| 54 | 0 | 10 |
| 下载次数 | 被引频次 | 阅读次数 |
[目的]精准掌握景泰灌区耕地盐渍化时空特征。[方法]结合遥感技术与机器学习方法，以Landsat 9 OLI影像和实地采集的土壤样品盐分数据，构建土壤含盐量反演模型，并利用最优模型对研究区2025年水浇地土壤含盐量进行反演分析。[结果]多数光谱指数对土壤含盐量的表征能力优于单一波段反射率，其中SI-T、NDSI、SRSI等盐分指数与土壤含盐量呈显著正相关，NDVI、GNDVI等植被指数因受盐分抑制与土壤含盐量呈强负相关；对比9种机器学习算法性能，随机森林模型在拟合能力与泛化能力上表现均衡最优，可高效反演景泰灌区耕地土壤含盐量；基于随机森林模型反演2025年景泰灌区水浇地盐渍化状况发现，灌区盐渍化以轻度和非盐渍化为主，空间上呈现“绿洲内部向边缘递增”特征。[结论]该研究可为景泰灌区及西北干旱区盐碱地综合整治、耕地利用效率提升提供科学数据与理论支撑，助力“藏粮于地”战略实施。
Abstract：[Objective]To precisely understand the spatiotemporal characteristics of cropland salinization in Jingtai Irrigation District.[Method] This research integrated remote sensing technology with machine learning methods.Landsat 9 OLI images and salinity data of soil samples collected in the field were utilized to establish a soil salt content inversion model.Subsequently, this model was employed to analyze the soil salt content of irrigated land in the study area in 2025.[Result]Most spectral indices were more effective in characterizing soil salt content compared to single-band reflectance.Salinity indices such as SI-T,NDSI,and SRSI exhibited significant positive correlation with soil salt content, while vegetation indices such as NDVI and GNDVI showed a strong negative correlation because of salt inhibition.Through the comparison of the performance of nine machine learning algorithms, the random forest model was found to achieve the optimal balance between fitting and generalization capabilities, facilitating the efficient inversion of soil salt content in the croplands of the Jingtai Irrigation District.Finally, based on the random forest model, the inversion of the salinization status of irrigated lands in the Jingtai Irrigation District in 2025 demonstrated that salinization in the district was mainly at mild and non-salinized levels, with a characteristic of increasing from the interior to the edge of the oasis.[Conclusion]The findings of this study can provide references for the comprehensive improvement of saline-alkali land and enhance the utilization efficiency of cropland in the Jingtai Irrigation District and other arid regions in northwestern China, which will contribute to the implementation of the “storing grain in the land” strategy.
[1] 付萍杰，补沅坤，马池杰，等.基于GEE的黄河三角洲地区土壤含盐量时空反演[J].测绘通报，2024(11):13-20,26.
[2] METTERNICHT G I,ZINCK J A.Remote sensing of soil salinity:potentials and constraints[J].Remote Sens Environ,2003,85(1):1-20.
[3] QADIR M,QUILLÉROU E,NANGIA V,et al.Economics of salt-induced land degradation and restoration[J].Nat Resour Forum,2014,38(4):282-295.
[4] SHRIVASTAVA P,KUMAR R.Soil salinity:A serious environmental issue and plant growth promoting bacteria as one of the tools for its alleviation[J].Saudi J Biol Sci,2015,22(2):123-131.
[5] 冯玉倩，米俊珍，赵宝平，等.秸秆配施微生物菌肥对盐碱地土壤理化性质及作物产量和品质的影响[J].中国土壤与肥料，2023(9):96-104.
[6] CHEN H F,WU J W,XU C.Monitoring soil salinity classes through remote sensing-based ensemble learning concept:Considering scale effects[J].Remote Sens,2024,16(4):642.
[7] AVDAN U,KAPLAN ■,et al.Soil salinity prediction models constructed by different remote sensors[J].Phys Chem Earth Parts A/B/C,2022,128:103230.
[8] 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.
[9] 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.
[10] 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.
[11] 王庆明，张越，郑荣伟，等.基于遥感模型SDI的土壤盐渍化临界水位研究[J].灌溉排水学报，2022,41(3):98-104.
[12] 冯娟，丁建丽，魏雯瑜.基于Albedo-MSAVI特征空间的渭库绿洲土壤盐渍化研究[J].中国农村水利水电，2018(2):147-152.
[13] 张思源，岳楚，袁国礼，等.基于ENDVI-SI3特征空间的盐渍化反演模型及风险评估[J].自然资源遥感，2022,34(4):136-143.
[14] 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.
[15] 董雨昕，韩文霆，崔欣，等.基于无人机与Sentinel-2A遥感数据协同的裸土期土壤含盐量反演[J].农业机械学报，2025,56(6):434-445.
[16] 陈猷，申晓晶，周博，等.基于遥感影像与随机森林算法的银北灌区土壤盐渍化监测方法研究[J].江西农业大学学报，2025,47(3):803-816.
[17] 姚一飞，王爽，张珺锐，等.基于GF-1卫星遥感的河套灌区土壤含水率反演模型研究[J].农业机械学报，2022,53(9):239-251.
[18] KAZEMI GARAJEH M,BLASCHKE T,HOSSEIN HAGHI V,et al.A comparison between sentinel-2 and landsat 8 OLI satellite images for soil salinity distribution mapping using a deep learning convolutional neural network[J].Can J Remote Sens,2022,48(3):452-468.
[19] 王学琴，汪西原.土壤盐渍化遥感监测信息提取与处理模型研究进展[J].安徽农业科学，2026,54(1):18-23.
[20] 吴炳方，苑全治，颜长珍，等.21世纪前十年的中国土地覆盖变化[J].第四纪研究，2014,34(4):723-731.
[21] 宁岸新.基于Sentinel2A影像的干旱区土壤盐渍化监测研究[J].安徽农业科学，2024,52(1):51-55,66.
[22] HABOUDANE D,MILLER J R,PATTEY E,et al.Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies:Modeling and validation in the context of precision agriculture[J].Remote Sens Environ,2004,90(3):337-352.
[23] TAGHIZADEH-MEHRJARDI R,MINASNY B,SARMADIAN F,et al.Digital mapping of soil salinity in Ardakan region,central Iran[J].Geoderma,2014,213:15-28.
[24] LOBELL D B,LESCH S M,CORWIN D L,et al.Regional-scale assessment of soil salinity in the red river valley using multi-year MODIS EVI and NDVI[J].J Env Quality,2010,39(1):35-41.
[25] ALLBED A,KUMAR L,ALDAKHEEL Y Y.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,2014,230:1-8.
[26] 张思源，岳楚，袁国礼，等.基于ENDVI-SI3特征空间的盐渍化反演模型及风险评估[J].自然资源遥感，2022,34(4):136-143.
[27] CHEN H,ZHAO G,CHEN J,et al.Remote sensing inversion of saline soil salinity based on modified vegetation index in estuary area of Yellow River[J].Trans Chin Soc Agric Eng,2015,31(5):107-114.
[28] 关红，贾科利，张至楠.采用高光谱指数的龟裂碱土盐碱化信息提取与分析[J].红外与激光工程，2014,43(12):4153-4158.
[29] EL KADER DOUAOUI A,NICOLAS H,WALTER C.Detecting salinity hazards within a semiarid context by means of combining soil and remote-sensing data[J].Geoderma,2006,134(1-2):217-230.
[30] ABBAS A,KHAN S.Using remote sensing techniques for appraisal of irrigated soil salinity[C]// Proceedings of International Congress on Modelling and Simulation (MODSIM).Modelling and Simulation Society of Australia and New Zealand,2007.
[31] GUEDON A M.Characterization of salinity and sodicity in semi-arid irrigated agricultural lands using remote sensing[D].Ottawa:University of Ottawa,2009.
[32] ABBAS A,KHAN S,HUSSAIN N,et al.Characterizing soil salinity in irrigated agriculture using a remote sensing approach[J].Phys Chem Earth Parts A/B/C,2013,55-57:43-52.
[33] MA Y X,TASHPOLAT N.Remote sensing monitoring of soil salinity in Weigan River-Kuqa River Delta oasis based on two-dimensional feature space[J].Water,2023,15(9):1694.
[34] KHAN N M,RASTOSKUEV V V,SATO Y,et al.Assessment of hydrosaline land degradation by using a simple approach of remote sensing indicators[J].Agric Water Manag,2005,77(1-3):96-109.
[35] ALHAMMADI M S,GLENN E P.Detecting date palm trees health and vegetation greenness change on the eastern coast of the United Arab Emirates using SAVI[J].Int J Remote Sens,2008,29(6):1745-1765.
[36] 曹雷，丁建丽，玉米提·哈力克，等.基于国产高分一号卫星数据的区域土壤盐渍化信息提取与建模[J].土壤学报，2016,53(6):1399-1409.
[37] HUANG C,WYLIE B,YANG L,et al.Derivation of a tasselled cap transformation based on Landsat 7 at-satellite reflectance[J].Int J Remote Sens,2002,23(8):1741-1748.
[38] FARIFTEH J,VAN DER MEER F,ATZBERGER C,et al.Quantitative analysis of salt-affected soil reflectance spectra:A comparison of two adaptive methods (PLSR and ANN)[J].Remote Sens Environ,2007,110(1):59-78.
[39] CAO X,CHEN J,MATSUSHITA B,et al.Developing a MODIS-based index to discriminate dead fuel from photosynthetic vegetation and soil background in the Asian steppe area[J].Int J Remote Sens,2010,31(6):1589-1604.
[40] ROUJEAN J L,BREON F M.Estimating PAR absorbed by vegetation from bidirectional reflectance measurements[J].Remote Sens Environ,1995,51(3):375-384.
[41] BAO Y L,USTIN S,MENG X T,et al.A regional-scale hyperspectral prediction model of soil organic carbon considering geomorphic features[J].Geoderma,2021,403:115263.
[42] GITELSON A A,MERZLYAK M N,CHIVKUNOVA O B.Optical properties and nondestructive estimation of anthocyanin content in plant leaves[J].Photochem Photobiol,2007,74(1):38-45.
[43] ESCADAFAL R.Remote sensing of arid soil surface color with Landsat thematic mapper[J].Adv Space Res,1989,9(1):159-163.
[44] LIU Q,HE L,GUO L,et al.Digital mapping of soil organic carbon density using newly developed bare soil spectral indices and deep neural network[J].Catena,2022,219:106603.
[45] RUPPERT D.The elements of statistical learning:Data mining,inference,and prediction[J].J Am Stat Assoc,2004,99(466):567.
[46] BREIMAN L.Random forests[J].Mach Learn,2001,45(1):5-32.
[47] GEURTS P,ERNST D,WEHENKEL L.Extremely randomized trees[J].Mach Learn,2006,63(1):3-42.
[48] FRIEDMAN J H.Greedy function approximation:A gradient boosting machine[J].Ann Statist,2001,29(5):1189-1232.
[49] SHERIDAN R P,WANG W M,LIAW A,et al.Extreme gradient boosting as a method for quantitative structure-activity relationships[J].J Chem Inf Model,2016,56(12):2353-2360.
[50] KE G,MENG Q,FINLEY T,et al.LightGBM:A highly efficient gradient boosting decision tree[C]// Advances in Neural Information Processing Systems 30 (NIPS 2017).2017:3146-3154.
[51] SMOLA A J,SCHÖLKOPF B.A tutorial on support vector regression[J].Stat Comput,2004,14(3):199-222.
[52] GELADI P,KOWALSKI B R.Partial least-squares regression:A tutorial[J].Anal Chim Acta,1986,185:1-17.
[53] RUMELHART D E,HINTON G E,WILLIAMS R J.Learning representations by back-propagating errors[J].Nature,1986,323(6088):533-536.
[54] 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].Ecol Indic,2024,166:112364.
[55] BRADY N C,WEIL R R.The nature and properties of soils[M].14th ed.Upper Saddle River,New Jersey:Pearson Prentice Hall,2008.
[56] XU X B,WANG X G,YANG P J,et al.Strategy for mapping soil salt contents during the bare soil period through a satellite image:Optimal calibration set combined with random forest[J].Catena,2023,223:106900.
[57] 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.
[58] 杨丽萍，任杰，王宇，等.基于多源遥感数据的居延泽地区土壤盐分估算模型[J].农业机械学报，2022,53(11):226-235.
基本信息:
中图分类号:S156.4;S127
引用信息:
[1]彭建清,宋翔,廖杰,等.基于Landsat 9 OLI数据与机器学习的景泰灌区水浇地盐渍化反演[J].安徽农业科学,2026,54(08):48-56.
基金信息:
甘肃省白银市景泰县盐碱地综合利用试点项目(第二标段)核心试验示范工程(JTYJDSDXMSG02); 国家自然科学基金项目(41801072)
2025-10-21
2025
2025-11-17
2025-11-20
2025
1
2026-04-28
2026-04-28