The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este estudo tenta prever a data de emergência das espigas das plantas de arroz, com base em registros de cultivo ao longo de 25 anos. A previsão da emergência de espigas de plantas de arroz é conhecida por ser crucial para a prática de uma boa qualidade de colheita, e há muito que depende de antigos agricultores que adquirem competências de previsão intuitiva com base nas suas experiências de longo prazo. Enfrentando agricultores idosos, foi adotada uma abordagem baseada em dados para a previsão. No entanto, não são necessariamente suficientes em termos de utilização prática. Uma das questões é adotar a previsão do tempo como recurso para que o desempenho preditivo varie de acordo com a precisão da previsão. A outra questão é que o desempenho varia por região e as características regionais não foram utilizadas como características para a previsão. Com esse pano de fundo, propomos uma engenharia de recursos para quantificar características regionais ocultas como recursos para a previsão. Além disso, o recurso é projetado com base apenas em dados observacionais, sem qualquer previsão. A aplicação da nossa proposta aos dados dos registros de cultivo resultou em desempenho preditivo suficiente, ±2.69 dias de RMSE.
Hiroshi UEHARA
Rissho University
Yasuhiro IUCHI
Akita Prefectural University
Yusuke FUKAZAWA
Waseda University
Yoshihiro KANETA
Akita Prefectural University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
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
Copiar
@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},}
Copiar
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 -