|
|
|
|
|
|
Prediction of Continuous Time Series Leaf Area Index Based on Long Short-Term Memory Network: a Case Study of Winter Wheat |
LONG Ze-hao1, QIN Qi-ming1, 2, 3*, ZHANG Tian-yuan1, XU Wei1 |
1. Institute of Remote Sensing and Geographical Information System, School of Earth and Space Science, Peking University, Beijing 100871, China
2. Geographic Information Foundation Software and Application Engineering Technology Research Center, Beijing 100871, China
3. Beijing Key Lab of Spatial Information Integration and 3S Application, Beijing 100871, China |
|
|
Abstract The continuous time series of Leaf Area Index (LAI) can reflect the growth of winter wheat, and the prediction of future LAI is important for guiding agricultural production. The crop growth models, such as the World Food Studies (WOFOST), can predict the future LAI by simulating the growth and development of winter wheat. But the simulation depends on numerous input parameters, such as future meteorological data, which is difficult to obtain. Due to the continuity and regularity of LAI variations of winter wheat, the future LAI can be predicted with historical LAI through deep learning methods. However, deep learning methods require a large number of samples with labels to build training dataset. The scarcity of training dataset limits the application of deep learning methods in practice. To solve the above problems, we used data assimilation framework to combine remote sensing data with WOFOST model and constructed 15-year time series dataset of winter wheat LAI in Hebei province. Shuffled Complex Evolution (SCE) algorithm was applied to minimize difference between corrected MODIS LAI and simulated LAI for optimizing initial parameters of WOFOST. Based on the dataset, multiple LAI prediction models with different input lengths of historical LAI were established by using the Long Short-Term Memory (LSTM). The abilities of different prediction models to delineate LAI variations of winter wheat were evaluated. Results showed that the LSTM-based models can predict the future LAI of winter wheat effectively. The prediction model with an input length of 20 days achieved the highest accuracy. and RMSE of the prediction model were 0.986 5 and 0.183 6 after winter wheat returned green. For different stages of winter wheat growth, the accuracy was higher before winter wheat bloomed and reduced slightly after winter wheat bloomed. Therefore, it could be concluded that the method of constructing training dataset proposed in this study could be a reference for the application of deep learning methods in similar problems. The prediction models built in this study also verified the effectiveness of the LSTM, which provided a helpful way for predicting the future LAI of crops.
|
Received: 2019-01-06
Accepted: 2019-04-21
|
|
Corresponding Authors:
QIN Qi-ming
E-mail: qmqinpku@163.com
|
|
[1] LIU Yang, LIU Rong-gao, CHEN Jing-ming, et al(刘 洋, 刘荣高, 陈镜明, 等). Journal of Geo-Information Science(地球信息科学学报), 2013, 15(5): 734.
[2] Campos-Taberner M, García-Haro F J, Camps-Valls G, et al. Remote Sensing of Environment, 2016, 187: 102.
[3] Rembold F, Atzberger C, Savin I, et al. Remote Sensing, 2013, 5(4): 1704.
[4] Dong T, Liu J, Qian B, et al. International Journal of Applied Earth Observation and Geoinformation, 2016, 49: 63.
[5] Marletto V, Ventura F, Fontana G, et al. Agricultural and Forest Meteorology, 2007, 147(1-2): 71.
[6] Xiao Z, Liang S, Wang J, et al. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(1): 209.
[7] Chen B, Wu Z, Wang J, et al. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 102: 148.
[8] Kim Y, Roh J H, Kim H Y. Sustainability, 2017, 10(1): 34.
[9] Rußwurm M, Körner M. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, 42: 551.
[10] Ma G, Huang J, Wu W, et al. Mathematical and Computer Modelling, 2013, 58(3-4): 634.
[11] Huang J, Tian L, Liang S, et al. Agricultural and Forest Meteorology, 2015, 204: 106. |
[1] |
HAO Zi-yuan1, YANG Wei1*, LI Hao1, YU Hao1, LI Min-zan1, 2. Study on Prediction Models for Leaf Area Index of Multiple Crops Based on Multi-Source Information and Deep Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3862-3870. |
[2] |
WANG Xiao-xuan1, LU Xiao-ping1*, MENG Qing-yan2, 3, LI Guo-qing4, WANG Jun4, ZHANG Lin-lin2, 3, YANG Ze-nan1. Inversion of Leaf Area Index Based on GF-6 WFV Spectral Vegetation
Index Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(07): 2278-2283. |
[3] |
KONG Yu-ru1, 2, WANG Li-juan1*, FENG Hai-kuan2, XU Yi1, LIANG Liang1, XU Lu1, YANG Xiao-dong2*, ZHANG Qing-qi1. Leaf Area Index Estimation Based on UAV Hyperspectral Band Selection[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(03): 933-939. |
[4] |
YU Xin-hua1, ZHAO Wei-qing2*, ZHU Zai-chun2, XU Bao-dong3, ZHAO Zhi-zhan4. Research in Crop Yield Estimation Models on Different Scales Based on Remote Sensing and Crop Growth Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(07): 2205-2211. |
[5] |
LU Shi-yang1, 2, ZHANG Lei-lei1, 2, PAN Jia-rong1, 2, YANG De-hong1, 2, SUI Ya-nan1, 2, ZHU Cheng1, 2*. Study on the Indetification of the Geographical Origin of Cherries Using Raman Spectroscopy and LSTM[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(04): 1177-1181. |
[6] |
SU Zhong-bin, LU Yi-wei, GU Jun-tao, GAO Rui, MA Zheng, KONG Qing-ming*. Research on Rice Leaf Area Index Inversion Model Based on Improved QGA-ELM Algorithm[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(04): 1227-1233. |
[7] |
WANG Xiang-yu1, YANG Han2, LI Xin-xing2, ZHENG Yong-jun3, YAN Hai-jun4, LI Na5*. Research on Maize Growth Monitoring Based on Visible Spectrum of UAV Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(01): 265-270. |
[8] |
YU Hao-yue, SHEN Tao*, ZHU Yan, LIU Ying-li, YU Zheng-tao. Terahertz Spectral Recognition Based on Bidirectional Long Short-Term Memory Recurrent Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(12): 3737-3742. |
[9] |
SUN Qi1, 2, JIAO Quan-jun2*, DAI Hua-yang1. Research on Retrieving Corn Canopy Chlorophyll Content under Different Leaf Inclination Angle Distribution Types Based on Spectral Indices[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(07): 2257-2263. |
[10] |
SUN Hua-lin, GENG Shi-ying, WANG Xiao-yan*, XIONG Qin-xue*. Estimation Method of Wheat Leaf Area Index Based on Hyperspectral Under Late Sowing Conditions[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(04): 1199-1206. |
[11] |
CHANG Hao-xue1, CAI Xiao-bin2, CHEN Xiao-ling1, 3*, SUN Kun1. Response Characteristics Analysis of Different Vegetation Indices to Leaf Area Index of Rice[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(01): 205-211. |
[12] |
HAN Zhao-ying1, ZHU Xi-cun1, 2*, FANG Xian-yi1, WANG Zhuo-yuan1, WANG Ling1, ZHAO Geng-xing1, JIANG Yuan-mao3. Hyperspectral Estimation of Apple Tree Canopy LAI Based on SVM and RF Regression [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(03): 800-805. |
[13] |
TAO Zhi-qiang, Shamim Ara Bagum, MA Wei, ZHOU Bao-yuan, FU Jin-dong, CUI Ri-xian, SUN Xue-fang, ZHAO Ming* . Establishment of The Crop Growth and Nitrogen Nutrition State Model Using Spectral Parameters Canopy Cover[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(01): 231-236. |
[14] |
TANG Jian-min1, LIAO Qin-hong1*, LIU Yi-qing1, YANG Gui-jun2, FENG Hai-kuan2, WANG Ji-hua2 . Estimating Leaf Area Index of Crops Based on Hyperspectral Compact Airborne Spectrographic Imager (CASI) Data [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(05): 1351-1356. |
[15] |
XIE Qiao-yun1, 2, HUANG Wen-jiang1*, CAI Shu-hong3, LIANG Dong2, PENG Dai-liang1, ZHANG Qing1, HUANG Lin-sheng2, YANG Gui-jun4, ZHANG Dong-yan2. Comparative Study on Remote Sensing Invertion Methods for Estimating Winter Wheat Leaf Area Index [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(05): 1352-1356. |
|
|
|
|