Towards an early warning system for wheat blast: epidemiological basis and model development

2021 ◽  
Author(s):  
J. M. Fernandes ◽  
◽  
E. M. Del Ponte ◽  
J. P. Ascari ◽  
T. J. Krupnik ◽  
...  
Keyword(s):  
Decision Support ◽  
South America ◽  
Support System ◽  
Early Warning System ◽  
Scientific Community ◽  
Model Development ◽  
Warning System ◽  
Original Research ◽  
Ecological Interactions ◽  
Wheat Blast

Wheat blast is caused by the fungus Pyricularia oryzae Triticum pathotype (PoT). Significantly damaging wheat blast epidemics are sporadic and limited to tropical wheat growing areas in South America. Unexpectedly, wheat blast was reported in Bangladesh and Zambia in 2016 and 2020, respectively. The urgent need to deal with a poorly studied disease has mobilized the scientific community. Original research and reviews have been published in various venues. Nevertheless, disease control is still a difficult task. Much less research has, however, focused on crucially important and complex ecological interactions at the field, landscape, or regional levels. This chapter reviews aspects of the epidemiology of wheat blast, mainly those related to inoculum and its role for the epidemics. It then describes the models that have been developed by the authors as well as the decision support system. Examples of the implementation of a warning system in Bangladesh and Brazil are also illustrated.

scholarly journals Retrospective Study on the Seasonal Forecast-Based Disease Intervention of the Wheat Blast Outbreaks in Bangladesh

2020 ◽  
Vol 11 ◽  
Author(s):  
Kwang-Hyung Kim ◽  
Eu Ddeum Choi
Keyword(s):  
Retrospective Study ◽  
Risk Prediction ◽  
Early Warning ◽  
Early Warning System ◽  
Disease Risk ◽  
National Level ◽  
Warning System ◽  
Seasonal Forecast ◽  
Seasonal Forecasts ◽  
Wheat Blast

Seasonal disease risk prediction using disease epidemiological models and seasonal forecasts has been actively sought over the last decades, as it has been believed to be a key component in the disease early warning system for the pre-season planning of local or national level disease control. We conducted a retrospective study using the wheat blast outbreaks in Bangladesh, which occurred for the first time in Asia in 2016, to study a what-if scenario that if there was seasonal disease risk prediction at that time, the epidemics could be prevented or reduced through prediction-based interventions. Two factors govern the answer: the seasonal disease risk prediction is accurate enough to use, and there are effective and realistic control measures to be used upon the prediction. In this study, we focused on the former. To simulate the wheat blast risk and wheat yield in the target region, a high-resolution climate reanalysis product and spatiotemporally downscaled seasonal climate forecasts from eight global climate models were used as inputs for both models. The calibrated wheat blast model successfully simulated the spatial pattern of disease epidemics during the 2014–2018 seasons and was subsequently used to generate seasonal wheat blast risk prediction before each winter season starts. The predictability of the resulting predictions was evaluated against observation-based model simulations. The potential value of utilizing the seasonal wheat blast risk prediction was examined by comparing actual yields resulting from the risk-averse (proactive) and risk-disregarding (conservative) decisions. Overall, our results from this retrospective study showed the feasibility of seasonal forecast-based early warning system for the pre-season strategic interventions of forecasted wheat blast in Bangladesh.

Research on the architecture of food safety risk intelligence early warning system

2021 ◽  
pp. 1-11
Author(s):  
Yu Zhang ◽  
Yarui Zhang ◽  
Xiaocui Li
Keyword(s):  
Decision Support ◽  
Food Safety ◽  
Early Warning ◽  
Early Warning System ◽  
System Development ◽  
Warning System ◽  
Risk Identification ◽  
Functional Modules ◽  
Safety Risk ◽  
Food Safety Risk

Food safety supervision involves all aspects of production, processing and sales. True, reliable and complete intelligence can realize the traceability of the entire process of food safety production, thereby ensuring that food safety incidents are controllable from the source. However, most studies only analyze the food safety risk identification and early warning from the perspective of information flow from the theoretical level, and lack specific applications at the practical level. Therefore, this study analyzes the system requirements and the overall business process of the system, expounds the goals and principles of system design, designs the overall framework of the system, and finally elaborates on the realization of its functions of the different functional modules of the system, so as to provide the early warning system development provides decision support and reference. Finally elaborates the realization of its functions according to the different functional modules of the system, so as to provide decision support and reference for the development of early warning system.

scholarly journals Developing models to establish seasonal forest fire early warning system

2021 ◽  
Vol 909 (1) ◽  
pp. 012005
Author(s):  
D E Nuryanto ◽  
R P Pradana ◽  
I D G A Putra ◽  
E Heriyanto ◽  
U A Linarka ◽  
...  
Keyword(s):  
Forest Fire ◽  
Early Warning ◽  
Forest Fires ◽  
Early Warning System ◽  
Model Development ◽  
Warning System ◽  
Climate Index ◽  
Management Decision ◽  
Forest Fire Management ◽  
Modeling Strategy

Abstract During a typically dry season in Sumatra or Kalimantan, the forest fire starts. In 2015, an El Nino year, forest fires in Sumatra and Kalimantan ranked among the worst episodes on record. Understanding the connection between accumulated monthly rainfall and the risk of hotspot occurrence is key to improving forest fire management decision-making. This study addresses model development to predict the number of 6-month fire hotspots, by combining the prediction of rainfall with hotspot patterns. Hotspot data were obtained from the Fire Information for Resources Management System (FIRMS) for the period of 2001–2018. For rainfall prediction, we used the output model of the European Centre for Medium-Range Weather Forecasts (ECMWF). The threshold of more than 10 hotspot events has been used to establish hotspot climatology. To get a threshold for rainfall that can cause forest fires, we used the Pulang Pisau rain station. We applied two rainfall thresholds to determine three categorical forecasts (low, moderate, high) as environment quality indicator. The two thresholds are 100 mm/month for the lower threshold and 130 mm/month for the upper threshold. The verification of the observational data showed an accuracy of > 0.83, which is relatively consistent and persistent with forest fire events. The weakness of this system is that it cannot determine the exact location of the forest fire because the spatial resolution used is 0.25 degrees. The predictions of the monthly climate index values were reasonably good suggesting the potential to be used as an operational tool to predict the number of fire hotspots expected. The seasonal forest fire early warning system is expected to be an effort to anticipate forest fires for the next six months. The modeling strategy presented in this study could be replicated for any fire index in any region, based on predictive rainfall information and patterns of the hotspot.

scholarly journals Three-Month Real-Time Dengue Forecast Models: An Early Warning System for Outbreak Alerts and Policy Decision Support in Singapore

2016 ◽  
Vol 124 (9) ◽  
pp. 1369-1375 ◽  
Author(s):  
Yuan Shi ◽  
Xu Liu ◽  
Suet-Yheng Kok ◽  
Jayanthi Rajarethinam ◽  
Shaohong Liang ◽  
...  
Keyword(s):  
Decision Support ◽  
Real Time ◽  
Early Warning ◽  
Early Warning System ◽  
Warning System ◽  
Policy Decision ◽  
Forecast Models

scholarly journals Artificial Intelligence Assisted Early Warning System for Acute Kidney Injury Driven by Multi-Center ICU Database

2020 ◽  
Author(s):  
Zhi Huang ◽  
Sai Huang ◽  
Li Chen ◽  
Wei-Hung Weng ◽  
Lili Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Early Warning ◽  
Early Warning System ◽  
Data Extraction ◽  
Model Development ◽  
Warning System ◽  
Kidney Injury ◽  
Machine Learning Algorithms ◽  
Mimic Iii

AbstractBackgroundTo improve the performance of early acute kidney injury (AKI) prediction in intensive care unit (ICU), we developed and externally validated machine learning algorithms in two large ICU databases.MethodsUsing eICU® Collaborative Research Database (eICU) and MIMIC-III databases, we selected all adult patients (age ≥ 18). The detection of AKI was based on both the oliguric and serum creatinine criteria of the KDIGO (Kidney Disease Improving Global Outcomes). We developed an early warning system for forecasting the onset of AKI within the first week of ICU stay, by using 6- or 12-hours as the data extraction window and make a prediction within a 1-hour window after a gap window of 6- or 12-hours. We used 52 features which are routinely available ICU data as predictors. eICU was used for model development, and MIMIC-III was used for externally validation. We applied and experimented on eight machine learning algorithms for the prediction task.Results3,816 unique admissions in multi-center eICU database were selected for model development, and 5,975 unique admissions in single-center MIMIC-III database were selected for external validation. The incidence of AKI within the first week of ICU stay in eICU and MIMIC-III cohorts was 52.1% (n=1,988) and 31.3% (n=1,870), respectively. In eICU cohort, the performance of AKI prediction is better with shorter extraction window and gap window. We found that the AdaBoost algorithm yielded the highest AUC (0.8859) on the model with 6-hours data extraction window and 6-hours gap window (model 6-6) rather than other prediction models. In MIMIC-III cohort, AdaBoost also performed well.ConclusionsWe developed the machine learning-based early AKI prediction model, which considered clinical important features and has been validated in two datasets.

Sign in / Sign up

Export Citation Format

Share Document