Climate risk zoning for wheat crops in the southeastern region of Brazil.

BACKGROUND: Wheat (Triticum aestivum L.) is the second most consumed food in the world. One way to meet this demand is the expansion of wheat cultivation to the Brazilian Cerrado in the southeastern region. However, one of the major limitations is that there are few studies related to wheat climate risk zoning. Thus, this study aimed to determine the agroclimatic zoning of wheat by estimating the water needs satisfaction index (ISNA) in the southeastern region of Brazil. For this purpose, a 60-year historical series of meteorological data was used to calculate the potential evapotranspiration, crop evapotranspiration, and climatological water balance values. To define the agroclimatic zones of wheat and sowing date, the ISNA method was used. The data were analyzed using descriptive statistics to determine the variations. To obtain the agroclimatic zoning of wheat, the geostatistical method of kriging interpolation was used. RESULTS: The regions with the highest rainfall are the south of Minas Gerais and the coast of São Paulo. The sowing period directly impacts the development of the crop, the available water capacity and the ISNA values indicated the spring and summer had better cultivation conditions, and the best window for wheat cultivation is concentrated in the fall due to the limitation of biotic factors. CONCLUSION: In terms of altitude (>700 m), Minas Gerais has 39.4% of the area suitable for wheat cultivation. Thus, climatic variations within and between the states of the southeastern region should be considered for the positioning of wheat cultivars in these regions to obtain the maximum yield. © 2023 Society of Chemical Industry.

Machine learning algorithms for soybean yield forecasting in the Brazilian Cerrado.

BACKGROUND: We evaluated different machine learning (ML) models for predicting soybean productivity up to 1 month in advance for the Matopiba agricultural frontier (States of Maranhão, Tocantins, Piauí, and Bahia). We collected meteorological data on the NASA-POWER platform and soybean yield on the SIDRA/IBGE base between 2008 and 2017. The ML models evaluated were random forest (RF), artificial neural networks, radial base support vector machines (SVM_RBF), linear model and polynomial regression. To assess the performance of the models, cross-validation was used, obtaining the value of precision by R2 , accuracy by root mean square error (RMSE), and trend by the mean error of the estimate (EME). RESULTS: The results showed that the RF algorithm achieves the highest precision and accuracy, with R2 of 0.81, RMSE of 176.93 kg ha-1 and trend (EME) of 1.99 kg ha-1 . On the other hand, the SVM_RBF algorithm showed the lowest performance, with R2 of 0.74, RMSE of 213.58 kg ha-1 and EME of -15.06 kg ha-1 . The average yield values predicted by the models were within the expected range for the region, which has a historical average value of 2.730 kg ha-1 . CONCLUSION: All models had acceptable precision, accuracy and trend indices, which makes it possible to use all algorithms to be applied in the prediction of soybean crop yield, observing the particularities of the region to be studied, in addition to being a useful tool for agricultural planning and decision making in soy-producing regions such as the Brazilian Cerrado. © 2021 Society of Chemical Industry.

Climate risk to peanut cultivation in Brazil across different planting seasons.

BACKGROUND: Peanuts are widely grown in Brazil because of their great importance in the domestic vegetable oil industry and the succession of sugarcane, soybean and maize crops, contributing to soil conservation and improvement in agricultural areas. Thus, the present study aimed to determine the zoning of peanuts' climatic risk by estimating the water requirement satisfaction index (WRSI) for the crop in Brazil. We used a historical series of data on average air temperature and rainfall between 1980 and 2016. Reference evapotranspiration was estimated using the method of Thornthwaite, and we subsequently calculated crop evapotranspiration and maximum evapotranspiration. Water balances for all stations were calculated using the method of Thornthwaite and Mather, with an available water capacity in the soil of 15, 30 and 45 mm. The definitions of suitable, unfit and restricted areas and the planting season were performed using the WRSI. RESULTS: Brazil has low climatic risk areas for growing peanuts throughout the year, except for winter. The country reveals that 88.19%, 97.93%, 99.16% and 39.25% of its area is suitable for planting peanuts on planting dates in spring, summer, autumn and winter, respectively. CONCLUSION: Brazil has a large part of the areas favorable to the planting of peanuts. The maximum availability of soil water at a depth of 15, 30 and 45 mm does not influence regions with respect to peanut growing in Brazil. The states of Piauí, Ceará and Bahia are the most unsuitable on the winter planting date, with an average WRSI of 0.22. © 2021 Society of Chemical Industry.

Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases.

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.

Agrometeorological models to forecast açaí (Euterpe oleracea Mart.) yield in the Eastern Amazon.

BACKGROUND: The increasing demand in Brazil and the world for products derived from the açaí palm (Euterpe oleracea Mart) has generated changes in its production process, principally due to the necessity of maintaining yield in situations of seasonality and climate fluctuation. The objective of this study was to estimate açaí fruit yield in irrigated system (IRRS) and rainfed system or unirrigated (RAINF) using agrometeorological models in response to climate conditions in the eastern Amazon. Modeling was done using multiple linear regression using the 'stepwise forward' method of variable selection. Monthly air temperature (T) values, solar radiation (SR), vapor pressure deficit (VPD), precipitation + irrigation (P + I), and potential evapotranspiration (PET) in six phenological phases were correlated with yield. The thermal necessity value was calculated through the sum of accumulated degree days (ADD) up to the formation of fruit bunch, as well as the time necessary for initial leaf development, using a base temperature of 10 °C. RESULTS: The most important meteorological variables were T, SR, and VPD for IRRS, and for RAINF water stress had the greatest effect. The accuracy of the agrometeorological models, using maximum values for mean absolute percent error (MAPE), was 0.01 in the IRRS and 1.12 in the RAINF. CONCLUSION: Using these models yield was predicted approximately 6 to 9 months before the harvest, in April, May, November, and December in the IRRS, and January, May, June, August, September, and November for the RAINF. © 2019 Society of Chemical Industry.

Climatic potential for summer and winter wine production.

BACKGROUND: The geoviticultural multicriteria climatic classification (MCC) system provides an efficient guide for assessing the influence of climate on wine varieties. Paraná is one of the three states in southern Brazil that has great potential for the expansion of wine production, mainly due to the conditions that favour two harvests a year. The objective was to apply the geoviticultural MCC system in two production seasons. We used maximum, mean and minimum air temperature and precipitation for 1990-2015 for the state of Paraná. Air temperature and Precipitation were used to calculate the evapotranspiration and water balance. We applied the MCC system to identify potential areas for grapevine production for harvests in both summer and winter and then determined the climatic zones for each geoviticultural climate. RESULTS: Paraná has viticultural climates with conditions favourable for grapevine cultivation for the production of fine wines from summer and winter harvests. The conditions for the winter harvest provided wines with good coloration and high aromatic potential relative to the summer harvest. CONCLUSION: Chardonnay, Merlot, Pinot Blanc and Müller-Thurgau were suitable for regions with lower air temperatures and water deficits. Pinot Blanc and Müller-Thurgau were typical for the southern region of Paraná. © 2017 Society of Chemical Industry.