基于土壤高光谱特征波段优选的盐分预测模型构建

doi:10.3864/j.issn.0578-1752.2025.20.003

Abstract

Abstract:

【Objective】Soil salinization is a key environmental problem threatening the sustainable development of agriculture in arid areas, leading to the deterioration of soil structure, crop yield reduction and ecosystem degradation. The purpose of this study is to use spectral transformation, band selection and a variety of machine learning methods to build a soil salinity prediction model, which can quickly and accurately estimate soil salinity, and provide technical support for the scientific management of salinized farmland.【Method】Taking farmland soil in Dalate Banner as the research object, soil samples were collected systematically and their electrical conductivity (EC) and spectral reflectance data were measured. Firstly, Savitzky-Golay (S-G) filter was used to smooth the original spectrum (R). On this basis, 12 kinds of spectral transformation processing including reciprocal, logarithmic, first-order differential and second-order differential were carried out to mine the hidden spectral features. Then, the correlation analysis (CA) and least angle regression (LAR) methods were used to reduce the feature dimension, and the competitive adaptive reweighted sampling (CARS) algorithm was combined to further screen the sensitive feature bands. Finally, partial least squares regression (PLSR), support vector machine (SVM), back propagation neural network (BPNN) and random forest (RF) models were constructed based on the optimal features. The performance of the model was comprehensively evaluated by determination coefficient (R²) and root mean square error (RMSE), and the modeling effects of feature sets in different algorithms were compared.【Result】After spectral transformation, the correlation coefficients of the original spectrum were improved in varying degrees, indicating that spectral transformation could significantly enhance the correlation between soil salinity and spectral characteristics; When CARS was used for feature band optimization, LAR had better feature dimension reduction effect than CA; The reciprocal logarithmic first-order differential (ATFD) combined with PLSR model performed best, and its validation set accuracy was R²=0.81, RMSE=2.04 dS·m^-1; The comparison of different modeling methods showed that the performance of PLSR prediction model was better than the other three models (BPNN/RF/SVM), indicating that PLSR model was more suitable for the prediction of soil salinity in this region.【Conclusion】The hyperspectral prediction model of soil salinity based on ATFD-LAR-CARS-PLSR has high accuracy and optimal prediction ability, which proves that hyperspectral technology combined with multi-dimensional feature optimization can effectively realize the prediction of soil salinity in arid areas.

Key words: soil salinity, spectral transformation, characteristic band selection, correlation analysis (CA), least angle regression (LAR), competitive adaptive reweighted sampling (CARS)

LI MingLi, WEN CaiYun, MA DongHao, LI CunJun, WANG YuWen, KANG Lu, LU Miao. Construction of Salinity Prediction Model Based on Optimal Selection of Soil Hyperspectral Characteristic Bands[J].Scientia Agricultura Sinica, 2025, 58(20): 4054-4069.

0
/ / Recommend

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: https://www.chinaagrisci.com/EN/10.3864/j.issn.0578-1752.2025.20.003

https://www.chinaagrisci.com/EN/Y2025/V58/I20/4054

Figures/Tables 11

Fig. 1

Table 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

References 46

[1]	刘霞, 胡宇, 张圣微, 白燕英, 张欢. 达拉特旗黄河南岸盐碱化土壤不同含盐量估算模型对比. 农业机械学报, 2024, 55(10): 360-370.
	LIU X, HU Y, ZHANG S W, BAI Y Y, ZHANG H. Comparison of different salinity estimation models for salinized soils on south bank of Yellow River in Dalate Banner. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(10): 360-370. (in Chinese)
[2]	顾晨, 梁建, 刘旭颖, 孙泊远, 孙同生, 俞坚钢, 孙晨曦, 万华伟, 高吉喜. 高光谱遥感在草原植物多样性监测中的应用与展望. 应用生态学报, 2024, 35(5): 1397-1407. doi: 10.13287/j.1001-9332.202405.024
	GU C, LIANG J, LIU X Y, SUN B Y, SUN T S, YU J G, SUN C X, WAN H W, GAO J X. Application and prospects of hyperspectral remote sensing in monitoring plant diversity in grassland. Chinese Journal of Applied Ecology, 2024, 35(5): 1397-1407. (in Chinese) doi: 10.13287/j.1001-9332.202405.024
[3]	郭艳萍, 王雪梅, 赵枫, 李平平. 基于最优数学和小波变换的绿洲耕层土壤盐分RF高光谱反演. 农业工程学报, 2025, 41(3): 83-93.
	GUO Y P, WANG X M, ZHAO F, LI P P. Hyperspectral inversion of the RF model for soil salinity in oasis tillage layer based on optimal mathematics and wavelet transform. Transactions of the Chinese Society of Agricultural Engineering, 2025, 41(3): 83-93. (in Chinese)
[4]	王英杰, 高欣梅, 包淑梅, 李乌日吉木斯, 福英, 乌日力格, 王靖宇, 郭龙玉. 基于高光谱数据的盐渍化土壤含盐量预测模型研究. 农业工程, 2024, 14(10): 113-120.
	WANG Y J, GAO X M, BAO S M, LI W R J M S, FU Y, WU R L G, WANG J Y, GUO L Y. Prediction model of salt content in salinized soil based on hyperspectral data. Agricultural Engineering, 2024, 14(10): 113-120. (in Chinese)
[5]	王丽娜, 朱西存, 刘庆, 赵庚星, 李海燕, 王凌, 张圣武. 黄河三角洲盐碱土盐分的高光谱定量估测研究. 土壤通报, 2013, 44(5): 1101-1106.
	WANG L N, ZHU X C, LIU Q, ZHAO G X, LI H Y, WANG L, ZHANG S W. Hypersperpectral quantitative estimation of saline- alkali soil salinity in the Yellow River Delta. Chinese Journal of Soil Science, 2013, 44(5): 1101-1106. (in Chinese)
[6]	ZHOU W, YANG H, XIE L J, LI H R, HUANG L, ZHAO Y P, YUE T X. Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model. Catena, 2021, 202: 105222.
[7]	侯化刚, 王丹阳, 马斯琦, 潘剑君, 李兆富. 黄河三角洲不同盐渍度土壤有机质含量的高光谱预测研究. 中国农业科学, 2023, 56(10): 1905-1919. doi: 10.3864/j.issn.0578-1752.2023.10.008.
	HOU H G, WANG D Y, MA S Q, PAN J J, LI Z F. Hyperspectral prediction of organic matter in soils of different salinity levels in the Yellow River Delta. Scientia Agricultura Sinica, 2023, 56(10): 1905-1919. doi: 10.3864/j.issn.0578-1752.2023.10.008. (in Chinese)
[8]	彭金英, 蒋金豹, 崔希民, 张建, 王思佳, 王明国, 聂铖. 宁夏盐碱地土壤盐分高光谱反演. 矿山测量, 2021, 49(1): 69-73.
	PENG J Y, JIANG J B, CUI X M, ZHANG J, WANG S J, WANG M G, NIE C. Hyperspectral inversion of the soil salt content in saline-alkali land of Ningxia. Mine Surveying, 2021, 49(1): 69-73. (in Chinese)
[9]	赵泽艺, 李朝阳, 王洪博, 张楠, 李国辉, 唐茂淞, 王兴鹏, 高阳. 南疆盐碱土水、氮、盐光谱特征及其反演模型. 灌溉排水学报, 2023, 42(7): 93-100.
	ZHAO Z Y, LI Z Y, WANG H B, ZHANG N, LI G H, TANG M S, WANG X P, GAO Y. Spectral characteristics and inversion models of water, nitrogen and salt in saline-alkali soils of southern Xinjiang. Journal of Irrigation and Drainage, 2023, 42(7): 93-100. (in Chinese)
[10]	ZHANG T Y, FU Q, TIAN R Q, ZHANG Y, SUN Z H. A spectrum contextual self-attention deep learning network for hyperspectral inversion of soil metals. Ecological Indicators, 2023, 152: 110351.
[11]	SHEN Q, XIA K, ZHANG S W, KONG C C, HU Q Q, YANG S W. Hyperspectral indirect inversion of heavy-metal copper in reclaimed soil of iron ore area. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 222: 117191.
[12]	朱赟, 申广荣, 项巧巧, 吴裕. 基于不同光谱变换的土壤盐含量光谱特征分析. 土壤通报, 2017, 48(3): 560-568.
	ZHU Y, SHEN G R, XIANG Q Q, WU Y. Spectral characteristics analysis of soil salinity content based on different spectral transformations. Chinese Journal of Soil Science, 2017, 48(3): 560-568. (in Chinese)
[13]	黄华雨, 丁启东, 张俊华, 周跃辉, 潘鑫, 贾科利. 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. 环境科学, 2025, doi: 10.13227/j.hjkx.202412303.
	HUANG H Y, DING Q D, ZHANG J H, ZHOU Y H, PAN X, JIA K L. Inversion of farmland soil salinity and pH by ground hyperspectral coupled with interpretable ensemble machine learning. Environmental Science, 2025, doi: 10.13227/j.hjkx.202412303. (in Chinese)
[14]	张晓娟, 张忠, 杨雪梅, 宋龙龙, 王景瑞, 王飞. 基于高光谱的景电灌区盐渍化土壤水、盐估算研究. 甘肃林业科技, 2024, 49(3): 60-66.
	ZHANG X J, ZHANG Z, YANG X M, SONG L L, WANG J R, WANG F. Estimation of water and salt in saline-alkali soil of Jingdian irrigation area based on hyperspectral data. Journal of Gansu Forestry Science and Technology, 2024, 49(3): 60-66. (in Chinese)
[15]	赵慧, 李新国, 靳万贵, 麦麦提吐尔逊·艾则孜, 牛芳鹏. 基于分数阶微分的博斯腾湖湖滨绿洲土壤电导率高光谱估算. 甘肃农业大学学报, 2021, 56(1): 118-125.
	ZHAO H, LI X G, JIN W G, MAMATTURSUN·E, NIU F P. Fractional differential based hyperspectral estimation model of soil electrical conductivity of Bosten Lake oasis. Journal of Gansu Agricultural University, 2021, 56(1): 118-125. (in Chinese)
[16]	陈睿华, 孙媛, 尚天浩, 张俊华. 基于光谱变换的宁夏银北地区可溶性阴离子反演. 中国土壤与肥料, 2022(8): 94-103.
	CHEN R H, SUN Y, SHANG T H, ZHANG J H. Retrieval of soluble anions in northern Yinchuan area of Ningxia region based on spectral transformation. Soil and Fertilizer Sciences in China, 2022(8): 94-103. (in Chinese)
[17]	孙亚楠, 李仙岳, 史海滨, 崔佳琪, 王维刚. 河套灌区土壤水溶性盐基离子高光谱综合反演模型. 农业机械学报, 2019, 50(5): 344-355.
	SUN Y N, LI X Y, SHI H B, CUI J Q, WANG W G. Hyperspectral integrated inverse model for water-soluble salt ions content in Hetao irrigation district. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(5): 344-355. (in Chinese)
[18]	周世勋, 尹娟, 王军涛, 常布辉, 杨震. 灌区土壤含盐量的高光谱估测与空间分布研究. 灌溉排水学报, 2025, 44(2): 72-82.
	ZHOU S X, YIN J, WANG J T, CHANG B H, YANG Z. Mapping soil salinity in irrigated areas using hyperspectral UAV imagery. Journal of Irrigation and Drainage, 2025, 44(2): 72-82. (in Chinese)
[19]	孟珊, 李新国, 焦黎. 基于机器学习算法的湖滨绿洲土壤电导率高光谱估算模型. 土壤通报, 2023, 54(2): 286-294.
	MENG S, LI X G, JIAO L. Hyperspectral estimation model of soil electrical conductivity in the lakeside oasis based on machine learning algorithm. Chinese Journal of Soil Science, 2023, 54(2): 286-294. (in Chinese)
[20]	WANG Z X, MIAO Z H, YU X Y, HE F. Vis-NIR spectroscopy coupled with PLSR and multivariate regression models to predict soil salinity under different types of land use. Infrared Physics & Technology, 2023, 133: 104826.
[21]	贾学宇, 郝永河, 张娟, 刘子瑶. 鄂尔多斯市黄河灌区重度盐碱地与作物主要表型性状的相关性分析. 黑龙江科学, 2025, 16(8): 92-95.
	JIA X Y, HAO Y H, ZHANG J, LIU Z Y. Correlation analysis between severe saline-alkali land and main phenotypic traits of crops in the Yellow River Irrigation District of Ordos City. Heilongjiang Science, 2025, 16(8): 92-95. (in Chinese)
[22]	穆其尔, 杨光, 陈昊宇, 张天琪. 实验室模拟不同盐分土壤的高光谱特性. 东北林业大学学报, 2021, 49(11): 68-75.
	MU Q E, YANG G, CHEN H Y, ZHANG T Q. Hyperspectral characteristics of simulated soils with different salinity in laboratory. Journal of Northeast Forestry University, 2021, 49(11): 68-75. (in Chinese)
[23]	高颖, 王延仓, 顾晓鹤, 周新武, 马样, 宣孝义. 基于微分变换定量反演土壤有机质及全氮含量. 江苏农业科学, 2020, 48(24): 220-225.
	GAO Y, WANG Y C, GU X H, ZHOU X W, MA Y, XUAN X Y. Quantitative inversion of soil organic matter and total nitrogen content based on differential transformation. Jiangsu Agricultural Sciences, 2020, 48(24): 220-225. (in Chinese)
[24]	代希君, 彭杰, 张艳丽, 罗华平, 向红英. 基于光谱分类的土壤盐分含量预测. 土壤学报, 2016, 53(4): 909-918.
	DAI X J, PENG J, ZHANG Y L, LUO H P, XIANG H Y. Prediction of soil salinity content based on spectral classification. Acta Pedologica Sinica, 2016, 53(4): 909-918. (in Chinese)
[25]	张俊华, 贾萍萍, 孙媛, 贾科利. 基于高光谱特征的盐渍化土壤不同土层盐分离子含量预测. 农业工程学报, 2019, 35(12): 106-115.
	ZHANG J H, JIA P P, SUN Y, JIA K L. Prediction of salinity ion content in different soil layers of saline-alkali soil based on hyperspectral characteristics. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(12): 106-115. (in Chinese)
[26]	李志, 李新国, 刘彬, 麦麦提吐尔逊·艾则孜. 博斯腾湖西岸湖滨带土壤盐分高光谱反演. 扬州大学学报(农业与生命科学版), 2019, 40(2): 33-39.
	LI Z, LI X G, LIU B, MAMATTURSUN·E. Hyperspectral inversion of soil salinity in the western lakeside of Bosten Lake. Journal of Yangzhou University (Agricultural and Life Science Edition), 2019, 40(2): 33-39. (in Chinese)
[27]	EFRON B, HASTIE T, JOHNSTONE I, TIBSHIRANI R. Least angle regression. Annals of Statistics, 2004, 32(2): 407-451.
[28]	WEI X, DENG C J, FANG W, XIE C Y, LIU S Y, LU M R, WANG F, WANG Y Z. Classification method for folded flue-cured tobacco based on hyperspectral imaging and conventional neural networks. Industrial Crops and Products, 2024, 212: 118279.
[29]	熊芩, 张若秋, 李辉, 陈万超, 杜一平. 最小角回归算法(LAR)结合采样误差分布分析(SEPA)建立稳健的近红外光谱分析模型. 分析测试学报, 2018, 37(7): 778-783.
	XIONG Q, ZHANG R Q, LI H, CHEN W C, DU Y P. Establishment of robust near-infrared spectroscopy analysis model by least angle regression algorithm (LAR) combined with sampling error profile analysis (SEPA). Journal of Instrumental Analysis, 2018, 37(7): 778-783. (in Chinese)
[30]	LI H D, LIANG Y Z, XU Q S, CAO D S. Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. Analytica Chimica Acta, 2009, 648(1): 77-84. doi: 10.1016/j.aca.2009.06.046 pmid: 19616692
[31]	张俊超, 胡琳, 胡建开, 杞应涛, 陆昱, 甘淑. 云南会泽矿区周边土壤镍含量的高光谱定量反演研究. 光学学报, 2025, doi: 10.3788/AOS251074.
	ZHANG J C, HU L, HU J K, QI Y T, LU Y, GAN S. Quantitative inversion of soil nickel content by hyperspectral data in the surrounding area of Huize mining area, Yunnan Province. Acta Optica Sinica, 2025, doi: 10.3788/AOS251074. (in Chinese)
[32]	SUBI X, EZIZ M, ZHONG Q, LI X G. Estimating the chromium concentration of farmland soils in an arid zone from hyperspectral reflectance by using partial least squares regression methods. Ecological Indicators, 2024, 161: 111987.
[33]	PAL M, FOODY G M. Feature selection for classification of hyperspectral data by SVM. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(5): 2297-2307.
[34]	WANG L, ZENG Y, CHEN T. Back propagation neural network with adaptive differential evolution algorithm for time series forecasting. Expert Systems with Applications, 2015, 42(2): 855-863.
[35]	如则麦麦提·米吉提, 买买提·沙吾提, 麦尔耶姆·亚森, 马春玥. 基于高光谱的干旱区盐渍化土壤盐分含量估算. 江苏农业科学, 2018, 46(22): 265-269.
	REZEMAMET·M, MAMAT·S, MAERYAM·Y, MA C Y. Estimation of salinity content in saline-alkali soil of arid area based on hyperspectral data. Jiangsu Agricultural Sciences, 2018, 46(22): 265-269. (in Chinese)
[36]	周凤玺, 滕祥帅, 郝君明, 王立业. 不同分数阶微分形式在盐渍土电导率高光谱反演中的适用性研究. 光谱学与光谱分析, 2025, 45(1): 272-281.
	ZHOU F X, TENG X S, HAO J M, WANG L Y. Applicability of different fractional differential forms in hyperspectral inversion of saline soil conductivity. Spectroscopy and Spectral Analysis, 2025, 45(1): 272-281. (in Chinese)
[37]	王建雯, 李振海, 朱红春, 徐新刚, 甘平, 王浩森, 杨贵军. 基于野外实测高光谱数据的盐碱土盐分含量估测研究. 山东科技大学学报(自然科学版), 2017, 36(3): 17-24.
	WANG J W, LI Z H, ZHU H C, XU X G, GAN P, WANG H S, YANG G J. Estimation of salinity content in saline-alkali soil based on field measured hyperspectral data. Journal of Shandong University of Science and Technology (Natural Science), 2017, 36(3): 17-24. (in Chinese)
[38]	WANG Z, ZHANG F, ZHANG X L, CHAN N W, KUNG H T, ARIKEN M, ZHOU X H, WANG Y S. Regional suitability prediction of soil salinization based on remote-sensing derivatives and optimal spectral index. Science of the Total Environment, 2021, 775: 145807.
[39]	LIU J B, DONG Z Y, XIA J S, WANG H Y, MENG T T, ZHANG R Q, HAN J C, WANG N, XIE J C. Estimation of soil organic matter content based on CARS algorithm coupled with random forest. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021, 258: 119823.
[40]	张楠楠, 张晓. 南疆枣园盐渍土电导率的近红外高光谱分析. 东北农业科学, 2022, 47(4): 118-121, 154.
	ZHANG N N, ZHANG X. Near-infrared hyperspectral analysis of electrical conductivity in saline-alkali soil of jujube orchards in southern Xinjiang. Journal of Northeast Agricultural Sciences, 2022, 47(4): 118-121, 154. (in Chinese)
[41]	OSCO L P, RAMOS A P M, PINHEIRO M M F, MORIYA É A S, IMAI N N, ESTRABIS N, IANCZYK F, DE ARAÚJO F F, LIESENBERG V, JORGE L A, et al. A machine learning framework to predict nutrient content in Valencia-orange leaf hyperspectral measurements. Remote Sensing, 2020, 12(6): 906.
[42]	栗方亮, 孔庆波, 张青. 基于光谱指数的琯溪蜜柚叶片钙素含量估测模型研究. 中国农业科学, 2025, 58(7): 1321-1332. doi: 10.3864/j.issn.0578-1752.2025.07.006.
	LI F L, KONG Q B, ZHANG Q. Research on the estimation model of calcium content in Guanxi honey pomelo leaves based on spectral index. Scientia Agricultura Sinica, 2025, 58(7): 1321-1332. doi: 10.3864/j.issn.0578-1752.2025.07.006. (in Chinese)
[43]	SIDIKE A, ZHAO S H, WEN Y M. Estimating soil salinity in Pingluo County of China using QuickBird data and soil reflectance spectra. International Journal of Applied Earth Observation and Geoinformation, 2014, 26: 156-175.
[44]	郭鹏, 赵阳, 孙子皓, 陈秀万. 基于CARS-PLSR算法的土壤有效磷高光谱反演研究. 中国农业信息, 2023, 35(1): 55-66.
	GUO P, ZHAO Y, SUN Z H, CHEN X W. Hyperspectral inversion of soil available phosphorus based on CARS-PLSR algorithm. China Agricultural Informatics, 2023, 35(1): 55-66. (in Chinese)
[45]	谭琨, 叶元元, 杜培军, 张倩倩. 矿区复垦农田土壤重金属含量的高光谱反演分析. 光谱学与光谱分析, 2014, 34(12): 3317-3322. pmid: 25881431
	TAN K, YE Y Y, DU P J, ZHANG Q Q. Estimation of heavy metal concentrations in reclaimed mining soils using reflectance spectroscopy. Spectroscopy and Spectral Analysis, 2014, 34(12): 3317-3322. (in Chinese) pmid: 25881431
[46]	骆振海, 张超, 冯绍元, 唐敏, 刘锐, 孔纪迎. 土壤盐渍化光学遥感监测方法研究进展. 自然资源遥感, 2024, 36(4): 9-22.
	LUO Z H, ZHANG C, FENG S Y, TANG M, LIU R, KONG J Y. Advances in research on methods for optical remote sensing monitoring of soil salinization. Remote Sensing for Natural Resources, 2024, 36(4): 9-22. (in Chinese)

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

盐渍化等级 Salinization grade	样本数量 Sample size	最大值 Max (dS·m^-1)	最小值 Min (dS·m^-1)	平均值 Mean (dS·m^-1)	标准差 SD (dS·m^-1)	变异系数 CV (%)
非盐渍化Non-salinized (0-2 dS·m^-1)	78	1.92	0.08	0.63	0.40	63.49
轻度盐渍化Slightly salinized (2-4 dS·m^-1)	14	3.91	2.10	3.00	0.57	16.64
中度盐渍化Moderately salinized (4-8 dS·m^-1)	37	7.90	4.05	6.57	1.07	16.29
重度盐渍化Heavily salinized (8-16 dS·m^-1)	36	15.16	8.08	11.41	1.92	16.83
盐土Saline soil (>16 dS·m^-1)	3	19.43	17.91	18.60	0.77	4.14

Construction of Salinity Prediction Model Based on Optimal Selection of Soil Hyperspectral Characteristic Bands

RichHTML

PDF

Abstract

Cite this article

share this article

Figures/Tables 11

References 46

Related Articles 7

Metrics

Comments

Recommended 0

[1]	WANG Long, WANG Jun, JIANG Jing, LIU Hao, LIU DeZhao, LI JiuSheng. Effects of Nitrogen and Potassium Application Rate on Soil Salinity, Yield and Quality of Korla Fragrant Pear Under Drip Irrigation in Southern Xinjiang [J]. Scientia Agricultura Sinica, 2025, 58(17): 3473-3487.
[2]	ZHANG JiFeng,WANG ZhenHua,ZHANG JinZhu,DOU YunQing,HOU YuSheng. The Influences of Different Nitrogen and Salt Levels Interactions on Fluorescence Characteristics, Yield and Quality of Processed Tomato Under Drip Irrigation [J]. Scientia Agricultura Sinica, 2020, 53(5): 990-1003.
[3]	XI Xue,ZHAO GengXing,GAO Peng,CUI Kun,LI Tao. Inversion of Soil Salinity in Coastal Winter Wheat Growing Area Based on Sentinel Satellite and Unmanned Aerial Vehicle Multi-Spectrum— A Case Study in Kenli District of the Yellow River Delta [J]. Scientia Agricultura Sinica, 2020, 53(24): 5005-5016.
[4]	WANG Fei,YANG ShengTian,WEI Yang,YANG XiaoDong,DING JianLi. Influence of Sub-Region Priority Modeling Constructed by Random Forest and Stochastic Gradient Treeboost on the Accuracy of Soil Salinity Prediction in Oasis Scale [J]. Scientia Agricultura Sinica, 2018, 51(24): 4659-4676.
[5]	LI Ping, Magzum Nurolla, LIANG ZhiJie, HUANG ZhongDong, QI XueBin. Effects of Canal Well Water Ratios on Root Layer Soil Desalination and Groundwater Hydrochemical Characteristics [J]. Scientia Agricultura Sinica, 2017, 50(3): 526-536.
[6]	ZHANG Lei, ZHANG Guo-Wei, MENG Ya-Li, CHEN Bing-Lin, WANG You-Hua, ZHOU Zhi-Guo. Changes of Related Physiological Characteristics of Cotton Under Salinity Condition and the Construction of the Cotton Water Stress Index [J]. Scientia Agricultura Sinica, 2013, 46(18): 3768-3775.
[7]	. Distributions of water, salinity, and nitrogen in cotton root zone by different fertigation strategies [J]. Scientia Agricultura Sinica, 2007, 40(3): 549-557 .