scholarly journals PREVISÃO DA PRODUTIVIDADE DO CAFÉ COM BASE EM DADOS AGROCLIMÁTICOS E APRENDIZAGEM DE MÁQUINA / FORECASTING COFFEE YIELD BASED ON AGROCLIMATIC DATA AND MACHINE LEARNING

Author(s):  
João Antonio Lorençone ◽  
Lucas Eduardo de Oliveira APARECIDO ◽  
Pedro Antonio LORENÇONE ◽  
José Reinaldo Da Silva Cabral de MORAES

Objetivou-se prever da produtividade do café com modelos regressivos usando dados meteorológicos em diferentes tipos de solo. O trabalho foi realizado em 15 localidades produtoras de C.arabica do Paraná. Os dados climáticos foram coletados por meio da plataforma NASA/POWER de 1989 e 2020 e os dados de produtividade do Coffea Arabica (sacas/ha) foram obtidos pela CONAB de 2003 a 2018. Para o calcula da evapotranspiração de referência (ETo) foi utilizado o método de Penman e Monteith, e o balanço hídrico climatológico (BH) de Thornthwaite e Mather (1955). Na modelagem dos dados, foi utilizado a regressão linear múltipla, em que a produtividade do C.arabica foi a variável dependente e as variáveis independentes foram temperatura do ar, precipitação, radiação solar, déficit hídrico, excedente hídrico e armazenamento de água no solo. Modelos de regressão linear múltipla são capazes de prever a produtividade do cafeeiro arábica no estado do Paraná com dois a três meses de antecedência a colheita. O elemento meteorológico que mais influencia o cafeeiro é a temperatura máxima do ar, principalmente durante a formação do fruto (março). Temperaturas máximas do ar em março de 31.01°C reduzem a produção do cafeeiro. Os modelos podem ser usados para previsão da produtividade do cafeeiro arábica auxiliando no planejamento dos cafeicultores da região do norte do Paraná.

Nematology ◽  
2017 ◽  
Vol 19 (5) ◽  
pp. 617-626 ◽  
Author(s):  
Ana Catarina J. Peres ◽  
Sonia M.L. Salgado ◽  
Valdir R. Correa ◽  
Marcilene F.A. Santos ◽  
Vanessa S. Mattos ◽  
...  

Root-knot nematodes negatively impact on coffee yield worldwide. The use of resistant cultivars is the most effective way to manage these pests. The goal of this study was to identify Coffea arabica genotypes with resistance to Meloidogyne paranaensis and M. incognita race 1. Eighteen C. arabica genotypes (EPAMIG’s Germplasm Bank), previously selected for poor host suitability in a M. paranaensis-infested field, plus a resistant and a susceptible standard, were inoculated with these two Meloidogyne species to determine their resistance using nematode reproduction factor (). Accessions for which were considered resistant, while those for which were considered moderately resistant or susceptible, also according to statistical analysis. Five accessions from crossing ‘Catuaí Vermelho’ × ‘Amphillo MR 2-161’, one from ‘Catuaí Vermelho’ × ‘Amphillo MR 2-474’, two from ‘Timor Hybrid (UFV 408-01)’ and the standard ‘IPR-100’ were resistant to M. incognita race 1 with . Four accessions from ‘Catuaí Vermelho’ × ‘Amphillo MR 2-161’, one from ‘Timor Hybrid (UFV 408-01)’, one from ‘Catuaí Vermelho’ × ‘Amphillo MR 2-474’ and the resistant standard ‘IPR100’ were resistant to M. paranaensis (). Field evaluations with parental genotypes showed that plants that originated from progenies ‘Catuaí Vermelho’ × ‘Amphillo MR 2-161’ were resistant to M. paranaensis and also gave a good yield compared to commercial cultivars, showing promising agronomic traits that can be used in breeding programmes to develop new cultivars of C. arabica.


2020 ◽  
Vol 7 (3) ◽  
pp. 223-229
Author(s):  
Afework Legesse

Coffee is an important source of annual income and employment contributing significantly to the economies of many developing countries. Ethiopia is the center of origin and diversity of Coffea arabica L., there is immense genetic variability that offers great potential for improvement of the crop. The objective of this paper is to assess the status of Coffee genetic diversity, identify major factors that cause coffee genetic erosion and status of coffee genetics resources management in Ethiopia.  The presences of high genetic diversity in wild Coffea arabica in Ethiopia were reported by different authors. However, the genetic diversity of coffea arabica L. are being lost rapidly due to several factors such as human population pressures leading to conversion of land to agriculture, deforestation and land degradation; low coffee prices leading to abandoning of coffee trees in forests and gardens and shifting cultivation to other more remunerative crops; and climate change. Additionally, narrow genetic basis of commercially used Arabica coffee cultivars and increased incidence of pests and diseases associated with climate change is leading to significant crop losses, threatening livelihoods in many coffee growing countries. Therefore, Conserving the wild Arabica coffee gene pool and its evolutionary potential present in Ethiopia is critically important for maintaining coffee yield, disease resistance, drought tolerant, quality and other important traits in future breeding program


PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0245298
Author(s):  
Weverton Gomes da Costa ◽  
Ivan de Paiva Barbosa ◽  
Jacqueline Enequio de Souza ◽  
Cosme Damião Cruz ◽  
Moysés Nascimento ◽  
...  

Several factors such as genotype, environment, and post-harvest processing can affect the responses of important traits in the coffee production chain. Determining the influence of these factors is of great relevance, as they can be indicators of the characteristics of the coffee produced. The most efficient models choice to be applied should take into account the variety of information and the particularities of each biological material. This study was developed to evaluate statistical and machine learning models that would better discriminate environments through multi-traits of coffee genotypes and identify the main agronomic and beverage quality traits responsible for the variation of the environments. For that, 31 morpho-agronomic and post-harvest traits were evaluated, from field experiments installed in three municipalities in the Matas de Minas region, in the State of Minas Gerais, Brazil. Two types of post-harvest processing were evaluated: natural and pulped. The apparent error rate was estimated for each method. The Multilayer Perceptron and Radial Basis Function networks were able to discriminate the coffee samples in multi-environment more efficiently than the other methods, identifying differences in multi-traits responses according to the production sites and type of post-harvest processing. The local factors did not present specific traits that favored the severity of diseases and differentiated vegetative vigor. Sensory traits acidity and fragrance/aroma score also made little contribution to the discrimination process, indicating that acidity and fragrance/aroma are characteristic of coffee produced and all coffee samples evaluated are of the special type in the Mata of Minas region. The main traits responsible for the differentiation of production sites are plant height, fruit size, and bean production. The sensory trait "Body" is the main one to discriminate the form of post-harvest processing.


2020 ◽  
Vol 64 (4) ◽  
pp. 671-688 ◽  
Author(s):  
Lucas Eduardo de Oliveira Aparecido ◽  
Glauco de Souza Rolim ◽  
Jose Reinaldo da Silva Cabral De Moraes ◽  
Cicero Teixeira Silva Costa ◽  
Paulo Sergio de Souza

2020 ◽  
Vol 43 ◽  
Author(s):  
Myrthe Faber

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.


2020 ◽  
Author(s):  
Mohammed J. Zaki ◽  
Wagner Meira, Jr
Keyword(s):  

2020 ◽  
Author(s):  
Marc Peter Deisenroth ◽  
A. Aldo Faisal ◽  
Cheng Soon Ong
Keyword(s):  

Author(s):  
Lorenza Saitta ◽  
Attilio Giordana ◽  
Antoine Cornuejols

Author(s):  
Shai Shalev-Shwartz ◽  
Shai Ben-David
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document