Spatiotemporal evolution characteristics and influencing factor analysis of soil salinization in the oasis area of northern Xinjiang

doi:10.14088/j.cnki.issn0439-8114.2026.08.007

Abstract

Abstract: To clarify the spatiotemporal evolution characteristics and driving mechanisms of soil salinization in the oasis area of northern Xinjiang from 2010 to 2023, this study constructed four soil salt content (SSC) inversion models, namely random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and partial least squares regression (PLS), based on measured soil salt data from 2010 and 2023, Landsat remote sensing images, and multi-source environmental factor data. By combining the salinization grade transfer matrix with random forest feature importance analysis, the spatiotemporal evolution pattern of soil salinization and the main influencing factors were revealed. The results indicated that the RF model constructed with Red, SI5, kNDVI, SDI, SAIO, and WI as input variables had the best comprehensive fitting performance. From 2010 to 2023, soil salinization in the oasis area of northern Xinjiang showed an improving trend, specifically manifested as the expansion of non-salinized areas, the reduction of extremely severe salinized areas, and the transfer from high-grade to low-grade salinization; however, local oasis edges, downstream ends of irrigation districts, and areas with poor drainage still faced the risk of aggravated salinization. The dominant influencing factors shifted from topographic background constraints in 2010 to the combined effects of climatic hydrothermal conditions and soil properties in 2023. Soil temperature remained an important individual factor in both periods, albeit with a slight decline in its relative importance contribution; in contrast, the relative importance contribution of soil factors overall showed a slight increase. Soil salinization in the oasis area of northern Xinjiang improved overall, but local marginal areas still faced the risk of salt re-accumulation; the mitigation process was mainly driven by climate-induced changes in soil moisture and temperature, together with human agricultural activities such as irrigation and drainage regulation and land consolidation.

Key words: soil salinization, spatiotemporal evolution characteristics, influencing factors, soil salt content, oasis area, northern Xinjiang

CLC Number:

S156.4
TP79

BI Yan-an, SHI Ming-jie, LIU Wen-hui, WU Hong-qi, LI Yun-hao, ZHAO Jia-hao, ZHONG Rui-hong. Spatiotemporal evolution characteristics and influencing factor analysis of soil salinization in the oasis area of northern Xinjiang[J]. HUBEI AGRICULTURAL SCIENCES, 2026, 65(8): 37-49.

References

[1] SINGH A.Soil salinization management for sustainable development:A review[J]. Journal of environmental management, 2021, 277:111383.
[2] ZHANG M L, FAN X L, GAO P, et al.Monitoring soil salinity in arid areas of northern Xinjiang using multi-source satellite data:A trusted deep learning framework[J]. Land, 2025, 14(1):110.
[3] 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.
[4] 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.
[5] YU X Y, CHANG C Y, SONG J X, et al.Precise monitoring of soil salinity in China's Yellow River Delta using UAV-borne multispectral imagery and a soil salinity retrieval index[J]. Sensors, 2022, 22(2):546.
[6] AKSOY S, SERTEL E, ROSCHER R, et al.Assessment of soil salinity using explainable machine learning methods and Landsat 8 images[J]. International journal of applied earth observation and geoinformation, 2024, 130:103879.
[7] ZENG T, LI Y Z, MA L, et al.Unveiling Latent interaction mechanisms influencing the spatial pattern of soil salinity in arid Oases:Insights from integrated modeling[J]. Catena, 2025, 250:108769.
[8] LIU J Y, GUO S, ZHANG P W, et al.Analysis of the evolution characteristics and driving mechanisms of salinization in arid regions based on multi-factor interaction with optimized parameter geographic detector (OPGD)[J]. Journal of environmental management, 2025, 394:127487.
[9] FU Y, WANG P Y, CAO W G, et al.Long-term assessment of soil salinization patterns in the Yellow River Delta using landsat imagery from 2003 to 2021[J]. Land, 2024, 14(1):24.
[10] 张智斌,范燕敏,武红旗,等.新疆阿勒泰地区耕地质量评价及障碍因素诊断[J].新疆农业科学,2022,59(7):1786-1794.
[11] 张新时. 天山北部山地-绿洲-过渡带-荒漠系统的生态建设与可持续农业范式[J].植物学报,2001(12):1294-1299.
[12] LIN J W, GUI D W, LIU Y F, et al.A high-precision oasis dataset for China from remote sensing images[J]. Scientific data, 2024, 11:726.
[13] 刘洪波,丁邦新,白云岗,等.典型干旱区绿洲春季土壤盐分空间分布特征分析[J].土壤通报,2021,52(2):279-285.
[14] 芦远闯,许华森,王晨宇,等.基于质量法的土壤水溶性盐总量测定方法改进[J].土壤通报,2022,53(4):815-820.
[15] 刘广明,杨劲松,姚荣江,等. 典型绿洲区土壤盐分含量的空间变异特征[J]. 农业工程学报, 2012, 28(16):109-115.
[16] SALEM O H, JIA Z H.Evaluation of different soil salinity indices using remote sensing techniques in Siwa Oasis, Egypt[J]. Agronomy, 2024, 14(4):723.
[17] ZHANG J Y, GE X H, HOU X H, et al.Strategies for soil salinity mapping using remote sensing and machine learning in the Yellow River Delta[J]. Remote sensing, 2025, 17(15):2619
[18] GORJI T, YILDIRIM A, HAMZEHPOUR N, et al.Soil salinity analysis of urmia lake basin using Landsat-8 OLI and Sentinel-2A based spectral indices and electrical conductivity measurements[J]. Ecological indicators, 2020, 112:106173.
[19] CAMPS-VALLS G,CAMPOS-TABERNER M,MORENO-MARTÍNEZ Á,et al. A unified vegetation index for quantifying the terrestrial biosphere[J]. Science advances,2021,7(9):eabc7447.
[20] BANDAK S, MOVAHEDI-NAEINI S A, MEHRI S, et al. A longitudinal analysis of soil salinity changes using remotely sensed imageries[J]. Scientific reports, 2024, 14:10383.
[21] HUETE A,DIDAN K,MIURA T,et al.Overview of the radiometric and biophysical performance of the MODIS vegetation indices[J]. Remote sensing of environment, 2002, 83(1-2):195-213.
[22] STRONG C J,BURNSIDE N G,LLEWELLYN D.The potential of small-unmanned aircraft systems for the rapid detection of threatened unimproved grassland communities using an enhanced normalized difference vegetation index[J].PLoS one,2017,12(10):e0186193.
[23] WU W C.The generalized difference vegetation index (GDVI) for dryland characterization[J]. Remote sensing, 2014, 6(2):1211-1233.
[24] MA H, ZHAO W J, DUAN W C, et al.Inversion model of soil salinity in alfalfa covered farmland based on sensitive variable selection and machine learning algorithms[J]. PeerJ,2024,12:e18186.
[25] WANG J Z, DING J L, YU D L, et al.Capability of Sentinel-2 MSI data for monitoring and mapping of soil salinity in dry and wet seasons in the Ebinur Lake region, Xinjiang, China[J]. Geoderma, 2019, 353:172-187.
[26] WANG J Q, PENG J, LI H Y, et al.Soil salinity mapping using machine learning algorithms with the sentinel-2 MSI in arid areas, China[J]. Remote sensing, 2021, 13(2):305.
[27] 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.
[28] ZHANG Y, WU H Q, KANG Y L, et al.Mapping the soil salinity distribution and analyzing its spatial and temporal changes in Bachu County, Xinjiang, based on google earth engine and machine learning[J]. Agriculture, 2024, 14(4):630.
[29] WANG N, CHEN S C, HUANG J Y, et al.Global soil salinity estimation at 10 m using multi-source remote sensing[J]. Journal of remote sensing, 2024, 4:130.
[30] WANG D,YANG J, ZHANG X, et al.Seasonal climate drives soil salinity dynamics through vegetation and water indices in saline farmland[J]. Agricultural water management,2025,310:109357.
[31] LIU Y N, ZHU Y, QIAN Y Z, et al.High-resolution soil salinity mapping and driving factor analysis at regional scale using multi-source remote sensing data[J]. Journal of hydrology, 2026, 664:134604.
[32] STAVI I, THEVS N, PRIORI S.Soil salinity and sodicity in drylands:A review of causes, effects, monitoring, and restoration measures[J]. Frontiers in environmental science,2021,9:712831.
[33] WANG L Y, HU P, ZHENG H W, et al.An automated framework for interaction analysis of driving factors on soil salinization in central Asia and western China[J]. Remote sensing, 2025, 17(6):987.
[34] LIU W L, JIANG L L, JIAPAER G, et al.Monitoring the salinization of agricultural land and assessing its drivers in the Altay region[J]. Ecological indicators, 2024, 167:112678.
[35] XIE J B, SHI C, LIU Y, et al.Soil salinization prediction through feature selection and machine learning at the irrigation district scale[J]. Frontiers in earth science, 2025, 12:1488504.
[36] LI J, ZHANG T T, SHAO Y, et al.Comparing machine learning algorithms for soil salinity mapping using topographic factors and sentinel-1/2 data:A case study in the Yellow River Delta of China[J]. Remote sensing, 2023, 15(9):2332.
[37] 赵文举,李钊钊,马芳芳,等.基于多光谱影像的苜蓿地不同生育期土壤含盐量反演模型研究[J].农业机械学报,2024,55(12):418-429.
[38] 范晓萱,刘耘华,王新军,等.基于XGBoost模型的克州平原地区土壤盐分遥感反演[J].新疆农业大学学报,2024,47(5):366-372.
[39] GAO S H, WANG X J, XU S X, et al.Soil salinity mapping of croplands in arid areas based on the soil-land inference model[J]. Agronomy, 2023, 13(12):3074.
[40] SHAO J R, LI S H, YANG X H, et al.Evaluating soil salinity dynamics under drip irrigation in the Manas River Basin, Xinjiang:A long-term analysis (1996—2019)[J]. PeerJ,2025,13:e19295.
[41] LI W H, KANG S Z, DU T S, et al.Optimal groundwater depth and irrigation amount can mitigate secondary salinization in water-saving irrigated areas in arid regions[J]. Agricultural water management, 2024, 302:109007.
[42] LI S Q, NURMEMET I, SEYDEHMET J, et al.Spatiotemporal dynamics and driving factors of soil salinization:A case study of the Yutian oasis, Xinjiang, China[J]. Land,2024,13(11):1941.
[43] 姚俊强,毛炜峄,陈静,等.新疆气候“湿干转折”的信号和影响探讨[J].地理学报,2021,76(1):57-72.
[44] 郭竞阳,王雅琦,张宝忠,等.新疆参考作物蒸散发趋势转折与大尺度气候变率的关系[J].农业工程学报,2023,39(13):123-130.
[45] 沈永平,苏宏超,王国亚,等.新疆冰川、积雪对气候变化的响应(Ⅰ):水文效应[J].冰川冻土,2013,35(3):513-527.
[46] CAI T Y, LUO X Y, FAN L Y, et al.The impact of cropland use changes on terrestrial ecosystem services value in newly added cropland hotspots in China during 2000—2020[J]. Land, 2022, 11(12):2294.
[47] 康颢严.“斤斤计较”每滴水[N].新疆日报(汉),2025-09-05(4).
[48] 汪思佳,王春霞,吴晨涛.北疆膜下滴灌棉田单个灌水周期内土壤水热盐迁移规律研究[J].土壤通报,2024,55(3):651-660.
[49] 刘玉国,杨海昌,王开勇,等.新疆浅层暗管排水降低土壤盐分提高棉花产量[J].农业工程学报,2014,30(16):84-90.