Advertisement

Tropical Plant Pathology

, Volume 43, Issue 2, pp 117–127 | Cite as

Machine learning prediction of coffee rust severity on leaves using spectroradiometer data

  • Abel Chemura
  • Onisimo Mutanga
  • Mbulisi Sibanda
  • Pardon Chidoko
Original Article

Abstract

The interest in using remote sensing data in agriculture, including plant disease assessments, has increased considerably in the last years. The satellite-based Sentinel-2 MultiSpectral Imager (MSI) sensor has been launched recently for multispectral vegetation condition assessment for agricultural and ecosystem applications. The aim of this pilot study conducted in the greenhouse using a hand-held spectroradiometer was to assess the utility of the same wavebands as used in the Sentinel-2 MSI in assessing and modeling coffee leaf rust (CLR) based on the non-linear radial basis function-partial least squares regression (RBF-PLS) machine learning algorithm, compared with ordinary partial least squared regression (PLSR). The RBF-PLS derived models satisfactorily described CLR severity (R 2=0.92 and RMSE=6.1% with all bands and R 2=0.78 and RMSE=10.2% with selected bands) when compared with PLSR (R 2 = 0.27 and RMSE = 18.7% with all bands and R 2 = 0.17 and RMSE = 19.8% with selected bands). Specifically, four bands, B2 (490 nm), B4 (665 nm), B5 (705 nm) and B7 (783 nm) were identified as the most important spectral bands in assessing and modeling CLR severity. Better accuracy was obtained for most severe levels of CLR (R 2=0.71 using all variables) than for moderate levels (R 2=0.38 using all variables). Overall, the findings of this study showed that the use of RBF-PLS and the four Sentinel-2 MSI bands could enhance CLR severity estimation at the leaf level. Further work will be needed to extrapolate these findings to the crop level using the Sentinel-2 platform.

Keywords

Hemileia vastatrix Multispectral imaging Coffee rust Machine learning 

Notes

Acknowledgements

We are very grateful to the Coffee Research Institute for providing facilities and staff to support this research. This research was also partly funded by IFS grant D/5441. We are also thankful to anonymous reviewers whose comments improved this paper.

References

  1. Atzberger C, Guerif M, Baret F, Werner W (2010) Comparative assessment of three chemometric techniques for the spectroradiometric assessment of canopy chlorophyll content in winter wheat. Computers and Electronics in Agriculture 73:165–173CrossRefGoogle Scholar
  2. Avelino J, Willocquet L, Savary S (2004) Effects of crop management patterns on coffee rust epidemics. Plant Pathology 53:541–547CrossRefGoogle Scholar
  3. Barbedo JGA (2013) Digital image processing techniques for detecting, quantifying and classifying plant diseases. Spinger Plus 2(660):1–12Google Scholar
  4. Baret F, Buis S (2008) Estimating canopy characteristics from remote sensing observations: review of methods and associated problems advances in land remote sensing. Springer, pp. 173–201Google Scholar
  5. Baret F, Guyot G (1991) Potentials and limits of vegetation indices for LAI and APAR assessment. Remote Sensing of Environment 35:161–173CrossRefGoogle Scholar
  6. Bauriegel E, Herppich WB (2014) Hyperspectral and chlorophyll fluorescence imaging for early detection of plant diseases, with special reference to Fusarium spec. infections on wheat. Agriculture 4:32–57CrossRefGoogle Scholar
  7. Belan LL, Pozza EA, de Oliveira Freitas ML, Pozza AAA, de Abreu MS, Alves E (2015) Nutrients distribution in diseased coffee leaf tissue. Australasian Plant Pathology 44:105–111CrossRefGoogle Scholar
  8. Brown JKM, Hovmøller MS (2002) Aerial dispersal of pathogens on the global and continental scales and its impact on plant disease. Science 297:537–541CrossRefPubMedGoogle Scholar
  9. Cao K.-AL, Gonzalez I, Dejean S (2015) Package ‘mixOmics’, University of Queensland, AustraliaGoogle Scholar
  10. Carter GA, Miller RL (1994) Early detection of plant stress by digital imaging within narrow stress-sensitive wavebands. Remote Sensing of Environment 50:295–302CrossRefGoogle Scholar
  11. Chemura A, Mutanga O, Dube T (2016) Separability of coffee leaf rust infection levels with machine learning methods at Sentinel-2 MSI spectral resolutions. Precision Agriculture 18:859-881Google Scholar
  12. Clevers JGPW, Gitelson AA (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 23:344–351CrossRefGoogle Scholar
  13. 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 93:1524–1532CrossRefPubMedGoogle Scholar
  14. Core Team R (2013) R: a language and environment for statistical computing. Austria, Vienna Retrieved from http://www.R-project.org/ Google Scholar
  15. Cressey D (2013) Coffee rust regains foothold. Nature 493:587CrossRefPubMedGoogle Scholar
  16. Cristancho M, Rozo Y, Escobar C, Rivillas C, Gaitán A (2012) Outbreak of coffee leaf rust (Hemileia vastatrix) in Colombia. New Disease Reports, 25  https://doi.org/10.5197/j.2044-0588.2012.025.019
  17. Darvishzadeh R, Atzberger C, Skidmore A, Schlerf M (2011) Mapping grassland leaf area index with airborne hyperspectral imagery: a comparison study of statistical approaches and inversion of radiative transfer models. SPRS Journal of Photogrammetry and Remote Sensing 66:894–906CrossRefGoogle Scholar
  18. Daszykowski M, Serneels S, Kaczmarek K, Van Espen P, Croux C, Walczak B (2007) TOMCAT: a MATLAB toolbox for multivariate calibration techniques. Chemometrics and Intelligent Laboratory Systems 85:269–277CrossRefGoogle Scholar
  19. de Almeida MR, Correa DN, Rocha WF, Scafi FJ, Poppi RJ (2013) Discrimination between authentic and counterfeit banknotes using Raman spectroscopy and PLS-DA with uncertainty estimation. Microchemical Journal 109:170–177Google Scholar
  20. DeJonge KC, Mefford n S, Chávez J (2016) Assessing corn water stress using spectral reflectance. International Journal of Remote Sensing 37:2294–2312CrossRefGoogle Scholar
  21. Devadas R, Lamb D, Backhouse D, Simpfendorfer S (2015) Sequential application of hyperspectral indices for delineation of stripe rust infection and nitrogen deficiency in wheat. Precision Agriculture 16:477–491CrossRefGoogle Scholar
  22. Dinesh KP, 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 2:1–7Google Scholar
  23. Eitel JUH, Vierling LA, Litvak ME, Long DS, Schulthess U, Ager AA, Krofcheck DJ, Stoscheck L (2011) Broadband, red-edge information from satellites improves early stress detection in a New Mexico conifer woodland. Remote Sensing of Environment 115:3640–3646CrossRefGoogle Scholar
  24. Eskes A (2005) Phenotypic expression of resistance to coffee leaf rust and its possible relationship with durability. Durable Resistance to Coffee Leaf Rust. Viçosa MG. Universidade Federal de Viçosa, 305–332Google Scholar
  25. Feng W, Shen W, He L, Duan J, Guo B, Li Y, Wang C, Guo T (2016) Improved remote sensing detection of wheat powdery mildew using dual-green vegetation indices. Precision Agriculture 17:608–627CrossRefGoogle Scholar
  26. Frampton WJ, Dash J, Watmough G, Milton EJ (2013) Evaluating the capabilities of Sentinel-2 for quantitative estimation of biophysical variables in vegetation. ISPRS Journal of Photogrammetry and Remote Sensing 82:83–92CrossRefGoogle Scholar
  27. Haddad F, Maffia LA, Mizubuti ES, Teixeira H (2009) Biological control of coffee rust by antagonistic bacteria under field conditions in Brazil. Biological Control 49:114–119CrossRefGoogle Scholar
  28. Hansen PM, Schjoerring JK (2003) Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression. Remote Sensing of Environment 86:542–553CrossRefGoogle Scholar
  29. Herrmann I, Pimstein A, Karnieli A, Cohen Y, Alchanatis V, Bonfil DJ (2011) LAI assessment of wheat and potato crops by VENμS and Sentinel-2 bands. Remote Sensing of Environment 115:2141–2151CrossRefGoogle Scholar
  30. Hillnhütter C, Mahlein A-K, Sikora R, Oerke E-C (2011) Remote sensing to detect plant stress induced by Heterodera schachtii and Rhizoctonia solani in sugar beet fields. Field Crops Research 122:70–77CrossRefGoogle Scholar
  31. Höskuldsson A (1988) PLS regression methods. Journal of Chemometrics 2:211–228CrossRefGoogle Scholar
  32. 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 8:187–197CrossRefGoogle Scholar
  33. Jia R, Mao Z, Chang Y (2010). A nonlinear robust partial least squares method with application. Paper presented at the 2010 Chinese control and decision conference, Xuzhou, China, 2334–2339Google Scholar
  34. Jiang J, Hu R, Han Z, Wang Z, Chen J (2013) Two-step superresolution approach for surveillance face image through radial basis function-partial least squares regression and locality-induced sparse representation. Journal of Electronic Imaging 22:041120–041120CrossRefGoogle Scholar
  35. Kanke Y, Tuban B, Dalen M, Harrell D (2016) Evaluation of red and red-edge reflectance-based vegetation indices for rice biomass and grain yield prediction models in paddy fields. Precision Agriculture 17:507–530CrossRefGoogle Scholar
  36. Larsolle A, Muhammed HH (2007) Measuring crop status using multivariate analysis of hyperspectral field reflectance with application to disease severity and plant density. Precision Agriculture 8:37–47Google Scholar
  37. 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. Paper presented at the 12th international conference on Geoinformatics − geospatial information research: bridging the Pacific and Atlantic, University of Gävle, SwedenGoogle Scholar
  38. Lelong CCD, Roger JM, Brégand S, Dubertret F, Lanore M, Sitorus NA, Raharjo DA, Caliman JP (2010) Evaluation of oil-palm fungal disease infestation with canopy hyperspectral reflectance data. Sensors 10:734–747CrossRefPubMedPubMedCentralGoogle Scholar
  39. Li H, Lee W, Wang K, Ehsani R, Yang C (2014) ‘Extended spectral angle mapping (ESAM)’ for citrus greening disease detection using airborne hyperspectral imaging. Precision Agriculture 15:162–183CrossRefGoogle Scholar
  40. Logan WJC, Biscoe J (1987) Coffee handbook. Zimbabwe Coffee Growers' Association, HarareGoogle Scholar
  41. Mahlein AK, Oerke E-C, Steiner U, Dehne HW (2012a) Recent advances in sensing plant diseases for precision crop protection. European Journal of Plant Pathology 133:197–209CrossRefGoogle Scholar
  42. Mahlein AK, Steiner U, Hillnhütter C, Dehne HW, Oerke E-C (2012b) Hyperspectral imaging for small-scale analysis of symptoms caused by different sugar beet diseases. Plant Methods 8:3CrossRefPubMedPubMedCentralGoogle Scholar
  43. Mahlein AK, Rumpf T, Welke P, Dehne HW, Plümer L, Steiner U, Oerke EC (2013) Development of spectral indices for detecting and identifying plant diseases. Remote Sensing of Environment 128:21–30CrossRefGoogle Scholar
  44. Martens H, Naes T (2001) Multivariate calibration by data compression. In P. Williams, Norris, K. (Ed.), Near infrared Technology in the agricultural and food industries (2nd ed., pp. 59–100). Minessota: American Association of Cereal ChemistsGoogle Scholar
  45. Melo GA, Shimizu MM, Mazzafera P (2006) Polyphenoloxidase activity in coffee leaves and its role in resistance against the coffee leaf miner and coffee leaf rust. Phytochemistry 67:277–285CrossRefPubMedGoogle Scholar
  46. Moriasi DN, Arnold JG, Van Liew MW, Bingner RL, Harmel RD, Veith TL (2007) Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE 50:885–900CrossRefGoogle Scholar
  47. Moscetti R, Haff RP, Stella E, Contini M, Monarca D, Cecchini M, Massantini R (2015) Feasibility of NIR spectroscopy to detect olive fruit infested by Bactrocera oleae. Postharvest Biology and Technology 99:58–62CrossRefGoogle Scholar
  48. Mulla DJ (2013) Twenty five years of remote sensing in precision agriculture: key advances and remaining knowledge gaps. Biosystems Engineering 114:358–371CrossRefGoogle Scholar
  49. Mutanga O, Ismail R (2010) Variation in foliar water content and hyperspectral reflectance of Pinus patula trees infested by Sirex noctilio. Southern Forests: A Journal of Forest Science 72:1–7CrossRefGoogle Scholar
  50. Mutanga O, Skidmore AK (2007) Red-edge shift and biochemical content in grass canopies. ISPRS Journal of Photogrammetry and Remote Sensing 62:34–42CrossRefGoogle Scholar
  51. Orr MJ (1996) Introduction to radial basis function networks: technical report. University of Edinburgh, Center for Cognitive ScienceGoogle Scholar
  52. Oumar Z, Mutanga O (2014) Predicting water stress induced by Thaumastocoris peregrinus infestations in plantation forests using field spectroscopy and neural networks. Journal of Spatial Science 59:79–90CrossRefGoogle Scholar
  53. Prabhakar M, Prasad YG, Desai S, Thirupathi M, Gopika K, Rao GR, Venkateswarlu B (2013) Hyperspectral remote sensing of yellow mosaic severity and associated pigment losses in Vigna mungo using multinomial logistic regression models. Crop Protection 45:132–140CrossRefGoogle Scholar
  54. Price T, Gross R, Wey J, Osborne C (1993) A comparison of visual and digital image-processing methods in quantifying the severity of coffee leaf rust (Hemileia vastatrix). Austraulian Journal of Experimental Agriculture 33:97–101CrossRefGoogle Scholar
  55. Ramoelo A, Cho M, Mathieu R, Skidmore AK (2015) Potential of Sentinel-2 spectral configuration to assess rangeland quality. Journal of Applied Remote Sensing 9:09409611–094096112CrossRefGoogle Scholar
  56. Ramoelo A, Skidmore AK, Cho MA, Mathieu R, Heitkönig IMA, Dudeni-Tlhone N, Schlerf M, Prins HHT (2013) Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data. ISPRS Journal of Photogrammetry and Remote Sensing 82:27–40Google Scholar
  57. Reynolds GJ, Windels CE, MacRae IV, Laguette S (2012) Remote sensing for assessing Rhizoctonia crown and root rot severity in sugar beet. Plant Disease 96:497–505CrossRefGoogle Scholar
  58. Rosipal R (2010) Nonlinear partial least squares: an overview. Chemoinformatics and advanced machine learning perspectives: complex computational methods and collaborative techniques, 169–189Google Scholar
  59. Rumpf T, Mahlein AK, Steiner U, Oerke EC, Dehne HW, Plümer L (2010) Early detection and classification of plant diseases with support vector machines based on hyperspectral reflectance. Computers and Electronics in Agriculture 74:91–99CrossRefGoogle Scholar
  60. Sankaran S, Mishra A, Ehsani R, Davis C (2010) A review of advanced techniques for detecting plant diseases. Computers and Electronics in Agriculture 72:1–13CrossRefGoogle Scholar
  61. Savitzky A, Golay M (1964) Smoothing and differentiation of data by simplified least square procedure. Analytical Chemistry 36:1627–1638CrossRefGoogle Scholar
  62. Shafri HZM, Anuar M, Seman IA, Noor M (2011) Spectral discrimination of healthy and Ganoderma-infected oil palms from hyperspectral data. International Journal of Remote Sensing 32:7111–7129CrossRefGoogle Scholar
  63. Sibanda M, Mutanga O, Rouget M (2016) Comparing the spectral settings of the new generation broad and narrow band sensors in estimating biomass of native grasses grown under different management practices. GIScience & Remote Sensing 53:614–633CrossRefGoogle Scholar
  64. Silva M d C, Várzea V, Guerra-Guimarães L, Azinheira HG, Fernandez D, Petitot A-S, Bertrand B, Lashermes P, Nicole M (2006) Coffee resistance to the main diseases: leaf rust and coffee berry disease. Brazilian Journal of Plant Physiology 18:119–147CrossRefGoogle Scholar
  65. Thenkabail PS, Smith RB, De Pauw E (2000) Hyperspectral vegetation indices and their relationships with agricultural crop characteristics. Remote Sensing of Environment 71:158–182CrossRefGoogle Scholar
  66. 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 52:3220–3235CrossRefGoogle Scholar
  67. Wold S, Sjöström M, Eriksson L (2001) PLS-regression: a basic tool of chemometrics. Chemometrics and Intelligent Laboratory Systems 58:109–130CrossRefGoogle Scholar
  68. Yan X, Du W, Qian F (2004) Development of a kinetic model for industrial oxidation of p-xylene by RBF-PLS and CCA. AICHE Journal 50:1169–1176CrossRefGoogle Scholar
  69. Yu K, Leufen G, Hunsche M, Noga G, Chen X, Bareth G (2014) Investigation of leaf diseases and estimation of chlorophyll concentration in seven barley varieties using fluorescence and hyperspectral indices. Remote Sensing 6:64–86CrossRefGoogle Scholar
  70. Yuan L, Zhang JC, Wang K, Loraamm RW, Huang WJ, Wang JH, Zhao JL (2013) Analysis of spectral difference between the foreside and backside of leaves in yellow rust disease detection for winter wheat. Precision Agriculture 14:495–511CrossRefGoogle Scholar
  71. Yuan L, Huang Y, Loraamm RW, Nie C, Wang J, Zhang J (2014) Spectral analysis of winter wheat leaves for detection and differentiation of diseases and insects. Field Crops Research 156:199–207CrossRefGoogle Scholar
  72. Yuan L, Zhang H, Zhang Y, Xing C, Bao Z (2017) Feasibility assessment of multi-spectral satellite sensors in monitoring and discriminating wheat diseases and insects. Optik-International Journal for Light and Electron Optics 131:598–608CrossRefGoogle Scholar
  73. Zambolim L (2016) Current status and management of coffee leaf rust in Brazil. Tropical Plant Pathology 41:1–8CrossRefGoogle Scholar
  74. Zarco-Tejada PJ, Ustin SL, Whiting ML (2005) Temporal and spatial relationships between within-field yield variability in cotton and high-spatial hyperspectral remote sensing imagery. Agronomy Journal 97:641–653CrossRefGoogle Scholar
  75. Zhang JC, Pu R-L, Wang J-H, Huang W-J, Yuan L, Luo J-H (2012) Detecting powdery mildew of winter wheat using leaf level hyperspectral measurements. Computers and Electronics in Agriculture 85:13–23CrossRefGoogle Scholar
  76. Zhang JC, Pu R, Yuan L, Wang J, Huang W, Yang G (2014) Monitoring powdery mildew of winter wheat by using moderate resolution multi-temporal satellite imagery. PloS One 9(4):e93107Google Scholar

Copyright information

© Sociedade Brasileira de Fitopatologia 2017

Authors and Affiliations

  1. 1.School of Agricultural, Earth & Environmental Sciences, Geography DepartmentUniversity of KwaZulu-NatalPietermaritzburgSouth Africa
  2. 2.Environmental Science & Technology Dept.Chinhoyi University of TechnologyChinhoyiZimbabwe
  3. 3.Coffee Research Institute, DR&SSChipingeZimbabwe

Personalised recommendations