Crop Yield Prediction Using Deep Neural Networks

Abstract

Crop yield is a highly complex trait determined by multiple factors such as genotype, environment, and their interactions. Accurate yield prediction requires fundamental understanding of the functional relationship between yield and these interactive factors, and to reveal such relationship requires both comprehensive datasets and powerful algorithms. In the 2018 Syngenta Crop Challenge, Syngenta released several large datasets that recorded the genotype and yield performances of 2,267 maize hybrids planted in 2,247 locations between 2008 and 2016 and asked participants to predict the yield performance in 2017. As one of the winning teams, we designed a deep neural network (DNN) approach that took advantage of state-of-the-art modeling and solution techniques. Our model was found to have a superior prediction accuracy, with a root-mean-square-error (RMSE) being 12% of the average yield and 50% of the standard deviation for the validation dataset using predicted weather data. With perfect weather data, the RMSE would be reduced to 11% of the average yield and 46% of the standard deviation. We also performed feature selection based on the trained DNN model, which successfully decreased the dimension of the input space without significant drop in the prediction accuracy. Our computational results suggested that this model significantly outperformed other popular methods such as Lasso, shallow neural networks (SNN), and regression tree (RT). The results also revealed that environmental factors had a greater effect on the crop yield than genotype.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 46

1. 1.

   Abadi M. Barham P. Chen J. Chen Z. Davis A. Dean J. (2016 ). TensorFlow: a system for large scale machine learning, in OSDI'16 Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, Vol. 16, (Savannah, GA), 265–283.

   Not in our library

2. 2.

   Abhishek K. Singh M. Ghosh S. Anand A. (2012 ). Weather forecasting model using artificial neural network. Procedia Technol. 4, 311–318.

   Not in our library10.1016/j.protcy.2012.05.047

3. 3.

   Allison P. D. (2001 ). Missing Data, Vol. 136 Thousand Oaks, CA: Sage Publications.

   Not in our library

4. 4.

   Baboo S. S. Shereef I. K. (2010 ). An efficient weather forecasting system using artificial neural network. Int. J. Environ. Sci. Dev. 1, 321

   Not in our library10.7763/ijesd.2010.v1.63

5. 5.

   Bengio Y. Simard P. Frasconi P. (1994 ). Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5, 157–166.

   Not in our library10.1109/72.279181

6. 6.

   Bou-Rabee M. Sulaiman S. A. Saleh M. S. Marafi S. (2017 ). Using artificial neural networks to estimate solar radiation in kuwait. Renewable Sustain. Energy Rev. 72, 434–438.

   Not in our library10.1016/j.rser.2017.01.013

7. 7.

   Breiman L. (2017 ). Classification and Regression Trees. Abingdon: Routledge.

   Not in our library

8. 8.

   Burgueño J. Crossa J. Cornelius P. L. Yang R.-C. (2008 ). Using factor analytic models for joining environments and genotypes without crossover genotype × environment interaction. Crop Sci. 48, 1291–1305.

   Not in our library10.2135/cropsci2007.11.0632

9. 9.

   Burgueño J. Crossa J. Cotes J. M. Vicente F. S. Das B. (2011 ). Prediction assessment of linear mixed models for multienvironment trials. Crop Sci. 51, 944–954.

   Not in our library10.2135/cropsci2010.07.0403

10. 10.

    Bustami R. Bessaih N. Bong C. Suhaili S. (2007 ). Artificial neural network for precipitation and water level predictions of bedup river. IAENG Int. J. Comput. Sci. 34, 228–233.

    Not in our library

11. 11.

    Chapman S. C. Cooper M. Hammer G. L. Butler D. G. (2000 ). Genotype by environment interactions affecting grain sorghum. II. Frequencies of different seasonal patterns of drought stress are related to location effects on hybrid yields. Aust. J. Agric. Res. 51, 209–222.

    Not in our library10.1071/ar99021

12. 12.

    Cooper M. DeLacy I. H. (1994 ). Relationships among analytical methods used to study genotypic variation and genotype-by-environment interaction in plant breeding multi-environment experiments. Theor. Appl. Genet. 88, 561–572.

    Not in our library10.1007/bf01240919

13. 13.

    Crossa J. Cornelius P. L. (1997 ). Sites regression and shifted multiplicative model clustering of cultivar trial sites under heterogeneity of error variances. Crop Sci. 37, 406–415.

    Not in our library10.2135/cropsci1997.0011183x003700020017x

14. 14.

    Crossa J. Cornelius P. L. Sayre K. Ortiz-Monasterio R. Iván J. (1995 ). A shifted multiplicative model fusion method for grouping environments without cultivar rank change. Crop Sci. 35, 54–62.

    Not in our library10.2135/cropsci1995.0011183x003500010010x

15. 15.

    Crossa J. Yang R.-C. Cornelius P. L. (2004 ). Studying crossover genotype × environment interaction using linear-bilinear models and mixed models. J. Agric. Biol. Environ. Stat. 9, 362–380.

    Not in our library10.1198/108571104x4423

16. 16.

    DeLacy I. H. Basford K. E. Cooper M. Bull J. K. McLaren C. G. (1996 ). Analysis of multi-environment trials, an historical perspective, in Plant Adaptation and Crop Improvement, eds Cooper M. Hammer G. L. (Wallingford: CABI), 39124.

    Not in our library

17. 17.

    Drummond S. T. Sudduth K. A. Joshi A. Birrell S. J. Kitchen N. R. (2003 ). Statistical and neural methods for site specific yield prediction. Trans. ASAE 46, 5

    Not in our library10.13031/2013.12541

18. 18.

    Glorot X. Bengio Y. (2010 ). Understanding the difficulty of training deep feedforward neural networks, in Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (Sardinia), 249–256.

    Not in our library

19. 19.

    Goodfellow I. Bengio Y. Courville A. (2016 ). Deep Learning, Vol. 1 Cambridge: MIT Press Cambridge.

    Not in our library

20. 20.

    He K. Zhang X. Ren S. Sun J. (2016 ). Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Las Vegas), 770–778.

    Not in our library

21. 21.

    Heslot N. Akdemir D. Sorrells M. E. Jannink J.-L. (2014 ). Integrating environmental covariates and crop modeling into the genomic selection framework to predict genotype by environment interactions. Theor. Appl. Genet. 127, 463–480.

    Not in our library10.1007/s00122-013-2231-5

22. 22.

    Horie T. Yajima M. Nakagawa H. (1992 ). Yield forecasting. Agric. Syst. 40, 211–236.

    Not in our library10.1016/0308-521x(92)90022-g

23. 23.

    Hornik K. Stinchcombe M. White H. (1990 ). Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Netw. 3, 551–560.

    Not in our library10.1016/0893-6080(90)90005-6

24. 24.

    Hu Q. Buyanovsky G. (2003 ). Climate effects on corn yield in missouri. J. Appl. Meteorol. 42, 1626–1635.

    Not in our library10.1175/1520-0450(2003)042<1626:ceocyi>2.0.co;2

25. 25.

    Ioffe S. Szegedy C. (2015 ). Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv [preprint] arXiv:1502.03167.

    Not in our library

26. 26.

    Kaur A. Sharma J. Agrawal S. (2011 ). Artificial neural networks in forecasting maximum and minimum relative humidity. Int. J. Comput. Sci. Netw. Secur. 11, 197–199.

    Not in our library

27. 27.

    Khaki S. (2019 ). Source Code. Available online at: https://github.com/saeedkhaki92/Yield-Prediction-DNN.

    Not in our library

28. 28.

    Kingma D. P. Ba J. (2014 ). Adam: a method for stochastic optimization. arXiv [preprint] arXiv:1412.6980.

    Not in our library

29. 29.
    Deep learning · 2015

    No notice
30. 30.

    LeCun Y. Bottou L. Orr G. B. Müller K.-R. (1998 ). Efficient backprop, in Neural Networks: Tricks of the Trade, eds Montavon G. Orr G. B. Müller K. R. (Berlin; Heidelberg: Springer), 9–50.

    Not in our library

31. 31.

    Liu J. Goering C. E. Tian L. (2001 ). A neural network for setting target corn yields. Trans. ASAE 44, 705

    Not in our library10.13031/2013.6097

32. 32.

    Maqsood I. Khan M. R. Abraham A. (2004 ). An ensemble of neural networks for weather forecasting. Neural Comput. Appl. 13, 112–122.

    Not in our library10.1007/s00521-004-0413-4

33. 33.

    Marko O. Brdar S. Panic M. Lugonja P. Crnojevic V. (2016 ). Soybean varieties portfolio optimisation based on yield prediction. Comput. Electron. Agric. 127, 467–474.

    Not in our library10.1016/j.compag.2016.07.009

34. 34.

    Marko O. Brdar S. Panić M. Šašić I. Despotović D. Knežević M.. (2017 ). Portfolio optimization for seed selection in diverse weather scenarios. PLOS ONE 12:e0184198.

    Not in our library10.1371/journal.pone.0184198

35. 35.

    Montesinos-López O. A. Montesinos-López A. Crossa J. Montesinos-López J. C. Mota-Sanchez D. Estrada-González F.. (2018 ). Prediction of multiple trait and multiple environment genomic data using recommender systems. G3 (Bethesda) 8, 131–147.

    Not in our library10.1534/g3.117.300309

36. 36.

    Muchow R. C. Sinclair T. R. Bennett J. M. (1990 ). Temperature and solar radiation effects on potential maize yield across locations. Agron. J. 82, 338–343.

    Not in our library10.2134/agronj1990.00021962008200020033x

37. 37.

    Ng A. Y. (2004 ). Feature selection, L1 vs. L2 regularization, and rotational invariance, in Proceedings of the Twenty-first International Conference on Machine Learning (Bnaff: ACM), 78.

    Not in our library

38. 38.

    Romero J. R. Roncallo P. F. Akkiraju P. C. Ponzoni I. Echenique V. C. Carballido J. A. (2013 ). Using classification algorithms for predicting durum wheat yield in the province of buenos aires. Comput. Electron. Agric. 96, 173–179.

    Not in our library10.1016/j.compag.2013.05.006

39. 39.

    Russello H. (2018 ). Convolutional neural networks for crop yield prediction using satellite images. IBM Center for Advanced Studies.

    Not in our library

40. 40.

    Springenberg J. T. Dosovitskiy A. Brox T. Riedmiller M. (2014 ). Striving for simplicity: the all convolutional net. arXiv [preprint] arXiv:1412.6806.

    Not in our library

41. 41.

    Srivastava N. Hinton G. Krizhevsky A. Sutskever I. Salakhutdinov R. (2014 ). Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958.

    Not in our library

42. 42.

    Syngenta (2018 ). Syngenta Crop Challenge In Analytics. Available online at: https://www.ideaconnection.com/syngenta-crop-challenge/challenge.php/.

    Not in our library

43. 43.

    Szegedy C. Liu W. Jia Y. Sermanet P. Reed S. Anguelov D. (2015 ). Going deeper with convolutions, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (Boston, MA).

    Not in our library

44. 44.

    Tibshirani R. (1996 ). Regression shrinkage and selection via the lasso. J. R. Stat. Soc. B 58, 267–288.

    Not in our library10.1111/j.2517-6161.1996.tb02080.x

45. 45.

    You J. Li X. Low M. Lobell D. Ermon S. (2017 ). Deep gaussian process for crop yield prediction based on remote sensing data, in Thirty-First AAAI Conference on Artificial Intelligence (San Francisco, CA), 4559–4566.

    Not in our library

46. 46.

    Zhang S. Tao F. Zhang Z. (2017 ). Spatial and temporal changes in vapor pressure deficit and their impacts on crop yields in China during 1980–2008. J. Meteorol. Res. 31, 800–808.

    Not in our library10.1007/s13351-017-6137-z

Cited by papers we hold 6

• Machine learning models for predicting morphological traits and optimizing genotype and planting date in roselle (Hibiscus Sabdariffa L.) · 2025
  Not checked
• Data Management and Modeling in Plant Biology · 2021
  Not checked
• A review of deep learning applications for genomic selection · 2021
  No notice
• A CNN-RNN Framework for Crop Yield Prediction · 2020
  Not checked
• County-Level Soybean Yield Prediction Using Deep CNN-LSTM Model · 2019
  Not checked
• A Guide on Deep Learning for Complex Trait Genomic Prediction · 2019
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.