Estimating Coffee Plant Yield Based on Multispectral Images and Machine Learning Models
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Area
2.2. Coffe Yield Data Collection
2.3. Multispectral Data Collection
2.4. Multispectral Data Processing
2.5. Remote Sensing Data Extraction and Calculation of Vegetation Indices
2.6. Descriptive and Exploratory Yield Analysis
2.7. Generation of Prediction Models and Quality Control
2.8. Analysis of Multispectral Model Accuracy in Predicting Yield
3. Results
3.1. Characterization of the Study Area: Exploratory Analysis of Yield Data
3.2. Statistical Analysis of the Agronomic Parameters
3.3. Analysis of the Correlation between Yield and Multispectral Bands and Their Derived Indices
3.4. Analysis of the Performance of Predictive and Forecast Models
3.5. Time-Space Distribution of Yield
4. Discussion
5. Study Limitations and Future Perspectives
6. Conclusions
- The Sentinel 2 satellite images were favorable in estimating coffee yield. Despite their low spatial resolution in estimating agricultural variables below the canopy, specific bands such as the red edge, mid-infrared and derived vegetation indices act as a countermeasure to this limitation.
- The blue band and GNDVI vegetation index showed the highest correlation with yield, but the low accuracy exhibited by the spectral models demonstrated the need to predict yield from non-parametrized algorithms. Additionally, other indices that also displayed significant correlations (CI_G and MCARI) indicate that leaf pigmentation and biomass remain a reasonable method to estimate coffee yield.
- After a data mining process, the NN algorithm exhibited the highest and lowest trend in predicting and forecasting yield.
- The high coefficients of determination showed the capacity of the spectral model to accurately estimate the spatial distribution of high and low-yield areas.
- The yield distribution maps demonstrated the sensitivity of spectral models to the biotic and abiotic factors present in the crop.
Author Contributions
Funding
Conflicts of Interest
References
- Coltri, P.P.; Pinto, H.S.; do Valle Gonçalves, R.R.; Junior, J.Z.; Dubreuil, V. Low levels of shade and climate change adaptation of Arabica coffee in southeastern Brazil. Heliyon 2019, 5, e01263. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Volsi, B.; Telles, T.S.; Caldarelli, C.E.; Camara, M.R.G.D. The dynamics of coffee production in Brazil. PLoS ONE 2019, 14, e0219742. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Silva, E.M.; Furtado, T.D.R.; Fernandes, J.G.; Cirillo, M.Â.; Muniz, J.A. Leaf count overdispersion in coffee seedlings. Rural Sci. 2019, 49. [Google Scholar] [CrossRef] [Green Version]
- Almeida, L.F.; Spers, E.E. (Eds.) Coffee Consumption and Industry Strategies in Brazil: A Volume in the Consumer Science and Strategic Marketing Series; Woodhead Publishing: Sawston, UK, 2019. [Google Scholar]
- Martinez, C.L.M.; Saari, J.; Melo, Y.; Cardoso, M.; de Almeida, G.M.; Vakkilainen, E. Evaluation of thermochemical routes for the valorization of solid coffee residues to produce biofuels: A Brazilian case. Renew. Sustain. Energy Rev. 2021, 137, 110585. [Google Scholar] [CrossRef]
- Embrapa. The Vision-of-the-Future of Brazilian Agriculture. Available online: https://www.embrapa.br/documents/10180/9543845/The+vision+of+the+future+of+Brazilian+Agro.pdf/4271ad06-20ac-ee4a-ddbe-fe20d928c3b3 (accessed on 1 July 2022).
- Chemura, A.; Mutanga, O.; Dube, T. Remote sensing leaf water stress in coffee (Coffea arabica) using secondary effects of water absorption and random forests. Phys. Chem. Earth Parts A/B/C 2017, 100, 317–324. [Google Scholar] [CrossRef]
- Durand-Bessart, C.; Tixier, P.; Quinteros, A.; Andreotti, F.; Rapidel, B.; Tauvel, C.; Allinne, C. Analysis of interactions amongst shade trees, coffee foliar diseases and coffee yield in multistrata agroforestry systems. Crop Prot. 2020, 133, 105137. [Google Scholar] [CrossRef]
- Gokavi, N.; Mote, K.; Jayakumar, M.; Raghuramulu, Y.; Surendran, U. The effect of modified pruning and planting systems on growth, yield, labour use efficiency and economics of Arabica coffee. Sci. Hortic. 2021, 276, 109764. [Google Scholar] [CrossRef]
- Mohammed, A.; Jambo, A. Importance and characterization of coffee berry disease (Colletotrichum kahawae) in Borena and Guji Zones, Southern Ethiopia. J. Plant Pathol. Microbiol. 2015, 6, 6–9. [Google Scholar] [CrossRef]
- Rodrigues, L.M.R.; Queiroz-Voltan, R.B.; Guerreiro, O. Anatomical changes on coffee leaves infected by Pseudomonas syringae pv. garcae. Summa Phytopathol. 2015, 41, 256–261. [Google Scholar] [CrossRef] [Green Version]
- Avelino, J.; Allinne, C.; Cerda, R.; Willocquet, L.; Savary, S. Multiple-disease system in coffee: From crop loss assessment to sustainable management. Annu. Rev. Phytopathol. 2018, 56, 611–635. [Google Scholar] [CrossRef]
- Le, K.D.; Perrine-Walker, F.; Stirling, G.R.; Guest, D.I.; Trinh, P.Q. Pathogenicity of migratory endoparasitic nematodes on coffee seedlings (Coffea arabica cv. K7) in Australia. Australas. Plant Pathol. 2021, 50, 341–348. [Google Scholar] [CrossRef]
- Nogueira, S.; Moreira, M.A.; Volpato, M.M. Relationship between coffee crop productivity and vegetation indexes derived from oli/landsat-8 sensor data with and without topographic correction. Agric. Eng. 2018, 38, 387–394. [Google Scholar] [CrossRef]
- Kouadio, L.; Byrareddy, V.M.; Sawadogo, A.; Newlands, N.K. Probabilistic yield forecasting of robusta coffee at the farm scale using agroclimatic and remote sensing derived indices. Agric. For. Meteorol. 2021, 306, 108449. [Google Scholar] [CrossRef]
- Arab, S.T.; Noguchi, R.; Matsushita, S.; Ahamed, T. Prediction of grape yields from time-series vegetation indices using satellite remote sensing and a machine-learning approach. Remote Sens. Appl. Soc. Environ. 2021, 22, 100485. [Google Scholar] [CrossRef]
- Islam, M.M.; Matsushita, S.; Noguchi, R.; Ahamed, T. Development of remote sensing-based yield prediction models at the maturity stage of boro rice using parametric and nonparametric approaches. Remote Sens. Appl. Soc. Environ. 2021, 22, 100494. [Google Scholar] [CrossRef]
- Picoli, M.C.A.; Rudorff, B.F.T.; Rizzi, R.; Giarolla, A. Vegetation index of the Modis sensor in the estimation of agricultural productivity of sugarcane. Bragantia 2009, 68, 789–795. [Google Scholar] [CrossRef] [Green Version]
- Johann, J.A.; Rocha, J.V.; Duft, D.G.; Lamparelli, R.A.C. Estimation of areas with summer crops in Paraná, through EVI/Modis multitemporal images. Braz. Agric. Res. 2012, 47, 1295–1306. [Google Scholar] [CrossRef] [Green Version]
- Almeida, T.S.; Sediyama, G.C.; de Alencar, L.P. Yield estimation of coffee trees irrigated by the spectral agroecological zone method. Eng. Agric. Mag. REVENG 2017, 25, 1–11. [Google Scholar] [CrossRef] [Green Version]
- Cerda, R.; Avelino, J.; Gary, C.; Tixier, P.; Lechevallier, E.; Allinne, C. Primary and secondary yield losses caused by pests and diseases: Assessment and modeling in coffee. PLoS ONE 2017, 12, e0169133. [Google Scholar] [CrossRef] [Green Version]
- Andrade, V.T.; Gonçalves, F.; Nunes, J.A.R.; Botelho, C.E. Statistical modeling implications for coffee progenies selection. Euphytica 2016, 207, 177–189. [Google Scholar] [CrossRef]
- Vieira Júnior, I.C.; Pereira da Silva, C.; Nuvunga, J.J.; Botelho, C.E.; Avelar Gonçalves, F.M.; Balestre, M. Mixture mixed models: Biennial growth as a latent variable in coffee bean progenies. Crop Sci. 2019, 59, 1424–1441. [Google Scholar] [CrossRef]
- Fanelli Carvalho, H.; Galli, G.; Ventorim Ferrão, L.F.; Vieira Almeida Nonato, J.; Padilha, L.; Perez Maluf, M.; Ribeiro de Resende, M.F., Jr.; Guerreiro Filho, O.; Fritsche-Neto, R. The effect of bienniality on genomic prediction of yield in arabica coffee. Euphytica 2020, 216, 101. [Google Scholar] [CrossRef]
- Treboux, J.; Genoud, D. Improved machine learning methodology for high precision agriculture. In Proceedings of the Global Internet of Things Summit (GIoTS), Bilbao, Spain, 4–7 June 2018; pp. 1–6. [Google Scholar] [CrossRef]
- Mekonnen, Y.; Namuduri, S.; Burton, L.; Sarwat, A.; Bhansali, S. Machine learning techniques in wireless sensor network based precision agriculture. J. Electrochem. Soc. 2019, 167, 037522. [Google Scholar] [CrossRef]
- Chlingaryan, A.; Sukkarieh, S.; Whelan, B. Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review. Comput. Electron. Agric. 2018, 151, 61–69. [Google Scholar] [CrossRef]
- Khanal, S.; Klopfenstein, A.; Kushal, K.C.; Ramarao, V.; Fulton, J.; Douridas, N.; Shearer, S.A. Assessing the impact of agricultural field traffic on corn grain yield using remote sensing and machine learning. Soil Tillage Res. 2021, 208, 104880. [Google Scholar] [CrossRef]
- Khanal, S.; Fulton, J.; Shearer, S. An overview of current and potential applications of thermal remote sensing in precision agriculture. Comput. Electron. Agric. 2017, 139, 22–32. [Google Scholar] [CrossRef]
- Jessen, J.R. Introductory Digital Image Processing: A Remote Sensing Perspective; Pearson: London, UK, 2015. [Google Scholar]
- Birth, G.S.; McVey, G.R. Measuring the color of growing turf with a reflectance spectrophotometer 1. Agron. J. 1968, 60, 640–643. [Google Scholar] [CrossRef]
- Rouse, J.W.; Haas, R.H.; Schell, J.A.; Deering, D.W. Monitoring vegetation systems in the Great Plains with ERTS. NASA Spec. Publ. 1974, 351, 309–317. [Google Scholar]
- Gitelson, A.A.; Kaufman, Y.J.; Merzlyak, M.N. Use of a green channel in remote sensing of global vegetation from EOS-MODIS. Remote Sens. Environ. 1996, 58, 289–298. [Google Scholar] [CrossRef]
- Gitelson, A.A.; Gritz, Y.; Merzlyak, M.N. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. J. Plant Physiol. 2003, 160, 271–282. [Google Scholar] [CrossRef]
- Daughtry, C.S.; Walthall, C.L.; Kim, M.S.; De Colstoun, E.B.; McMurtrey Iii, J.E. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sens. Environ. 2000, 74, 229–239. [Google Scholar] [CrossRef]
- Haboudane, D.; Miller, J.R.; Tremblay, N.; Zarco-Tejada, P.J.; Dextraze, L. Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture. Remote Sens. Environ. 2002, 81, 416–426. [Google Scholar] [CrossRef]
- Jordan, C.F. Derivation of leaf-area index from quality of light on the forest floor. Ecology 1969, 50, 663–666. [Google Scholar] [CrossRef]
- Huete, A.R. A soil-adjusted vegetation index (SAVI). Remote Sens. Environ. 1988, 25, 295–309. [Google Scholar] [CrossRef]
- Vincini, M.; Frazzi, E.R.M.E.S.; D’Alessio, P.A.O.L.O. A broad-band leaf chlorophyll vegetation index at the canopy scale. Precis. Agric. 2008, 9, 303–319. [Google Scholar] [CrossRef]
- Leroux, L.; Falconnier, G.N.; Diouf, A.A.; Ndao, B.; Gbodjo, J.E.; Tall, L.; Balde, A.A.; Clermont-Dauphin, C.; Bégué, A.; Affholder, F.; et al. Using remote sensing to assess the effect of trees on millet yield in complex parklands of Central Senegal. Agric. Syst. 2020, 184, 102918. [Google Scholar] [CrossRef]
- Paul, G.C.; Saha, S.; Hembram, T.K. Application of phenology-based algorithm and linear regression model for estimating rice cultivated areas and yield using remote sensing data in Bansloi River Basin, Eastern India. Remote Sens. Appl. Soc. Environ. 2020, 19, 100367. [Google Scholar] [CrossRef]
- Oliveira, M.F.; dos Santos, A.F.; Kazama, E.H.; de Souza Rolim, G.; da Silva, R.P. Determination of application volume for coffee plantations using artificial neural networks and remote sensing. Comput. Electron. Agric. 2021, 184, 106096. [Google Scholar] [CrossRef]
- De Oliveira Pires, M.S.; de Carvalho Alves, M.; Pozza, E.A. Multispectral radiometric characterization of coffee rust epidemic in different irrigation management systems. International J. Appl. Earth Obs. Geoinf. 2020, 86, 102016. [Google Scholar] [CrossRef]
- Chemura, A.; Mutanga, O.; Odindi, J.; Kutywayo, D. Mapping spatial variability of foliar nitrogen in coffee (Coffea arabica L.) plantations with multispectral Sentinel-2 MSI data. ISPRS J. Photogramm. Remote Sens. 2018, 138, 1–11. [Google Scholar] [CrossRef]
- Martins, G.D.; Galo, M.D.L.B.T.; Vieira, B.S. Detecting and mapping root-knot nematode infection in coffee crop using remote sensing measurements. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017, 10, 5395–5403. [Google Scholar] [CrossRef] [Green Version]
- Hunt, D.A.; Tabor, K.; Hewson, J.H.; Wood, M.A.; Reymondin, L.; Koenig, K.; Schmitt-Harsh, M.; Follett, F. Review of Remote Sensing Methods to Map Coffee Production Systems. Remote Sens. 2020, 12, 2041. [Google Scholar] [CrossRef]
- Coltri, P.P.; Zullo, J.; do Valle Goncalves, R.R.; Romani, L.A.S.; Pinto, H.S. Coffee crop’s biomass and carbon stock estimation with usage of high resolution satellites images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2013, 6, 1786–1795. [Google Scholar] [CrossRef]
- Alves, M.C.; Sanches, L.; Pozza, E.A.; Pozza, A.A.; da Silva, F.M. The role of machine learning on Arabica coffee crop yield based on remote sensing and mineral nutrition monitoring. Biosyst. Eng. 2022, 221, 81–104. [Google Scholar] [CrossRef]
Index | Equation | RMSE |
---|---|---|
NDRE | [31] | |
NDVI | [32] | |
GNDVI | [33] | |
CI-RE | [34] | |
MCARI | [35] | |
TCARI | [36] | |
RVI | [37] | |
SAVI | [38] | |
CVI | [39] | |
CI-G | [34] |
Yield | Minimum | Q1 | Median | Q3 | Maximum | CV% |
---|---|---|---|---|---|---|
2017 | 95.4 | 169.2 | 265.2 | 445.2 | 802.2 | 91.5% |
2018 | 3.900 | 4.830 | 5.454 | 6148.8 | 7319.4 | 90.2 |
2019 | 78.9 | 472.8 | 1003.2 | 1852.2 | 2672.4 | 92.3 |
Parameters | Means | Standard Deviations | CV (%) |
---|---|---|---|
Yield | 42.98 | 39.17 | 91.14 |
173.53 | 53.46 | 30.81 | |
345.20 | 72.42 | 20.98 | |
303.56 | 130.21 | 42.89 | |
688.40 | 146.90 | 21.35 | |
2078.00 | 119.10 | 5.73 | |
2811.60 | 140.90 | 5.01 | |
2766.90 | 127.90 | 4.62 | |
3035.50 | 157.10 | 5.18 | |
1561.70 | 288.10 | 18.45 | |
822.70 | 264.00 | 32.09 |
Band/Index | Correlation | Coefficient of Determination |
---|---|---|
0.72 | 53.00 | |
0.65 | 43.00 | |
MCARI | 0.55 | 29.30 |
0.50 | 24.60 | |
0.46 | 24.60 | |
0.41 | 13.80 | |
0.40 | 12.80 | |
0.33 | 10.50 | |
0.16 | 2.10 | |
0.06 | 0.00 | |
0.05 | 0.00 | |
SAVI | −0.34 | 10.70 |
NDVI | −0.34 | 10.70 |
RVI | −0.37 | 13.20 |
TCARI | −0.45 | 20.00 |
NDRE | −0.48 | 22.70 |
CI_RE | −0.49 | 23.40 |
CVI | −0.52 | 26.60 |
CI_G | −0.60 | 35.90 |
GNDVI | −0.62 | 38.30 |
P.S. | RF | SVM | LR | NN | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
RMSE% | MAPE% | R² | RMSE% | MAPE% | R² | RMSE% | MAPE% | R² | RMSE% | MAPE% | R² | |
Test 80% | 27 | 23 | 0.81 | 37 | 33 | 0.75 | 39 | 34 | 0.68 | 27 | 23 | 0.81 |
Test 85% | 27 | 23 | 0.81 | 35 | 30 | 0.75 | 38 | 32 | 0.67 | 23 | 20 | 0.82 |
Test 90% | 28 | 24 | 0.80 | 36 | 31 | 0.75 | 39 | 39 | 0.68 | 36 | 27 | 0.75 |
Y.P. 2020 | 32 | 38 | 41 | 27 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Abreu Júnior, C.A.M.d.; Martins, G.D.; Xavier, L.C.M.; Vieira, B.S.; Gallis, R.B.d.A.; Fraga Junior, E.F.; Martins, R.S.; Paes, A.P.B.; Mendonça, R.C.P.; Lima, J.V.d.N. Estimating Coffee Plant Yield Based on Multispectral Images and Machine Learning Models. Agronomy 2022, 12, 3195. https://doi.org/10.3390/agronomy12123195
Abreu Júnior CAMd, Martins GD, Xavier LCM, Vieira BS, Gallis RBdA, Fraga Junior EF, Martins RS, Paes APB, Mendonça RCP, Lima JVdN. Estimating Coffee Plant Yield Based on Multispectral Images and Machine Learning Models. Agronomy. 2022; 12(12):3195. https://doi.org/10.3390/agronomy12123195
Chicago/Turabian StyleAbreu Júnior, Carlos Alberto Matias de, George Deroco Martins, Laura Cristina Moura Xavier, Bruno Sérgio Vieira, Rodrigo Bezerra de Araújo Gallis, Eusimio Felisbino Fraga Junior, Rafaela Souza Martins, Alice Pedro Bom Paes, Rafael Cordeiro Pereira Mendonça, and João Victor do Nascimento Lima. 2022. "Estimating Coffee Plant Yield Based on Multispectral Images and Machine Learning Models" Agronomy 12, no. 12: 3195. https://doi.org/10.3390/agronomy12123195
APA StyleAbreu Júnior, C. A. M. d., Martins, G. D., Xavier, L. C. M., Vieira, B. S., Gallis, R. B. d. A., Fraga Junior, E. F., Martins, R. S., Paes, A. P. B., Mendonça, R. C. P., & Lima, J. V. d. N. (2022). Estimating Coffee Plant Yield Based on Multispectral Images and Machine Learning Models. Agronomy, 12(12), 3195. https://doi.org/10.3390/agronomy12123195