Explore the vast range of titles available.

Disease and pest alert models are able to generate information for agrochemical applications only when needed, reducing costs and environmental impacts. With machine learning algorithms, it is possible to develop models to be used in disease and pest warning systems as a function of the weather in order to improve the efficiency of chemical control of pests of the coffee tree. Thus, we correlated the infection rates with the weather variables and also calibrated and tested machine learning algorithms to predict the incidence of coffee rust, cercospora, coffee miner, and coffee borer. We used weather and field data obtained from coffee plantations in production in the southern regions of the State of Minas Gerais (SOMG) and from the region of the Cerrado Mineiro; these crops did not receive phytosanitary treatments. The algorithms calibrated and tested for prediction were (a) Multiple linear regression (RLM); (b) K Neighbors Regressor (KNN); (c) Random Forest Regressor (RFT), and (d) Artificial Neural Networks (MLP). As dependent variables, we considered the monthly rates of coffee rust, cercospora, coffee miner, and coffee tree borer, and the weather elements were considered as independent (predictor) variables. Pearson correlation analyses were performed considering three different time periods, 1–10 d (from 1 to 10 days before the incidence evaluation), 11–20 d, and 21–30 d, and used to evaluate the unit correlations between the weather variables and infection rates of coffee diseases and pests. The models were calibrated in years of high and low yields, because the biannual variation of harvest yield of coffee beans influences the severity of the diseases. The models were compared by the Willmott’s ‘d’, RMSE (root mean square error), and coefficient of determination (R2) indices. The result of the more accurate algorithm was specialized for the SOMG and Cerrado Mineiro regions using the kriging method. The weather variables that showed significant correlations with coffee rust disease were maximum air temperature, number of days with relative humidity above 80%, and relative humidity. RFT was more accurate in the prediction of coffee rust, cercospora, coffee miner, and coffee borer using weather conditions. In the SOMG, RFT showed a greater accuracy in the predictions for the Cerrado Mineiro in years of high and low yields and for all diseases. In SOMG, the RMSE values ranged from 0.227 to 0.853 for high-yield and 0.147 and 0.827 for low-yield coffee in the coffee borer forecasting.

We developed models for simulating trends over time as functions of the thermal index and models for estimating the levels of infestation of the coffee leaf miner and coffee berry borer and the severity of disease for coffee leaf rust and cercospora, the main phytosanitary problems in coffee crops around the world. We used historical series of climatic data and levels of pest infestation and disease severity in Coffea arabica for high and low yields for seven locations in the two main coffee-producing regions in the state of Minas Gerais in Brazil, Sul de Minas Gerais and Cerrado Mineiro. We conducted two analyses: (a) we simulated the trends of the progress of diseases and pests over time using non-linear models. We only used the thermal index because air temperature is commonly measured by farmers in the regions. (b) We estimated the levels of pest infestation and disease severity using multiple linear regression, with the levels of diseases and pests as dependent variables and accumulated degree days (DD), coffee foliage (LF) estimated by DD and the number of nodes (NN) estimated by DD as independent variables. We used DD and LF = f (DD) and NN = f (DD) to predict diseases and pests with accuracy. MAPEs were 19.6, 5.7, 9.5, and 15.8% for rust, cercospora, leaf miner, and berry borer, respectively, for Sul de Minas Gerais. Establishing phytosanitary alerts using only air temperature was possible with these models.

The natural quality (NQ) of a coffee drink is defined as the one that is obtained in the year of bean production with the standard postharvest treatments of the region. The NQ varies with the climatic conditions during the crop cycle and with the drying period of beans in the sun. A well-formed bean can provide a good drink if well processed, but a bean grown during unfavourable environmental conditions will have poor quality regardless of the postharvest options. The goals of this study were to (1) increase our understanding of the relationship between meteorological elements (MEs) and NQ in coffee-producing regions, (2) identify the ranges of the MEs during the crop cycle that optimise quality, and (3) develop models to predict NQ based on the MEs. We used the two major regions of coffee production in the Brazilian state of Minas Gerais, the Cerrado Mineiro (CEMG), and the southern Minas Gerais (SOMG). We mapped the influences of ME on NQ successfully. Air temperature in November and December for SOMG and precipitation from November to January for CEMG were generally the most important MEs for NQ. Water deficiency, water storage, and rainfall became increasingly more important during winter (June to September) than during other seasons. The crop models were accurate, with errors < 7.9% for predicting NQ for all regions. These models used precipitation in June and December, the actual evapotranspiration in May, and the water deficit in April as the MEs for CEMG, and the rainfall in June and December, the water storage in April, and the actual evapotranspiration in May as the MEs for SOMG.

Climate directly and indirectly influences agriculture, being the main responsible for low and high yields. Prior knowledge on yield helps coffee farmers in their decision-making and planning for the future harvest, avoiding unnecessary costs and losses during the harvesting process. Thus, we sought to predict coffee yield with regressive models using meteorological data of the state of Paraná, Brazil. This study was carried out in 15 localities that produce Coffea arabica in this Brazilian state. The climate data were collected using the NASA/POWER platform from 1989 to 2020, while the data of arabica coffee yield (bags/ha) were obtained by CONAB from 2003 to 2018. The Penman–Monteith method was used to calculate the reference evapotranspiration and the climatological water balance (WB) was calculated based on Thornthwaite and Mather (1955). Multiple linear regression was used in the data modeling, in which C. arabica yield was the dependent variable and air temperature, precipitation, solar radiation, water deficit, water surplus, and soil water storage were the independent variables. The comparison between the estimation models and the actual data was performed using the statistical indices RMSE (accuracy) and adjusted coefficient of determination (R2adj) (precision). Multiple linear regression models can predict arabica coffee yield in the state of Paraná 2 to 3 months before harvest. The maximum air temperature is the climate element that most influences coffee plants, especially during fruit formation (March). Maximum air temperatures of 31.01 °C in March can reduce coffee production. Wenceslau Braz, Jacarezinho, and Ibaiti presented the highest yields, with mean values of 32.5, 29.9, and 29.3 bags ha−1, respectively. The models calibrated for localities that have Argisol had the highest mean accuracy, with an RMSE of 2.68 bags ha−1. The best models were calibrated for Paranavaí (Latosol), with an RMSE of 0.78 bags ha−1 and R2adj of 0.89, and Ibaiti (Argisol), with RMSE and R2adj values of 3.09 bags ha−1 and 0.83, respectively. Paranavaí has a mean difference between the actual and estimated coffee yield of only 0.86 bags ha−1. The highest deviations were observed in Wenceslau Braz (9.17 bags ha−1) and the lowest deviations were found in Paranavaí (0.86 bags ha−1). The models can be used to predict arabica coffee yield, assisting the planning of coffee farmers in the northern region of the state of Paraná.

Climate change is a major problem for humanity, as it can drastically alter the current climate scenario, affecting mainly agriculture. In the state of Mato Grosso do Sul (MS), agribusiness is the main economic activity representing a large part of the state’s GDP. Therefore, the aim of this study was to evaluate the influence of climate change on the climatological water balance in the Pantanal regions of Brazil. We used a 30-year historical series (1987–2018) of air temperature data (Tar, °C) and rainfall (P, mm) from the state of MS; climatic data were collected by the National Aeronautics and Space Administration platform/Prediction of World Wide Energy Resources - (NASA/POWER). Potential evapotranspiration (PET) was estimated using the Camargo (1971) method. The water balance (WB) was calculated using the Thornthwaite and Mather (1955) method, with soil water storage capacity equal to 100 mm. We calculated the aridity, hydric, and moisture indices for all municipalities in MS, and later classified according to Thornthwaite (1948). The scenarios used were based on the (IPCC 2014) projections. Air temperatures in the MS ranged from 22.5 to 27.6 °C in the current scenario; rainfall and PET have an average of 1400 mm annual−1 and 1188 mm annual−1, respectively. The WB of the state of MS has an EXC and DEF of 197.7 mm annual−1 and 64.2 mm annual−1, respectively. The predominant climatic type is C2 - subhumid. The highest values for SWS and EXC occur in scenarios S5, S10, S15, and S20, which are the most moisture scenarios. The highest DEF occurred in scenarios S1, S11, S16, and S21; these scenarios showed the driest climatic types. The northwestern region of the state, where the Pantanal is located, was the driest. In scenario S21, the climate of the state has a drastic change that makes several crops in the MS unfeasible, thus negatively influencing the fauna and flora of the Pantanal biome.

Cotton is the most widely consumed natural fiber globally and emits fewer greenhouse gases compared to synthetic alternatives. Brazil is currently the largest cotton exporter, and understanding its potential for sustainable expansion is crucial. This study developed agroclimatic zoning maps for cotton (Gossypium hirsutum L.) across Brazil under current and future climate conditions using data from the World-Clim and MapBiomas platforms. Four climate change scenarios (SSP1-2.6, SSP2-4.5, SSP3-7.0, SSP5-8.5) were assessed over multiple time periods. Results showed that rising temperatures and reduced rainfall will likely reduce cotton suitability in traditional producing regions such as Bahia. However, areas with potential for cotton cultivation, especially in Mato Grosso, which currently accounts for 90% of national production, remain extensive, with agroclimatic conditions indicating a theoretical expansion potential of up to 40 times the current cultivated area. This projection must be interpreted with caution, as it does not account for economic, logistical, or social constraints. Notably, Brazilian cotton is cultivated with minimal irrigation, low fertilizer input, and high adoption of no-till systems, making it one of the least carbon-intensive globally.

The study of climatic variables in large scales with surface meteorological stations is limited due to the low density of these stations in many regions, possible sources of errors related to missing data, and uncertainties about the calibration sensors. Global gridded data (GD) systems can minimize these problems. Thus, studies that validate GDs with “ground truth” are important for several applications such as climate change. The objective of this study was to compare long series of surface data with 10-day estimates of average air temperature (T) and precipitation (P) using data from the European Center for Medium-Range Weather Forecast (ECMWF) and the National Aeronautics and Space Administration (NASA) for important agricultural locations in the states of Minas Gerais and São Paulo in Brazil. Despite the different spatial resolutions between ECMWF and NASA, the purpose of this paper was to evaluate the two data sources as they are readily available. The GD performance was evaluated by linear regression analysis. Analyses were performed for each meteorological variable for entire years and separated by seasons. The estimates of T from both ECMWF and NASA systems were accurate with the minimum Willmott concordance index (d) and RMSEp of 0.86, 0.37 °C, respectively, and precision with R2 0.61. The estimates of P had a minimum R2, d, and RMSEp of 0.48, 0.79, 2.15 °C respectively. The decreasing orders of (R2) were autumn > winter > spring > summer for T and winter > autumn > spring > summer for P, varying from 0.93 to 0.61 for T and from 0.77 to 0.48 for P.

We evaluated the performance of general atmosphere circulation model (GCM) from the European Center for Medium Range Weather Forecasts (ECMWF) for estimating surface air temperature (T) and precipitation (P) in 55 locations in the Brazilian Amazon. We compared data from surface meteorological stations obtained by the Brazilian Institute of Meteorology (INMET) and ECMWF by linear regression analysis (LRA) using R2 and Willmott et al. (J Geophys Res C5:8995–9005,1985) index (d) as measurement of precision and accuracy, respectively. We applied the Fourier series analysis by extracting the trend and frequency components of P events with noise reduction in the time series. We used the multivariate K-means method to separate weather stations by Groups of Similar Performances (GSPs). The northwest region is characterized as the area with the highest precipitation supply but the lowest performances for T and P, with R2 lower than 0.18. ECMWF tend to overestimate P in dry season and to underestimate in rainy season. The proposed methodology of calibration of P data by the Fourier series was a good tool to predict an extreme event every 5 to 7 months in the region. ECMWF presented high performance (R2 > 0.60) when estimating P in a monthly scale and medium performance (R2 < 0.60) when estimating T in a monthly and 10-day period. The highest concentrations of surface meteorological stations in the eastern/southeastern portion of the Amazon region were decisive in the ECMWF performance expression, indicating an increased meteorological predictability in the anthropic areas, precisely where the agricultural areas of grain were established in the region.

Climate efficiency is an index that shows quantitative reduction related to production caused by the drought. Using climate efficiency in zoning agricolas sure is a vanguard in agrometeorology. Therefore, we aimed to simulate the climate efficiency for sugarcane production in Brazil and test its use in agricultural zoning. Mean annual air temperature, total annual precipitation, and climate efficiency were the climatic variables used to define suitable areas for sugarcane cultivation. Potential and actual yield was established using the agroecological zone method. Regions with mean annual temperatures between 28 and 38 °C, annual precipitations between 1000 and 1500 mm year −1 , and climate efficiency higher than 0.65 were considered climatically suitable for cultivation. The interpolation and crossing of information allowed obtaining the climatic aptitude zoning of sugarcane production for Brazil. Kriging was used as an interpolation method, using the spherical model, one neighbor, and a 0.25° resolution (27.75 km). The Brazilian states were divided into three major groups, according to sugarcane climate efficiency. The most favorable states for sugarcane production had a mean climate efficiency of 0.92. On the other hand, the states with the lowest climate efficiencies presented values of 0.59. Climatic aptitude zoning shows that 24.45% of the Brazilian territory is climatically suitable for sugarcane cultivation. Mato Grosso do Sul State has favorable climatic aptitude in 98% of its territory. The aptitude of productive losses due to climate efficiency is the lowest from January to April in Brazil. The Midwest and Northeast regions have the lowest climate efficiencies from June to September, thus requiring other alternatives, such as irrigation systems for crop maintenance. The use of climate efficiency to elaborate agricultural zoning allows determining with a high accuracy suitable areas for sugarcane cultivation.

Abstract Soybean cultivation plays an important role in Mato Grosso do Sul and around the world. Given the inherent complexity of the agricultural system, this study aimed to develop climate-based yield prediction models using ML, considering the most correlated meteorological variables for each condition, test the best model with independent data, and define zones of higher soybean yield in Mato Grosso do Sul to recommend better planting sites. The study was carried out in two stages. First, meteorological and soybean yield data obtained from 47 locations in the state of Mato Grosso do Sul were used to calibrate the machine learning (ML) algorithms. Second, the best algorithm was used to predict soybean yields throughout Mato Grosso do Sul. Daily meteorological data of air temperature (T, °C), precipitation (P, mm), global solar irradiance (Qg, MJ m−2 day−1), wind speed (u2, m s−1), net radiation (Rn, MJ m−2 day−1), and relative humidity (RH, %) of the NASA-POWER system from 2002 to 2021 were used. The reference evapotranspiration (ETo) by the standard FAO method and water balance (WB) by Thornthwaite and Mather (1955) were calculated for each collection point. The MLs used in this stage consisted of multiple linear regression (MLR), multilayer perceptron (MLP), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBOOSTING), and gradient boosted decision (GradBOOSTING). The ML models were calibrated using 70% of the data selected for training and 30% for validation. Algorithms were evaluated by accuracy, precision, and tendency. All analyses were performed using Python 3.8 software. Climate variables showed high spatial and seasonal variability throughout Mato Grosso do Sul (MS). Pearson’s univariate correlations between soybean yield and climate variables of the phenological period showed distinct relationships and different intensities. For instance, soil water storage (ARM) showed negative, neutral, and positive correlations in October, November, and December, respectively. The calibrated ML algorithms had a high precision and accuracy in both calibration and testing. For instance, the best model in the calibration was XGBOOSTING, which showed MAPE, R2, RMSE, MSE, and MAE values of 1.84%, 0.95, 2.06%, 4.24%, and 0.921%, respectively. Random forest (RF), extreme gradient boosting (XGBOOSTING), and gradient boosting (GradBOOSTING) were the most precise machine learning algorithms, with R2 values of 0.71, 0.62, and 0.62 in the test, respectively.