Search

Coffee production is significantly impacted by various diseases, predominantly those caused by fungi. One such notable disease in coffee crops is caused by the fungus Phoma spp. This pathogen leads to several symptoms detrimental to coffee plants, such as leaf lesions, drying of branches, and rotting of flowers and fruits. These symptoms often result in the dropping of the affected parts, subsequently leading to a decrease in the overall yield of the coffee crop. In response to this challenge, our objective was to develop a forecasting model for the incidence of Phoma leaf spot in Brazilian coffee crops, utilizing advanced machine learning algorithms. This approach is intended to predict disease outbreaks, thereby enabling timely and effective management strategies to mitigate the impact on coffee yield. The study was conducted in two stages: (1) calibration of machine learning models for locations (Boa Esperança, Carmo de Minas, Muzambinho, Varginha, Araxá, Araguari, and Patrocínio) with field data between 2010 and 2022; (2) Phoma leaf spot incidence forecast in municipalities of coffee-producing states in Brazil [Paraná (PR), São Paulo (SP), Rio de Janeiro (RJ), Espírito Santo (ES), Minas Gerais (MG), Goiás (GO), and Bahia (BA)]. Thirty-year climate data were retrieved from the NASA/POWER platform. Reference evapotranspiration was estimated by the Penman–Monteith method, generating water balance according to Thornthwaite and Mather (1955). To understand the effect of climate variables on the disease incidence, Pearson's univariate correlation was performed for each location. We used six algorithms to forecast the disease incidence, considering a 7-day latency period to define input variables. It is noteworthy that the evaluated locations present similar climatic conditions. Summer was the hottest and rainiest period, while winter was the coldest and driest. Annual averages of air temperature, cumulative rainfall, potential evapotranspiration, soil water storage, and incident radiation were 21.1 °C, 1208.9 mm, 1283.2 mm, 58.0 mm, 435.7 mm, and 18.1 MJ m2 day−1, respectively. The XGBoost model demonstrated superior performance for both high- and low-yield coffee trees, achieving an impressive precision (R2fit) of 0.46 and 0.51, respectively. Additionally, it exhibited high accuracy, with Root Mean Square Error (RMSE) values of 3.45% for high-yielding and 3.16% for low-yielding trees. In contrast, the multilayer perceptron (MLP) model displayed suboptimal results under both yield conditions. Given these findings, the XGBoost model proves effective in predicting the incidence of the disease at least 7 days ahead, based on the parameters applied in this study. [ABSTRACT FROM AUTHOR]

Brown eye spot (Cercospora coffeicola) is one of the main fungal diseases of coffee, leading to a significant drop in crop productivity and beverage quality in Brazil. The identification of potential risk areas for the development of the disease provides promising information for the management of the pathogen. This study aimed to elaborate an agroclimatic zoning for the incidence of brown eye spot on coffee under climate change scenarios, as suggested by IPCC (IPCC-AR5), in the main coffee-growing regions. Climate data of air temperature, precipitation, and relative humidity were collected from the National Aeronautics and Space Administration/Prediction of Worldwide Energy Resources (NASA/POWER) platform from 1989 to 2020 for 46 municipalities in the states of Paraná, São Paulo, Minas Gerais, Espírito Santo, Goiás, and Bahia. The ideal climate for brown eye spot occurrence consists of an air temperature (Tmean) between 18 and 30 °C, relative humidity (RHmean) > 90%, and leaf wetness duration (LWD) > 9 h. The number of hours of leaf wetness was determined by the sum of hours with relative humidity > 90%. Relative humidity was estimated for each hour of the day using air temperature and estimated data of mean dew point temperature, maximum relative humidity, and minimum relative humidity. Climate change scenarios were designed based on sets of climate simulations for the twenty-first century. Scenario S1 is the current scenario without changes, while scenarios S2 and S3 show Tmean + 1.5 °C and 3.0 °C, respectively, with RHmean without changes. Scenarios S4 and S5 present RHmean varying from − 30% to + 30%, respectively, with Tmean unchanged. In the current scenario (S1), Minas Gerais presented a predominance of 100% for low climate risk to brown eye spot in September. Paraná presented a medium risk in 76.15% of the state in April. Scenarios S2 and S3 showed significant changes, increasing the average fitness class in the study region, mainly in the states of São Paulo, Minas Gerais, Rio de Janeiro, and Paraná. Scenario S4 showed 100% predominance of the low-risk class. In contrast, S5 showed the occurrence of the high-risk class for the study region with a + 30% increase in relative humidity. Minas Gerais presented a predominance of the high-risk class for the development of C. coffeicola in 76%, 100%, 97.83%, 89.30%, 93.46%, 80.64%, and 57.77% from November to May, respectively. The presence of high relative humidity represents the main factor for the expansion of the high-risk class for the development of C. coffeicola. Producers knowing the months of the year and the places in Brazil with the highest incidence of brown eye spot will be able to prevent the disease in a more sustainable way, using more ecological products, such as the early application of copper. [ABSTRACT FROM AUTHOR]