Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The data/material is opened.
Code availability
The software used was Python and scripts are available.
References
Adla S et al (2022) Analysing the impact of calibrating a low-cost soil moisture sensor on FAO Aquacrop model performance. [s.l.] display, 28 mar. Disponível em: <https://meetingorganizer.copernicus.org/EGU22/EGU22-11810.html>. Acesso em: 23 jul. 2022
Almeida IMG, Maciel KW, Beriam LOS, Rodrigues LMR, Destéfano SAL, Rodrigues Neto J, Patrício FRA (2012) Increase in incidence of bacterial halo blight (Pseudomonas syringae pv. garcae), in coffee producing areas in Brazil. In: INTERNATIONAL CONFERENCE ON COFFEE SCIENCE, 24., San José. Proceedings… San José: ASIC pp 1080-1084
Antico PL et al (2021) Foehn-like wind in the mountains of Southeastern Brazil as seen by the Eta model simulation. Revista Brasileira de Meteorologia 36(1):79–86
Barguil BM et al (2005) Effect of extracts from citric biomass, rusted coffee leaves and coffee berry husks on Phoma costarricencis of coffee plants. Fitopatol Bras 30:535–537
Bernard F et al (2013) The development of a foliar fungal pathogen does react to leaf temperature! New Phytol 198(1):232–240
Bravo C et al (2003) Early disease detection in wheat fields using spectral reflectance. Biosys Eng 84(2):137–145
Chalfoun N (1997) Design and application of natural down-draft evaporative cooling devices. Am Solar Energy Soc Inc
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. Anais
Coakley SM, Scherm H, Chakraborty S (1999) Climate change and plant disease management. Annu Rev Phytopathol 37(1):399–426
CorreiaFilho WLF et al (2022) The wind regime over the Brazilian Southeast: spatial and temporal characterization using multivariate analysis. Int J Climatol 42(3):1767–1788
Craparo ACW et al (2015) Coffea arabica yields decline in Tanzania due to climate change: global implications. Agric For Meteorol 207:1–10
Da Silva Júnior MB et al (2018) Foliar fertilizers for the management of phoma leaf spot on coffee seedlings. J Phytopathol 166(10):686–693
De Aparecido LEO, De Rolim GS (2018) Forecasting of the annual yield of Arabic coffee using water deficiency. Pesquisa Agropecuária Brasileira 53:1299–1310
De Mantaras RL, Armengol E (1998) Machine learning from examples: inductive and Lazy methods. Data Knowl Eng 25(1–2):99–123
De CarvalhoAlves M, Sanches L, De Carvalho LG (2022) Geostatistical surfaces of climatological normals of mean air temperature in Minas Gerais. Environ Monit Assess 194(7):1–21
De Resende MLV et al (2021) Strategies for coffee leaf rust management in organic crop systems. Agronomy 11(9):1865
DE Camargo MBP (2010) The impact of climatic variability and climate change on arabic coffee crop in Brazil. Bragantia 69(1):239–247
Delp CJ (1980) Coping with resistance to plant disease. Plant Dis 64:652–657
Esteves JT, De Souza Rolim G, Ferraudo AS (2019) Rainfall prediction methodology with binary multilayer perceptron neural networks. Clim Dyn 52(3–4):2319–2331
Gill HK, Garg H (2014) Pesticide: environmental impacts and management strategies. Pesticides-Toxic Aspects 8:187
Holdridge LR (1967) Life zone ecology. San José: Costa Rica: Tropical Science Center
Honorato J et al (2015) DMI and QoI fungicides for the control of coffee leaf rust. Australasian Plant Pathol 44(5):575–581
Huang M, Liu C, Ke K (2021) Calibration of cavity pressure simulation using autoencoder and multilayer perceptron neural networks. Polymer Eng Sci 61(10):2511–2521
Ighalo JO, Igwegbe CA, Adeniyi AG (2021) Multi-layer perceptron artificial neural network (MLP-ANN) prediction of biomass higher heating value (hhv) using combined biomass proximate and ultimate analysis data. Modeling Earth Systems and Environment 7(3):1–15
Jain A et al (2019) A review of plant leaf fungal diseases and its environment speciation. Bioengineered 10(1):409–424
Jayalakshmi K et al (2021) Important diseases of coffee (Coffee Arabica L.) and their management. Em: Diseases of Horticultural Crops. [s.l.] Apple Academic Press p 97–117
Jones S et al (2007) Baseline sensitivity of Australian Phoma ligulicola isolates from pyrethrum to azoxystrobin and difenoconazole. J Phytopathol 155(6):377–380
Juroszek P, Von Tiedemann A (2011) Potential strategies and future requirements for plant disease management under a changing climate. Plant Pathol 60(1):100–112
Kauserud H et al (2010) Climate change and spring-fruiting fungi. Proceed R Soc B: Biol Sci 277(1685):1169–1177
Krige DG (1951) A statistical approach to some basic mine valuation problems on the Witwatersrand. J South Afr Inst Min Metall 52(6):119–139
Li D-W, Kendrick B (1995) A year-round comparison of fungal spores in indoor and outdoor air. Mycologia 87(2):190–195
Lorenzetti ER et al (2015) Effect of temperature and leaf wetness on Phomatarda and Phoma leaf spot in coffee seedlings, Coffee Science, Lavras, 10(1):1–9
Lu J et al (2017) Field detection of anthracnose crown rot in strawberry using spectroscopy technology. Comput Electron Agric 135:289–299
Ma M et al (2021) XGBoost-based method for flash flood risk assessment. J Hydrol 598:126382
Mahmood I et al (2016) Effects of pesticides on environment. Em: Plant, soil and microbes. [s.l.] Springer p 253–269
Maneesha A, Suresh C, Kiranmayee BV (2021) Prediction of rice plant diseases based on soil and weather conditions. Proceedings of International Conference on Advances in Computer Engineering and Communication Systems. Anais...Springer
Mannaa M, Kim KD (2018) Effect of temperature and relative humidity on growth of Aspergillus and Penicillium spp. and biocontrol activity of Pseudomonas protegens AS15 against aflatoxigenic Aspergillus flavus in stored rice grains. Mycobiology 46(3):287–295
Mengistu AD, Alemayehu DM, Mengistu SG (2016) Ethiopian coffee plant diseases recognition based on imaging and machine learning techniques. Int J Database Theory Appl 9(4):79–88
Moon T, Park J, Son JE (2021) Prediction of the fruit development stage of sweet pepper (Capsicum annum var. annuum) by an ensemble model of convolutional and multilayer perceptron. Biosyst Eng 210:171–180
Nosratabadi S et al (2021) Prediction of food production using machine learning algorithms of multilayer perceptron and ANFIS. Agriculture 11(5):408, 2 maio
Orchi H, Sadik M, Khaldoun M (2021) On using artificial intelligence and the internet of things for crop disease detection: a contemporary survey. Agriculture 12(1):9
Panigrahi KP et al (2020) Maize leaf disease detection and classification using machine learning algorithms. Em: Das, H. et al. (Eds.). Progress in computing, analytics and networking. Advances in Intelligent Systems and Computing. Singapore: Springer Singapore 1119:659–669
Pezzopane JRM et al (2003) Escala para avaliação de estádios fenológicos do cafeeiro arábica. Bragantia 62(3):499–505
Pons D et al (2018) Climate variability and coffee productivity in Southern Guatemala. AGU Fall Meeting Abstracts v. 51, 1 dez
Rahman KA, Zhang D (2018) Effects of fertilizer broadcasting on the excessive use of inorganic fertilizers and environmental sustainability. Sustainability 10(3):759
Rodrigues LMR et al (2019) Multiple resistance to bacterial halo blight and bacterial leaf spot in Coffea spp. Scientific article, Plant Pathology, p 86
Salgado M et al (2003) Influência da temperatura e do tempo de incubação no crescimento micelial e produção de conídios in vitro de espécies de Phoma do cafeeiro
Seabra R et al (2016) Equatorial range limits of an intertidal ectotherm are more linked to water than air temperature. Global Change Biol 22(10):3320–3331
Shrivastava P, Kumar R (2015) Soil salinity: a serious environmental issue and plant growth promoting bacteria as one of the tools for its alleviation. Saudi J Biol Sci 22(2):123–131
Soulas G, Lagacherie B (2001) Modelling of microbial degradation of pesticides in soils. Biol Fertil Soils 33(6):551–557
Sparks AH (2018) nasapower: a NASA POWER global meteorology, surface solar energy and climatology data client for R. J Open Source Software 3(30):1035
Taugourdeau S et al (2014) Leaf area index as an indicator of ecosystem services and management practices: an application for coffee agroforestry. Agr Ecosyst Environ 192:19–37
Torres Castillo NE et al (2020) Impact of climate change and early development of coffee rust – an overview of control strategies to preserve organic cultivars in Mexico. Sci Total Environ 738:140225
Waller JM (1985) Control of coffee diseases. Em: Coffee. [s.l.] Springer, p 219–229
Wu W, Sun Q (2018) Applying machine learning to accelerate new materials development. Scientia Sinica Physica Mechanica Astronomica 48(10):107001
Zambolim L (1999) Encontro sobre produção de café com qualidade. Universidade Federal de Viçosa, Viçosa
Funding
This work was funded by the Fundação de Amparo à Pesquisa de Minas Gerais (FAPEMIG) – Process: APQ-00065–21, and Instituto Federal de Mato Grosso do Sul (IFMS), and Instituto Federal do Sul de Minas Gerais – Campus Muzambinho (IFSULDEMINAS).
Author information
Authors and Affiliations
Contributions
Lucas Eduardo de Oliveira Aparecido: conceptualization, methodology, supervision, project administration. Guilherme Botega Torsoni: formal analysis, investigation, data curation, writing review and editing, visualization. Pedro Antonio Lorençone: writing, review and editing. João Antonio Lorençone: writing, review and editing. Rafael Fausto de Lima: writing, review and editing. Felipe Padilha: writing, review and editing. Paulo Sergio de Souza: writing, review and editing. Glauco de Souza Rolim: writing, review and editing. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethics approval
It is not necessary.
Consent to participate
All authors approved.
Consent for publication
All authors approved.
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
de Oliveira Aparecido, L.E., Lorençone, P.A., Lorençone, J.A. et al. Addressing coffee crop diseases: forecasting Phoma leaf spot with machine learning. Theor Appl Climatol 155, 2261–2282 (2024). https://doi.org/10.1007/s00704-023-04739-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00704-023-04739-z