Back
 AS  Vol.11 No.9 , September 2020
Research on Dynamic Forecast of Flowering Period Based on Multivariable LSTM and Ensemble Learning Classification Task
Abstract: The flowering forecast provides recommendations for orchard cleaning, pest control, field management and fertilization, which can help increase tree vigor and resistance. Flowering forecast is not only an important part of the construction of agro-meteorological index system, but also an important part of the meteorological service system. In this paper, by analyzing local meteorological data and phenological data of “Red Fuji” apples in Fen County, Linfen City, Shanxi Province, with the help of machine learning and neural networks, we proposed a method based on the combination of time series forecasting and classification forecasting is proposed to complete the dynamic forecasting model of local flowering in Ji County. Then, we evaluated the effectiveness of the model based on the number of error days and the number of days in advance. The implementation shows that the proposed multivariable LSTM network has a good effect on the prediction of meteorological factors. The model loss is less than 0.2. In the two-category task of flowering judgment, the idea of combining strategies in ensemble learning improves the effect of flowering judgment, and its AUC value increases from 0.81 and 0.80 of single model RF and AdaBoost to 0.82. The proposed model has high applicability and accuracy for flowering forecast. At the same time, the model solves the problem of rounding decimals in the prediction of flowering dates by the regression method.
Cite this paper: Chen, C. , Zhang, X. and Tian, S. (2020) Research on Dynamic Forecast of Flowering Period Based on Multivariable LSTM and Ensemble Learning Classification Task. Agricultural Sciences, 11, 777-792. doi: 10.4236/as.2020.119050.
References

[1]   Ahas, R., Jaagus, J. and Aasa, A. (2000) The Phenological Calendar of Estonia and Its Correlation with Mean Air Temperature. International Journal of Biometeorology, 44, 159-166.
https://doi.org/10.1007/s004840000069

[2]   Ge, Q.S., Wang, H.J., Rutishauser, T. and Dai, J.H. (2015) Phenological Response to Climate Change in China: A Meta-Analysis. Global Change Biology, 21, 265-274.
https://doi.org/10.1111/gcb.12648

[3]   Menzel, A. (2003) Plant Phenological Anomalies in Germany and Their Relation to Air Temperature and NAO. Climatic Change, 57, 243-263.
https://doi.org/10.1023/A:1022880418362

[4]   Liu, Y.J. and Dai, L. (2020) Modelling the Impacts of Climate Change and Crop Management Measures on Soybean Phenology in China. Journal of Cleaner Production, 262, Article ID: 121271.
https://doi.org/10.1016/j.jclepro.2020.121271

[5]   Walther, G.R., Post, E., Convey, P., Menzel, A., Parmesan, C., Beebee, T.J.C., Fromentin, J.M., Guldberg, O.H. and Bairlein, F. (2002) Ecological Responses to Recent Climate Change. Nature, 416, 389-395.
https://doi.org/10.1038/416389a

[6]   Rohde, A. and Bhalerao, R.P. (2007) Plant Dormancy in the Perennial Context. Trends in Plant Science, 12, 217-223.
https://doi.org/10.1016/j.tplants.2007.03.012

[7]   Alcalá, A.R. and Barranco, D. (1992) Prediction of Flowering Time in Olive for the Cordoba Olive Collection. American Society for Horticultural Science, 27, 1205-1207.
https://doi.org/10.21273/HORTSCI.27.11.1205

[8]   Behdani, M.A., Koocheki, A., Nassiri, M. and Rezvani, P. (2008) Models to Predict Flowering Time in the Main Saffron Production Regions of Khorasan Province. Journal of Applied Sciences, 8, 907-909.
https://doi.org/10.3923/jas.2008.907.909

[9]   Yasuyuki, A.O.N.O. and Yukio, O.M.O.T.O. (1990) A Simplified Method for Estimation of Blooming Date for the Cherry by Means of DTS. Journal of Agricultural Meteorology, 46, 147-151.

[10]   Aono, Y. (1993) Climatological Studies on Blooming of Cherry Tree (Prunus yedoensis) by Means of DTS Method. Bulletin of the University of Osaka Prefecture. Ser. B, Agriculture & Life Sciences, 45, 155-192.

[11]   Sugiura, T. and Honjo, H. (1997) A Dynamic Model for Predicting E Flowering Date Developed Using an Endodormancy Break Model and A Flower Bud Development Model in Japanese Pear. Journal of Agricultural Meteorology, 52, 897-900.

[12]   Chun, J.A., Kang, K., Kim, D., Han, H.-H. and Son, I.-C. (2017) Prediction of Full Blooming Dates of Five Peach Cultivars (Prunus persica) Using Temperature-Based Models. Scientia Horticulturae, 220, 250-258.
https://doi.org/10.1016/j.scienta.2017.04.007

[13]   Hur, J. and Ahn, J.B. (2017) Assessment and Prediction of the First-Flowering Dates for the Major Fruit Trees in Korea Using a Multi-RCM Ensemble. International Journal of Climatology, 37, 1603-1618.
https://doi.org/10.1002/joc.4800

[14]   El Yaacoubi, A., Oukabli, A., Hafidi, M., Farrera, I., Ainane, T., Cherkaoui, S.I. and Legave, J.-M. (2019) Validated Model for Apple Flowering Prediction in the Mediterranean Area in Response to Temperature Variation. Scientia Horticulturae, 249, 59-64.
https://doi.org/10.1016/j.scienta.2019.01.036

[15]   Chauhan, Y.S., Ryan, M., Chandra, S. and Sadras, V.O. (2019) Accounting for Soil Moisture Improves Prediction of Flowering Time in Chickpea and Wheat. Scientific Reports, 9, Article No. 7510.
https://doi.org/10.1038/s41598-019-43848-6

[16]   Schneemilch, M., Michael, K. and Williams, C.R. (2012) Flowering Timing Prediction in Australian Native Understorey Species (Acrotriche R.Br Ericaceae) Using Meteorological Data. International Journal of Biometeorology, 56, 95-105.
https://doi.org/10.1007/s00484-010-0400-7

[17]   Cenci, C.A. and Ceschia, M. (2000) Forecasting of the Flowering Time for Wild Species Observed at Guidonia, Central Italy. International Journal of Biometeorology, 44, 88-96.
https://doi.org/10.1007/s004840000065

[18]   Park, I., Jones, A. and Mazer, S.J. (2019) Phenoforecaster: A Software Package for the Prediction of Flowering Phenology. Applications in Plant Sciences, 7, 1230-1236.
https://doi.org/10.1002/aps3.1230

[19]   Elizondo, D.A., Mcclendon, R.W. and Hoogenboom, G. (1994) Neural Network Models for Predicting Flowering and Physiological Maturity of Soybean. Transactions of the ASAE, 37, 981-988.
https://doi.org/10.13031/2013.28168

[20]   Hermans, M. and Schrauwen, B. (2013) Training and Analysis Deep Recurrent Neural Networks. Advances in Neural Information Processing Systems, 190-198.

[21]   Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780.
https://doi.org/10.1162/neco.1997.9.8.1735

[22]   Gers, F.A., Schmidhuber, J. and Cummins, F. (2000) Learning to Forget: Continual Prediction with LSTM. Neural Computation, 12, 2451-2471.
https://doi.org/10.1162/089976600300015015

[23]   Gers, F.A., Schraudolph, N.N. and Schmidhuber, J. (2003) Learning Precise Timing with LSTM Recurrent Networks. Journal of Machine Learning Research, 3, 115-143.

[24]   Vega-Pons, S. and Ruiz-Shulcloper, J. (2011) A Survey of Clusering Ensemble Algorithms. International Journal of Pattern Recognition and Artificial Intelligence, 25, 337-372.
https://doi.org/10.1142/S0218001411008683

[25]   Barnett, T.L. and Thompson, D.R. (1982) The Use of Large-Area Spectral Data in Wheat Yield Estimation. Remote Sensing of Environment, 12, 509-518.
https://doi.org/10.1016/0034-4257(82)90025-6

[26]   Tollenaar, M., Fridgen, J., Tyagi, P., Stackhouse, P.W. and Kumudini, S. (2017) The Contribution of Solar Brightening to the US Maize Yield Trend. Nature Climate Change, 7, 275-278.
https://doi.org/10.1038/nclimate3234

[27]   Togliatti, K., Archontoulis, S.V., Dietzel, R., Dietzel, R., Puntel, L. and Vanloocke, A. (2017) How Does Inclusion of Weather Forecasting Impact In-Season Crop Model Predictions? Field Crops Research, 214, 261-272.
https://doi.org/10.1016/j.fcr.2017.09.008

 
 
Top