Skip to main content
SpringerLink
Log in

Separability of coffee leaf rust infection levels with machine learning methods at Sentinel-2 MSI spectral resolutions

  • Published:
Precision Agriculture Aims and scope Submit manuscript

Abstract

Coffee leaf rust (CLR) caused by the fungus Hemileia vastarix is a devastating disease in almost all coffee producing countries and remote sensing approaches have the potential to monitor the disease. This study evaluated the potential of Sentinel-2 band settings for discriminating CLR infection levels at leaf levels. Field spectra were resampled to the band settings of the Sentinel-2, and evaluated using the random forest (RF) and partial least squares discriminant analysis (PLS-DA) algorithms with and without variable optimization. Using all variables, Sentinel-2 Multispectral Imager (MSI)-derived vegetation indices achieved higher overall accuracy of 76.2% when compared to 69.8% obtained using raw spectral bands. Using the RF out-of-bag (OOB) scores, 4 spectral bands and 7 vegetation indices were identified as important variables in CLR discrimination. Using the PLS-DA Variable Importance in Projection (VIP) score, 3 Sentinel-2 spectral bands (B4, B6 and B5) and 5 vegetation indices were found to be important variables. Use of the identified variables improved the CLR discrimination accuracies to 79.4 and 82.5% for spectral bands and indices respectively when discriminated with the RF. Discrimination accuracy slightly increased through variable optimization for PLS-DA using spectral bands (63.5%) and vegetation indices (71.4%). Overall, this study showed the potential of the Sentinel 2 MSI band settings for CLR discrimination as part of crop condition assessment. Nevertheless further studies are required under field conditions.

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

Similar content being viewed by others

References

  • Avelino, J., Romero-Gurdián, A., Cruz-Cuellar, H. F., & Declerck, F. A. (2012). Landscape context and scale differentially impact coffee leaf rust, coffee berry borer, and coffee root-knot nematodes. Ecological Applications, 22(2), 584–596.

    Article  PubMed  Google Scholar 

  • Avelino, J., Willocquet, L., & Savary, S. (2004). Effects of crop management patterns on coffee rust epidemics. Plant Pathology, 53(5), 541–547.

    Article  Google Scholar 

  • Baker, P., Bentley, J., Charveriat, C., Dugne, H., Leftoy, T., & Munyua, H. (2001). The Coffee Smallholder. In P. Baker (Ed.), Coffee Futures: A source book of some critical issues confronting the coffee industries. Chinchina: Cabi-Federacafe-USDA-ICO.

    Google Scholar 

  • Barbedo, J. G. A. (2013). Digital image processing techniques for detecting, quantifying and classifying plant diseases. Spinger Plus, 2(660), 1–12.

    Google Scholar 

  • Baret, F., & Buis, S. (2008). Estimating canopy characteristics from remote sensing observations: Review of methods and associated problems. In S. Liang (Ed.), Advances in land remote sensing: System, modeling, inversion and application (pp. 173–201). Amsterdam, The Netherlands: Springer.

    Chapter  Google Scholar 

  • Baret, F., & Guyot, G. (1991). Potentials and limits of vegetation indices for LAI and APAR assessment. Remote Sensing of Environment, 35, 161–173.

    Article  Google Scholar 

  • Barnes, E. M., Clarke, T. R., Richards, S. E., Colaizzi, P. D., Haberland, J., Kostrzewski, M., et al. (2000). Coincident detection of crop water stress, nitrogen status and canopy density using ground based multispectral data. In: P. C. Robert, R. H. Rust, W. E. Larson (Eds.) Proceedings of the 5th international conference on precision agriculture (pp 16–19). Madison, USA: American Society of Agronomy

  • Belan, L. L., Pozza, E. A., de Oliveira Freitas, M. L., Pozza, A. A. A., de Abreu, M. S., & Alves, E. (2015). Nutrients distribution in diseased coffee leaf tissue. Australasian Plant Pathology, 44(1), 105–111.

    Article  CAS  Google Scholar 

  • Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.

    Article  Google Scholar 

  • Breiman, L., & Cutler, A. (2007). Random forests-classification description. Berkeley, USA: Department of Statistics.

    Google Scholar 

  • Brown, H. B. (2008). Smallholder coffee production in Zimbabwe. Harare, Zimbabwe: CRS Press.

    Google Scholar 

  • Brown, J. K. M., & Hovmøller, M. S. (2002). Aerial dispersal of pathogens on the global and continental scales and its impact on plant disease. Science, 297, 537–541.

    Article  CAS  PubMed  Google Scholar 

  • Cao, K.-A. L., Gonzalez, I., & Dejean, S. (2015). Package ‘mixOmics’. Retrieved 1 December, 2016 from http://www.mixOmics.org.

  • Carter, G. A., & Knapp, A. K. (2001). Leaf optical properties in higher plants: linking spectral characteristics to stress and chlorophyll concentration. American Journal of Botany, 88(4), 677–684.

    Article  CAS  PubMed  Google Scholar 

  • Chemura, A., Kutywayo, D., Chidoko, P., & Mahoya, C. (2015). Bioclimatic modelling of current and projected climatic suitability of coffee (Coffea arabica) production in Zimbabwe. Regional Environmental Change, 16(2), 473–485.

    Article  Google Scholar 

  • Chemura, A. & Mutanga, O. (2016). Developing detailed age-specific thematic maps for coffee (Coffea arabica L.) in heterogeneous agricultural landscapes using random forests applied on Landsat 8 multispectral sensor. Geocarto International, 1–18 (inpress).

  • Clevers, J. G. P. W., & Gitelson, A. A. (2013). Remote estimation of crop and grass chlorophyll and nitrogen content using red-edge bands on Sentinel-2 and -3. International Journal of Applied Earth Observation and Geoinformation, 23, 344–351.

    Article  Google Scholar 

  • Coops, N., Stanford, M., Old, K., Dudzinski, M., Culvenor, D., & Stone, C. (2003). Assessment of Dothistroma needle blight of Pinus radiata using airborne hyperspectral imagery. Phytopathology, 93(12), 1524–1532.

    Article  CAS  PubMed  Google Scholar 

  • Cressey, D. (2013). Coffee rust regains foothold. Nature, 493, 587.

    Article  CAS  PubMed  Google Scholar 

  • D’Odorico, P., Gonsamo, A., Damm, A., & Schaepman, M. E. (2013). Experimental evaluation of Sentinel-2 spectral response functions for NDVI time-series continuity. IEEE Transactions of GeoScience & Remote Sensing, 51(3), 1336–1348.

    Article  Google Scholar 

  • Dangwal, N., Patel, N., Kumari, M., & Saha, S. (2016). Monitoring of water stress in wheat using multispectral indices derived from Landsat-TM. Geocarto International, 31(6), 682–693.

    Article  Google Scholar 

  • de Almeida, M. R., Correa, D. N., Rocha, W. F. C., Scafi, F. J. O., & Poppi, R. J. (2013). Discrimination between authentic and counterfeit banknotes using Raman spectroscopy and PLS-DA with uncertainty estimation. Microchemical Journal, 109, 170–177.

    Article  Google Scholar 

  • Devadas, R., Simpfendorfer, S., Backhouse, D., & Lamb, D. W. (2014). Effect of stripe rust on the yield response of wheat to nitrogen. The Crop Journal, 2(4), 201–206.

    Article  Google Scholar 

  • Dinesh, K. P., Shivanna, P., & Santa Ram, A. (2011). Identification of RAPD (Random Amplified Polymorphic DNA) markers for Ethiopian wild Coffea arabica L genetic resources in the tropics. Research: plant Genomics, 2(11), 1–7.

    CAS  Google Scholar 

  • Dube, T., & Mutanga, O. (2015). Evaluating the utility of the medium-spatial resolution Landsat 8 multispectral sensor in quantifying aboveground biomass in uMgeni catchment, South Africa. ISPRS Journal of Photogrammetry and Remote Sensing, 101, 36–46.

    Article  Google Scholar 

  • Eitel, J. U. H., Gessler, P. E., Smith, A. M. S., & Robberecht, R. (2006). Suitability of existing and novel spectral indices to remotely detect water stress in Populus spp. Forest Ecology and Management, 229(1–3), 170–182.

    Article  Google Scholar 

  • Eitel, J. U. H., Vierling, L. A., Litvak, M. E., Long, D. S., Schulthess, U., Ager, A. A., et al. (2011). Broadband, red-edge information from satellites improves early stress detection in a New Mexico conifer woodland. Remote Sensing of Environment, 115(12), 3640–3646.

    Article  Google Scholar 

  • Feng, W., Shen, W., He, L., Duan, J., Guo, B., Li, Y., et al. (2016). Improved remote sensing detection of wheat powdery mildew using dual-green vegetation indices. Precision Agriculture, 17(5), 608–627.

    Article  Google Scholar 

  • Foody, G. M. (2004). Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy. Photogrammetric Engineering & Remote Sensing, 70(5), 627–633.

    Article  Google Scholar 

  • Frampton, W. J., Dash, J., Watmough, G., & Milton, E. J. (2013). Evaluating the capabilities of Sentinel-2 for quantitative estimation of biophysical variables in vegetation. ISPRS Journal of Photogrammetry and Remote Sensing, 82, 83–92.

    Article  Google Scholar 

  • Ghimire, B., Rogan, J., Galiano, V. R., Panday, P., & Neeti, N. (2012). An evaluation of bagging, boosting, and random forests for land-cover classification in Cape Cod, Massachusetts`, USA. GIScience & Remote Sensing, 49(5), 623–643.

    Article  Google Scholar 

  • Ghini, R., Bettiol, W., & Hamada, E. (2011). Diseases in tropical and plantation crops as affected by climate change: Current knowledge and perspectives. Plant Pathology, 60, 122–132.

    Article  Google Scholar 

  • Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2004). Random forest classification of multisource remote sensing and geographic data. In: Geoscience and remote sensing symposium, 2004 (IGARSS’04) (Vol 2, pp. 1049–1052). Piscataway: IEEE International

  • Gitelson, A. A., Kaufman, Y. J., & Merzlyak, M. N. (1996). Use of a green channel in remote sensing of global vegetation from EOS-MODIS. Remote Sensing of Environment, 58, 289–298.

    Article  Google Scholar 

  • Gitelson, A. A., & Merzlyak, M. N. (1994). Quantitative estimation of chlorophyll-a using reflectance spectra: Experiments with autumn chestnut and maple leaves. Journal of Photochemistry and Photobiology B: Biology, 22(3), 247–252.

    Article  CAS  Google Scholar 

  • Gitelson, A. A., Viña, A., Ciganda, V., Rundquist, D. C., & Arkebauer, T. J. (2005). Remote estimation of canopy chlorophyll content in crops. Geophysical Research Letters, 32, L08403.

    Article  Google Scholar 

  • Glenn, E. P., Huete, A. R., Nagler, P. L., & Nelson, S. G. (2008). Relationship between remotely-sensed vegetation indices, canopy attributes and plant physiological processes: What vegetation indices can and cannot tell us about the landscape. Sensors, 8(4), 2136–2160.

    Article  PubMed  PubMed Central  Google Scholar 

  • Gresser, C., & Tickell, S. (2002). Mugged: Poverty in your coffee cup. Boston, USA: Oxfam.

    Google Scholar 

  • Haddad, F., Maffia, L. A., Mizubuti, E. S., & Teixeira, H. (2009). Biological control of coffee rust by antagonistic bacteria under field conditions in Brazil. Biological Control, 49(2), 114–119.

    Article  Google Scholar 

  • Hansen, M. C., & Loveland, T. R. (2012). A review of large area monitoring of land cover change using Landsat data. Remote Sensing of Environment, 122, 66–74.

    Article  Google Scholar 

  • Hedley, J., Roelfsema, C., Koetz, B., & Phinn, S. (2012). Capability of the Sentinel 2 mission for tropical coral reef mapping and coral bleaching detection. Remote Sensing of Environment, 120, 145–155.

    Article  Google Scholar 

  • Hill, M. J. (2013). Vegetation index suites as indicators of vegetation state in grassland and savanna: An analysis with simulated Sentinel 2 data for a North American transect. Remote Sensing of Environment, 137, 94–111.

    Article  Google Scholar 

  • Honorato Júnior, J., Zambolim, L., Aucique-Pérez, C. E., Resende, R. S., & Rodrigues, F. A. (2015). Photosynthetic and antioxidative alterations in coffee leaves caused by epoxiconazole and pyraclostrobin sprays and Hemileia vastatrix infection. Pesticide Biochemistry and Physiology, 123, 31–39.

    Article  PubMed  Google Scholar 

  • Huang, W., Lamb, D., Niu, Z., Zhang, Y., Liu, L., & Wang, J. (2007). Identification of yellow rust in wheat using in situ spectral reflectance measurements and airborne hyperspectral imaging. Precision Agriculture, 8(4–5), 187–197.

    Article  Google Scholar 

  • Kutywayo, D., Chemura, A., Kusena, W., Chidoko, P., & Mahoya, C. (2013). The impact of climate change on the potential distribution of agricultural pests: The case of the coffee white stem borer (Monochamus leuconotus P.) in Zimbabwe. PLOS ONE, 8(8), e73432.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Lanfredi, M., Coppola, R., Simoniello, T., Coluzzi, R., Imbrenda, V., & Macchiato, M. (2015). Early identification of land degradation hotspots in complex bio-geographic regions. Remote Sensing, 7(6), 8154–8179.

    Article  Google Scholar 

  • Laudien, R., Bareth, G., & Doluschitz, R. (2004). Comparison of remote sensing based analysis of crop diseases by using high resolution multispectral and hyperspectral data: Case study: Rhizoctonia solani in sugar beet. In: S.A. Brandt (Ed.) Proceedings of the 12th International Conference on Geoinformatics, Gävle (pp. 670-676). Sweden: Gävle University Press.

  • Lebedev, A., Westman, E., Van Westen, G., Kramberger, M., Lundervold, A., Aarsland, D., et al. (2014). Random Forest ensembles for detection and prediction of Alzheimer’s disease with a good between-cohort robustness. NeuroImage: Clinical, 6, 115–125.

    Article  Google Scholar 

  • Li, X.-L., Yi, S.-L., He, S.-L., Lv, Q., Xie, R.-J., Zheng, Y.-Q., et al. (2016). Identification of pummelo cultivars by using Vis/NIR spectra and pattern recognition methods. Precision Agriculture, 17(3), 365–374.

    Article  Google Scholar 

  • Liaw, A., Wiener, M., Breiman, L., & Cutler, A. (2009). Package “randomForest”. Retrieved 1 December, 2016 from https://cran.r-project.org/package=randomForest.

  • Logan, W. J. C., & Biscoe, J. (1987). Coffee handbook. Harare: Zimbabwe Coffee Growers’ Association.

    Google Scholar 

  • Mahlein, A. K., Rumpf, T., Welke, P., Dehne, H.-W., Plümer, L., Steiner, U., et al. (2013). Development of spectral indices for detecting and identifying plant diseases. Remote Sensing of Environment, 128, 21–30.

    Article  Google Scholar 

  • Mutanga, O., Adam, E., & Cho, M. A. (2012). High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm. International Journal of Applied Earth Observation and Geoinformation, 18, 399–406.

    Article  Google Scholar 

  • Mutanga, O., & Skidmore, A. K. (2004). Narrow band vegetation indices overcome the saturation problem in biomass estimation. International Journal of Remote Sensing, 25(19), 3999–4014.

    Article  Google Scholar 

  • Mutanga, O., & Skidmore, A. K. (2007). Red edge shift and biochemical content in grass canopies. ISPRS Journal of Photogrammetry and Remote Sensing, 62(1), 34–42.

    Article  Google Scholar 

  • Nitze, I., Schulthess, U., & H., A. (2012). Comparison of machine learning algorithms random forest, artificial neural network and support vector machine to maximum likelihood for supervised crop type classification. In: R.Q. Feitosa, G.A.O.P. Costa, C. M. Almeida, L. M. G. Fonseca, H.J.H. Kux (Eds.) Proceedings of the 4th GEOBIA (pp. 35–40). Rio de Janeiro, Brazil: Brazilian National Institute for Space Research.

  • Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1), 217–222.

    Article  Google Scholar 

  • Pal, M., & Foody, G. M. (2010). Feature selection for classification of hyperspectral data by SVM. IEEE Transactions on Geoscience and Remote Sensing, 48(5), 2297–2307.

    Article  Google Scholar 

  • Prabhakar, M., Prasad, Y. G., Desai, S., Thirupathi, M., Gopika, K., Rao, G. R., et al. (2013). Hyperspectral remote sensing of yellow mosaic severity and associated pigment losses in Vigna mungo using multinomial logistic regression models. Crop Protection, 45, 132–140.

    Article  Google Scholar 

  • R Core Team. (2013). R: a language and environment for statistical computing. Vienna, Austria. Retrieved from 31 Novemer 2016 http://www.R-project.org/.

  • Rembold, F., Atzberger, C., Savin, I., & Rojas, O. (2013). Using low resolution satellite imagery for yield prediction and yield anomaly detection. Remote Sensing, 5, 1704–1733. doi:10.3390/rs5041704.

    Article  Google Scholar 

  • Rodriguez-Galiano, V., Ghimire, B., Rogan, J., Chica-Olmo, M., & Rigol-Sanchez, J. (2012). An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 67, 93–104.

    Article  Google Scholar 

  • Rogan, J., Franklin, J., Stow, D., Miller, J., Woodcock, C., & Roberts, D. (2008). Mapping land-cover modifications over large areas: a comparison of machine learning algorithms. Remote Sensing of Environment, 112(5), 2272–2283.

    Article  Google Scholar 

  • Rouse, J. W., Haas, R. H., Schell, J. A., & Deering, D. W. (1973). Monitoring vegetation systems in the Great Plains with ERTS. In: S.C. Freden, E.P. Mercanti, M.A. Becker (Eds.) Proceedings of the third earth resources technology satellite-1 symposium, Greenbelt, Maryland, USA (pp 309).

  • Rulinda, C. M., Dilo, A., Bijker, W., & Stein, A. (2012). Characterising and quantifying vegetative drought in East Africa using fuzzy modelling and NDVI data. Journal of Arid Environments, 78, 169–178.

    Article  Google Scholar 

  • Saeys, Y., Inza, I., & Larrañaga, P. (2007). A review of feature selection techniques in bioinformatics. Bioinformatics, 23(19), 2507–2517.

    Article  CAS  PubMed  Google Scholar 

  • Sankaran, S., Mishra, A., Ehsani, R., & Davis, C. (2010). A review of advanced techniques for detecting plant diseases. Computers and Electronics in Agriculture, 72, 1–13.

    Article  Google Scholar 

  • Savitzky, A., & Golay, M. (1964). Smoothing and differentiation of data by simplified least square procedure. Analytical Chemistry, 36(8), 1627–1638.

    Article  CAS  Google Scholar 

  • Silva, M. C., Várzea, V., Guerra-Guimarães, L., Azinheira, H. G., Fernandez, D., Petitot, A.-S., et al. (2006). Coffee resistance to the main diseases: Leaf rust and coffee berry disease. Brazilian Journal of Plant Physiology, 18(1), 119–147.

    Article  CAS  Google Scholar 

  • Stone, C., Chisholm, L., & Coops, N. (2001). Spectral reflectance characteristics of eucalypt foliage damaged by insects. Australian Journal of Botany, 49(6), 687–698.

    Article  Google Scholar 

  • Suresh, N., Santa, R. A., & Shivanna, M. B. (2012). Coffee leaf rust(CLR) and disease triangle: A case study. International Journal of Food, Agriculture and Veterinary Sciences, 2(2), 50–55.

    Google Scholar 

  • Ustin, S. L., Gitelson, A. A., Jacquemoud, S., Schaepman, M., Asner, G. P., Gamon, J. A., et al. (2009). Retrieval of foliar information about plant pigment systems from high resolution spectroscopy. Remote Sensing of Environment, 113, S67–S77.

    Article  Google Scholar 

  • Vincini, M., Amaducci, S., & Frazzi, E. (2014). Empirical estimation of leaf chlorophyll density in winter wheat canopies using Sentinel-2 spectral resolution. IEEE Transactions of GeoScience & Remote Sensing, 52(6), 3220–3235.

    Article  Google Scholar 

  • Wang, C., Fritschi, F. B., Stacey, G., & Yang, Z. W. (2011). Phenology-based assessment of perennial energy crops in North American tallgrass prairie. Annals of the Association of American Geographers, 101(4), 742–751.

    Article  Google Scholar 

  • Wang, Q., Tenhunen, J., Dinh, N. Q., Reichstein, M., Vesala, T., & Keronen, P. (2004). Similarities in ground- and satellite-based NDVI time series and their relationship to physiological activity of a scots pine forest in Finland. Remote Sensing of Environment, 93(1–2), 225–237.

    Article  Google Scholar 

Download references

Acknowledgements

We are grateful to Coffee Research Institute for providing facilities and staff to support this research. This research was also partly funded by International Foundation for Science (IFS) Grants D/5441.

Author information

Authors and Affiliations

  1. School of Agricultural, Earth & Environmental Sciences, Geography Department, University of KwaZulu-Natal, P/Bag X01, Scottsville, Pietermaritzburg, 3209, South Africa

    Abel Chemura & Onisimo Mutanga

  2. Environmental Science and Technology Department, Chinhoyi University of Technology, P.Bag 7724, Chinhoyi, Zimbabwe

    Abel Chemura

  3. Department of Geography & Environmental Studies, University of Limpopo, P/Bag X1106, Sovenga, Polokwane, 0727, South Africa

    Timothy Dube

Authors
  1. Abel Chemura
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Onisimo Mutanga
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Timothy Dube
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Abel Chemura.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chemura, A., Mutanga, O. & Dube, T. Separability of coffee leaf rust infection levels with machine learning methods at Sentinel-2 MSI spectral resolutions. Precision Agric 18, 859–881 (2017). https://doi.org/10.1007/s11119-016-9495-0

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11119-016-9495-0

Keywords

Search

Navigation