Maize yield forecasting by linear regression and artificial neural networks in Jilin, China
Problem
Forecasting maize yields in Jilin, China from 1962-2004 using climate conditions and fertilizer data, which is hard to obtain.
Why it matters
Reliable yield forecasts inform agricultural and food-supply planning.
What the AI did
Non-linear artificial neural network models using precipitation and fertilizer (or prior-year yield as substitute) predictors were compared against multiple linear regression and persistence forecasts.
Results
ANN significantly outperformed MLR and persistence under both cross-validation and retroactive validation; skill score values not stated in source.
Impact
ANN models provided significantly better maize yield forecasts than traditional regression methods.
Record
| Venue | The Journal of Agricultural Science |
|---|---|
| Published | 2014 |
| Work type | article |
| Authors | Kanichiro Matsumura, Carlos F. Gaitán, K. SUGIMOTO, Alex J. Cannon, William W. Hsieh |
| Citations | 100 (OpenAlex, at import time) |
| References | 42 |
| Model or method | artificial neural networks |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1017/s0021859614000392 |
| Open access | bronze |
| Keywords | neural networks, yield forecasting, maize, climate predictors |
Importance rating
real but narrower advance
Regional maize yield forecasting for a single province; better forecasts aid food-supply planning, but scope is narrow (one crop, one province).
More in Climate & Environment
| # | Paper | Year | Citations | Importance |
|---|---|---|---|---|
| 1 | Learning skillful medium-range global weather forecasting | 2023 | 1,416 |
8
|
| 2 | Accurate medium-range global weather forecasting with 3D neural networks | 2023 | 1,631 |
8
|
| 3 | FuXi: a cascade machine learning forecasting system for 15-day global weather forecast | 2023 | 355 |
8
|
| 4 | Skilful nowcasting of extreme precipitation with NowcastNet | 2023 | 451 |
8
|
| 5 | Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects | 2023 | 378 |
8
|