基于综合指标协同优化的冬小麦植株水分含量预测

doi:10.3864/j.issn.0578-1752.2023.22.004

摘要/Abstract

摘要：

【目的】基于冬小麦冠层温度参数、形态指标和生理指标3种综合指标构建不同生育时期冬小麦植株含水量（PWC）反演模型，探寻更全面、精准的水分亏缺监测方法，为冬小麦抗旱提供理论依据。【方法】以冬小麦为研究对象，设置3个水分梯度，分别为水分亏缺处理（W1）：35 mm和（W2）：48 mm，对照处理（W3）：68 mm；2个小麦品种洛麦22（一般耐旱品种）和周麦27（弱耐旱品种）。分别获取拔节期、孕穗期和灌浆期冬小麦的冠层温度参数（冠层温度标准差（CTSD）和作物水分胁迫指数（CWSI））、形态指标（株高、茎粗、地上部生物量和叶面积指数）和生理指标（气孔导度、蒸腾速率和光合速率），按照平均权重原则分别构建综合温度参数指标（comprehensive temperature parameter indicator，CTPI）、综合生长指标（comprehensive growth indicator，CGI）和综合生理指标（comprehensive physiological indicator，CPI）。分析植株含水量与综合指标之间的相关关系，并采用多元线性回归（MLR）、偏最小二乘回归（PLSR）和支持向量机（SVM）方法分生育时期构建基于综合指标的PWC反演模型。【结果】不同生育时期内冬小麦的冠层温度参数、形态指标及生理指标水分亏缺处理（W1、W2）较对照处理（W3）均表现出显著性差异（P<0.05）。孕穗期和灌浆期的综合指标（CTPI、CGI和CPI）与PWC具有显著相关关系，相关系数（r）分别为-0.70（-0.78）、0.84（0.80）和0.83（0.76）。采用MLR、PLSR和SVM方法，基于综合指标（CTPI、CGI和CPI）构建PWC反演预测模型均具有较高的预测精度，其中以SVM构建的孕穗期PWC模型最优，R²_cal（R²_val）、RMSE_cal（RMSE_val）和nRMSE_cal（nRMSE_val）分别为0.878（0.815）、2.06%（2.37%）和3.10%（3.33%）。【结论】基于综合指标（CTPI、CGI和CPI）构建的SVM-PWC模型能够很好地预测冬小麦各生育时期水分亏缺状况，可为黄淮海平原冬小麦防旱抗旱提供理论依据。

关键词: 冬小麦, 水分亏缺, 综合指标, 植株含水量, 支持向量机

Abstract:

【Objective】To find a more comprehensive and accurate method to monitor the water deficit and to provide a theoretical basis for drought relief of winter wheat, the present study was conducted to construct an inversion model of plant water content (PWC) at different growth stages based on three comprehensive indexes, namely, canopy temperature, morphology and physiology indexes of winter wheat.【Method】The winter wheat was studied by setting up three water treatments (water deficit treatment W1: 35 mm, water deficit treatment W2: 48 mm, and control treatment W3: 68 mm) and two wheat varieties (general drought resistant variety Luomai 22 and weak drought resistant variety Zhoumai 27). Canopy temperature parameters (canopy temperature standard deviation (CTSD) and crop water stress index (CWSI)), morphological indicators (plant height, stem diameter, aboveground biomass, and leaf aera index (LAI)) and physiological indicators (stomatal conductance, transpiration rate, and photosynthetic rate) of winter wheat were obtained at jointing, booting, and filling stages, respectively. Comprehensive temperature parameter indicators (CTPI), comprehensive growth indicators (CGI) and comprehensive physiological indicators (CPI) based on the average weight principle were constructed. The correlation between PWC and comprehensive indicators was analyzed, and multiple linear regression (MLR), partial least squares recurrence (PLSR) and support vector machine (SVM) methods were used to construct the PWC inversion model based on comprehensive indicators according to the growth period.【Result】The canopy temperature parameters, morphology and physiological indexes of winter wheat at different growth stages showed significant differences between water deficit treatments (W1, W2) and control treatment (W3) (P<0.05). Comprehensive indicators (CTPI, CGI and CPI) at booting and filling stages have a significant correlation with PWC, with correlation coefficients (r) of -0.70 (-0.78), 0.84 (0.80) and 0.83 (0.76), respectively. Using MLR, PLSR and SVM methods, the PWC inversion prediction model based on comprehensive indicators (CTPI, CGI and CPI) has high prediction accuracy, among which the PWC model built by SVM is the best, R²_cal (R²_val), RMSE_cal (RMSE_val), and nRMSE_cal (nRMSE_val) were 0.878 (0.815), 2.06% (2.37%), and 3.10% (3.33%), respectively.【Conclusion】The SVM-PWC model based on the comprehensive indicators CTPI, CGI and CPI can well predict the water deficit of winter wheat at different growth stages, and provide theoretical basis for drought prevention and drought resistance of winter wheat in the Huang-Huai-Hai Plain.

Key words: winter wheat, water deficit, comprehensive index, plant water content (PWC), support vector machine (SVM)

高晨凯, 刘水苗, 李煜铭, 吴鹏年, 王艳丽, 刘长硕, 乔毅博, 关小康, 王同朝, 温鹏飞. 基于综合指标协同优化的冬小麦植株水分含量预测[J]. 中国农业科学, 2023, 56(22): 4403-4416.

GAO ChenKai, LIU ShuiMiao, LI YuMing, WU PengNian, WANG YanLi, LIU ChangShuo, QIAO YiBo, GUAN XiaoKang, WANG TongChao, WEN PengFei. Prediction of Water Content of Winter Wheat Plant Based on Comprehensive Index Synergetic Optimization[J]. Scientia Agricultura Sinica, 2023, 56(22): 4403-4416.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2023.22.004

https://www.chinaagrisci.com/CN/Y2023/V56/I22/4403

图/表 7

图1

表1

图2

图3

表2

图4

图5

参考文献 43

[1]	王莺, 张强, 王劲松, 韩兰英, 王素萍, 张良, 姚玉璧, 郝小翠, 王胜. 21世纪以来干旱研究的若干新进展与展望. 干旱气象, 2022, 40(4): 549-566. doi: 10.11755/j.issn.1006-7639(2022)-04-0549
	WANG Y, ZHANG Q, WANG J S, HAN L Y, WANG S P, ZHANG L, YAO Y B, HAO X C, WANG S. New progress and prospect of drought research since the 21st century. Journal of Arid Meteorology, 2022, 40(4): 549-566. (in Chinese)
[2]	宋艳玲. 全球干旱指数研究进展. 应用气象学报, 2022, 33(5): 513-526.
	SONG Y L. Global research progress on drought indices. Journal of Applied Meteorological Science, 2022, 33(5): 513-526. (in Chinese)
[3]	姚玉璧, 杨金虎, 肖国举, 雷俊, 牛海洋, 张秀云. 气候变暖对西北雨养农业及农业生态影响研究进展. 生态学杂志, 2018, 37(7): 2170-2179.
	YAO Y B, YANG J H, XIAO G J, LEI J, NIU H Y, ZHANG X Y. Research advances in the impacts of climate warming on rainfed agriculture and agroecology in Northwest China. Chinese Journal of Ecology, 2018, 37(7): 2170-2179. (in Chinese)
[4]	徐建文, 居辉, 刘勤, 杨建莹. 黄淮海地区干旱变化特征及其对气候变化的响应. 生态学报, 2014, 34(2): 460-470.
	XU J W, JU H, LIU Q, YANG J Y. Variation of drought and regional response to climate change in Huang-Huai-Hai Plain. Acta Ecologica Sinica, 2014, 34(2): 460-470. (in Chinese)
[5]	胡实, 莫兴国, 林忠辉. 冬小麦种植区域的可能变化对黄淮海地区农业水资源盈亏的影响. 地理研究, 2017, 36(5): 861-871. doi: 10.11821/dlyj201705005
	HU S, MO X G, LIN Z H. Impacts of possibility planting region change for winter wheat on agricultural water surplus and deficit in Huang-Huai-Hai Region. Geographical Research, 2017, 36(5): 861-871. (in Chinese) doi: 10.11821/dlyj201705005
[6]	刘宪锋, 朱秀芳, 潘耀忠, 李双双, 刘焱序. 农业干旱监测研究进展与展望. 地理学报, 2015, 70(11): 1835-1848. doi: 10.11821/dlxb201511012
	LIU X F, ZHU X F, PAN Y Z, LI S S, LIU Y X. Agricultural drought monitor: Progress, challenges and prospect. Acta Geographica Sinica, 2015, 70(11): 1835-1848. (in Chinese) doi: 10.11821/dlxb201511012
[7]	王正航, 武仙山, 昌小平, 李润植, 景蕊莲. 小麦旗叶叶绿素含量及荧光动力学参数与产量的灰色关联度分析. 作物学报, 2010, 36(2): 217-227. doi: 10.3724/SP.J.1006.2010.00217
	WANG Z H, WU X S, CHANG X P, LI R Z, JING R L. Chlorophyll content and chlorophyll fluorescence kinetics parameters of flag leaf and their gray relational grade with yield in wheat. Acta Agronomica Sinica, 2010, 36(2): 217-227. (in Chinese) doi: 10.3724/SP.J.1006.2010.00217
[8]	高丽华, 孙书洪. 不同时期水分胁迫对冬小麦产量及形态指标的影响研究. 节水灌溉, 2014(7): 1-3.
	GAO L H, SUN S H. Study on effects of water deficit in different periods on yield and morphological index of winter wheat. Water Saving Irrigation, 2014(7): 1-3. (in Chinese)
[9]	ABID M, TIAN Z W, ATA-UL-KARIM S T, LIU Y, CUI Y K, ZAHOOR R, JIANG D, DAI T B. Improved tolerance to post-anthesis drought stress by pre-drought priming at vegetative stages in drought-tolerant and -sensitive wheat cultivars. Plant Physiology and Biochemistry, 2016, 106: 218-227. doi: 10.1016/j.plaphy.2016.05.003 pmid: 27179928
[10]	NA Z, GUO X Q, JUN W X. Eco-physiological and morphological responses of Pinellia ternate from different sources under drought stress. Pakistan Journal of Agricultural Sciences, 2022, 59(6): 1043-1052. doi: 10.21162/PAKJAS
[11]	FLEXAS J, NIINEMETS U, GALLÉ A, BARBOUR M M, CENTRITTO M, DIAZ-ESPEJO A, DOUTHE C, GALMÉS J, RIBAS-CARBO M, RODRIGUEZ P L, et al. Diffusional conductances to CO₂ as a target for increasing photosynthesis and photosynthetic water-use efficiency. Photosynthesis Research, 2013, 117(1/3): 45-59. doi: 10.1007/s11120-013-9844-z
[12]	LUAN Y, XU J, LV Y, LIU X, WANG H, LIU S. Improving the performance in crop water deficit diagnosis with canopy temperature spatial distribution information measured by thermal imaging. Agricultural Water Management, 2021, 246: 106699. doi: 10.1016/j.agwat.2020.106699
[13]	FANG J J, MA W Y, ZHAO X Q, HE X, LI B, TONG Y P, LI Z S. Lower canopy temperature is associated with higher cytokinin concentration in the flag leaf of wheat. Crop Science, 2012, 52(6): 2743-2756. doi: 10.2135/cropsci2012.03.0163
[14]	赵福年, 王瑞君, 张虹, 张龙, 陈家宙. 基于冠气温差的作物水分胁迫指数经验模型研究进展. 干旱气象, 2012, 30(4): 522-528.
	ZHAO F N, WANG R J, ZHANG H, ZHANG L, CHEN J Z. Advances in crop water stress index empirical model research based on canopy and atmosphere temperature difference. Journal of Arid Meteorology, 2012, 30(4): 522-528. (in Chinese)
[15]	YU M H, DING G D, GAO G L, ZHAO Y Y, YAN L, SAI K. Using plant temperature to evaluate the response of stomatal conductance to soil moisture deficit. Forests, 2015, 6(12): 3748-3762. doi: 10.3390/f6103748
[16]	张鑫, 孔祥, 李勇, 骆永丽, 黄翠, 金敏. 外源ABA对干旱条件下小麦冠层温度及光合同化物积累与分配的调控效应. 麦类作物学报, 2019, 39(9): 1080-1094.
	ZHANG X, KONG X, LI Y, LUO Y L, HUANG C, JIN M. Effect of exogenous ABA on the canopy temperature and accumulation and distribution of photoassimilates in wheat under drought conditions. Journal of Triticeae Crops, 2019, 39(9): 1080-1094. (in Chinese)
[17]	MORALES I, ÁLVARO J E, URRESTARAZU M. Contribution of thermal imaging to fertigation in soilless culture. Journal of Thermal Analysis and Calorimetry, 2014, 116(2): 1033-1039. doi: 10.1007/s10973-013-3529-x
[18]	MANGUS D, SHARDA A, ZHANG N. Development and evaluation of thermal infrared imaging system for high spatial and temporal resolution crop water stress monitoring of corn within a greenhouse. Computers and Electronics in Agriculture, 2016, 121(2): 149-159. doi: 10.1016/j.compag.2015.12.007
[19]	刘伟琦, 马绍休, 宫毓来, 冯坤, 梁林昊. 农业干旱业务化监测研究进展与展望. 中国沙漠, 2023, 43(1): 197-211. doi: 10.7522/j.issn.1000-694X.2022.00120
	LIU W Q, MA S X, GONG Y L, FENG K, LIANG L H. Research progress and prospective for operationalization of agricultural drought monitoring. Journal of Desert Research, 2023, 43(1): 197-211. (in Chinese)
[20]	杨天垚, 邱建秀, 肖国安. 华北农业干旱监测与冬小麦估产研究. 生态学报, 2023, 43(5): 1936-1947.
	YANG T Y, QIU J X, XIAO G A. Agricultural drought monitoring and winter wheat yield estimation in north China. Acta Ecologica Sinica, 2023, 43(5): 1936-1947. (in Chinese)
[21]	张宇亮, 吴志勇, 何海. 基于水文-作物耦合模型和CWAPI指数的农业干旱评估. 水利学报, 2022, 53(10): 1168-1179, 1193.
	ZHANG Y L, WU Z Y, HE H. Agricultural drought assessment based on the coupled hydrology-crop growth model and CWAPI. Journal of Hydraulic Engineering, 2022, 53(10): 1168-1179, 1193. (in Chinese)
[22]	单捷, 孙玲, 王志明, 卢必慧, 王晶晶, 邱琳, 黄晓军. GF-1影像遥感监测指标与冬小麦长势参数的关系. 江苏农业学报, 2019, 35(6): 1323-1333.
	SHAN J, SUN L, WANG Z M, LU B H, WANG J J, QIU L, HUANG X J. Relationship between remote sensing monitoring indices and growth parameters in winter wheat based on GF-1 images. Jiangsu Journal of Agricultural Sciences, 2019, 35(6): 1323-1333. (in Chinese)
[23]	翟丽婷, 魏峰远, 冯海宽, 李长春, 杨贵军. 基于综合指标的冬小麦长势监测. 江苏农业科学, 2020, 48(18): 244-249.
	ZHAI L T, WEI F Y, FENG H K, LI C C, YANG G J. Winter wheat growth monitoring based on comprehensive indicators. Jiangsu Agricultural Sciences, 2020, 48(18): 244-249. (in Chinese)
[24]	裴浩杰, 冯海宽, 李长春, 金秀良, 李振海, 杨贵军. 基于综合指标的冬小麦长势无人机遥感监测. 农业工程学报, 2017, 33(20): 74-82.
	PEI H J, FENG H K, LI C C, JIN X L, LI Z H, YANG G J. Remote sensing monitoring of winter wheat growth with UAV based on comprehensive index. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(20): 74-82. (in Chinese)
[25]	孟雨, 温鹏飞, 丁志强, 田文仲, 张学品, 贺利, 段剑钊, 刘万代, 冯伟. 基于热红外图像的小麦品种抗旱性鉴定与评价. 中国农业科学, 2022, 55(13): 2538-2551. doi: 10.3864/j.issn.0578-1752.2022.13.005.
	MENG Y, WEN P F, DING Z Q, TIAN W Z, ZHANG X P, HE L, DUAN J Z, LIU W D, FENG W. Identification and evaluation of drought resistance of wheat varieties based on thermal infrared image. Scientia Agricultura Sinica, 2022, 55(13): 2538-2551. doi: 10.3864/j.issn.0578-1752.2022.13.005. (in Chinese)
[26]	张智韬, 边江, 韩文霆, 付秋萍, 陈硕博, 崔婷. 无人机热红外图像计算冠层温度特征数诊断棉花水分胁迫. 农业工程学报, 2018, 34(15): 77-84.
	ZHANG Z T, BIAN J, HAN W T, FU Q P, CHEN S B, CUI T. Cotton moisture stress diagnosis based on canopy temperature characteristics calculated from UAV thermal infrared image. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(15): 77-84. (in Chinese)
[27]	张智韬, 许崇豪, 谭丞轩, 李宇, 宁纪锋. 基于无人机热红外遥感的玉米地土壤含水率诊断方法. 农业机械学报, 2020, 51(3): 180-190.
	ZHANG Z T, XU C H, TAN C X, LI Y, NING J F. Diagnosing method of soil moisture content in corn field based on thermal infrared remote sensing of UAV. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(3): 180-190. (in Chinese)
[28]	JACKSON R D, IDSO S B, REGINATO R J, PINTER P J. Canopy temperature as a crop water stress indicator. Water Resources Research, 1981, 17(4): 1133-1138. doi: 10.1029/WR017i004p01133
[29]	陶惠林, 徐良骥, 冯海宽, 杨贵军, 苗梦珂, 林博文. 基于无人机高光谱长势指标的冬小麦长势监测. 农业机械学报, 2020, 51(2): 180-191.
	TAO H L, XU L J, FENG H K, YANG G J, MIAO M K, LIN B W. Monitoring of winter wheat growth based on UAV hyperspectral growth index. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(2): 180-191. (in Chinese)
[30]	蔡苇荻, 张羽, 刘海燕, 郑恒彪, 程涛, 田永超, 朱艳, 曹卫星, 姚霞. 基于成像高光谱的小麦冠层白粉病早期监测方法. 中国农业科学, 2022, 55(6): 1110-1126. doi: 10.3864/j.issn.0578-1752.2022.06.005.
	CAI W D, ZHANG Y, LIU H Y, ZHENG H B, CHENG T, TIAN Y C, ZHU Y, CAO W X, YAO X. Early detection on wheat canopy powdery mildew with hyperspectral imaging. Scientia Agricultura Sinica, 2022, 55(6): 1110-1126. doi: 10.3864/j.issn.0578-1752.2022.06.005. (in Chinese)
[31]	刘相龙, 刘仲武, 马灵会, 任凯, 王晓东. 基于支持向量机的边坡稳定性系数预测及变量分析. 水利与建筑工程学报, 2023, 21(1): 172-178.
	LIU X L, LIU Z W, MA L H, REN K, WANG X D. Slope stability coefficient prediction and variable analysis based on support vector machine. Journal of Water Resources and Architectural Engineering, 2023, 21(1): 172-178. (in Chinese)
[32]	张智韬, 谭丞轩, 许崇豪, 陈硕博, 韩文霆, 李宇. 基于无人机多光谱遥感的玉米根域土壤含水率研究. 农业机械学报, 2019, 50(7): 246-257.
	ZHANG Z T, TAN C X, XU C H, CHEN S B, HAN W T, LI Y. Retrieving soil moisture content in field maize root zone based on UAV multispectral remote sensing. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(7): 246-257. (in Chinese)
[33]	曾占奎, 王征宏, 王黎明, 庞玉辉, 韩志鹏, 郭程, 王春平. 北部冬麦区小麦新品种(系)的节水生理特性与综合评判. 干旱地区农业研究, 2019, 37(5): 137-143.
	ZENG Z K, WANG Z H, WANG L M, PANG Y H, HAN Z P, GUO C, WANG C P. Water-saving physiological characteristics and comprehensive evaluation of new wheat varieties (lines) in northern winter wheat region. Agricultural Research in the Arid Areas, 2019, 37(5): 137-143. (in Chinese)
[34]	姚宁, 宋利兵, 刘健, 冯浩, 吴淑芳, 何建强. 不同生长阶段水分胁迫对旱区冬小麦生长发育和产量的影响. 中国农业科学, 2015, 48(12): 2379-2389. doi: 10.3864/j.issn.0578-1752.2015.12.011.
	YAO N, SONG L B, LIU J, FENG H, WU S F, HE J Q. Effects of water stress at different growth stages on the development and yields of winter wheat in arid region. Scientia Agricultura Sinica, 2015, 48(12): 2379-2389. doi: 10.3864/j.issn.0578-1752.2015.12.011. (in Chinese)
[35]	史博, 马祖凯, 刘小军, 田永超, 朱艳, 曹卫星, 曹强. 小麦植株水分状况遥感监测研究进展与展望. 麦类作物学报, 2022, 42(4): 495-503.
	SHI B, MA Z K, LIU X J, TIAN Y C, ZHU Y, CAO W X, CAO Q. Progress and prospects of wheat plant water status monitoring by remote sensing. Journal of Triticeae Crops, 2022, 42(4): 495-503. (in Chinese)
[36]	SHABANI A, SEPASKHAH A R, KAMGAR-HAGHIGHI A A. Responses of agronomic components of rapeseed (Brassica napus L.) as influenced by deficit irrigation, water salinity and planting method. International Journal of Plant Production, 2013, 7(2): 313-340.
[37]	ALI S, XU Y Y, JIA Q M, AHMAD I, WEI T, REN X L, ZHANG P, DIN R, CAI T, JIA Z K. Cultivation techniques combined with deficit irrigation improves winter wheat photosynthetic characteristics, dry matter translocation and water use efficiency under simulated rainfall conditions. Agricultural Water Management, 2018, 201: 207-218. doi: 10.1016/j.agwat.2018.01.017
[38]	DEJONGE K C, TAGHVAEIAN S, TROUT T J, COMAS L H. Comparison of canopy temperature-based water stress indices for maize. Agricultural Water Management, 2015, 156: 51-62. doi: 10.1016/j.agwat.2015.03.023
[39]	李德, 孙有丰, 孙义. 皖北砂姜黑土地冬小麦生育期尺度干旱指标研究. 麦类作物学报, 2017, 37(2): 220-231.
	LI D, SUN Y F, SUN Y. Study on drought indices of winter wheat during the growth stages in the lime concretion black soil in northern Anhui Province. Journal of Triticeae Crops, 2017, 37(2): 220-231. (in Chinese)
[40]	陈倩. 基于综合指标的冬小麦长势高光谱遥感监测与估产研究[D]. 杨凌: 西北农林科技大学, 2022: 98.
	CHEN Q. Hyperspectral remote sensing monitoring and yield estimation of winter wheat growth based on comprehensive index[D]. Yangling: Northwest A&F University, 2022: 98. (in Chinese)
[41]	樊意广, 冯海宽, 刘杨, 边明博, 孟炀, 杨贵军. 基于冠层光谱特征和株高的马铃薯植株氮含量估算. 农业机械学报, 2022, 53(6): 202-208, 294.
	FAN Y G, FENG H K, LIU Y, BIAN M B, MENG Y, YANG G J. Estimation of potato plant nitrogen content based on canopy spectral characteristics and plant height. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(6): 202-208, 294. (in Chinese)
[42]	刘方园, 王水花, 张煜东. 支持向量机模型与应用综述. 计算机系统应用, 2018, 27(4): 1-9.
	LIU F Y, WANG S H, ZHANG Y D. Overview on models and applications of support vector machine. Computer Systems & Applications, 2018, 27(4): 1-9. (in Chinese)
[43]	LI Z, NIE C, WEI C, XU X, SONG X, WANG J. Comparison of four chemometric techniques for estimating leaf nitrogen concentrations in winter wheat (Triticum aestivum) based on hyperspectral features. Journal of Applied Spectroscopy, 2016, 83(2): 240-247. doi: 10.1007/s10812-016-0276-3

生育时期 Growing stage	处理 Treatment		CETR	MTD	CTSD	CTCV	CRTD	CWSI
拔节期 Jointing stage	洛麦22 Luomai 22	W1	19.41-29.61	10.85-14.14	1.21-1.46	0.052-0.059	0.163-0.184	0.41-0.45
		W2	16.94-25.17	8.03-8.63	0.92-1.00	0.047-0.049	0.136-0.144	0.34-0.36
		W3	15.85-22.01	5.52-7.03	0.83-0.88	0.042-0.044	0.113-0.124	0.30-0.32
	周麦27 Zhoumai 27	W1	20.37-29.56	14.29-15.26	1.09-1.64	0.052-0.069	0.174-0.191	0.42-0.49
		W2	17.21-25.26	8.26-9.52	0.96-1.08	0.048-0.051	0.169-0.178	0.40-0.43
		W3	16.38-23.18	6.24-6.68	0.83-0.87	0.041-0.045	0.134-0.162	0.34-0.37
孕穗期 Booting stage	洛麦22 Luomai 22	W1	23.74-33.91	9.43-13.40	1.55-1.94	0.066-0.081	0.179-0.191	0.42-0.48
		W2	21.60-28.26	5.99-6.36	0.73-0.87	0.031-0.036	0.117-0.134	0.37-0.39
		W3	20.24-26.04	4.43-5.71	0.55-0.69	0.024-0.029	0.088-0.116	0.29-0.33
	周麦27 Zhoumai 27	W1	24.34-37.74	9.59-13.67	1.66-2.29	0.074-0.093	0.216-0.244	0.41-0.49
		W2	22.80-29.69	7.15-8.06	0.85-0.93	0.032-0.036	0.131-0.143	0.42-0.48
		W3	20.48-26.44	5.38-6.12	0.64-0.79	0.027-0.033	0.101-0.127	0.29-0.39
灌浆期 Filling stage	洛麦22 Luomai 22	W1	31.32-42.48	11.37-12.21	1.72-1.95	0.051-0.056	0.167-0.185	0.45-0.51
		W2	29.31-40.07	7.80-8.38	1.35-1.61	0.041-0.046	0.115-0.146	0.42-0.45
		W3	27.86-34.51	5.99-7.40	0.61-0.89	0.021-0.028	0.085-0.106	0.31-0.38
	周麦27 Zhoumai 27	W1	31.68-43.53	10.70-13.35	1.98-2.53	0.058-0.070	0.173-0.208	0.50-0.55
		W2	30.74-41.23	8.41-9.63	1.29-1.63	0.041-0.048	0.126-0.144	0.43-0.46
		W3	28.40-36.35	7.65-8.52	0.73-1.15	0.024-0.036	0.119-0.123	0.37-0.41

生育时期 Growing stage	建模Modeling									验证Validation
	MLR			PLSR			SVM			MLR			PLSR			SVM
	R²	RMSE	nRMSE	R²	RMSE	nRMSE	R²	RMSE	nRMSE	R²	RMSE	nRMSE	R²	RMSE	nRMSE	R²	RMSE	nRMSE
拔节期 Jointing stage	0.707	2.62%	3.30%	0.735	3.91%	5.48%	0.728	2.97%	4.48%	0.622	4.67%	6.21%	0.658	7.50%	10.04%	0.702	3.71%	5.07%
孕穗期 Booting stage	0.771	2.70%	3.86%	0.827	2.23%	3.20%	0.878	2.06%	3.10%	0.676	4.11%	5.87%	0.766	3.98%	5.65%	0.815	2.37%	3.33%
灌浆期 Filling stage	0.721	3.30%	5.53%	0.744	3.30%	4.98%	0.770	3.16%	5.54%	0.668	4.04%	6.57%	0.704	3.72%	5.67%	0.718	3.70%	5.31%
全生育期 Whole reproductive period	0.494	6.02%	8.23%	0.572	5.10%	6.38%	0.711	5.06%	6.32%	0.387	10.71%	17.83%	0.508	9.26%	16.21%	0.665	7.62%	13.34%