Spatiotemporal patterns and driving factors of aeolian desertification in the Horqin Sandy Land based on kNDVI-Albedo-SWCI three-dimensional feature space and XGBoost-SHAP analysis

doi:10.7522/j.issn.1000-694X.2026.00055

Journal of Desert Research ›› 2026, Vol. 46 ›› Issue (4): 204-216.DOI: 10.7522/j.issn.1000-694X.2026.00055

Previous Articles Next Articles

Spatiotemporal patterns and driving factors of aeolian desertification in the Horqin Sandy Land based on kNDVI-Albedo-SWCI three-dimensional feature space and XGBoost-SHAP analysis

Wanying Cao¹^,²(), Hanchen Duan¹, Xiaopeng Jia¹()

^1.State Key Laboratory of Ecological Safety and Sustainable Development in Arid Lands，Northwest Institute of Eco-Environment and Resources，Chinese Academy of Sciences，Lanzhou 730000，China
^2.University of Chinese Academy of Sciences，Beijing 100049，China

Received:2026-01-07 Revised:2026-04-05 Online:2026-07-20 Published:2026-08-27
Contact: Xiaopeng Jia

Abstract

Abstract:

The Horqin Sandy Land， located in northern China， represents a quintessential agro-pastoral ecotone and serves as a critical area for the implementation of the Three-North Shelter Forest Program. Due to its intricate desertification evolution processes， it is an exemplary region for conducting desertification research. In order to precisely elucidate the spatiotemporal evolution patterns and driving mechanisms of desertification within the Horqin Sandy Land， this study introduces an innovative three-dimensional feature space model， denoted as kNDVI-Albedo-SWCI， to facilitate the dynamic monitoring of desertification across spatial and temporal dimensions. Building upon this framework， the XGBoost model is employed to examine the driving factors of desertification， and the SHAP method is utilized to quantitatively assess the relative contributions of both natural and anthropogenic factors to the evolution of desertification. The findings indicate that：（1） The incorporation of the moisture component within the kNDVI-Albedo-SWCI three-dimensional feature space model enables a comprehensive characterization of vegetation， albedo， and surface water information， thereby enhancing the depiction of desertification characteristics in complex surface environments. （2） The three-dimensional feature space model， utilizing kNDVI-Albedo-SWCI， demonstrates a robust capability in accurately identifying the degree of desertification in the Horqin Sandy Land， achieving an overall classification accuracy of 0.80 and a Kappa coefficient of 0.75. This indicates the model's substantial stability and reliability in extracting desertification information. （3） From a temporal perspective， the desertified area within the Horqin Sandy Land has generally exhibited a declining trend from 2000 to 2025， with marked signs of desertification reversal， suggesting that regional ecological restoration initiatives have yielded positive outcomes. （4） The driving force analysis， conducted using XGBoost-SHAP， highlights that soil texture and actual evapotranspiration are among the most significant driving factors， playing a crucial role in influencing the desertification dynamics of the Horqin Sandy Land. The integration of the three-dimensional feature space model developed in this study with the interpretable machine learning approach of XGBoost-SHAP offers reliable technical support for dynamic monitoring of desertification， analysis of driving mechanisms， and evaluation of the effectiveness of sand prevention and control projects in arid and semi-arid regions.

Key words: three-dimensional feature space, XGBoost-SHAP, aeolian desertification monitoring, driving factors, Horqin Sandy Land

CLC Number:

P931.3

Wanying Cao, Hanchen Duan, Xiaopeng Jia. Spatiotemporal patterns and driving factors of aeolian desertification in the Horqin Sandy Land based on kNDVI-Albedo-SWCI three-dimensional feature space and XGBoost-SHAP analysis[J]. Journal of Desert Research, 2026, 46(4): 204-216.

Figures/Tables 10

Fig.1 Overview of the study area

Table 1 Key indicators for aeolian desertification status and dynamic monitoring

指标	公式
kNDVI	$k N D V I = t a n h N I R - R E D 2 σ 2$
Albedo	$A l b e d o = 0.356 B L U E + 0.13 R E D + 0.373 N I R + 0.085 S W I R 1 + 0.072 S W I R 2 - 0.0018$
SWCI	$S W C I = S W I R 1 - S W I R 2 S W I R 1 + S W I R 2$

Table 1 Key indicators for aeolian desertification status and dynamic monitoring

指标	公式
kNDVI	$k N D V I = t a n h N I R - R E D 2 σ 2$
Albedo	$A l b e d o = 0.356 B L U E + 0.13 R E D + 0.373 N I R + 0.085 S W I R 1 + 0.072 S W I R 2 - 0.0018$
SWCI	$S W C I = S W I R 1 - S W I R 2 S W I R 1 + S W I R 2$

Table 2 Data sources of aeolian desertification driving factors

类型	驱动因子	年份	空间分辨率	数据来源
自然环境	坡度	2000—2025	1 km	地理空间数据云
	坡向	2000—2025	1 km	地理空间数据云
	海拔	2000—2025	1 km	地理空间数据云
	土壤质地	2000—2025	1 km	国家地球系统科学数据中心
	土壤深度	2000—2025	1 km	国家青藏高原科学数据中心
	降水量	2000—2025	1 km	Terra Climate全球高分辨率气候数据集
	实际蒸散发	2000—2025	1 km	Terra Climate全球高分辨率气候数据集
	年平均温度	2000—2025	1 km	Terra Climate全球高分辨率气候数据集
人类活动	人类足迹	2000—2022	1 km	中国农业大学土地科学与技术学院UEMM团队全球逐年人类足迹数据(GHF)
人类活动	土地利用	2000—2023	1 km	武汉大学杨杰、黄昕团队中国土地利用/覆盖数据集(CLCD)

Fig.2 kNDVI-Albedo-SWCI 3D feature space model schematic

Table 3 TDDI classification of the Horqin Sandy Land from 2000 to 2025

年份	沙漠化程度
年份	极重度沙漠化	重度沙漠化	中度沙漠化	轻度沙漠化	非沙漠化
2000	≤0.84	0.84~0.90	0.90~0.95	0.95~0.96	≥0.96
2005	≤0.78	0.78~0.87	0.87~0.92	0.92~0.93	≥0.93
2010	≤0.64	0.64~0.71	0.71~0.78	0.78~0.80	≥0.80
2015	≤0.75	0.75~0.83	0.83~0.89	0.89~0.94	≥0.94
2020	≤1.15	1.15~1.20	1.20~1.23	1.23~1.25	≥1.25
2025	≤0.79	0.79~0.80	0.80~0.82	0.82~0.83	≥0.83

Fig.3 Proportion of each aeolian desertification type area in the Horqin Sandy Land from 2000 to 2025

Fig.4 Changes of aeolian desertification land transfer in the Horqin Sandy Land from 2000 to 2025

Fig.5 Spatiotemporal distribution of aeolian desertification in the Horqin Sandy Land from 2000 to 2025

Fig.6 Aeolian desertification trends in the Horqin Sandy Land from 2000 to 2025

Fig.7 SHAP explainable analysis based on the XGBoost model

References 40

[1]	曾永年，向南平，冯兆东，等.Albedo-NDVI特征空间及沙漠化遥感监测指数研究［J］.地理科学，2006，26（1）：75-81.
[2]	郭瑞霞，管晓丹，张艳婷.我国荒漠化主要研究进展［J］.干旱气象，2015，33（3）：505-513.
[3]	傅伯杰，刘焱序，王帅，等.科学改善荒漠化地区人与自然关系［J］.中国科学院院刊，2024，39（12）：2027-2036.
[4]	康文平，刘树林.沙漠化遥感监测与定量评价研究综述［J］.中国沙漠，2014，34（5）：1222-1229.
[5]	Zhi Y， Liu S， Wang T，et al.Extraction of desertification information and spatiotemporal change in the Qinghai-Tibetan Plateau based on optimal feature space combination ［J］.Land Degradation & Development，2025，36（8）：2746-2763.
[6]	赵鸿雁，颜长珍，李森，等.黄河流域2000-2020年土地沙漠化遥感监测及驱动力分析［J］.中国沙漠，2023，43（3）：127-137.
[7]	丁建丽，姚远，王飞.基于三维光谱特征空间的干旱区土壤盐渍化遥感定量研究［J］.土壤学报，2013，50（5）：853-861.
[8]	刘盼盼，郭兵.基于随机森林-三维特征空间法的西南山区石漠化演变格局及主导因子分析［J］.生态学报，2026，46（4）：1731-1751.
[9]	Guo B， Xu M， Zhang R，et al.Dynamic monitoring of rocky desertification utilizing a novel model based on Sentinel-2 images and KNDVI［J］.Geomatics，Natural Hazards and Risk，2024，15（1）：2399659.
[10]	何思璇，杨杰皓，张国有，等.基于XGBoost-SHAP模型的滇中典型区采矿损毁地植被变化及影响因子分析［J］.测绘通报，2025（7）：58-65.
[11]	谭洁，危千骏，廖朝阳，等.基于XGBoost-SHAP可解释机器学习模型的城市形态与地表温度的关系［J］.应用生态学报，2025，36（3）：659-670.
[12]	赵学勇，张春民，左小安，等.科尔沁沙地沙漠化土地恢复面临的挑战［J］.应用生态学报，2009，20（7）：1559-1564.
[13]	赵哈林，赵学勇，张铜会，等.我国西北干旱区的荒漠化过程及其空间分异规律［J］.中国沙漠，2011，31（1）：1-8.
[14]	Duan H C， Wang T， Xue X，et al.Dynamic monitoring of aeolian desertification based on multiple indicators in Horqin Sandy Land，China［J］.Science of the Total Environment，2019，650：2374-2388.
[15]	常学礼，蔡明玉，张继平，等.科尔沁沙地典型地区人工造林对沙漠化过程的影响［J］.中国沙漠，2009，29（4）：611-616.
[16]	龚相文，李玉强，王旭洋，等.近20年科尔沁地区植被净初级生产力时空动态及其影响因素定量评估［J］.地球科学进展，2025，40（12）：1333-1349.
[17]	任雨，张勃，陈曦东.科尔沁沙地土地荒漠化敏感性评估［J］.中国沙漠，2023，43（2）：159-169.
[18]	常嘉乐，石昊，李方昊，等.科尔沁沙地土壤沙化进程与风蚀驱动因子关系［J］.地理学报，2026，81（1）：48-63.
[19]	Li H， Hu Y F， Ao Z D.Identification of critical drought thresholds affecting vegetation on the Mongolian Plateau［J］.Ecological Indicators，2024，166：111234.
[20]	于静，高亚敏，付铭.科尔沁草原NDVI时空变化特征及其对气候的响应［J］.中国草地学报，2020，42（6）：82-90.
[21]	段翰晨，黄背英.基于AHP与改进型MEDALUS模型耦合的科尔沁沙地土地沙漠化敏感性综合评价［J］.中国沙漠，2024，44（4）：137-148.
[22]	刘永杰，杜鹤强，范亚伟，等.基于Google Earth Engine（GEE）的毛乌素沙地风蚀荒漠化过程监测［J］.中国沙漠，2025，45（2）：262-274.
[23]	Shao W Y， Wang Q Z， Guan Q Y，et al.Environmental sensitivity assessment of land desertification in the Hexi Corridor，China［J］.Catena，2023，220：106728.
[24]	Song X， Wang T， Xue X，et al.Monitoring and analysis of aeolian desertification dynamics from 1975 to 2010 in the Heihe River Basin，northwestern China［J］.Environmental Earth Sciences，2015，74（4）：3123-3133.
[25]	岳辉，刘英.基于NDVI-Albedo特征空间的陕西省干旱与荒漠化遥感监测［J］.西北林学院学报，2019，34（1）：198-205.
[26]	任艳群，刘海隆，唐立新，等.基于NDVI-Albedo特征空间的沙漠化动态变化研究：以准格尔盆地南缘为例［J］.水土保持通报，2014，34（2）：267-271.
[27]	赵哈林，苏永中，周瑞莲.我国北方沙区退化植被的恢复机理［J］.中国沙漠，2006，26（3）：323-328.
[28]	段翰晨，王涛，薛娴，等.基于RS与GIS的科尔沁沙地沙漠化时空演变［J］.中国沙漠，2013，33（2）：470-477.
[29]	Chen Q， Fu H， Li X M，et al.Classification of karst rocky desertification levels in Jinsha County using a feature space method based on SDGSAT-1 multispectral data［J］.Remote Sensing，2024，16（24）：4786.
[30]	刘俊壕，周海盛，郭群.中国北方干旱半干旱区沙漠化治理对植被格局的影响［J］.中国沙漠，2023，43（5）：204-213.
[31]	花婷，王训明.东亚干旱半干旱区沙漠化与气候变化相互影响研究进展［J］.地理科学进展，2014，33（6）：841-852.
[32]	连杰，赵学勇，左小安，等.科尔沁沙地水域景观格局的时空动态：以奈曼旗为例［J］.中国沙漠，2012，32（1）：210-218.
[33]	张钤，张方敏，卢琦，等.生态工程对科尔沁沙地主要生态服务功能的影响［J］.水土保持通报，2021，41（5）：154-159.
[34]	金海珍，于德永，郝蕊芳，等.科尔沁沙地关键生态系统服务的约束关系分析［J］.生态学报，2021，41（18）：7249-7259.
[35]	罗永清，白浩江，贾豪，等.科尔沁沙地生态恢复研究进展与思考［J］.中国沙漠，2025，45（4）：75-84.
[36]	王永芳.基于多源数据融合与DPSIR模型的科尔沁沙地沙漠化生态风险评价［D］.长春：东北师范大学，2016.
[37]	勿吉斯古冷，那日苏，丽娜，等.2001-2020年呼伦贝尔草原土地沙漠化敏感性时空格局演化［J］.干旱区地理，2025，48（5）：825-837.
[38]	吴小燕，高永，党晓宏，等.1989-2019年库布齐沙漠植被覆盖度的时空变化［J］.水土保持通报，2022，42（2）：300-306.
[39]	李乃强，徐贵阳.基于自然间断点分级法的土地利用数据网格化分析［J］.测绘通报，2020（4）：106-110.
[40]	Zhi Y， Liu S， Wang T，et al.Quantifying the impact of natural and human activity factors on desertification in the Qinghai-Tibetan Plateau［J］.Catena，2024，246：108392.

Spatiotemporal patterns and driving factors of aeolian desertification in the Horqin Sandy Land based on kNDVI-Albedo-SWCI three-dimensional feature space and XGBoost-SHAP analysis

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 40

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Fei Wang, Jun Han. Spatiotemporal evolution and driving factors of land use carbon emissions in the Lanzhou-Xining Urban Agglomeration [J]. Journal of Desert Research, 2026, 46(4): 1-11.
[2]	Jing Yu, Wenshuo Wu, Ming Fu, Yamin Gao. Spatiotemporal variation and causes of vegetation coverage in Horqin Sandy Land [J]. Journal of Desert Research, 2026, 46(4): 160-174.
[3]	Yamin Gao, Yuhan Jiang, Jing Yu, Linli Sun, Lasu Na, Xiaohui Bai, Chengzhuo Zheng. Characteristics of extreme climate change in Horqin Sandy Land from 1971 to 2025 [J]. Journal of Desert Research, 2026, 46(4): 175-192.
[4]	Aimin Li, Peixia Yan, Hongzhen Tang, Ming Zhou, Yanxia Pan, Juan Ma. Ecosystem functional zoning of the Horqin Sandy Land based on the coupling of multi-dimensional ecological characteristics [J]. Journal of Desert Research, 2026, 46(4): 22-33.
[5]	Xiaopeng Li, Kang Li, Jing Xu, Fugui Jia, Shuang Lei. Eco-environment evolution and driving factors of the Loess Plateau based on the XGBoost-SHAP approach [J]. Journal of Desert Research, 2026, 46(3): 175-186.
[6]	Anqi Cong, Jin Zhan, Ning Wang, Tonghui Zhang, Xinping Liu. Effects of long-term cultivation on soil physicochemical properties and enzyme activities of artificial sandy paddy field in semi-arid region [J]. Journal of Desert Research, 2026, 46(3): 187-194.
[7]	Yuan Yuan, Caiyun Zhang, Xiaoxu Lang, Qing Zhang. Current status of invasive alien plants in the Horqin Sandy Land [J]. Journal of Desert Research, 2026, 46(3): 296-303.
[8]	Xiaofeng Zuo, Yajuan Wei, Hejun Zuo, Haibing Wang, Min Yan, Xinglong Xie. Biomass distribution and carbon sink function of Nitraria tangutorum nebkhas in different climate zones [J]. Journal of Desert Research, 2026, 46(2): 86-94.
[9]	Jing Xu, Bin Yang, Hui Feng. The coupling pattern between new-type urbanization and economic resilience in Gansu Province and their driving factors [J]. Journal of Desert Research, 2026, 46(2): 263-276.
[10]	Bo Han, Jing Zhang, Xiaoguang Wang, Guangwei Huo, Peiying Liao, Zixiao Yang, Yitong Tao, Yunna Wu. Dynamic characteristics and driving forces of net primary productivity of vegetation in Horqin Sandy Land in 2001-2020 [J]. Journal of Desert Research, 2026, 46(2): 348-357.
[11]	Lutong Wan, Xiaodan Liu, Hanqing Guo, Wanlai Xue, Kexuan Liu, Jin Li, Lili Wang, Honghao Liu. Multi-scale characteristics and driving factors of trade-off / synergy of ecosystem services in the ecological conservation area of western Beijing [J]. Journal of Desert Research, 2025, 45(6): 206-219.
[12]	Guanghui Shen, Jianying Zhang, Yue Han, Long Jia. Spatial distribution pattern and driving factors of Tenebrionidae in the Badain Jaran Desert margin [J]. Journal of Desert Research, 2025, 45(6): 323-333.
[13]	Pengfei Zhang, Jiaqi Han, Zhenjiang Zhao, Yanyan Dai, Geng Liu, Jinlong Chao, Lei Zhang. Coupling characteristics and the driving factors of agricultural water poverty and food production vulnerability in Fenhe River basin， China [J]. Journal of Desert Research, 2025, 45(5): 13-23.
[14]	Siqi Li, Haibing Wang, Xiaofei Yuan, Huricha Ao, Haoqin Yang. Temporal and spatial evolution of landscape ecological risks and driving forces in the Mu Us Sandy Land [J]. Journal of Desert Research, 2025, 45(5): 230-240.
[15]	Bo Yao, Jie Lian, Xiangwen Gong, Xiaoming Mou, Yulin Li, Yuqiang Li, Xuyang Wang. Spatial patterns and influencing factors of soil microbial carbon， nitrogen and phosphorus stoichiometry in Horqin Sandy Land [J]. Journal of Desert Research, 2025, 45(4): 153-165.