Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Adapted from Aparecido et al. (2018)
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
Abbaszadeh P, Gavahi K, Alipour A et al (2022) Bayesian multi-modeling of deep neural nets for probabilistic crop yield prediction. Agric for Meteorol 314:108773. https://doi.org/10.1016/j.agrformet.2021.108773
Abdelaziz A, Elhoseny M, Salama AS, Riad AM (2018) A machine learning model for improving healthcare services on cloud computing environment. Measurement 119:117–128. https://doi.org/10.1016/j.measurement.2018.01.022
Abrecht DG, Carberry P, s. (1993) The influence of water deficit prior to tassel initiation on maize growth, development and yield. Field Crop Res 31:55–69. https://doi.org/10.1016/0378-4290(93)90050-W
Aceves-Navarro LA, Rivera-Hernández B, Santillán-Fernández A, et al (2020) Impact of climatic change on the adaptation of coffee (Coffea arabica L.) crops in Tabasco, Mexico. Agroproductividad 13:53–58. https://doi.org/10.32854/agrop.vi.1618
Allen RG, Pereira LS, Raes D, Smith M (1998) Crop evapotranspiration-guidelines for computing crop water requirements-FAO irrigation and drainage paper 56. FAO, Rome 300:D05109
Almeida WL, Ávila RT, Pérez-Molina JP et al (2021) The interplay between irrigation and fruiting on branch growth and mortality, gas exchange and water relations of coffee trees. Tree Physiol 41:35–49. https://doi.org/10.1093/treephys/tpaa116
Alvares CA, Stape JL, Sentelhas PC, et al (2013) Köppen’s climate classification map for Brazil. metz 22:711–728. https://doi.org/10.1127/0941-2948/2013/0507
Barbosa A, Trevisan R, Hovakimyan N, Martin NF (2020) Modeling yield response to crop management using convolutional neural networks. Comput Electron Agric 170:105197. https://doi.org/10.1016/j.compag.2019.105197
Bortolotto RP, Bruno IP, Dourado-Neto D et al (2011) Soil profile internal drainage for a central pivot fertigated coffee crop. Revista Ceres 58:723–728. https://doi.org/10.1590/S0034-737X2011000600007
Brown JN, Hochman Z, Holzworth D, Horan H (2018) Seasonal climate forecasts provide more definitive and accurate crop yield predictions. Agric for Meteorol 260–261:247–254. https://doi.org/10.1016/j.agrformet.2018.06.001
Cai Y, Guan K, Lobell D et al (2019) Integrating satellite and climate data to predict wheat yield in Australia using machine learning approaches. Agric for Meteorol 274:144–159. https://doi.org/10.1016/j.agrformet.2019.03.010
Camargo ÂPD, Camargo MBPD (2001) Definição e esquematização das fases fenológicas do cafeeiro arábica nas condições tropicais do Brasil. Bragantia 60:65–68. https://doi.org/10.1590/S0006-87052001000100008
Camargo MBPD, Ortolani AA, Pedro Júnior MJ, Rosa SM (1999) Modelo agrometeorológico de estimativa de produtividade para o cultivar de laranja Valência. Bragantia 58:171–178. https://doi.org/10.1590/S0006-87051999000100016
Camargo MBP de (2010) The impact of climatic variability and climate change on Arabic coffee crop in Brazil. Bragantia 69:239–247. https://doi.org/10.1590/S0006-87052010000100030
Camargo A de (1977) Zoneamento de aptidão climática para a cafeicultura de arábica e robusta no Brasil. Fundação IBGE, Recursos, meio ambiente e poluição 68–76
Carr MKV (2001) The water relations and irrigation requirements of coffee. Ex Agric 37:1–36. https://doi.org/10.1017/S0014479701001090
Carvalho CF, Carvalho SM, Souza B (2019) Coffee. In: Souza B, Vázquez LL, Marucci RC (eds) Natural enemies of insect pests in Neotropical agroecosystems. Springer International Publishing, Cham, pp 277–291
Chiputwa B, Blundo-Canto G, Steward P et al (2022) Co-production, uptake of weather and climate services, and welfare impacts on farmers in Senegal: a panel data approach. Agric Syst 195:103309. https://doi.org/10.1016/j.agsy.2021.103309
CONAB CNDAC (2019) Acompanhamento da safra brasileira: café
Cornell JA, Berger RD (1987) Factors that influence the coefficient of determination in single linear and nonlinear models. Phytopathology 77:63–70
Crisosto CH, Grantz DA, Meinzer FC (1992) Effects of water deficit on flower opening in coffee (Coffea arabica L.). Tree Physiol 10:127–139. https://doi.org/10.1093/treephys/10.2.127
da Rosa VGC, Moreira MA, Rudorff BFT, Adami M (2010) Estimativa da produtividade de café com base em um modelo agrometeorológico-espectral. Pesq Agropec Bras 45:1478–1488. https://doi.org/10.1590/S0100-204X2010001200020
da Tavares P, S, Giarolla A, Chou SC, et al (2018) Climate change impact on the potential yield of Arabica coffee in southeast Brazil. Reg Environ Change 18:873–883. https://doi.org/10.1007/s10113-017-1236-z
DaMatta FM, Ramalho JDC (2006) Impacts of drought and temperature stress on coffee physiology and production: a review. Braz J Plant Physiol 18:55–81. https://doi.org/10.1590/S1677-04202006000100006
DaMatta FM, Avila RT, Cardoso AA et al (2018) Physiological and agronomic performance of the coffee crop in the context of climate change and global warming: a review. J Agric Food Chem 66:5264–5274. https://doi.org/10.1021/acs.jafc.7b04537
de Monteiro JEB, A, Assad ED, Sentelhas PC, Azevedo L da C, (2017) Modeling of corn yield in Brazil as a function of meteorological conditions and technological level. Pesq Agropec Bras 52:137–148. https://doi.org/10.1590/s0100-204x2017000300001
de Sousa P, Nery JT (2002) Análise da variabilidade anual e interanual da precipitação pluviométrica da região de Manuel Ribas, Estado do Paraná. Acta Scientiarum Technology 24:1707–1713. https://doi.org/10.4025/actascitechnol.v24i0.2513
de Aparecido LE, O, Rolim G de S, Richetti J, et al (2016) Köppen, Thornthwaite and Camargo climate classifications for climatic zoning in the State of Paraná, Brazil. Ciência e Agrotecnologia 40:405–417. https://doi.org/10.1590/1413-70542016404003916
de Aparecido LE, O, Rolim G de S, Lamparelli RAC, et al (2017) Agrometeorological models for forecasting coffee yield. Agron J 109:249–258. https://doi.org/10.2134/agronj2016.03.0166
de Camargo MBP, Brunini O, de Miranda MAC (1986) Modelo agrometeorológico para estimativa da produtividade para a cultura da soja no Estado de São Paulo. Bragantia 45:279–292. https://doi.org/10.1590/S0006-87051986000200007
Doorenbos J, Kassam AH (1979) Yield response to water.
Duarte YCN, Sentelhas PC (2020) Intercomparison and performance of maize crop models and their ensemble for yield simulations in Brazil. Int J Plant Prod 14:127–139. https://doi.org/10.1007/s42106-019-00073-5
FAO F and AO (2020) FAOSTAT online database. http://faostat.fao.org/
Da Gama TCP, Sales Junior JC, Castanheira DT, et al (2017) Anatomia foliar, fisiologia e produtividade de cafeeiros em diferentes níveis de adubação. CSci 12:42. https://doi.org/10.25186/cs.v12i1.1195
Guleryuz D (2022) Estimation of soil temperatures with machine learning algorithms—Giresun and Bayburt stations in Turkey. Theor Appl Climatol 147:109–125. https://doi.org/10.1007/s00704-021-03819-2
Hajjar R, Newton P, Adshead D et al (2019) Scaling up sustainability in commodity agriculture: transferability of governance mechanisms across the coffee and cattle sectors in Brazil. J Clean Prod 206:124–132. https://doi.org/10.1016/j.jclepro.2018.09.102
Hameed A, Hussain SA, Suleria HAR (2020) “Coffee bean-related” agroecological factors affecting the coffee. In: Mérillon J-M, Ramawat KG (eds) Co-evolution of secondary metabolites. Springer International Publishing, Cham, pp 641–705
Hernandez-Espinoza LH, Barrios-Masias FH (2020) Physiological and anatomical changes in tomato roots in response to low water stress. Sci Hortic 265:109208. https://doi.org/10.1016/j.scienta.2020.109208
IBGE IBDGEE (2020) Sistema IBGE de Recuperação Automática - SIDRA: Produção Agrícola Municipal. In: Sistema IBGE de Recuperação Automática. https://sidra.ibge.gov.br/pesquisa/ppm/quadros/brasil/2020. Accessed 28 Jan 2021
ICO (2021) International Coffee Organization - historical data on the global coffee trade. http://www.ico.org/new_historical.asp. Accessed 18 Aug 2021
Iizumi T, Shin Y, Kim W et al (2018) Global crop yield forecasting using seasonal climate information from a multi-model ensemble. Climate Services 11:13–23. https://doi.org/10.1016/j.cliser.2018.06.003
Jayakumar M, Rajavel M, Surendran U (2016) Climate-based statistical regression models for crop yield forecasting of coffee in humid tropical Kerala, India. Int J Biometeorol 60:1943–1952. https://doi.org/10.1007/s00484-016-1181-4
Jerszurki D, de Souza JLM (2013) Parametrização das equações de Hargreaves & Samani e Angströn-Prescott para estimativa da radiação solar na região de Telêmaco Borba, estado do Paraná. Ciência Rural 43:383–389. https://doi.org/10.1590/S0103-84782013005000004
Kogan F, Kussul N, Adamenko T et al (2013) Winter wheat yield forecasting in Ukraine based on Earth observation, meteorological data and biophysical models. Int J Appl Earth Obs Geoinf 23:192–203. https://doi.org/10.1016/j.jag.2013.01.002
Krige DG (1951) A statistical approach to some basic mine valuation problems on the Witwatersrand. J South Afr Inst Min Metall 52:119–139
Läderach P, Ramirez-Villegas J, Navarro-Racines C et al (2017) Climate change adaptation of coffee production in space and time. Clim Change 141:47–62. https://doi.org/10.1007/s10584-016-1788-9
Lee JH, Shin J, Realff MJ (2018) Machine learning: overview of the recent progresses and implications for the process systems engineering field. Comput Chem Eng 114:111–121. https://doi.org/10.1016/j.compchemeng.2017.10.008
Liakos K, Busato P, Moshou D et al (2018) Machine learning in agriculture: a review. Sensors 18:2674. https://doi.org/10.3390/s18082674
Martins MA, Tomasella J, Rodriguez DA et al (2018) Improving drought management in the Brazilian semiarid through crop forecasting. Agric Syst 160:21–30. https://doi.org/10.1016/j.agsy.2017.11.002
Merle I, Tixier P, de Virginio Filho E, M, et al (2020) Forecast models of coffee leaf rust symptoms and signs based on identified microclimatic combinations in coffee-based agroforestry systems in Costa Rica. Crop Prot 130:105046. https://doi.org/10.1016/j.cropro.2019.105046
Meshram V, Patil K (2022) FruitNet: Indian fruits image dataset with quality for machine learning applications. Data Brief 40:107686. https://doi.org/10.1016/j.dib.2021.107686
Mesquita CM de, REZENDE J de, Carvalho J, et al (2016) Manual do café: distúrbios fisiológicos, pragas e doenças do cafeeiro (Coffea arabica L.). Belo Horizonte: EMATER-MG 22–42
Minuzzi RB, Caramori PH, Borrozino E (2011) Trends in annual and seasonal climate variability of the minimum and maximum air temperatures in the State of Paraná, Brazil. Bragantia 70:471–479. https://doi.org/10.1590/S0006-87052011000200031
Monteiro LA, Sentelhas PC (2017) Sugarcane yield gap: can it be determined at national level with a simple agrometeorological model? Crop Pasture Sci 68:272. https://doi.org/10.1071/CP16334
Moreto VB, Rolim GDS (2015) Agrometeorological models for groundnut crop yield forecasting in the Jaboticabal, São Paulo State region. Brazil Acta Sci Agron 37:403. https://doi.org/10.4025/actasciagron.v37i4.19766
Muharam FM, Ruslan SA, Zulkafli SL et al (2017) Remote sensing derivation of land surface temperature for insect pest monitoring. Asian J of Plant Sciences 16:160–171. https://doi.org/10.3923/ajps.2017.160.171
Nery JT, Roseghini WFF, Martins MDLOF (2001) CARACTERIZAÇÃO DA PRECIPITAÇÃO NA REGIÃO NOROESTE DO ESTADO DO PARANÁ. Boletim De Geografia 19:99–114. https://doi.org/10.4025/bolgeogr.v19i1.12055
Nolasco M, Ovando G, Sayago S et al (2021) Estimating soybean yield using time series of anomalies in vegetation indices from MODIS. Int J Remote Sens 42:405–421. https://doi.org/10.1080/01431161.2020.1809736
Pagani V, Stella T, Guarneri T et al (2017) Forecasting sugarcane yields using agro-climatic indicators and Canegro model: a case study in the main production region in Brazil. Agric Syst 154:45–52. https://doi.org/10.1016/j.agsy.2017.03.002
Portugal I, Alencar P, Cowan D (2018) The use of machine learning algorithms in recommender systems: a systematic review. Expert Syst Appl 97:205–227. https://doi.org/10.1016/j.eswa.2017.12.020
Rapoport HF, Hammami SBM, Martins P et al (2012) Influence of water deficits at different times during olive tree inflorescence and flower development. Environ Exp Bot 77:227–233. https://doi.org/10.1016/j.envexpbot.2011.11.021
Rena A, Barros R (2004) Aspectos críticos no estudo da floração do café. Efeitos da irrigação sobre a qualidade e produtividade do café 149–172
Ribeiro W, Gonçalves M, Pinheiro A et al (2018) Limitation of relative transpiration and growth of Arabic coffee in response to water deficit. JEAI 24:1–12. https://doi.org/10.9734/JEAI/2018/41818
Rodrigues WP, Silva JR, Ferreira LS, et al (2018) Stomatal and photochemical limitations of photosynthesis in coffee (Coffea spp.) plants subjected to elevated temperatures. Crop Pasture Sci 69:317. https://doi.org/10.1071/CP17044
Sambasivam G, Opiyo GD (2021) A predictive machine learning application in agriculture: cassava disease detection and classification with imbalanced dataset using convolutional neural networks. Egyptian Informatics Journal 22:27–34
Sampaio SC, Queiroz MMF de, Frigo EP, et al (2007) ESTIMATIVA E DISTRIBUIÇÃO DE PRECIPITAÇÕES DECENDIAIS PARA O ESTADO DO PARANÁ. IRRIGA 12:38–53. https://doi.org/10.15809/irriga.2007v12n1p38-53
Sanches RG, Santos BC, Neves GZ, et al (2019) Influence of climate variability on sugarcane production in the São Carlos/Sp microregion in the period 1994 to 2014. Revista Brasileira de Climatologia, 25:
Santinato R, Fernandes A (2012) Cultivo do cafeeiro irrigado por gotejamento. Uberaba: Autores, 388p
Serra E (2018) Cooperativas do café do Norte do Paraná: trajetória e evolução. RCT 13:89–111. https://doi.org/10.14393/RCT132904
Sessa Fialho G, Paulúcio da Silva D, Fialho Dos Reis E et al (2010) COMPORTAMENTO DE PLANTAS DE CAFÉ ARÁBICA SUBMETIDAS A DÉFICIT HÍDRICO DURANTE O DESENVOLVIMENTO INICIAL. Idesia (arica) 28:35–39. https://doi.org/10.4067/S0718-34292010000300005
Silva WL, Dereczynski C, Chang M et al (2015) Observed trends in climate extreme indicators of temperature and precipitation in the state of Paraná. Revista Brasileira De Meteorologia 30:181–194. https://doi.org/10.1590/0102-778620130622
Smith G (2018) Step away from stepwise. J Big Data 5:32. https://doi.org/10.1186/s40537-018-0143-6
Sneath PH, Sokal RR (1973) Numerical taxonomy. The principles and practice of numerical classification.
Stackhouse PW, Westberg D, Hoell JM, et al (2015) Prediction of worldwide energy resource (POWER)-agroclimatology methodology-(1.0 latitude by 1.0 longitude spatial resolution). Prediction of worldwide energy resource (POWER)-agroclimatology methodology-(1.0 latitude by 1.0 longitude spatial resolution).
Taiz L, Zeiger E, Moller I, Murphy A (2017) Physiology and plant development, 6th edn. Artmed, Porto Alegre
Thornthwaite C, Mather J (1955) The water balance publications in climatology, 8 (1). DIT, Laboratory of climatology, Centerton, NJ, USA
Volsi B, Telles TS, Caldarelli CE, da Camara MRG (2019) The dynamics of coffee production in Brazil. PLoS ONE 14:e0219742. https://doi.org/10.1371/journal.pone.0219742
Wagner S, Jassogne L, Price E, et al (2021) Impact of climate change on the production of Coffea arabica at Mt. Kilimanjaro, Tanzania. Agriculture 11:53. https://doi.org/10.3390/agriculture11010053
Wang X, Zhang J, Ali M et al (2016) Impact of climate change on regional irrigation water demand in Baojixia irrigation district of China. Mitig Adapt Strateg Glob Change 21:233–247. https://doi.org/10.1007/s11027-014-9594-z
Ward JH (1963) Hierarchical grouping to optimize an objective function. J Am Stat Assoc 58:236–244. https://doi.org/10.1080/01621459.1963.10500845
WTO WTO (2020) Statistics on merchandise trade. In: World Trade Organization. timeseries.wto.org/. Accessed 28 May 2020
Yamashita T, Wakata Y, Nakaguma H et al (2022) Machine learning for classification of postoperative patient status using standardized medical data. Comput Methods Programs Biomed 214:106583. https://doi.org/10.1016/j.cmpb.2021.106583
Zaro GC, da Ricce W, S, Caramori PH, et al (2014) Zoneamento agroclimático para a cultura do abacateiro no Estado do Paraná. Rev Bras Frutic 36:363–372. https://doi.org/10.1590/0100-2945-286/13
Zayed A, Abdelwareth A, Mohamed TA et al (2022) Dissecting coffee seeds metabolome in context of genotype, roasting degree, and blending in the Middle East using NMR and GC/MS techniques. Food Chem 373:131452. https://doi.org/10.1016/j.foodchem.2021.131452
Funding
This study was funded by IFMS Campus of Naviraí and IFSULDEMINAS Campus Muzambinho.
Author information
Authors and Affiliations
Contributions
Lucas Eduardo de Oliveira Aparecido: formal analysis, writing—original draft, writing—review and editing, investigation, conceptualization, methodology, supervision, project administration; João Antonio Lorençone: writing—review and editing; Pedro Antonio Lorençone: writing—review and editing; Guilherme Botega Torsoni: writing—review and editing; Rafael Fausto Lima: writing—review and editing; José Reinaldo da Silva Cabral de Moraes: writing—review and editing.
Corresponding author
Ethics declarations
Ethics approval.
Not applicable.
Consent to participate.
Not applicable.
Consent for publication.
Not applicable.
Conflict of interest
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
About this article
Cite this article
de Oliveira Aparecido, L.E., Lorençone, J.A., Lorençone, P.A. et al. Predicting coffee yield based on agroclimatic data and machine learning. Theor Appl Climatol 148, 899–914 (2022). https://doi.org/10.1007/s00704-022-03983-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00704-022-03983-z