Advertisement

GeoInformatica

, Volume 22, Issue 2, pp 363–381 | Cite as

Spatio-temporal prediction of crop disease severity for agricultural emergency management based on recurrent neural networks

  • Wei Xu
  • Qili Wang
  • Runyu Chen
Article

Abstract

As crop diseases bring huge losses every year in both developed and developing countries, determining how to precisely predict crop disease severity to facilitate agricultural emergency management is really a worldwide problem. Previous studies have introduced machine learning (ML) techniques into crop disease prediction and achieved better experimental results. However, the architectures of these ML models are unsuitable to model time series data. Moreover, the dependences among observations over time and across space have not been taken into account in model construction. By applying data-mining techniques to dynamic spatial panels of remote sensing data and considering features of bioclimatic, topographic and soil conditions as a supplement, we propose a novel crop disease prediction framework for agricultural emergency management based on ensemble learning techniques and spatio-temporal recurrent neural network (STRNN) which is an extension of recurrent neural network (RNN) in time and space. Empirical experiments are conducted on a specific dataset which is built based on reported cases of wheat yellow rust outbreaks in the Longnan city. Experimental results indicate that our proposed method outperforms all baseline models in crop disease severity prediction. The managerial implication of our work is that by applying the proposed methodology, some preparedness measures can be implemented in advance to prevent or mitigate the possible disasters according to predicted results. Notable economic and ecological benefits can be achieved by optimizing the frequency and timing of application of fungicide, pesticides and other preventative measures.

Keywords

Crop disease prediction Deep learning Recurrent neural network Ensemble learning Emergency management 

Notes

Acknowledgements

This work was supported in part by National Natural Science Foundation of China (Grant No. 71301163, 71771212), Humanities and Social Sciences Foundation of the Ministry of Education (No. 14YJA630075, 15YJA630068), Hebei Social Science Fund (HB13GL021), and the Fundamental Research Funds for the Central Universities, and the Research Funds of Renmin University of China (No. 15XNLQ08).

References

  1. 1.
    Aydin B, Akkineni V, Angryk R (2016) Mining spatiotemporal co-occurrence patterns in non-relational databases. GeoInformatica 20(4):801–828.  https://doi.org/10.1007/s10707-016-0255-0 CrossRefGoogle Scholar
  2. 2.
    Babaei S, Geranmayeh A, Seyyedsalehi SA (2012) Towards designing modular recurrent neural networks in learning protein secondary structures. Expert Syst Appl 39(6):6263–6274.  https://doi.org/10.1016/j.eswa.2011.12.059 CrossRefGoogle Scholar
  3. 3.
    Beed FD (2014) Managing the biological environment to promote and sustain crop productivity and quality. Food Security 6(2):169–186.  https://doi.org/10.1007/s12571-014-0333-9 CrossRefGoogle Scholar
  4. 4.
    Bradley PE, Paul N (2014) Comparing G-maps with other topological data structures. GeoInformatica 18(3):595–620.  https://doi.org/10.1007/s10707-013-0191-1 CrossRefGoogle Scholar
  5. 5.
    Cang S, Yu H (2012) Mutual information based input feature selection for classification problems. Decis Support Syst 54(1):691–698.  https://doi.org/10.1016/j.dss.2012.08.014 CrossRefGoogle Scholar
  6. 6.
    Chakraborty S, Ghosh R, Ghosh M, Fernandes CD, Charchar MJ, Kelemu S (2004) Weather-based prediction of anthracnose severity using artificial neural network models. Plant Pathol 53(4):375–386.  https://doi.org/10.1111/j.1365-3059.2004.01044.x CrossRefGoogle Scholar
  7. 7.
    Chen G, Wang H, Ma Z (2005) Forecasting wheat stripe rust by discrimination analysis. Plant Prot 32(4):24–27Google Scholar
  8. 8.
    Chen W, Wellings C, Chen X, Kang Z, Liu T (2014) Wheat stripe (yellow) rust caused by Puccinia striiformis f. Sp. tritici. Mol Plant Pathol 15(5):433–446.  https://doi.org/10.1111/mpp.12116 CrossRefGoogle Scholar
  9. 9.
    Chen X, Liu X, Wang Y, Gales MJ, Woodland PC (2016) Efficient training and evaluation of recurrent neural network language models for automatic speech recognition. IEEE Trans Audio Speech Lang Process 24(11):2146–2157.  https://doi.org/10.1109/TASLP.2016.2598304 CrossRefGoogle Scholar
  10. 10.
    Chherawala Y, Roy PP, Cheriet M (2016) Feature set evaluation for offline handwriting recognition systems: application to the recurrent neural network model. IEEE Trans Cybernetics 46(12):2825–2836.  https://doi.org/10.1109/TCYB.2015.2490165 CrossRefGoogle Scholar
  11. 11.
    Coakley SM, Line RF, McDaniel LR (1988) Predicting stripe rust severity on winter wheat using an improved method for analyzing meteorological and rust data. Phytopathology 78(5):543–550.  https://doi.org/10.1094/Phyto-78-543 CrossRefGoogle Scholar
  12. 12.
    De Wolf ED, Franel LJ (1997) Neural networks that distinguish infection periods of wheat tan spot in an outdoor environment. Phytopathology 87(1):83–87.  https://doi.org/10.1094/PHYTO.1997.87.1.83 CrossRefGoogle Scholar
  13. 13.
    Dos Santos RF, Boedihardjo A, Shah S, Chen F, CT L, Ramakrishnan N (2016) The big data of violent events: algorithms for association analysis using spatio-temporal storytelling. GeoInformatica 20(4):879–921.  https://doi.org/10.1007/s10707-016-0247-0 CrossRefGoogle Scholar
  14. 14.
    El Jarroudi M, Kouadio L, Bock CH, El Jarroudi M, Junk J, Pasquali M, Maraite H, Delfosse P (2017) A threshold-based weather model for predicting stripe rust infection in winter wheat. Plant Dis 101(5):693–703.  https://doi.org/10.1094/PDIS-12-16-1766-RE CrossRefGoogle Scholar
  15. 15.
    Farquad MAH, Bose I (2012) Preprocessing unbalanced data using support vector machine. Decis Support Syst 53(1):226–233.  https://doi.org/10.1016/j.dss.2012.01.016 CrossRefGoogle Scholar
  16. 16.
    Grabow BS, Shah DA, DeWolf ED (2016) Environmental conditions associated with stripe rust in Kansas winter wheat. Plant Dis 100(11):2306–2312.  https://doi.org/10.1094/PDIS-11-15-1321-RE CrossRefGoogle Scholar
  17. 17.
    Haghighat M, Abdel-Mottaleb M, Alhalabi W (2016) Discriminant correlation analysis: real-time feature level fusion for multimodal biometric recognition. IEEE Trans Inf Forensics Secur 11(9):1984–1996.  https://doi.org/10.1109/TIFS.2016.2569061 CrossRefGoogle Scholar
  18. 18.
    Hammer B (2000) On the approximation capability of recurrent neural networks. Neurocomputing 31(1):107–123.  https://doi.org/10.1016/S0925-2312(99)00174-5 CrossRefGoogle Scholar
  19. 19.
    Hijmans RJ, Cameron SE, Parra JL, Jones PG, Jarvis A (2005) Very high resolution interpolated climate surfaces for global land areas. Int J Climatol 25(15):1965–1978.  https://doi.org/10.1002/joc.1276 CrossRefGoogle Scholar
  20. 20.
    Hua T, Chen F, Zhao L, CT L, Ramakrishnan N (2016) Automatic targeted-domain spatiotemporal event detection in twitter. GeoInformatica 20(4):765–795.  https://doi.org/10.1007/s10707-016-0263-0 CrossRefGoogle Scholar
  21. 21.
    Jalal ME, Hosseini M, Karlsson S (2016) Forecasting incoming call volumes in call centers with recurrent neural networks. J Bus Res 69(11):4811–4814.  https://doi.org/10.1016/j.jbusres.2016.04.035 CrossRefGoogle Scholar
  22. 22.
    Kaundal R, Kapoor AS, Raghava GP (2006) Machine learning techniques in disease forecasting: a case study on rice blast prediction. BMC Bioinf 7(1):485.  https://doi.org/10.1186/1471-2105-7-485 CrossRefGoogle Scholar
  23. 23.
    Kumar PV (2014) Development of weather-based prediction models for leaf rust in wheat in the indo-Gangetic plains of India. Eur J Plant Pathol 140(3):429–440.  https://doi.org/10.1007/s10658-014-0478-6 CrossRefGoogle Scholar
  24. 24.
    Landschoot S, Waegeman W, Audenaert K, Van Damme P, Vandepitte J, De Baets B, Haesaert G (2013) A field-specific web tool for the prediction of fusarium head blight and deoxynivalenol content in Belgium. Comput Electron Agric 93:140–148.  https://doi.org/10.1016/j.compag.2013.02.011 CrossRefGoogle Scholar
  25. 25.
    Landschoot S, Waegeman W, Audenaert K, Haesaert G, Baets B (2013) Ordinal regression models for predicting deoxynivalenol in winter wheat. Plant Pathol 62(6):1319–1329.  https://doi.org/10.1111/ppa.12041 CrossRefGoogle Scholar
  26. 26.
    Lawrence S, Giles CL, Fong S (2000) Natural language grammatical inference with recurrent neural networks. IEEE Trans Knowl Data Eng 12(1):126–140.  https://doi.org/10.1109/69.842255 CrossRefGoogle Scholar
  27. 27.
    Luo J, Zhang J, Huang W, Xu X, Jin N (2010) Preliminary study on the relationship between land surface temperature and occurrence of yellow rust in winter wheat. Disaster. Advances 3(4):288–292Google Scholar
  28. 28.
    Medeiros CB, Joliveau M, Jomier G, De Vuyst F (2010) Managing sensor traffic data and forecasting unusual behaviour propagation. GeoInformatica 14(3):279–305.  https://doi.org/10.1007/s10707-010-0102-7 CrossRefGoogle Scholar
  29. 29.
    Mehra LK, Cowger C, Gross K, Ojiambo PS (2016) Predicting pre-planting risk of Stagonospora nodorum blotch in winter wheat using machine learning models. Front Plant Sci 7.  https://doi.org/10.3389/fpls.2016.00390
  30. 30.
    Oerke EC, Dehne HW, Schönbeck F, Weber A (2012) Crop production and crop protection: estimated losses in major food and cash crops. Elsevier, AmsterdamGoogle Scholar
  31. 31.
    Paul PA, Munkvold GP (2005) Regression and artificial neural network modeling for the prediction of gray leaf spot of maize. Phytopathology 95(4):388–396.  https://doi.org/10.1094/PHYTO-95-0388 CrossRefGoogle Scholar
  32. 32.
    Pérez-Ariza CB, Nicholson AE, Flores MJ (2012) Prediction of coffee rust disease using bayesian networks. In: Proceedings of the Sixth European Workshop on Probabilistic Graphical Models. DECSAI University of Granada, Spain, pp 259–266Google Scholar
  33. 33.
    Rather AM, Agarwal A, Sastry VN (2015) Recurrent neural network and a hybrid model for prediction of stock returns. Expert Syst Appl 42(6):3234–3241.  https://doi.org/10.1016/j.eswa.2014.12.003 CrossRefGoogle Scholar
  34. 34.
    Sapoukhina N, Paillard S, Dedryver F, Vallavieille-Pope C (2013) Quantitative plant resistance in cultivar mixtures: wheat yellow rust as a modeling case study. New Phytol 200(3):888–897.  https://doi.org/10.1111/nph.12413 CrossRefGoogle Scholar
  35. 35.
    Savary S, Nelson A, Willocquet L, Pangga I, Aunario J (2012) Modeling and mapping potential epidemics of rice diseases globally. Crop Prot 34:6–17.  https://doi.org/10.1016/j.cropro.2011.11.009 CrossRefGoogle Scholar
  36. 36.
    Shi MW (2011) Based on time series and RBF network plant disease forecasting. Procedia Engineering 15:2384–2387.  https://doi.org/10.1016/j.proeng.2011.08.447 CrossRefGoogle Scholar
  37. 37.
    Te Beest DE, Paveley ND, Shaw MW, Van Den Bosch F (2008) Disease–weather relationships for powdery mildew and yellow rust on winter wheat. Phytopathology 98(5):609–617.  https://doi.org/10.1094/PHYTO-98-5-0609 CrossRefGoogle Scholar
  38. 38.
    Tian Y, Klasky S, Abbasi H, Lofstead J, Grout R, Podhorszki N, Liu Q, Wang Y, Yu W (2011) EDO: improving read performance for scientific applications through elastic data organization. In: IEEE International Conference on Cluster Computing. IEEE, Austin, pp 93–102Google Scholar
  39. 39.
    Übeylï M, Übeylï ED (2010) Using recurrent neural networks for estimation of minor actinides’ transmutation in a high power density fusion reactor. Expert Syst Appl 37(4):2742–2746.  https://doi.org/10.1016/j.eswa.2009.08.005 CrossRefGoogle Scholar
  40. 40.
    Wakie TT, Kumar S, Senay GB, Takele A, Lenho A (2016) Spatial prediction of wheat septoria leaf blotch (Septoria tritici) disease severity in Central Ethiopia. Eco Inform 36:15–30.  https://doi.org/10.1016/j.ecoinf.2016.09.003 CrossRefGoogle Scholar
  41. 41.
    Wang J, Wang J (2016) Forecasting energy market indices with recurrent neural networks: case study of crude oil price fluctuations. Energy 102:365–374.  https://doi.org/10.1016/j.energy.2016.02.098 CrossRefGoogle Scholar
  42. 42.
    Yue H, Rilett LR, Revesz PZ (2016) Spatio-temporal traffic video data archiving and retrieval system. GeoInformatica 20(1):59–94.  https://doi.org/10.1007/s10707-015-0231-0 CrossRefGoogle Scholar
  43. 43.
    Zhang J, Pu R, Loraamm RW, Yang G, Wang J (2014) Comparison between wavelet spectral features and conventional spectral features in detecting yellow rust for winter wheat. Comput Electron Agric 100:79–87.  https://doi.org/10.1016/j.compag.2013.11.001 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2017

Authors and Affiliations

  1. 1.School of InformationRenmin University of ChinaBeijingPeople’s Republic of China
  2. 2.Smart City Research CenterRenmin University of ChinaBeijingPeople’s Republic of China

Personalised recommendations