18]	巴亚岚, 张智韬, 谢坪良, 等. 集成Sentinel-1/2和环境变量的新疆农田土壤含盐量反演[J]. 农业工程学报, 2024, 40(16): 171-179.
	[Ba Yalan, Zhang Zhitao, Xie Pingliang, et al. Inverting soil salinity of farmland in Xinjiang by integrating Sentinel-1/2 and environmental variables[J]. Transactions of the Chinese Society of Agricultural Engineering, 2024, 40(16): 171-179.]
[19]	骆振海, 张超, 冯绍元, 等. 土壤盐渍化光学遥感监测方法研究进展[J]. 自然资源遥感, 2024, 36(4): 9-22.
	[Luo Zhenhai, Zhang Chao, Feng Shaoyuan, et al. Advances in research on methods for optical remote sensing monitoring of soil salinization[J]. Remote Sensing for Natural Resources, 2024, 36(4): 9-22.]
[20]	张佘淑, 赵军. 机器学习在土壤盐渍化遥感中应用的文献计量分析[J]. 草业科学, 2023, 40(11): 2812-2821.
	[Zhang Sheshu, Zhao Jun. Bibliometric analysis of machine learning applications in remote sensing of soil salinization[J]. Pratacultural Science, 2023, 40(11): 2812-2821.]
[21]	Ponce B A V, Schmitt V, Maier C S, et al. Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development[J]. Clinical and Translational Science, 2024, 17(11): e70056, doi: 10.1111/cts.70056.
[22]	Wang F, Liang R L, Li S Y, et al. Assessing the impact of multi-source environmental variables on soil organic carbon in different land use types of China using an interpretable high-precision machine learning method[J]. Ecological Indicators, 2024, 169: 112865, doi: 10.1016/j.ecolind.2024.112865.
[23]	Li X H, Chen J J, Chen Z Z, et al. Explainable machine learning-based fractional vegetation cover inversion and performance optimization: A case study of an alpine grassland on the Qinghai-Tibet Plateau[J]. Ecological Informatics, 2024, 82: 102768, doi: 10.1016/j.ecoinf.2024.102768.
[24]	尚天浩, 陈睿华, 贾萍萍, 等. 基于多源光谱遥感估算银北地区土壤可溶性盐基氯离子含量[J]. 生态学杂志, 2024, 44(4): 1161-1169.
	[Shang Tianhao, Chen Ruihua, Jia Pingping, et al. Estimation of soil soluble salt-based Cl^-content in northern Ningxia, China based on multi-source spectral remote sensing[J]. Chinese Journal of Ecology, 2024, 44(4): 1161-1169.]
[25]	高怡婷, 罗栋梁, 陈方方, 等. 黄河源头区地面热状态及冻融特征[J]. 地理学报, 2023, 78(3): 604-619. doi: 10.11821/dlxb202303007
	[Gao Yiting, Luo Dongliang, Chen Fangfang, et al. Characteristics of the thermal regime and freeze-thaw cycles on the ground surface in permafros regions in the headwater area of the Yellow River[J]. Acta Geographica Sinica, 2023, 78(3): 604-619.] doi: 10.11821/dlxb202303007
[26]	谢俊博, 王兴鹏, 何帅, 等. 基于光谱指数建模的沙井子灌区土壤盐分反演[J]. 干旱区地理, 2024, 47(7): 1199-1209. doi: 10.12118/j.issn.1000-6060.2023.584
	[Xie Junbo, Wang Xingpeng, He Shuai, et al. Soil salinity inversion in the Shajingzi irrigation district based on spectral index modeling[J]. Arid Land Geography, 2024, 47(7): 1199-1209.] doi: 10.12118/j.issn.1000-6060.2023.584
[27]	杨练兵, 陈春波, 郑宏伟, 等. 基于优化随机森林回归模型的土壤盐渍化反演[J]. 地球信息科学学报, 2021, 23(9): 1662-1674. doi: 10.12082/dqxxkx.2021.200711
	[Yang Lianbing, Chen Chunbo, Zheng Hongwei, et al. Retrieval of soil salinity content based on random forests regression optimized by Bayesian optimization algorithm and gentic algorithm[J]. Journal of Geo-Information Science, 2021, 23(9): 1662-1674.]
[28]	谢志英, 朱文泉, 付永硕. 植被物候遥感监测关键问题[J]. 遥感学报, 2024, 28(9): 2131-2143.
	[Xie Zhiying, Zhu Wenquan, Fu Yongshuo. Key issues of remote sensing-based vegetation phenologymonitoring[J]. National Remote Sensing Bulletin, 2024, 28(9): 2131-2143.] doi: 10.11834/jrs.20233088
[29]	Andersen C M, Bro R. Variable selection in regression: Atutorial[J]. Journal of Chemometrics, 2010, 24(11-12): 728-737. doi: 10.1002/cem.v24.11/12
[30]	Duan K B, Rajapakse J C, Wang H, et al. Multiple SVM-RFE for gene selection in cancer classification with expression data[J]. IEEE Transactions on Nanobioscience, 2005, 4(3): 228-234. doi: 10.1109/TNB.2005.853657
[31]	Smith G. Step away from stepwise[J]. Journal of Big Data, 2018, 5(1): 32, doi: 10.1186/s40537-018-0143-6.
[32]	Bentéjac C, Csörgő A, Martínez-Muñoz G. A comparative analysis of gradient boosting algorithms[J]. Artificial Intelligence Review, 2021, 54(3): 1937-1967. doi: 10.1007/s10462-020-09896-5
[33]	黄华雨, 丁启东, 张俊华, 等. 地面高光谱耦合可解释性集成机器学习的农田土壤含盐量和pH反演[J]. 环境科学, 2026, 47(2): 1080-1091.
	[Huang Huayu, Ding Qidong, Zhang Junhua, et al. Ground-based hyperspectral coupled interpretable integrated machine learning for salinity and pH inversion in agricultural soils[J]. Environment Science, 2026, 47(2): 1080-1091.]
[34]	Ge J, Hou M J, Liang T G, et al. Spatiotemporal dynamics of grassland aboveground biomass and its driving factors in north China over the past 20 years[J]. Science of the Total Environment, 2022, 826: 154226, doi: 10.1016/j.scitotenv.2022.154226.
[35]	Yang M X, Chen A, Cao W Q, et al. Spatial and temporal patterns of grassland species diversity and their driving factors in the Three Rivers Headwater region of China from 2000 to 2021[J]. Remote Sensing, 2024, 16(21): 4005, doi: 10.3390/rs16214005.
[36]	李春泽, 张超, 张皓源, 等. 基于XGBoost与地理加权回归的吉林省西部土壤盐渍化反演[J]. 中国农业大学学报, 2024, 29(2): 1-10.
	[Li Chunze, Zhang Chao, Zhang Haoyuan, et al. Inversion of soil salinization in western Jilin Province based on XGBoost and geographically weighted regression[J]. Journal of China Agricultural University, 2024, 29(2): 1-10.]
[37]	蒙莉娜, 丁建丽, 王敬哲, 等. 基于环境变量的渭干河-库车河绿洲土壤盐分空间分布[J]. 农业工程学报, 2020, 36(1): 175-181.
	[Meng Lina, Ding Jianli, Wang Jingzhe, et al. Spatial distribution of soil salinity in Ugan-Kuqa River delta oasis based on environmental variables[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(1): 175-181.]
[38]	张永杰, 兰文旭, 蔡和生. 新疆科克苏湿地边缘带土壤水盐和养分含量的空间分布特征[J]. 湿地科学与管理, 2025, 21(2): 10-16.
	[Zhang Yongjie, Lan Wenxu, Cai Hesheng. The spatial distribution characteristics of soil water, salt, and nutrient content in the marginal zone of the Kokso wetland in Xinjiang[J]. Wetland Science & Management, 2025, 21(2): 10-16.]
[39]	Jiang Z H, Hao Z, Ding J L, et al. Weighted variable optimization-based method for estimating soil salinity using multi-source remote sensing data: A case study in the weiku oasis, Xinjiang, China[J]. Remote Sensing, 2024, 16(17): 3145, doi: 10.3390/rs16173145.
[40]	Li Y F, Wang C, Wright A, et al. Combination of GF-2 high spatial resolution imagery and land surface factors for predicting soil salinity of muddy coasts[J]. Catena, 2021, 202: 105304, doi: 10.1016/j.catena.2021.105304.

光谱指数	计算公式	参考文献
盐分指数（S1）	Blue/Re d	[27]
盐分指数（S2）	(Blue-Re d)/(Blue+Re d)	[27]
盐分指数（S3）	Green×Re d/Blue	[27]
盐分指数（S4）	$\sqrt{Blue\times NIR}$	[15]
盐分指数（S5）	Blue×Re d/Green	[27]
盐分指数（S6）	Re d×NIR/Green	[27]
盐分指数（S7）	$(Swir1-Swir\left.2\right)/(Swri1+Swri\left.2\right)$	[18]
盐分指数（S8）	(Green+Re d)/2	[18]
盐分指数（S9）	(Green+Re d+NIR)/2	[18]
盐分指数（SI）	$\sqrt{Blue+Re d}$	[27]
盐分指数（SI_T）	Re d×NIR×100	[27]
盐分指数（SI1）	$\sqrt{Green\times Re d}$	[18]
盐分指数（SI2）	$\sqrt{Gree{n}^{2}+Re {d}^{2}+NI{R}^{2}}$	[18]
盐分指数（SI3）	$\sqrt{Gree{n}^{2}+Re {d}^{2}}$	[18]
盐分指数（SI4）	Swir1/NIR	[18]
归一化盐分指数（NDSI）	(Re d-NIR)/(Re d+NIR)	[27]
归一化植被指数（NDVI）	(NIR-Re d)/(NIR+Re d)	[19]
增强型植被指数（EVI）	$2.5\times \left[(NIR-Re d)/(NIR+6\times Re d-7.5\times Blue+1)\right]$	[27]
归一化物候指数（NDPI）	$\left[NIR-(0.74\times Re d+0.26\times Swir\left.1\right)\right]/\left[NIR+(0.74\times Re d+0.26\times Swir\left.1\right)\right]$	[28]
红外植被指数（IPVI）	NIR/(NIR+Re d)	[18]
归一化水体指数（NDWI）	(NIR-Swir1)/(NIR+Swir1)	[19]
土壤调节植被指数（SAVI）	$1.5\times (NIR-Re d)/(NIR+Re d+0.5)$	[19]

盐渍化等级	分级标准/g·kg^-1	样本量	最小值/g·kg^-1	最大值/g·kg^-1	平均值/g·kg^-1	标准差/g·kg^-1	变异系数/%
非盐渍化	<1	18	0.57	0.95	0.80	0.12	15.44
轻度盐渍化	1~2	86	1.00	1.99	1.44	0.29	19.88
中度盐渍化	2~4	17	2.00	3.56	2.66	0.50	18.76
重度盐渍化	4~6	4	4.30	5.56	4.90	0.56	11.46
盐土	≥6	4	6.01	11.65	8.07	2.51	31.12
所有实测数据		129	0.57	11.65	3.57	1.45	40.61

基于可解释机器学习模型的高寒草地土壤盐渍化反演

Inversion of soil salinization in alpine grasslands based on explainable machine learning models

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 40

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	尼格拉·塔什甫拉提, 马莹轩, 阿不都外力·热合曼, 杨磊. 基于哨兵数据与特征空间模型的新疆渭库绿洲土壤盐渍化遥感反演[J]. 干旱区地理, 2026, 49(2): 287-300.
[2]	李佳琳, 李新虎, 王弘超, 崔萌萌, 郭语博, 靳浩东, 任萧萧. 不同影响因素下盐结皮蒸发阻力定量模拟研究[J]. 干旱区地理, 2026, 49(1): 80-93.
[3]	郭佳丽, 马勇刚, 潘恒, 李娜, 孙长宁, 孙倩, 周文昶, 党瑀璇. 艾比湖春夏季土壤盐渍化卫星监测对比分析[J]. 干旱区地理, 2025, 48(12): 2143-2157.
[4]	高瑞翔, 罗格平, 张文强, 谢明娟, 王渊刚. 长短期记忆网络在生态系统碳通量反演中的优势与应用[J]. 干旱区地理, 2025, 48(12): 2210-2219.
[5]	辛悦, 苏立娟, 郑旭程, 李慧, 衣娜娜, 靳雨晨. 内蒙古冰雹特征及基于机器学习的冰雹识别方法研究[J]. 干旱区地理, 2025, 48(1): 11-19.
[6]	蒙慧敏, 占车生, 胡实, 林忠辉. 大型灌区土壤水盐运移模拟研究进展[J]. 干旱区地理, 2024, 47(9): 1566-1576.
[7]	谢俊博, 王兴鹏, 何帅, 刘洋, 忠智博, 李妍, 洪国军. 基于光谱指数建模的沙井子灌区土壤盐分反演[J]. 干旱区地理, 2024, 47(7): 1199-1209.
[8]	刘瑞亮, 贾科利, 李小雨, 陈睿华, 王怡婧, 张俊华. 组合光学和微波遥感的耕地土壤含盐量反演[J]. 干旱区地理, 2024, 47(3): 433-444.
[9]	唐太斌, 周保, 金晓媚, 魏赛拉加, 马涛, 张永艳. 黄河源区夏季地表温度变化研究[J]. 干旱区地理, 2023, 46(8): 1250-1259.
[10]	李科, 丁建丽, 韩礼敬, 葛翔宇, 顾永昇, 周倩, 吕阳霞. 基于PlanetScope影像的典型绿洲土壤盐渍化数字制图[J]. 干旱区地理, 2023, 46(8): 1291-1302.
[11]	石聪, 陈礼瀚, 张怡菲, 何帅, 谢海霞. 新疆小海子灌区耕地土壤盐渍化特征研究[J]. 干旱区地理, 2023, 46(8): 1314-1323.
[12]	成硕, 李艳忠, 星寅聪, 于志国, 王渊刚, 黄曼捷. 遥感降水产品对黄河源区水文干旱特征的模拟性能分析[J]. 干旱区地理, 2023, 46(7): 1063-1072.
[13]	崔锦涛, 买买提·沙吾提. 基于特征波段选择和机器学习的陆地棉叶片水分估算[J]. 干旱区地理, 2023, 46(11): 1836-1847.
[14]	蒋磊, 刘小龙, 郭帅, 何亮, 邢建磊, 郭俊杰. 基于Logistic回归分析的土壤盐渍化易发性评价——以新疆南疆塔里木灌区为例[J]. 干旱区地理, 2023, 46(11): 1858-1867.
[15]	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.