Predicting A Growing Stage of Rice Plants Based on The Cropping Records over 25 Years — A Trial of Feature Engineering Incorporating Hidden Regional Characteristics —

Hiroshi UEHARA; Yasuhiro IUCHI; Yusuke FUKAZAWA; Yoshihiro KANETA

doi:10.1587/transinf.2021DAP0013

Predicting A Growing Stage of Rice Plants Based on The Cropping Records over 25 Years — A Trial of Feature Engineering Incorporating Hidden Regional Characteristics —

Hiroshi UEHARA, Yasuhiro IUCHI, Yusuke FUKAZAWA, Yoshihiro KANETA

Full Text Views

0

Cite this

Summary :

This study tries to predict date of ear emergence of rice plants, based on cropping records over 25 years. Predicting ear emergence of rice plants is known to be crucial for practicing good harvesting quality, and has long been dependent upon old farmers who acquire skills of intuitive prediction based on their long term experiences. Facing with aging farmers, data driven approach for the prediction have been pursued. Nevertheless, they are not necessarily sufficient in terms of practical use. One of the issue is to adopt weather forecast as the feature so that the predictive performance is varied by the accuracy of the forecast. The other issue is that the performance is varied by region and the regional characteristics have not been used as the features for the prediction. With this background, we propose a feature engineering to quantify hidden regional characteristics as the feature for the prediction. Further the feature is engineered based only on observational data without any forecast. Applying our proposal to the data on the cropping records resulted in sufficient predictive performance, ±2.69days of RMSE.

Publication: IEICE TRANSACTIONS on Information Vol.E105-D No.5 pp.955-963

Publication Date: 2022/05/01

Publicized: 2021/12/29

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2021DAP0013

Type of Manuscript: Special Section PAPER (Special Section on Data Engineering and Information Management)

Category

Authors

Hiroshi UEHARA
  Rissho University
Yasuhiro IUCHI
  Akita Prefectural University
Yusuke FUKAZAWA
  Waseda University
Yoshihiro KANETA
  Akita Prefectural University

Keyword

e-agriculture, crop prediction, feature engineering, hidden Markov model, knowledge acquisition

Cite this

Copy

Hiroshi UEHARA, Yasuhiro IUCHI, Yusuke FUKAZAWA, Yoshihiro KANETA, "Predicting A Growing Stage of Rice Plants Based on The Cropping Records over 25 Years — A Trial of Feature Engineering Incorporating Hidden Regional Characteristics —" in IEICE TRANSACTIONS on Information, vol. E105-D, no. 5, pp. 955-963, May 2022, doi: 10.1587/transinf.2021DAP0013.
Abstract: This study tries to predict date of ear emergence of rice plants, based on cropping records over 25 years. Predicting ear emergence of rice plants is known to be crucial for practicing good harvesting quality, and has long been dependent upon old farmers who acquire skills of intuitive prediction based on their long term experiences. Facing with aging farmers, data driven approach for the prediction have been pursued. Nevertheless, they are not necessarily sufficient in terms of practical use. One of the issue is to adopt weather forecast as the feature so that the predictive performance is varied by the accuracy of the forecast. The other issue is that the performance is varied by region and the regional characteristics have not been used as the features for the prediction. With this background, we propose a feature engineering to quantify hidden regional characteristics as the feature for the prediction. Further the feature is engineered based only on observational data without any forecast. Applying our proposal to the data on the cropping records resulted in sufficient predictive performance, ±2.69days of RMSE.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021DAP0013/_p

Copy

@ARTICLE{e105-d_5_955,
author={Hiroshi UEHARA, Yasuhiro IUCHI, Yusuke FUKAZAWA, Yoshihiro KANETA, },
journal={IEICE TRANSACTIONS on Information},
title={Predicting A Growing Stage of Rice Plants Based on The Cropping Records over 25 Years — A Trial of Feature Engineering Incorporating Hidden Regional Characteristics —},
year={2022},
volume={E105-D},
number={5},
pages={955-963},
abstract={This study tries to predict date of ear emergence of rice plants, based on cropping records over 25 years. Predicting ear emergence of rice plants is known to be crucial for practicing good harvesting quality, and has long been dependent upon old farmers who acquire skills of intuitive prediction based on their long term experiences. Facing with aging farmers, data driven approach for the prediction have been pursued. Nevertheless, they are not necessarily sufficient in terms of practical use. One of the issue is to adopt weather forecast as the feature so that the predictive performance is varied by the accuracy of the forecast. The other issue is that the performance is varied by region and the regional characteristics have not been used as the features for the prediction. With this background, we propose a feature engineering to quantify hidden regional characteristics as the feature for the prediction. Further the feature is engineered based only on observational data without any forecast. Applying our proposal to the data on the cropping records resulted in sufficient predictive performance, ±2.69days of RMSE.},
keywords={},
doi={10.1587/transinf.2021DAP0013},
ISSN={1745-1361},
month={May},}

Copy

TY - JOUR
TI - Predicting A Growing Stage of Rice Plants Based on The Cropping Records over 25 Years — A Trial of Feature Engineering Incorporating Hidden Regional Characteristics —
T2 - IEICE TRANSACTIONS on Information
SP - 955
EP - 963
AU - Hiroshi UEHARA
AU - Yasuhiro IUCHI
AU - Yusuke FUKAZAWA
AU - Yoshihiro KANETA
PY - 2022
DO - 10.1587/transinf.2021DAP0013
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2022
AB - This study tries to predict date of ear emergence of rice plants, based on cropping records over 25 years. Predicting ear emergence of rice plants is known to be crucial for practicing good harvesting quality, and has long been dependent upon old farmers who acquire skills of intuitive prediction based on their long term experiences. Facing with aging farmers, data driven approach for the prediction have been pursued. Nevertheless, they are not necessarily sufficient in terms of practical use. One of the issue is to adopt weather forecast as the feature so that the predictive performance is varied by the accuracy of the forecast. The other issue is that the performance is varied by region and the regional characteristics have not been used as the features for the prediction. With this background, we propose a feature engineering to quantify hidden regional characteristics as the feature for the prediction. Further the feature is engineered based only on observational data without any forecast. Applying our proposal to the data on the cropping records resulted in sufficient predictive performance, ±2.69days of RMSE.
ER -