基于无人机平台多模态数据融合的小麦产量估算研究

doi:10.3724/SP.J.1006.2022.11053

Abstract

Abstract:

Crop yield estimations are important for national food security, people, and the environment. Timely and accurate estimation of crop yield at the field scale is of great significance for crop management, harvest and trade. It ultimately enables farmers to optimize inputs and economic return. We selected an irrigated wheat field in a region near Kaifeng, Henan province, for this study. The terrain in that region is undulating and spatial differences. We used a low-altitude unmanned aerial vehicle (UAV) remote sensing platform equipped with a multi-spectral camera, thermal infrared camera, and RGB camera to simultaneously obtain different remote sensing parameters during the key growth stages of wheat. Based on the extracted spectral reflectivity, thermal infrared temperature, and digital elevation information, we calculated the spatial variability of remote sensing parameters, and growth indices under different terrain characteristics. We also analyzed the correlations between vegetation indices, temperature parameters and wheat yield. By means of four machine learning methods, including multiple linear regression method (MLR), partial least squares regression method (PLSR), support vector machine regression method (SVR), and random forest regression method (RFR), we compared the yield estimation capability of single-modal data versus multimodal data fusion frameworks. The results showed that slope was an important factor affecting crop growth and yield. We observed significant differences in remote sensing parameters under different slope grades. Soil water content, water content of plants, and above-ground biomass at the three growth stages were significantly correlated with slope. Most of the vegetation indices and temperature parameters of three growth stages were significantly correlated with yield as well. Based on the strength of their correlation with yield, seven vegetation indices (NDVI, GNDVI, EVI2, OSAVI, SAVI, NDRE, and WDRVI) and two temperature parameters (NRCT, CTD) were selected as the final input variables for the model. For the single-modal data framework, the model constructed with the vegetation indices was better than the yield model constructed with the temperature parameters, and the highest accuracy was obtained with a RFR model based on vegetation indices at filling stage (R²= 0.724, RMSE = 614.72 kg hm^-2, MAE = 478.08 kg hm^-2). For the double modal data fusion approach, the highest accuracy resulted at flowering stage, using the temperature parameters combined with the vegetation indices of RFR model (R²=0.865, RMSE=440.73 kg hm^-2, MAE=374.86 kg hm^-2). Even higher accuracies were obtained, using the multimodal data fusion approach with a RFR model based on vegetation indices, temperature parameters and slope information at flowering stage (R²= 0.893, RMSE = 420.06 kg hm^-2, MAE = 352.69 kg hm^-2), and the highest validation model (R²= 0.892, RMSE = 423.55 kg hm^-2, MAE = 334.43 kg hm^-2) for fusion of the flowering stage. The results revealed that by using a multimodal data fusion framework of terrain factors combined with RFR, we can fully exploit the complementary and synergistic roles of different remote sensing information sources. This effectively improves the accuracy and stability of the yield estimation model, and provides a reference and support for crop growth monitoring and yield estimation.

Key words: winter wheat, unmanned aerial vehicle (UAV), yield estimation, terrain factor, multimodal data

ZHANG Shao-Hua, DUAN Jian-Zhao, HE Li, JING Yu-Hang, Urs Christoph Schulthess, Azam Lashkari, GUO Tian-Cai, WANG Yong-Hua, FENG Wei. Wheat yield estimation from UAV platform based on multi-modal remote sensing data fusion[J].Acta Agronomica Sinica, 2022, 48(7): 1746-1760.

Figures/Tables 11

Fig. 1

Fig. 2

Fig. 3

Table 1

Spectral indices and temperature parameter in this study"

参数 Index	公式 Formula	参考文献 Reference
归一化植被指数Normalized difference vegetation index (NDVI)	$\frac{\left( {{R}_{\text{nir}}}-{{R}_{\text{red}}} \right)}{\left( {{R}_{\text{nir}}}+{{R}_{\text{red}}} \right)}$	[25]
归一化绿度植被指数Green normalized difference vegetation index (GNDVI)	$\frac{\left( {{R}_{\text{nir}}}-{{R}_{\text{green}}} \right)}{\left( {{R}_{\text{nir}}}+{{R}_{\text{green}}} \right)}$	[26]
双波段增强植被指数Two-band enhanced vegetation index (EVI2)	$2.5\times \frac{\left( {{R}_{\text{nir}}}-{{R}_{\text{red}}} \right)}{\left( {{R}_{\text{nir}}}+2.4\times {{R}_{\text{red}}}+1 \right)}$	[27]
优化土壤调整植被指数Optimized soil adjusted vegetation index (OSAVI)	$1.16\times \frac{\left( {{R}_{\text{nir}}}-{{R}_{\text{red}}} \right)}{\left( {{R}_{\text{nir}}}+{{R}_{\text{red}}}+0.16 \right)}$	[28]
土壤调整植被指数Soil adjusted vegetation index (SAVI)	$1.5\times \frac{\left( {{R}_{\text{nir}}}-{{R}_{\text{red}}} \right)}{\left( {{R}_{\text{nir}}}+{{R}_{\text{red}}}+0.5 \right)}$	[29]
红边归一化植被指数Red edge normalized index (NDRE)	$\frac{\left( {{R}_{\text{nir}}}-{{R}_{\text{re}}} \right)}{\left( {{R}_{\text{nir}}}+{{R}_{\text{re}}} \right)}$	[30]
宽动态植被指数Wide dynamic range vegetation index (WDRVI)	$\frac{\left( 0.1\times {{R}_{\text{nir}}}-{{R}_{\text{red}}} \right)}{\left( 0.1\times {{R}_{\text{nir}}}+{{R}_{\text{red}}} \right)}$	[31]
改善简单比率植被指数Modified simple ratio index (MSR)	$\frac{\left( \frac{{{R}_{\text{nir}}}}{{{R}_{\text{red}}}-1} \right)}{\left( \sqrt{\frac{{{R}_{\text{nir}}}}{{{R}_{\text{red}}}}}+1 \right)}$	[32]
改良叶绿素吸收率指数 Modified chlorophyll absorption ratio index (MCARI)	$\frac{\left[ {{R}_{\text{re}}}-{{R}_{\text{red}}}-0.2\left( {{R}_{\text{re}}}-{{R}_{\text{green}}} \right) \right]}{\left( \frac{{{R}_{\text{re}}}}{{{R}_{\text{red}}}} \right)}$	[33]
参数 Index	公式 Formulas	参考文献 References
红波段比值植被指数Red ratio vegetation index (RVI_red)	$\frac{{{R}_{\text{nir}}}}{{{R}_{\text{red}}}}$	[34]
标准化相对冠层温度Normalized relative canopy temperature (NRCT)	$\frac{\left( {{T}_{c}}-{{T}_{\text{min}}} \right)}{\left( {{T}_{\max }}+{{T}_{\text{min}}} \right)}$	[35]
冠-气温差Canopy temperature depression (CTD)	${{T}_{c}}-{{T}_{\alpha }}$	[36]

Table 1

Table 2

Table 3

Table 4

Table 5

Fig. 4

Table 6

Fig. 5

References 58

[1]	He L, Asseng S, Zhao G, Wu D R, Yang X Y, Zhuang W, Jin N, Yu Q. Impacts of recent climate warming, cultivar changes, and crop management on winter wheat phenology across the Loess Plateau of China. Agric Forest Meteorol, 2015, 200: 135-143. doi: 10.1016/j.agrformet.2014.09.011
[2]	Mueller N, Gerber J S, Johnston M, Ray D K, Ramankutty N, Foley J A. Closing yield gaps through nutrient and water management. Nature, 2012, 490: 254-257. doi: 10.1038/nature11420
[3]	杨绚, 汤绪, 陈葆德, 田展, 赵思健. 利用CMIP5多模式集合模拟气候变化对中国小麦产量的影响. 中国农业科学, 2014, 47: 3009-3024.
	Yang X, Tang X, Chen B D, Tian Z, Zhao S J. Impacts of climate change on wheat yield in China simulated by CMIP5 multi-model ensemble projections. Sci Agric Sin, 2014, 47: 3009-3024. (in Chinese with English abstract)
[4]	Reshef I B, Vermote E, Lindeman M, Justice C. A generalized regression-based model for forecasting winter wheat yields in Kansas and Ukraine using MODIS data. Remote Sens Environ, 2010, 114: 1312-1323. doi: 10.1016/j.rse.2010.01.010
[5]	Zaman-Allah M, Vergara O, Araus J L, Tarekegne A, Magorokosho C, Zarco-Tejada P J, Hornero A, Albà A H, Das B, Craufurd P, Olsen M, Prasanna B M, Cairns J. Unmanned aerial platform-based multi-spectral imaging for field phenotyping of maize. Plant Methods, 2015, 11: 35. doi: 10.1186/s13007-015-0078-2 pmid: 26106438
[6]	Wang L G, Tian Y G, Yao X, Zhu Y, Cao W X. Predicting grain yield and protein content in wheat by fusing multisensory and multi-temporal remote-sensing images. Field Crops Res, 2014, 164: 178-188. doi: 10.1016/j.fcr.2014.05.001
[7]	纪景纯, 赵原, 邹晓娟, 宣可凡, 王伟鹏, 刘建立, 李晓鹏. 无人机遥感在农田信息监测中的应用进展. 土壤学报, 2019, 56: 773-784.
	Ji J C, Zhao Y, Zou X J, Xuan K F, Wang W P, Liu J L, Li X P. Advancement in application of UAV remote sensing to monitoring of farmlands. Acta Pedol Sin, 2019, 56: 773-784. (in Chinese with English abstract)
[8]	胡健波, 张健. 无人机遥感在生态学中的应用进展. 生态学报, 2018, 38: 20-30.
	Hu J B, Zhang J. Unmanned aerial vehicle remote sensing in ecology: advances and prospects. Acta Ecol Sin, 2018, 38: 20-30. (in Chinese with English abstract)
[9]	孙刚, 黄文江, 陈鹏飞, 高帅, 王秀. 轻小型无人机多光谱遥感技术应用进展. 农业机械学报, 2018, 49(3): 1-17.
	Sun G, Huang W J, Chen P F, Gao S, Wang X. Advances in UAV-based multispectral remote sensing applications. Trans CSAM, 2018, 49(3): 1-17. (in Chinese with English abstract)
[10]	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 Z J. Remote sensing monitoring of winter wheat growth with UAV based on comprehensive index. Trans CSAE, 2017, 33(20): 74-82. (in Chinese with English abstract)
[11]	Navarro A, Young M, Allan B, Carnell P, Macreadie P, Ierodiaconou D. The application of unmanned aerial vehicles (UAVs) to estimate aboveground biomass of mangrove ecosystems. Remote Sens Environ, 2020, 242: 111747. doi: 10.1016/j.rse.2020.111747
[12]	Zhang C H, Kovacs J M. The application of small unmanned aerial systems for precision agriculture: a review. Precis Agric, 2012, 13: 693-712. doi: 10.1007/s11119-012-9274-5
[13]	朱婉雪, 李仕冀, 张旭博, 李洋, 孙志刚. 基于无人机遥感植被指数优选的田块尺度冬小麦估产. 农业工程学报, 2018, 34(11): 78-86.
	Zhu W X, Li S J, Zhang X B, Li Y, Sun Z G. Estimation of winter wheat yield using optimal vegetation indices from unmanned aerial vehicle remote sensing. Trans CSAE, 2018, 34(11): 78-86. (in Chinese with English abstract)
[14]	程千, 徐洪刚, 曹引波, 段福义, 陈震. 基于无人机多时相植被指数的冬小麦产量估测. 农业机械学报, 2021, 52(3): 160-167.
	Cheng Q, Xu H G, Cao Y B, Duan F Y, Chen Z. Grain yield prediction of winter wheat using multi-temporal UAV based multispectral vegetation index. Trans CSAM, 2021, 52(3): 160-167. (in Chinese with English abstract)
[15]	刘畅, 杨贵军, 李振海, 汤伏全, 王建雯, 张春兰, 张丽妍. 融合无人机光谱信息与纹理信息的冬小麦生物量估测. 中国农业科学, 2018, 51: 3060-3073.
	Liu C, Yang G J, Li Z H, Tang F Q, Wang J W, Zhang C L, Zhang L Y. Biomass estimation in winter wheat by UAV spectral information and texture information fusion. Sci Agric Sin, 2018, 51: 3060-3073. (in Chinese with English abstract)
[16]	Fu Y Y, Yang G J, Song X Y, Li Z H, Xu X G, Feng H K, Zhao C J. Improved estimation of winter wheat aboveground biomass using multiscale textures extracted from UAV-based digital images and hyperspectral feature analysis. Remote Sens, 2021, 13: 581. doi: 10.3390/rs13040581
[17]	Elsayed S, Elhoweity M, Ibrahim H H, Dewir Y H, Migdadi H M, Schmidhalter U. Thermal imaging and passive reflectance sensing to estimate the water status and grain yield of wheat under different irrigation regimes. Agric Water Manage, 2017, 189: 98-110. doi: 10.1016/j.agwat.2017.05.001
[18]	Rischbeck P, Elsayed S, Mistele B, Barmeier G, Heil K, Schmidhalter U. Data fusion of spectral, thermal and canopy height parameters for improved yield prediction of drought stressed spring barley. Eur J Agron, 2016, 78: 44-59. doi: 10.1016/j.eja.2016.04.013
[19]	Maimaitijiang M, Sagan V, Sidike P, Hartling S, Esposito F, Fritschi F B. Soybean yield prediction from UAV using multimodal data fusion and deep learning. Remote Sens Environ, 2020, 237: 111599. doi: 10.1016/j.rse.2019.111599
[20]	Riihimäki H, Heiskanen J, Luoto M. The effect of topography on arctic-alpine aboveground biomass and NDVI patterns. Int J Appl Earth Obs, 2017, 56: 44-53.
[21]	Nie X D, Guo W, Huang B, Zhuo M N, Li D Q, Li Z W, Yuan Z J. Effects of soil properties, topography and landform on the understory biomass of a pine forest in a subtropical hilly region. Catena (Giessen), 2019, 176: 104-111. doi: 10.1016/j.catena.2019.01.007
[22]	Yang Q Y, Jiang Z C, Li W J, Li H. Prediction of soil organic matter in peak-cluster depression region using kriging and terrain indices. Soil Tillage Res, 2014, 144: 126-132. doi: 10.1016/j.still.2014.07.011
[23]	张新乐, 徐梦园, 刘焕军, 孟令华, 邱政超, 潘越, 谢雅慧. 引入地形因子的黑土区大豆干生物量遥感反演模型及验证. 农业工程学报, 2017, 33(16): 168-173.
	Zhang X L, Xu M Y, Liu H J, Meng L H, Qiu Z C, Pan Y, Xie Y H. Remote sensing inversion models and validation of aboveground biomass in soybean with introduction of terrain factors in black soil area. Trans CSAE, 2017, 33(16): 168-173. (in Chinese with English abstract)
[24]	侯淑涛, 崔杨, 孟令华, 武丹茜, 钱蕾, 鲍依临, 叶强, 刘焕军. 地形对漫川漫岗黑土区大豆产量的影响. 农业工程学报, 2020, 36(8): 88-95.
	Hou S T, Cui Y, Meng L H, Wu D Q, Qian L, Bao Y L, Ye Q, Liu H J. Effects of terrain on soybean yields in rolling hilly black soil areas. Trans CSAE, 2020, 36(8): 88-95. (in Chinese with English abstract)
[25]	Qi J, Kerr Y, Moran M, Weltz M, Huete A, Sorooshian S, Bryant R. Leaf area index estimates using remotely sensed data and BRDF models in a semiarid region. Remote Sens Environ, 2000, 73: 18-30. doi: 10.1016/S0034-4257(99)00113-3
[26]	Anatoly A G, Mark N M. Remote sensing of chlorophyll concentration in higher plant leaves. Adv Space Res, 1998, 22: 689-692. doi: 10.1016/S0273-1177(97)01133-2
[27]	Jiang Z, Huete A R, Didan K, Miurab T. Development of a two-band enhanced vegetation index without a blue band. Remote Sense Environ, 2008, 112: 3833-3845. doi: 10.1016/j.rse.2008.06.006
[28]	Geneviève R, Michael S, Frédéric B, Optimization of soil-adjusted vegetation indices. Remote Sense Environ, 1996, 55: 95-107. doi: 10.1016/0034-4257(95)00186-7
[29]	Huete A R. Soil-adjust vegetation index (SAVI). Remote Sense Environ, 1988, 25: 295-309. doi: 10.1016/0034-4257(88)90106-X
[30]	Githlson A, Merzlyak M N. Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. leaves. Spectral features and relation to chlorophyll estimation. J Plant Physiol, 1994, 143: 286-292. doi: 10.1016/S0176-1617(11)81633-0
[31]	Gitelson A A. Wide dynamic range vegetation index for remote quantification of biophysical characteristics of vegetation. J Plant Physiol, 2004, 161: 165-173.
[32]	Chen J M. Evaluation of vegetation indices and a modified simple ratio for boreal applications. Can J Remote Sens, 2014, 22: 229-242. doi: 10.1080/07038992.1996.10855178
[33]	Daughtry C S T, Walthall C L, Kim M S, Colstoun E B D, McMurtrey J E. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sense Environ, 2000, 74: 229-239. doi: 10.1016/S0034-4257(00)00113-9
[34]	Tucker C J. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sense Environ, 1979, 8: 127-150. doi: 10.1016/0034-4257(79)90013-0
[35]	Elsayed S, Rischbeck P, Schmidhalter U. Comparing the performance of active and passive reflectance sensors to assess the normalized relative canopy temperature and grain yield of drought-stressed barley cultivars. Field Crops Res, 2015, 177: 148-160. doi: 10.1016/j.fcr.2015.03.010
[36]	Purushothaman R, Thudi M, Krishnamurthy L, Upadhyayaa H D, Kashiwagib J, Gowdaa C L L, Varshney R K. Association of mid-reproductive stage canopy temperature depression with the molecular markers and grain yields of chickpea (Cicer arietinum L.) germplasm under terminal drought. Field Crops Res, 2015, 174: 1-11. doi: 10.1016/j.fcr.2015.01.007
[37]	Valtera M, Šamonil, Svoboda M, Janda P. Effects of topography and forest stand dynamics on soil morphology in three natural Picea abies mountain forests. Plant Soil, 2015, 392: 57-69. doi: 10.1007/s11104-015-2442-4
[38]	马雨阳, 官海翔, 杨昊轩, 邵帅, 邵逸群, 刘焕军. 利用地形、土壤和作物信息辅助提高东北漫岗地数字高程模型精度的新方法. 中国农业科学, 2021, 54: 1715-1727.
	Ma Y Y, Guan H X, Yang H X, Shao S, Shao Y Q, Liu H J. A new method to improve the accuracy of digital elevation model in northeast China by using terrain, soil and crop Information. Sci Agric Sin, 2021, 54: 1715-1727 (in Chinese with English abstract).
[39]	朱高龙, 柳艺博, 居为民, 陈镜明. 4种常用植被指数的地形效应评估. 遥感学报, 2013, 17: 210-234.
	Zhu G L, Liu Y B, Ju W M, Chen J M. Evaluation of topographic effects on four commonly used vegetation indices. J Remote Sens, 2013, 17: 210-234. (in Chinese with English abstract)
[40]	刘海丰, 薛达元, 桑卫国. 地形因子对暖温带森林群落物种丰富度-地上生物量关系的影响. 生态环境学报, 2012, 21: 1403-1407.
	Liu H F, Xue D Y, Sang W G. Effect of topographic factors on the relationship between species richness and aboveground biomass in a warm temperate forest. Ecol Environ Sci, 2012, 21: 1403-1407. (in Chinese with English abstract)
[41]	Takyu M, Aiba S I, Kitayama K. Changes in biomass, productivity and decomposition along topographical gradients under different geological conditions in tropical lower montane forests on mount Kinabalu, Borneo. Oecologia, 2003, 134: 397-404. doi: 10.1007/s00442-002-1115-1
[42]	杨仕曦, 吕广斌, 黄云, 向华辉, 王正银. 九龙坡花椒种植区地形、土壤肥力与花椒产量的关系. 中国生态农业学报, 2019, 27: 1823-1832.
	Yang S X, Lyu G B, Huang Y, Xiang H H, Wang Z Y. Relationships of Zanthoxylum bungeanum yield with topography and soil fertility in Jiulongpo area. Chin J Eco-Agric, 2019, 27: 1823-1832. (in Chinese with English abstract)
[43]	Kross A, Mcnairn H, Lapen D, Sunohara M, Champagne C. Assessment of rapid eye vegetation indices for estimation of leaf area index and biomass in corn and soybean crops. Int J Appl Earth Obs, 2015, 34: 235-248.
[44]	Guo J X, Tian G L, Zhou Y, Wang M, Ling N, Shen Q R, Guo S W. Evaluation of the grain yield and nitrogen nutrient status of wheat (Triticum aestivum L.) using thermal imaging. Field Crops Res, 2016, 196: 463-472. doi: 10.1016/j.fcr.2016.08.008
[45]	Hou A, Chen P, Alloatti J, Li D, Mozzoni L, Zhang B, Shi A. Genetic variability of seed sugar content in worldwide soybean germplasm ppubs. Crop Sci, 2009, 49: 903-912. doi: 10.2135/cropsci2008.05.0256
[46]	Virlet N, Lebourgeois V, Martinez S, Costes E, Labbe S, Regnard J L. Stress indicators based on airborne thermal imagery for field phenotyping a heterogeneous tree population for response to water constraints. J Exp Bot, 2014, 65: 5429-5442. doi: 10.1093/jxb/eru309
[47]	Du W Y., Zhang L D, Hu Z F, Shamaila Z, Zeng A J, Song J L, Liu Y J, Wolfram S, Joachim M, He X K. Utilization of thermal infrared image for inversion of winter wheat yield and biomass. Spectr Spectr Anal, 2011, 31: 1476-1480.
[48]	González F G, Miralles D J, Slafer G A. Wheat floret survival as related to pre-anthesis spike growth. J Exp Bot, 2011, 62: 4889-4901. doi: 10.1093/jxb/err182
[49]	Laurent A, Loyce C, Makowski D, Pelzer E. Using site-specific data to estimate energy crop yield. Environ Modell Softw, 2015, 74: 104-113. doi: 10.1016/j.envsoft.2015.09.008
[50]	Yue J B, Yang G J, Li C C, Li Z H, Wang Y J, Feng H K, Xu B. Estimation of winter wheat above-ground biomass using unmanned aerial vehicle-based snapshot hyperspectral sensor and crop height improved models. Remote Sens, 2017, 9: 708. doi: 10.3390/rs9070708
[51]	陶惠林, 徐良骥, 冯海宽, 杨贵军, 杨小冬, 苗梦珂, 代阳. 基于无人机数码影像的冬小麦株高和生物量估算. 农业工程学报, 2019, 35(19): 107-116.
	Tao H L, Xu L J, Feng H K, Yang G J, Yang X D, Miao M K, Dai Y. Estimation of plant height and biomass of winter wheat based on UAV digital image. Trans CSAE, 2019, 35(19): 107-116. (in Chinese with English abstract)
[52]	潘治利, 祁萌, 魏春阳, 李锋, 张仕祥, 王建伟, 过伟民, 艾志录. 基于图像处理和支持向量机的初烤烟叶颜色特征区域分类. 作物学报, 2012, 38: 374-379.
	Pan Z L, Qi M, Wei C Y, Li F, Zhang S X, Wang J W, Guo W M, Ai Z L. Color region classification of flue-cured tobacco leaves based on the image. Acta Agron Sin, 2012, 38: 374-379. (in Chinese with English abstract) doi: 10.3724/SP.J.1006.2012.00374
[53]	Xu J X, Ma J, Tang Y N, Wu W X, Shao J H, Wu W B, Wei S Y, Liu Y F, Wang Y C, Guo H Q. Estimation of sugarcane yield using a machine learning approach based on UAV-LiDAR data. Remote Sens, 2020, 12: 2823. doi: 10.3390/rs12172823
[54]	Nawar S, Buddenbaum H, Hill J, Kozak J. Modeling and mapping of soil salinity with reflectance spectroscopy and landsat data using two quantitative methods (PLSR and MARS). Remote Sens, 2014, 6: 10813-10834. doi: 10.3390/rs61110813
[55]	Liu H Z, Shi T Z, Chen Y Y, Wang J J, Fei T, Wu G F. Improving spectral estimation of soil organic carbon content through semi-supervised regression. Remote Sens, 2017, 9: 29. doi: 10.3390/rs9010029
[56]	Aghighi H, Azadbakht M, Ashourloo D, Shahrabi H S, Radiom S.Machine learning regression techniques for the silage maize yield prediction using time-series images of Landsat 8 OLI. IEEE J-Selec Topic Appl Earth Observ Remote Sens, 2018, 11: 4563-4577.
[57]	杨北萍, 陈圣波, 于海洋, 安秦. 基于随机森林回归方法的水稻产量遥感估算. 中国农业大学报, 2020, 25(6): 26-34.
	Yang B P, Chen S B, Yu H Y, An Q. Remote sensing estimation of rice yield based on random forest regression method. J China Agric Univ, 2020, 25(6): 26-34 (in Chinese with English abstract).
[58]	Jeong J H, Resop J P, Mueller N D, Fleisher D H, Yun K, Butler E E, Timlin D J, Shim K M, Gerber J S, Reddy V R, Kim S H. Random forests for global and regional crop yield predictions. PLoS One, 2016, 11: e0156571. doi: 10.1371/journal.pone.0156571

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

生育期 Growth stage	坡度 Slope (°)	GNDVI				CT (℃)
生育期 Growth stage	坡度 Slope (°)	最大值 Max.	最小值 Min.	均值 Mean	标准差 SD	最大值 Max.	最小值 Min.	均值 Mean	标准差 SD
孕穗期 Booting stage	2-4	0.805	0.731	0.778	0.051	26.62	25.46	26.24	0.44
	4-6	0.723	0.602	0.637	0.049	28.24	27.56	27.42	0.34
	6-8	0.671	0.526	0.594	0.087	28.51	27.84	28.26	0.61
开花期 Flowering stage	2-4	0.837	0.758	0.809	0.047	28.64	27.14	27.84	0.46
	4-6	0.772	0.652	0.725	0.054	29.85	28.37	29.02	0.51
	6-8	0.713	0.608	0.634	0.069	30.64	29.02	29.79	0.58
灌浆期 Filling stage	2-4	0.796	0.719	0.747	0.053	31.05	29.46	30.54	0.52
	4-6	0.705	0.564	0.598	0.064	31.46	29.85	31.12	0.56
	6-8	0.669	0.518	0.573	0.081	33.97	30.31	32.85	0.78

生长参数 Growth parameter	孕穗期 Booting stage	开花期 Flowering stage	灌浆期 Filling stage
土壤含水量 Soil moisture content (%)	-0.605^**	-0.673^**	-0.731^**
植株含水量 Plant water content (%)	-0.450^**	-0.503^**	-0.521^**
地上部生物量 Above-ground biomass (kg hm^-2)	-0.332^*	-0.406^**	-0.434^**

指数 Indices	孕穗期 Booting stage	开花期 Flowering stage	灌浆期 Filling stage
NDVI	0.587^**	0.718^**	0.799^**
GNDVI	0.616^**	0.756^**	0.821^**
EVI2	0.663^**	0.732^**	0.806^**
OSAVI	0.653^**	0.741^**	0.820^**
SAVI	0.668^**	0.735^**	0.809^**
NDRE	0.666^**	0.770^**	0.743^**
WDRVI	0.567^**	0.705^**	0.796^**
MSR	0.390^**	0.689^**	0.688^**
MCARI	0.475^**	0.614^**	0.714^**
RVI	0.280^*	0.664^**	0.752^**
NRCT	‒0.487^**	‒0.758^**	‒0.590^**
CTD	0.443^**	0.669^**	0.467^**

参数 Index	回归模型 Regression model	孕穗期Booting stage			开花期Flowering stage			灌浆期Filling stage
参数 Index	回归模型 Regression model	R²	RMSE (kg hm^-2)	MAE (kg hm^-2)	R²	RMSE (kg hm^-2)	MAE (kg hm^-2)	R²	RMSE (kg hm^-2)	MAE (kg hm^-2)
VI	MLR	0.496	760.76	648.32	0.663	659.23	567.27	0.672	638.43	502.93
	PLSR	0.508	765.69	635.14	0.626	662.28	574.84	0.648	644.11	523.51
	SVR	0.521	755.52	597.46	0.673	648.37	532.46	0.680	618.41	486.64
	RFR	0.564	700.62	576.70	0.711	645.85	527.65	0.724	614.72	478.08
TH	MLR	0.340	902.84	728.61	0.637	676.12	608.38	0.391	859.12	654.23
	PLSR	0.349	883.15	694.48	0.609	680.17	615.89	0.368	880.24	676.27
	SVR	0.361	876.73	671.52	0.659	668.87	581.64	0.463	807.35	594.65
	RFR	0.417	839.74	650.37	0.707	642.19	530.89	0.540	788.59	563.06

参数 Index	回归模型 Regression model	孕穗期Booting stage			开花期Flowering stage			灌浆期Filling stage
参数 Index	回归模型 Regression model	R²	RMSE (kg hm^-2)	MAE (kg hm^-2)	R²	RMSE (kg hm^-2)	MAE (kg hm^-2)	R²	RMSE (kg hm^-2)	MAE (kg hm^-2)
VI+TF	MLR	0.544	766.67	642.58	0.677	615.09	546.26	0.727	625.12	497.92
	PLSR	0.513	722.35	615.79	0.635	654.25	559.85	0.711	650.38	513.67
	SVR	0.604	693.45	567.62	0.729	598.46	514.24	0.769	584.27	481.37
	RFR	0.633	671.14	541.46	0.746	576.69	495.46	0.786	561.47	459.64
VI+TH	MLR	0.644	743.29	634.84	0.801	521.62	439.67	0.780	596.92	482.47
	PLSR	0.609	749.22	629.75	0.790	542.45	456.87	0.752	606.89	489.67
	SVR	0.663	709.49	574.57	0.822	495.88	423.15	0.795	573.61	474.35
	RFR	0.699	643.36	535.74	0.865	440.73	374.86	0.831	480.73	401.91
TF+TH	MLR	0.371	863.76	705.27	0.652	671.64	571.29	0.417	816.05	639.37
	PLSR	0.403	854.87	685.23	0.622	694.52	586.13	0.432	832.48	656.74
	SVR	0.495	838.46	664.67	0.708	658.24	546.82	0.562	727.13	587.68
	RFR	0.561	797.06	642.13	0.727	640.49	518.79	0.594	697.58	559.98
VI+TF+TH	MLR	0.660	656.07	527.41	0.817	460.94	375.15	0.787	507.92	447.26
	PLSR	0.654	637.50	514.79	0.805	505.66	412.35	0.753	585.85	479.84
	SVR	0.702	600.37	487.37	0.824	451.26	379.65	0.813	476.67	421.31
	RFR	0.729	611.19	470.94	0.893	420.06	352.69	0.856	457.56	380.71

Wheat yield estimation from UAV platform based on multi-modal remote sensing data fusion

RichHTML400

PDF

Abstract

Cite this article

share this article

Figures/Tables 11

References 58

Related Articles 15

Metrics

Comments

Recommended 0

[1]	Wang Zhuang-Zhuang, Wu Zi-Jun, Zhang Yong-Xin, Zhang Xin-Yuan, Yuan Li-Xue, Chen Ru-Xue, Liu Shi-Ju, Duan Jian-Zhao, Feng Wei, Wang Tong-Chao, Wang Yong-Hua. Optimized water-nitrogen synergy enhances winter wheat yield and nitrogen use efficiency in clay-loam fluvo-aquic soils of southeastern Henan, China [J]. Acta Agronomica Sinica, 2026, 52(5): 1501-1521.
[2]	Qiao Yu-Xin, Li Cheng-Yue, Kang Xiao-Yu, Zhang Xin-Qi, Jia Shao-Hui, Liu Qian, Cao Ya-Li, Shi Xin-Rui, Hao Xing-Yu, Li Ping. Study on the effects of long-term no-tillage straw mulching on wheat yield improvement in dryland areas based on the APSIM model [J]. Acta Agronomica Sinica, 2026, 52(4): 1181-1192.
[3]	WU Liu-Ge, CHEN Jian, ZHANG Xin, DENG Ai-Xing, SONG Zhen-Wei, ZHENG Cheng-Yan, ZHANG Wei-Jian. Changes in yield and quality traits of nationally approved winter wheat varieties in China over last twenty years [J]. Acta Agronomica Sinica, 2025, 51(7): 1814-1826.
[4]	CHEN Ru-Xue, SUN Li-Fang, ZHANG Xin-Yuan, MU Hai-Meng, ZHANG Yong-Xin, YUAN Li-Xue, PENG Shi-Le, WANG Zhuang-Zhuang, WANG Yong-Hua. Effects of combined straw returning and microbial inoculant application on carbon-nitrogen metabolism in flag leaves and yield formation in winter wheat [J]. Acta Agronomica Sinica, 2025, 51(7): 1901-1913.
[5]	ZHAO Gang, ZHANG Jian-Jun, DANG Yi, FAN Ting-Lu, WANG Lei, ZHOU Gang, WANG Shu-Ying, LI Xing-Mao, NI Sheng-Li, MI Wen-Bo, ZHOU Xu-Jiao, CHENG Wan-Li, LI Shang-Zhong. Effects of straw mulching on soil water temperature effect and winter wheat yield in different rainfall years in Dryland Loess Plateau [J]. Acta Agronomica Sinica, 2025, 51(6): 1643-1653.
[6]	WANG Dong, WANG Sen, SHANG Li, FENG Hao-Wei, ZHANG Yong-Qiao, CUI Jia-Ming, LI Shuang, ZHANG Jia-Cong, CHE Huan. Effect of supplementary irrigation on winter wheat yield and water use efficiency in semi humid areas of the Loess Plateau [J]. Acta Agronomica Sinica, 2025, 51(5): 1312-1325.
[7]	WANG Jiao, BAI Hai-Xia, HAN Yu-Yan, LIANG Hui, FENG Ya-Nan, ZHANG Dong-Sheng, LI Ping, ZONG Yu-Zheng, SHI Xin-Rui, HAO Xing-Yu. Effects of elevated CO₂ concentration, increased temperature and their interaction on the carbon and nitrogen metabolism in Liangxing 99 winter wheat leaves [J]. Acta Agronomica Sinica, 2025, 51(4): 1061-1076.
[8]	LUO Zhen, YANG Ni, SHANG Xiao-Hui, YU Xin-Cheng, ZHU Jing-Yi, YANG Guang, HU Xiao-Tao. Extraction of planting structure information in the Baojixia irrigation district based on planet scope satellite and UAV multispectral imagery [J]. Acta Agronomica Sinica, 2025, 51(12): 3317-3330.
[9]	ZHANG Yan-Yan, LI Ying, LIU Xu-Chen, HUANG Chao, LYU Jia-Ning, ZHOU Hai-Jia, MA Shou-Tian, QIN An-Zhen, GAO Zi-Le, WU Guang-Hui, CHEN Dan, JI Xia-Nan, LIU Zhan-Dong. Effects of drip irrigation on post-anthesis dry matter accumulation and grain-filling characteristics of winter wheat under subsoiling tillage [J]. Acta Agronomica Sinica, 2025, 51(11): 3065-3079.
[10]	ZHANG Jun, HU Chuan, ZHOU Qi-Hui, REN Kai-Ming, DONG Shi-Yan, LIU Ao-Han, WU Jin-Zhi, HUANG Ming, LI You-Jun. Effects of nitrogen reduction and organic fertilizer substitution on dry matter accumulation, translocation, distribution, and yield of dryland winter wheat [J]. Acta Agronomica Sinica, 2025, 51(1): 207-220.
[11]	MA Yan-Ming, LOU Hong-Yao, WANG Wei, SUN Na, YAN Guo-Rong, ZHANG Sheng-Jun, LIU Jie, NI Zhong-Fu, XU Lin. Genetic difference and genome association analysis of grain quality traits in Xinjiang winter wheat [J]. Acta Agronomica Sinica, 2024, 50(6): 1394-1405.
[12]	HUANG Hong-Sheng, ZHANG Xin-Yue, JU Hui, HAN Xue. Spectral characteristics of winter wheat canopy and estimation of aboveground biomass under elevated atmospheric CO₂ concentration [J]. Acta Agronomica Sinica, 2024, 50(4): 991-1003.
[13]	ZHAO Rong-Rong, CONG Nan, ZHAO Chuang. Optimal phase selection for extracting distribution of winter wheat and summer maize over central subregion of Henan Province based on Landsat 8 imagery [J]. Acta Agronomica Sinica, 2024, 50(3): 721-733.
[14]	XIE Wei, HE Peng, MA Hong-Liang, LEI Fang, HUANG Xiu-Lan, FAN Gao-Qiong, YANG Hong-Kun. Effects of straw mulching from autumn fallow and phosphorus application on nitrogen uptake and utilization of winter wheat [J]. Acta Agronomica Sinica, 2024, 50(2): 440-450.
[15]	YANG Xiao-Hui, WANG Bi-Sheng, SUN Xiao-Lu, HOU Jin-Jin, XU Meng-Jie, WANG Zhi-Jun, FANG Quan-Xiao. Modeling the response of winter wheat to deficit drip irrigation for optimizing irrigation schedule [J]. Acta Agronomica Sinica, 2023, 49(8): 2196-2209.