Early forecasting of rice blast disease using long short-term memory recurrent neural networks

Yangseon Kim, Jae Hwan Roh, Ha Young Kim

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Among all diseases affecting rice production, rice blast disease has the greatest impact. Thus, monitoring and precise prediction of the occurrence of this disease are important; early prediction of the disease would be especially helpful for prevention. Here, we propose an artificial-intelligence-based model for rice blast disease prediction. Historical data on rice blast occurrence in representative areas of rice production in South Korea and historical climatic data are used to develop a region-specific model for three different regions: Cheolwon, Icheon and Milyang. A rice blast incidence is then predicted a year in advance using long-term memory networks (LSTMs). The predictive performance of the proposed LSTM model is evaluated by varying the input variables (i.e., rice blast disease scores, air temperature, relative humidity and sunshine hours). The most widely cultivated rice varieties are also selected and the prediction results for those varieties are analyzed. Application of the LSTM model to the accumulated rice-blast disease score data confirms successful prediction of rice blast incidence. In all regions, the predictions are most accurate when all four input variables are combined. Rice blast fungus prediction using the proposed LSTM model is variety-based; therefore, this model will be more helpful for rice breeders and rice blast researchers than conventional rice blast prediction models.

Original languageEnglish
Article number34
JournalSustainability (Switzerland)
Volume10
Issue number1
DOIs
Publication statusPublished - 2017 Dec 23

Fingerprint

Recurrent neural networks
neural network
rice
Disease
prediction
incidence
Long short-term memory
artificial intelligence
Fungi
South Korea
Artificial intelligence
Atmospheric humidity
air
monitoring
Data storage equipment
Monitoring
Air
relative humidity

All Science Journal Classification (ASJC) codes

  • Geography, Planning and Development
  • Renewable Energy, Sustainability and the Environment
  • Management, Monitoring, Policy and Law

Cite this

@article{b20fa71f8e644a46aaef3b73eac2a500,
title = "Early forecasting of rice blast disease using long short-term memory recurrent neural networks",
abstract = "Among all diseases affecting rice production, rice blast disease has the greatest impact. Thus, monitoring and precise prediction of the occurrence of this disease are important; early prediction of the disease would be especially helpful for prevention. Here, we propose an artificial-intelligence-based model for rice blast disease prediction. Historical data on rice blast occurrence in representative areas of rice production in South Korea and historical climatic data are used to develop a region-specific model for three different regions: Cheolwon, Icheon and Milyang. A rice blast incidence is then predicted a year in advance using long-term memory networks (LSTMs). The predictive performance of the proposed LSTM model is evaluated by varying the input variables (i.e., rice blast disease scores, air temperature, relative humidity and sunshine hours). The most widely cultivated rice varieties are also selected and the prediction results for those varieties are analyzed. Application of the LSTM model to the accumulated rice-blast disease score data confirms successful prediction of rice blast incidence. In all regions, the predictions are most accurate when all four input variables are combined. Rice blast fungus prediction using the proposed LSTM model is variety-based; therefore, this model will be more helpful for rice breeders and rice blast researchers than conventional rice blast prediction models.",
author = "Yangseon Kim and Roh, {Jae Hwan} and Kim, {Ha Young}",
year = "2017",
month = "12",
day = "23",
doi = "10.3390/su10010034",
language = "English",
volume = "10",
journal = "Sustainability",
issn = "2071-1050",
publisher = "MDPI AG",
number = "1",

}

Early forecasting of rice blast disease using long short-term memory recurrent neural networks. / Kim, Yangseon; Roh, Jae Hwan; Kim, Ha Young.

In: Sustainability (Switzerland), Vol. 10, No. 1, 34, 23.12.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Early forecasting of rice blast disease using long short-term memory recurrent neural networks

AU - Kim, Yangseon

AU - Roh, Jae Hwan

AU - Kim, Ha Young

PY - 2017/12/23

Y1 - 2017/12/23

N2 - Among all diseases affecting rice production, rice blast disease has the greatest impact. Thus, monitoring and precise prediction of the occurrence of this disease are important; early prediction of the disease would be especially helpful for prevention. Here, we propose an artificial-intelligence-based model for rice blast disease prediction. Historical data on rice blast occurrence in representative areas of rice production in South Korea and historical climatic data are used to develop a region-specific model for three different regions: Cheolwon, Icheon and Milyang. A rice blast incidence is then predicted a year in advance using long-term memory networks (LSTMs). The predictive performance of the proposed LSTM model is evaluated by varying the input variables (i.e., rice blast disease scores, air temperature, relative humidity and sunshine hours). The most widely cultivated rice varieties are also selected and the prediction results for those varieties are analyzed. Application of the LSTM model to the accumulated rice-blast disease score data confirms successful prediction of rice blast incidence. In all regions, the predictions are most accurate when all four input variables are combined. Rice blast fungus prediction using the proposed LSTM model is variety-based; therefore, this model will be more helpful for rice breeders and rice blast researchers than conventional rice blast prediction models.

AB - Among all diseases affecting rice production, rice blast disease has the greatest impact. Thus, monitoring and precise prediction of the occurrence of this disease are important; early prediction of the disease would be especially helpful for prevention. Here, we propose an artificial-intelligence-based model for rice blast disease prediction. Historical data on rice blast occurrence in representative areas of rice production in South Korea and historical climatic data are used to develop a region-specific model for three different regions: Cheolwon, Icheon and Milyang. A rice blast incidence is then predicted a year in advance using long-term memory networks (LSTMs). The predictive performance of the proposed LSTM model is evaluated by varying the input variables (i.e., rice blast disease scores, air temperature, relative humidity and sunshine hours). The most widely cultivated rice varieties are also selected and the prediction results for those varieties are analyzed. Application of the LSTM model to the accumulated rice-blast disease score data confirms successful prediction of rice blast incidence. In all regions, the predictions are most accurate when all four input variables are combined. Rice blast fungus prediction using the proposed LSTM model is variety-based; therefore, this model will be more helpful for rice breeders and rice blast researchers than conventional rice blast prediction models.

UR - http://www.scopus.com/inward/record.url?scp=85039070416&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039070416&partnerID=8YFLogxK

U2 - 10.3390/su10010034

DO - 10.3390/su10010034

M3 - Article

AN - SCOPUS:85039070416

VL - 10

JO - Sustainability

JF - Sustainability

SN - 2071-1050

IS - 1

M1 - 34

ER -