Performance of a weather-based forecast system for chemical control of coffee leaf rust

Hinnah, Fernando Dill; Sentelhas, Paulo César; Patrício, Flávia Rodrigues Alves; Paiva, R. N.; Parenti, Matheus Vilhena

doi:10.1016/j.cropro.2020.105225

Cited by 11 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models are mainly based on CLR severity values, occurrence of favorable leaf temperature and humidity, and meteorological data. Since the 1960s, more than 20 models have been developed to predict different indicators of the disease's development and can help manage it [55][56][57][58][59]. However, these models are not yet used to control rust in coffee farms.…”

Section: Frequency Of Fungicide Spraying In Brazilmentioning

confidence: 99%

Coffee Leaf Rust in Brazil: Historical Events, Current Situation, and Control Measures

Sera

Carvalho

Rezende³

et al. 2022

Agronomy

View full text Add to dashboard Cite

In this review of coffee leaf rust (CLR) in Brazil, we report: (i) the historical introduction of CLR in Brazil and the first control measures; (ii) favorable environmental conditions and times of year for the disease; (iii) breeding methods and strategies used for developing CLR-resistant cultivars; (iv) the levels, sources, and types of CLR resistance; (v) the development of Brazilian resistant cultivars; and (vi) chemical and cultural control methods. Most plantations are cultivated with susceptible cultivars, such as those of the Catuaí and Mundo Novo groups. Brazilian research institutes have developed dozens of cultivars with different levels of resistance, and significantly increased the planting of new resistant cultivars. The main sources of CLR resistance are genotypes from Híbrido de Timor, Icatu, BA series carrying the SH3 gene, and Ethiopian wild coffees. High CLR resistance is still observed in Sarchimor and SH3-carrying genotypes. Intermediate CLR resistance is observed in Ethiopian wild coffees and in Sarchimor and Icatu derivatives, where qualitative resistance has been supplanted by races of Hemileia vastatrix. Contact, mesostemic, and systemic fungicides are used for chemical control in Brazil. CLR incidence in Brazil begins to increase after the rainy season onset in November, reaches a peak in June, and remains high until August. Thus, chemical control is typically applied from December to April.

show abstract

Section: Frequency Of Fungicide Spraying In Brazilmentioning

confidence: 99%

Coffee Leaf Rust in Brazil: Historical Events, Current Situation, and Control Measures

Sera

Carvalho

Rezende³

et al. 2022

Agronomy

View full text Add to dashboard Cite

show abstract

“…The fungicide spray warning in the DSS 1 treatment was issued when two of the three formulas calculated a disease incidence of 5% or more in three consecutive days. These three formulas are the two formulas selected in phase 2 (Carmo do Rio Claro 15-30 DBRI and Nova Resende 15-30 DBRI models); a third one by Hinnah et al [34] was also incorporated. The notification methodology for DSS 2 remained the same as for phase 2.…”

Section: Phase 3: Expansion Of the Warning System With New Modelsmentioning

confidence: 99%

“…Therefore, to avoid a fixed spraying schedule and applications on dates unfavorable to rust or after infection and colonization of the pathogen, warning or forecast systems could be used [33]. According to Pinto et al [18] and Hinnah et al [34], using variables from the disease triangle, that is, the pathogen, the host, or the environment, the disease forecast systems can be used as a tool to contribute and guide crop disease management and the rational use of fungicides, and, in this way, reaching global demands to mitigate risks to the environment, in the context of green thinking. Therefore, environmental sustainability could be balanced with the economic and social needs of the agricultural production [35][36][37].…”

Section: Introductionmentioning

confidence: 99%

“…The main objectives of the disease forecast system are to optimize or increase efficiency of fungicide applications, decreasing production cost and the risk of economic losses caused by diseases and consequently increasing productivity [33,34,38,39]. The cost-benefit ratio is another criterion mentioned by Campbell and Madden [33] for early warning or forecast systems.…”

Section: Introductionmentioning

confidence: 99%

“…The variables used to build up forecasting systems in this new scenario can be selected from mathematical and statistical tools, besides the use of artificial intelligence, according to the characteristics of the pathosystem to which they are related. The variables selected by these methods, which belong to the disease triangle, that is, pathogen, environment and host [33], were used in several studies to build and validate disease prediction systems for coffee crops [34,[52][53][54].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Coffee Rust Forecast Systems: Development of a Warning Platform in a Minas Gerais State, Brazil

et al. 2021

View full text Add to dashboard Cite

This study aimed to develop a warning system platform for coffee rust incidence fifteen days in advance, as well as validating and regionalizing multiple linear regression models based on meteorological variables. The models developed by Pinto were validated in five counties. Experiments were set up in a randomized block design with five treatments and five replications. The experimental plot had six lines with 20 central plants of useful area. Assessments of coffee rust incidence were carried out fortnightly. The data collected from automatic stations were adjusted in new multiple linear regression models (MLRM) for five counties. Meteorological variables were lagged concerning disease assessment dates. After the adjustments, two models were selected and calculated for five counties, later there was an expansion to include ten more counties and 35 properties to validate these models. The result showed that the adjusted models of 15–30 days before rust incidence for Carmo do Rio Claro and Nova Resende counties were promising. These models were the best at forecasting disease 15 days in advance. With these models and the geoinformation systems, the warning platform and interface will be improved in the coffee grower region of the south and savannas of the Minas Gerais State, Brazil.

show abstract

Climate and disease: tackling coffee brown‐eye spot with advanced forecasting models

de Oliveira Aparecido,

de Lima,

Torsoni

et al. 2024

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUNDClimate significantly influences the interaction between pathogens and their hosts, and this is particularly evident in the coffee industry, where fungal diseases like Cercospora coffeicola, causing brown eye spot, can drastically reduce yields. Our study focuses on forecasting coffee brown eye spot using various models that incorporate agrometeorological data, allowing for predictions at least one week prior to disease occurrence. Data was gathered from eight locations across São Paulo and Minas Gerais, encompassing the South and Cerrado regions of Minas Gerais State. In the initial phase, various machine learning (ML) models and topologies were calibrated to forecast brown eye spot, identifying one with potential for advanced decision‐making. The top‐performing models were then employed in the next stage to forecast and spatially project the severity of brown eye spot across 2,681 key Brazilian coffee‐producing municipalities. Meteorological data were sourced from NASA's POWER platform, and the Penman‐Monteith method was used to estimate reference evapotranspiration, leading to a Thornthwaite and Mather (1955) water balance calculation. Six ML models — K‐Nearest Neighbors (KNN), Artificial Neural Network Multilayer Perceptron (MLP), Support Vector Machine (SVM), Random Forests (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting Regression (GradBOOSTING) — were employed, considering a 7‐day disease latency to define input variables.RESULTSThese models utilized climatic elements such as average air temperature, relative humidity, leaf wetness duration, rainfall, evapotranspiration, water deficit, and surplus. The XGBoost model proved most effective in high‐yielding conditions, demonstrating high precision and accuracy. Conversely, the SVM model excelled in low‐yielding scenarios. The incidence of brown eye spot varied noticeably between high and low‐yield conditions, with significant regional differences observed. The accuracy of predicting brown eye spot severity in coffee plantations depended on the biennial production cycle. High‐yielding trees showed superior results with the XGBoost model (R2 = 0.77, RMSE = 10.53), while under low‐yielding conditions, the Support Vector Machine (SVM) model performed better (precision 0.76, RMSE = 12.82).CONCLUSIONThe study's application of agrometeorological variables and ML models successfully predicted the incidence of brown eye spot in coffee plantations with a seven‐day lead time, illustrating a valuable tool for managing this significant agricultural challenge.This article is protected by copyright. All rights reserved.

show abstract

Performance of a weather-based forecast system for chemical control of coffee leaf rust

Cited by 11 publications

References 29 publications

Coffee Leaf Rust in Brazil: Historical Events, Current Situation, and Control Measures

Coffee Leaf Rust in Brazil: Historical Events, Current Situation, and Control Measures

Coffee Rust Forecast Systems: Development of a Warning Platform in a Minas Gerais State, Brazil

Climate and disease: tackling coffee brown‐eye spot with advanced forecasting models

Contact Info

Product

Resources

About