Publication Abstracts

Liu et al. 2022

Liu, Q., M. Yang, K. Mohammadi, D. Song, J. Bi, and G. Wang, 2022: Machine learning crop yield models based on meteorological features and comparison with a process-based model. Artif. Intell. Earth Syst., 1, no. 4, e220002, doi:10.1175/AIES-D-22-0002.1.

A major challenge for food security worldwide is the large interannual variability of crop yield, and climate change is expected to further exacerbate this volatility. Accurate prediction of the crop response to climate variability and change is critical for short-term management and long-term planning in multiple sectors. In this study, using maize in the U.S. Corn Belt as an example, we train and validate multiple machine learning (ML) models predicting crop yield based on meteorological variables and soil properties using the leaving-one-year-out approach, and compare their performance with that of a widely used process-based crop model (PBM). Our proposed long short-term memory model with attention (LSTMatt) outperforms other ML models (including other variations of LSTM developed in this study) and explains 73% of the spatiotemporal variance of the observed maize yield, in contrast to 16% explained by the regionally calibrated PBM; the magnitude of yield prediction errors in LSTMatt is about one-third of that in the PBM. When applied to the extreme drought year 2012 that has no counterpart in the training data, the LSTMatt performance drops but still shows advantage over the PBM. Findings from this study suggest a great potential for out-of-sample application of the LSTMatt model to predict crop yield under a changing climate.

Export citation: [ BibTeX ] [ RIS ]

BibTeX Citation

@article{li07310h,
  author={Liu, Q. and Yang, M. and Mohammadi, K. and Song, D. and Bi, J. and Wang, G.},
  title={Machine learning crop yield models based on meteorological features and comparison with a process-based model},
  year={2022},
  journal={Artif. Intell. Earth Syst.},
  volume={1},
  number={4},
  pages={e220002},
  doi={10.1175/AIES-D-22-0002.1},
}

[ Close ]

RIS Citation

TY  - JOUR
ID  - li07310h
AU  - Liu, Q.
AU  - Yang, M.
AU  - Mohammadi, K.
AU  - Song, D.
AU  - Bi, J.
AU  - Wang, G.
PY  - 2022
TI  - Machine learning crop yield models based on meteorological features and comparison with a process-based model
JA  - Artif. Intell. Earth Syst.
VL  - 1
IS  - 4
SP  - e220002
DO  - 10.1175/AIES-D-22-0002.1
ER  -

[ Close ]

• Return to 2022 Publications

• Return to Publications Homepage