Skip to main content
SpringerLink
Log in

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

  • Original Paper
  • Published:
International Journal of Biometeorology Aims and scope Submit manuscript

Abstract

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  • Androcioli HG, Hoshino AT, Menezes Júnior AO, Morais H, Bianco R (2018) Coffee leaf miner incidence and its predation bay wasp in coffee intercropped with rubber trees. Coffee Sci 13(3):389–400

    Google Scholar 

  • Aparecido LEO, Rolim GS (2018) Forecasting of the annual yield of Arabic coffee using water deficiency. Pesq Agropec Bras 53(12):1299–1310

    Google Scholar 

  • Avelino J; Cristancho M; Georgiou S; Imbach P; Aguilar L 2015 The coffee rust crises in Colombia and Central America (2008–2013): impacts, plausible causes and proposed solutions. : 303–321

  • Badnakhe MR, Durbha SS, Jagarlapudi A, Gade RM (2018) Evaluation of Citrus Gummosis disease dynamics and predictions with weather and inversion based leaf optical model. Comput Electron Agric 155:130–141

    Google Scholar 

  • Benali L, Notton G, Fouilloy A, Voyant C, Dizene R (2019) Solar radiation forecasting using artificial neural network and random forest methods: application to normal beam, horizontal diffuse and global components. Renew Energy 132(2019):871–884

    Google Scholar 

  • Botelho DMS, Resende MLV, Andrade VT, Pereira AA, Patricio FRA (2017) Cercosporiosis resistance in coffee germplasm collection. Euphytica 213(6). https://doi.org/10.1007/s10681-017-1901-9

  • Caixeta SL, Martinez HEP, Picanço MC, Cecon PR, Espoti MDD, Amaral JFT (2004) Leaf-miner attack in relation to nutrition and vigor of coffee-tree seedlings. Ciência Rural 34(5):1429–1435

    Google Scholar 

  • Campbell CL, Madden LV (1990) Introduction to plant disease epidemiology. John Wiley & Sons, New York

    Google Scholar 

  • Carvalho HP, Dourado Neto D, Teodoro REF, Melo B (2011) Climatological hydric balance, effective soil water storage and transpiration in coffee culture. Biosc J 27(2):221–229

    Google Scholar 

  • Carvalho-Junior WC, Calderano Filho B, Silva Chagas C, Bhering SB, Pereira NR, Pinheiro HSK (2016) Multiple linear regression and random Forest model to estimate soil bulk density in mountainous regions. Pesq Agrop Brasileira 51(9):1428–1437

    Google Scholar 

  • Chalfoun SM (1997) Doenças do cafeeiro: importância, identificação e métodos de controle, First. FAEPE, Lavras

    Google Scholar 

  • Chaves E, Pozza EA, Neto HS, Vasco GB, Dornelas GA (2018) Temporal analysis of brown eye spot of coffee and its response to the interaction of irrigation with phosphorous levels. J Phytopathol 166(9):613–622

    CAS  Google Scholar 

  • Conceição CHC, Guerreiro-Filho O, Gonçalves W (2005) Fluctuation of leaf miner population in resistant arabica coffee cultivars to leaf rust. Bragantia 64(4):625–631

    Google Scholar 

  • Cornell JA, Berger RD (1987) Factors that influence the coefficient of determination in single linear and nonlinear models. Phytopathology 77:63–70

    Google Scholar 

  • Correia FM, Mingoti SA, D'angelo JVH (2015) Predição do número kappa de um digestor contínuo de celulose kraft usando análise de regressão múltipla. Blucher Chem Eng Proc 1(2):11845–11852

    Google Scholar 

  • Creamer GG; Freund Y 2004 Predicting Performance and Quantifying Corporate Governance Risk for Latin American Adrs and Banks (November 1, 2004). FINANCIAL ENGINEERING AND APPLICATIONS, MIT, Cambridge

  • Damatta FM (2004) Ecophysiological constraints on the production of shaded and unshaded coffee: a review. Field Crop Res 86:99–114

    Google Scholar 

  • Das B, Nair B, Reddy VK, Venkatesh P (2018) Evaluation of multiple linear, neural network and penalised regression models for prediction of rice yield based on weather parameters for west coast of India. Int J Biometeorol 62(10):1809–1822. https://doi.org/10.1007/s00484-018-1583-6

    Article  Google Scholar 

  • Echandi E (1959) La chasparria de los cafetos causada por el hongo Cercospora coffeicola Berk & Cooke. Turrialba 9(2):54–67

    Google Scholar 

  • Fe V, Infante F, Castillo A, Jaramillo J (2009) The coffee berry borer, Hypothenemus hampei (Ferrari) (Coleoptera: Curculionidae): a short review, with recent findings and future research directions. Terrestrial Arthropod Reviews, 129-147. DOI: https://doi.org/10.1163/187498209X12525675906031

    Google Scholar 

  • Fernandes FL, Mantovani EC, Bonfim-Neto H, Numes VV (2009) Effects of irrigation, environmental variability and predatory wasp on Leucoptera coffeella (GuérinMéneville) (Lepidoptera: Lyonetiidae), in coffee plants. Neotropical Entomol 38(3):410–417

    Google Scholar 

  • Girolamo Neto CD, Rodrigues LHA, Meira CAA (2014) Warning models for coffee rust (Hemileia vastatrix Berkeley & Broome) by data mining techniques. Coffee Science:408–418

  • Gichimu BM 2013 Arabica coffee breeding: challenges posed by climate change. In: Proc. 10th AFCA Conference, Kampala, Uganda, 1–16

  • Harvey CA, Saborio-Rodríguez M, Martinez-Rodríguez MR, Viguera B, Chain-Guadarrama A (2018) Climate change impacts and adaptation among smallholder farmers in Central America. Agric Food Secur 7(1):1–20

    Google Scholar 

  • Hinnah FD, Sentelhas PC, Meira CAA, Paiva RN (2018) Weather-based coffee leaf rust apparent infection rate modeling. Int J Biometeorol 62(10):1847–1860. https://doi.org/10.1007/s00484-018-1587-2

    Article  Google Scholar 

  • Kushalappa AC, Akutsu M, Ludwig A (1983) Application of survival ratio for monocyclic process of Hemileia vastatrix in predicting coffee rust infection rates. Phytopathology 73:96. https://doi.org/10.1094/Phyto-73-96

    Article  Google Scholar 

  • Krige D (1951) A statistical approach to some basic mine valuation problems on the Witwatersrand. J Chem Metal Min Soc South Africa 52:119–139

    Google Scholar 

  • Kumar M; Thenmozhi M 2006."Forecasting stock index movement: A comparison of support vector machines and random forest." Indian institute of capital markets 9th capital markets conference paper.

  • Larivière B, Poel DVD 2004 “Predicting customer retention and profitability by using random forests and regression forests techniques”, working paper, Department of Marketing, Hoveniersberg 24, 9000, Gent

  • Laurentino E; Costa JNM 2004 Description and biological characterization of coffee borer (Hypothenemus hampei, Ferrari 1867) in Rondônia State. 1. ed. Porto Velho: Embrapa Rondônia. 21 p. (Embrapa Rondônia. Documentos, 90)

  • Li YH, Xu JY, Tao L, Li XF, Li S, Zeng X et al (2016) SVM-Prot 2016: a web-server for machine learning prediction of protein functional families from sequence irrespective of similarity. PloS one 11(8):e0155290

    Google Scholar 

  • Li C, Tao Y, Ao W, Yang S, Bai Y (2018) Improving forecasting accuracy of daily enterprise electricity consumption using a random forest based on ensemble empirical mode decomposition. Energy 165:1220–1227

    Google Scholar 

  • Lu J, Ehsani R, Shi Y, Abdulridha J, Castro AI (2017) Field detection of anthracnose crown rot in strawberry using spectroscopy technology. Comput Electron Agric 135:289–299. https://doi.org/10.1016/j.compag.2017.01.017

    Article  Google Scholar 

  • Machado JL, Silva RA, Souza JC, Figueiredo UJ, Carvalho TAF, Matos CSM (2014) Coffee pests: bioecology and integrated management. Inf Agropecuário Belo Horizonte 35(280):7–13

    Google Scholar 

  • Malau S, Lumbanraja P, Pandiangan S, Tarigan JR, Tindaon F (2018) Performance of Coffea arabica L In Changing Climate of North Sumatra of Indonesia. Sci Agric Bohem 49(4):340–349. https://doi.org/10.2478/sab-2018-0041

    Article  Google Scholar 

  • Marcari MA, Rolim GS, Aparecido LEO (2015) Agrometeorological models for forecasting yield and quality of sugarcane. Australian Journal of Crop Science. 9(11):1049–1056

    Google Scholar 

  • Meira CAA, Rodrigues LHA, Moraes AS (2008) Warning models for coffee rust control in growing areas with large fruit load. Pesq. Agropec. Bras. 44(3):233–242

    Google Scholar 

  • Morais H, Caramori P, Koguishi MS, Ribeiro AMA (2007) Caracterização microclimática de cafeeiros cultivados sob malha de sombreamento e a pleno sol. Revista Brasileira de Agrometeorologia, 133-142.

  • Moreto VB, Rolim GS (2015) Estimation of annual yield and quality of ‘Valencia orange’ related to monthly water deficiencies. Afr J Agric Res 10:543–553. https://doi.org/10.5897/AJAR2014.9090

    Article  Google Scholar 

  • Pereira CS, Guimaraes RJ, Pozza EA (2008) Controle da cercosporiose e da ferrugem do cafeeiro com extrato etanólico de própolis. Rev Ceres 55(5):369–376

    Google Scholar 

  • Pinto ACS, Pozza EA, Souza PE, Pozza AAA, Talamini V, Boldini JM, Santos FS (2002) Description of epidemics of coffee rust with neural networks. Fitopatol Bras 27:517–524

    Google Scholar 

  • Plata-Rueda A, Martínez LC, Costa NCR, Zanuncio JC, Sena-Fernandes ME (2019) Chlorantraniliprole–mediated effects on survival, walking abilities, and respiration in the coffee berry borer, Hypothenemus hampei. Ecotoxicol Environ Saf 172:53–58. https://doi.org/10.1016/j.ecoenv.2019.01.063

    Article  CAS  Google Scholar 

  • Reyes EIM, Farias ES, Silva EMP, Filomeno CA, Plata MAB (2019) Eucalyptus resinifera essential oils have fumigant and repellent action against Hypothenemus hampei. Crop Prot 116:49–55

    CAS  Google Scholar 

  • Rolim GS, Ribeiro RV, Azevedo FA, Camargo MBP, Machado E (2008) Predicion of fruits number from the quantity of reproductive structures of orange. Rev Bras Frutic 30(1):48–53

    Google Scholar 

  • Rowlandson T, Gleason M, Sentelhas PC (2015) Reconsidering leaf wetness duration determination for plant disease management. Plant Dis 99:310–319. https://doi.org/10.1094/PDIS-05-14-0529-FE

    Article  Google Scholar 

  • Sabino PHS, Reis-Júnior FA, Carvalho GA, Mantovani JR (2018) Nitrogen fertilizers and occurrence of Leucoptera coffeella (Guérin-Mèneville & Perrottet) in transplanted coffee seedlings. Coffee Sci 13(3):410–414

    Google Scholar 

  • Sahoo S, Ta R, Elliott J, Foster I (2017) Machine learning algorithms for modeling groundwater level changes in agricultural regions of the US. Water Resources Research 53(5):3878–3895

    Google Scholar 

  • Salgado BG, Macedo RLG, Carvalho VL, Salgado M, Venturin N (2007) Progress of rust and coffee plant cercosporiose mixed with grevílea, with ingazeiro and in the full sunshine in Lavras - MG. Ciênc Agrotec 31(4):1067–1074

    Google Scholar 

  • Santana MF, Zambolim EM, Caixeta ET, Zambolim L (2018) Population genetic structure of the coffee pathogen Hemileia vastatrix in Minas Gerais. Brazil. 43(5):473–476

    Google Scholar 

  • Sentelhas PC, Dalla-Marta A, Orlandini S (2008) Suitability of relative humidity as an estimator of leaf wetness duration. Agric For Meteorol 148:392–400. https://doi.org/10.1016/j.agrformet.2007.09.011

    Article  Google Scholar 

  • Shekoofa A, Emam Y, Shekoufa N, Ebrahimi M, Ebrahimie E (2014) Determining the most important physiological and agronomic traits contributing to maize grain yield through machine learning algorithms: a new avenue in intelligent agriculture. PloS one 9(5):e97288

    Google Scholar 

  • Silva MG, Pozza EA, Chaves E, Neto HS, Vasco GB (2019) Spatio-temporal aspects of brown eye spot and nutrients in irrigated coffee. Eur J Plant Pathol 153(3):931–946. https://doi.org/10.1007/s10658-018-01611-z

    Article  CAS  Google Scholar 

  • Souza VCO, Cunha RL, Andrade LN, Volpato MML, Carvalho VL, Esmin AAA (2013) Technical knowledge extraction applied to modeling of occurrence (cercospora coffeicola Berkeley & cooke) coffee in the southern region of Minas Gerais. Coffee Sci 8(1):91–100

    Google Scholar 

  • Spongoski S, Pr R, Ms Z (2005) Acarofauna of cerrado's coffee crops in Patrocínio. Minas Gerais. Ciência e Agrotecnologia, 9-17.

    Google Scholar 

  • Syvertsen JP, Garcia-Sanchez F (2014) Mutiple abiotic stresses occurring with salinity stress in citrus. Env Exp Bot 103:128–137

    CAS  Google Scholar 

  • Talamini V, Pozza EA, Souza PE, Silva AM (2003) Progresso da ferrugem e da cercosporiose em cafeeiro (Coffea arabica l.) Com diferentes épocas de início e parcelamentos da fertirrigação. Ciênc Agrotec 27(1):141–149

    Google Scholar 

  • Thornthwaite CW (1948) An approach towards a rational classification of climate. Geographical Review. 38:55–94

    Google Scholar 

  • Thornthwaite CW, Mather Jr (1955) The water balance. Centerton: Drexel Institute of Technology. 104 p. (Publications in Climatology, v. 8, n. 1).

  • Verhage FYF, Anten NPR, Sentelhas PC (2017) Carbon dioxide fertilization offsets negative impacts of climate change on Arabica coffee yield in Brazil. Clim Chang 144(4):671–685. https://doi.org/10.1007/s10584-017-2068-z

    Article  CAS  Google Scholar 

  • Walker HE, Lehman KA, Wall MM, Siderhurst M (2019) S analysis of volatile profiles of green Hawai’ian coffee beans damaged by the coffee berry borer (Hypothenemus hampei). J Sci Food Agric 99(4):1954–1960

    CAS  Google Scholar 

  • Wheeler DL, Scott J, Sung Dung JK, Johnson DA (2019) Evidence of a trans-kingdom plant disease complex between a fungus and plant-parasitic nematodes. PLoS One 14(2). https://doi.org/10.1371/journal.pone.0211508

    CAS  Google Scholar 

  • Zambolim L, Vale FXR, Pereira AA, Chaves GM (1997) Café (Cof ea arabica L.) controle de doenças. In: Vale FXR, do Zambolim L (eds) Plant Disease Control: Large Crops. Viçosa: UFV; Brasília, DF: Ministério da Agricultura e Abastecimento, vol 2, pp 83–179

    Google Scholar 

Download references

Funding

This research was supported by the São Paulo Research Foundation (FAPESP, 2015/17797-4).

Author information

Authors and Affiliations

  1. Science and Technology of Mato Grosso do Sul - Campus of Naviraí, IFMS - Federal Institute of Education, Naviraí,, Brazil

    Lucas Eduardo de Oliveira Aparecido, Jose Reinaldo da Silva Cabral De Moraes & Cicero Teixeira Silva Costa

  2. Department of Exact Sciences, State University of São Paulo-UNESP, Jaboticabal, Brazil

    Glauco de Souza Rolim

  3. Science and Technology of Sul of Minas - Campus of Muzambinho, IFSULDEMINAS - Federal Institute of Education, Muzambinho, Brazil

    Paulo Sergio de Souza

Authors
  1. Lucas Eduardo de Oliveira Aparecido
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Glauco de Souza Rolim
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jose Reinaldo da Silva Cabral De Moraes
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Cicero Teixeira Silva Costa
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Paulo Sergio de Souza
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lucas Eduardo de Oliveira Aparecido.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

de Oliveira Aparecido, L., de Souza Rolim, G., da Silva Cabral De Moraes, J.R. et al. Machine learning algorithms for forecasting the incidence of Coffea arabica pests and diseases. Int J Biometeorol 64, 671–688 (2020). https://doi.org/10.1007/s00484-019-01856-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00484-019-01856-1

Keywords

Search

Navigation