Application-oriented deep learning model for early warning of rice blast in Taiwan

Jie-Hao Ou; Chang-Hsin Kuo; Yea-Fang Wu; Guo-Gih Lin; Miin-Huey Lee; Rong-Kuen Chen; Hau-Ping Chou; Hsin-Yuh Wu; Sheng-Chi Chu; Qiao-Juan Lai; Yi-Chen Tsai; Chun-Chi Lin; Chien-Chih Kuo; Chung-Ta Liao; Yi-Nian Chen; Yen-Wei Chu; Chi-Yu Chen

doi:10.1016/j.ecoinf.2022.101950

Application-oriented deep learning model for early warning of rice blast in Taiwan

Journal

Ecological Informatics

Journal Volume

73

Pages

101950

Date Issued

2023-03

Author(s)

Jie-Hao Ou

Chang-Hsin Kuo

Yea-Fang Wu

Guo-Gih Lin

Miin-Huey Lee

Rong-Kuen Chen

Hau-Ping Chou

Hsin-Yuh Wu

Sheng-Chi Chu

Qiao-Juan Lai

Yi-Chen Tsai

Chun-Chi Lin

Chien-Chih Kuo

Chung-Ta Liao

Yi-Nian Chen

Yen-Wei Chu

Chi-Yu Chen

DOI

10.1016/j.ecoinf.2022.101950

URI

https://www.sciencedirect.com/science/article/pii/S1574954122004009?via%3Dihub

https://scholars.tari.gov.tw/handle/123456789/18788

Abstract

Rice blast is one of the most devastating diseases that threatens rice production in Taiwan. A rice blast fore-casting model is required to guide the precise application of fungicide. Therefore, BlastGRU-TW model based on deep learning algorithms was developed in this study. The input data comprised approximately 1000 rice blast surveys, collected from 50 fields throughout Taiwan between 2014 and 2021, and the corresponding weather data retrieved from weather observation network in Taiwan. Common and easily accessible meteorological factors, i.e. temperature, humidity, precipitation, and wind, were converted into 20 daily meteorological features which were coupled with different time intervals between 1 and 30 days before survey (DBS) to train the model. The results showed that seven meteorological features (daily maximum temperature, daily mean temperature, daily minimum temperature, daily mean humidity, daily mean WV and daily mean Wu) and the interval from-4 to-24 DBS were informative in disease prediction, thereby indicating that the proposed model could predict the risk of rice blast by using meteorological data 4-24 days before new disease symptoms appeared. The proposed BlastGRU-TW model achieved an accuracy of 87.3%. Furthermore, on adding the 3 day forecast weather data from Weather Research and Forecasting (WRF) model in the proposed model, the forecast extended to 7 days ahead of the appearance of new symptoms. Moreover, the BLASTAM model developed in Japan was imple-mented and validated in Taiwan to evaluate its applicability in different geographical areas. Finally, a rice blast early warning system (https://mycolab.pp.nchu.edu.tw/blast_forecast/index_en.php) equipped with an interac-tive web-based map is now available for real-time forecasting of the risk of rice blast in paddy field across Taiwan.

Subjects

Rice blast early warning system

Weather observation network

Gridded weather forecast

Recurrent neural network

BLASTAM

Publisher

Elsevier Science Inc.

Type

journal article