Cocoa swollen shoot is a viral disease prevalent mainly in West Africa. It is responsible for significant yield losses. Effective monitoring and accurate detection of this disease are essential to ensure stable and reliable cocoa production, as well as the income of thousands of farmers. Current standard methods often rely on visual inspection for disease symptoms. This method is costly, time-consuming, and prone to errors due to the subjectivity of inspectors. Recent advances in precision agriculture, using spectral data at different scales (leaf, canopy, and space), offer the potential to solve these problems at low cost and with high efficiency. Spectral vegetation indices are widely used for the indirect detection of plant diseases. Therefore, this work aims to evaluate the potential of hyperspectral reflectance spectroscopy, using vegetation indices, for the early detection of cocoa swollen shoot. Thus, reflectance spectra of healthy, asymptomatic and symptomatic cocoa tree leaves were collected using an Ocean Optics USB 4000 spectrometer, with a wavelength range from 350 to 1100 nm. To reduce scattering and noise effects in the collected data, we applied three essential spectroscopic preprocessing methods: the Multiplicative Scattering Correction (MSC), the Standard Normal Variable (SNV), and the first order Savitzky-Golay derivative (SG-D1). Principal Component Analysis (PCA) identified MSC as the most effective preprocessing method. Subsequently, eight vegetation indices (NDVI, GNDVI, Datt5, Ctr2, PSRI, SIPI, PRI, Lic2) selected from the literature were calculated. Using classification algorithms such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree (DT) and Random Forest (RF) applied to all eight vegetation indices, the performance of each index was evaluated for the infection detection and the classification of the three types of cocoa trees. The results obtained indicate that the most efficient model is RF combined with MSC pretreatment with an overall accuracy of 97.59%, thus showing the strong potential of reflectance spectroscopy for the early detection of cocoa tree infection by the swollen shoot virus.
References
[1]
Cuatrecasas, J. (1964) Cacao and Its Allies: A Taxonomic Revision of the Genus Theobroma. In: Contributions from the United States National Herbarium, Smithsonian Institution Press, 379-614.
[2]
Food and Agriculture Organization of the United Nations (2025) FAOSTAT: Crops and Livestock Products. https://www.fao.org/faostat/en/#data/QCL/visualize
[3]
Sultan, B., Defrance, D. and Iizumi, T. (2019) Evidence of Crop Production Losses in West Africa Due to Historical Global Warming in Two Crop Models. Scientific Reports, 9, Article No. 12834. https://doi.org/10.1038/s41598-019-49167-0
[4]
Morillo, F., Sánchez, P., Herrera, B., Liendo-Barandiaran, C., Mu？oz, W. and Vicente Hernández, J. (2009) Pupal Development, Longevity and Behavior of Carmenta theobromae (Lepidoptera: Sesiidae). Florida Entomologist, 92, 355-361. https://doi.org/10.1653/024.092.0222
[5]
Muller, E. (2016) Cacao Swollen Shoot Virus (CSSV): History, Biology, and Genome. In: Cacao Diseases: A History of Old Enemies and New Encounters, Springer, 337-358.
[6]
Sena, K., Alemanno, L. and Gramacho, K.P. (2014) The Infection Process of Moniliophthora perniciosa in Cacao. Plant Pathology, 63, 1272-1281. https://doi.org/10.1111/ppa.12224
[7]
Posnette, A.F. and Strickland, A.H. (1948) Virus Diseases of Cacao in West Africa. Annals of Applied Biology, 35, 53-63. https://doi.org/10.1111/j.1744-7348.1948.tb07350.x
[8]
Ofori, A., Padi, F.K., Ameyaw, G.A., Dadzie, A.M., Opoku-Agyeman, M., Domfeh, O., et al. (2022) Field Evaluation of the Impact of Cocoa Swollen Shoot Virus Disease Infection on Yield Traits of Different Cocoa (Theobroma cacao L.) Clones in Ghana. PLOS ONE, 17, e0262461. https://doi.org/10.1371/journal.pone.0262461
[9]
Dzahini-Obiatey, H., Ameyaw, G.A. and Ollennu, L.A. (2006) Control of Cocoa Swollen Shoot Disease by Eradicating Infected Trees in Ghana: A Survey of Treated and Replanted Areas. Crop Protection, 25, 647-652. https://doi.org/10.1016/j.cropro.2005.09.004
[10]
Kouakou, K., Kébé, B.I., Kouassi, N., Anno, A.P., Aké, S. and Muller, E. (2011) Impact de la Maladie Virale du Swollen Shoot du Cacaoyer sur la Production de Cacao en Milieu Paysan à Bazré (C？te d’Ivoire).Journal of Applied Biosciences, 43, 2947-2957. http://www.m.elewa.org/JABS/2011/43/7.pdf
[11]
Ramos-Sobrinho, R., Kouakou, K., Bi, A.B., Keith, C.V., Diby, L., Kouame, C., et al. (2021) Molecular Detection of Cacao Swollen Shoot Badnavirus Species by Amplification with Four PCR Primer Pairs, and Evidence That Cacao Swollen Shoot Togo B Virus-Like Isolates Are Highly Prevalent in C？te d’Ivoire. European Journal of Plant Pathology, 159, 941-947. https://doi.org/10.1007/s10658-021-02203-0
[12]
Muller, E., Jacquot, E. and Yot, P. (2001) Early Detection of Cacao Swollen Shoot Virus Using the Polymerase Chain Reaction. Journal of Virological Methods, 93, 15-22. https://doi.org/10.1016/s0166-0934(00)00241-x
[13]
Sagemann, W., Lesemann, D.E., Paul, H.L., Adomako, D. and Owusu, G.K. (1985) Detection and Comparison of Some Ghanaian Isolates of Cacao Swollen Shoot Virus (CSSV) by Enzyme-Linked Immunosorbent Assay (ELISA) and Immunoelectron Microscopy (IEM) Using an Antiserum to CSSV Strain 1a. Journal of Phytopathology, 114, 79-89. https://doi.org/10.1111/j.1439-0434.1985.tb04339.x
[14]
Ameyaw, G.A., Dzahini-Obiatey, H.K. and Domfeh, O. (2014) Perspectives on Cocoa Swollen Shoot Virus Disease (CSSVD) Management in Ghana. Crop Protection, 65, 64-70. https://doi.org/10.1016/j.cropro.2014.07.001
[15]
Coulibaly, M., Kouassi, K.H., Kolo, S. and Asseu, O. (2020) Detection of “Swollen Shoot” Disease in Ivorian Cocoa Trees via Convolutional Neural Networks. Engineering, 12, 166-176. https://doi.org/10.4236/eng.2020.123014
[16]
Kumi, S., Kelly, D., Woodstuff, J., Lomotey, R.K., Orji, R. and Deters, R. (2022) Cocoa Companion: Deep Learning-Based Smartphone Application for Cocoa Disease Detection. Procedia Computer Science, 203, 87-94. https://doi.org/10.1016/j.procs.2022.07.013
[17]
Kouassi, K.S., Diarra, M., Edi, K.H. and Koua, B.J. (2024) Detection of Cocoa Leaf Diseases Using the CNN-Based Feature Extractor and XGBOOST Classifier. Open Journal of Applied Sciences, 14, 2955-2972. https://doi.org/10.4236/ojapps.2024.1410193
[18]
Batool, T., Allainguillaume, J., Zhang, W. and Bell, M.J. (2025) Application of Machine Learning to Screen Hyperspectral Data of Cacao Plants to Identify Cacao Swollen Shoot Virus (CSSV). In: Precision Agriculture 25 (SET TWO VOLUMES), Brill Wageningen Academic, 105-112. https://doi.org/10.1163/9789004725232_012
[19]
Lacotte, V., Peignier, S., Raynal, M., Demeaux, I., Delmotte, F. and da Silva, P. (2022) Spatial-Spectral Analysis of Hyperspectral Images Reveals Early Detection of Downy Mildew on Grapevine Leaves. International Journal of Molecular Sciences, 23, Article 10012. https://doi.org/10.3390/ijms231710012
[20]
Khan, I.H., Liu, H., Li, W., Cao, A., Wang, X., Liu, H., et al. (2021) Early Detection of Powdery Mildew Disease and Accurate Quantification of Its Severity Using Hyperspectral Images in Wheat. Remote Sensing, 13, Article 3612. https://doi.org/10.3390/rs13183612
[21]
Kamate, A., Soro, P.A., Zoro-Diama, E.G., Diomandé, K.S. and Adohi-Krou, A.V. (2023) Detection of Rice Yellow Mottle at the Asymptomatic Stage by Hyperspectral Fluorescence and Reflectance Spectroscopies. Optics and Photonics Journal, 13, 63-78. https://doi.org/10.4236/opj.2023.134005
[22]
Falcioni, R., Antunes, W.C., Demattê, J.A.M. and Nanni, M.R. (2023) Reflectance Spectroscopy for the Classification and Prediction of Pigments in Agronomic Crops. Plants, 12, Article 2347. https://doi.org/10.3390/plants12122347
[23]
Schaepman, M.E., Ustin, S.L., Plaza, A.J., Painter, T.H., Verrelst, J. and Liang, S. (2009) Earth System Science Related Imaging Spectroscopy—An Assessment. Remote Sensing of Environment, 113, S123-S137. https://doi.org/10.1016/j.rse.2009.03.001
[24]
Liu, N., Zhang, W., Liu, F., Zhang, M., Du, C., Sun, C., et al. (2022) Development of a Crop Spectral Reflectance Sensor. Agronomy, 12, Article 2139. https://doi.org/10.3390/agronomy12092139
[25]
Skoneczny, H., Kubiak, K., Spiralski, M., Kotlarz, J., Mikiciński, A. and Pu？awska, J. (2020) Fire Blight Disease Detection for Apple Trees: Hyperspectral Analysis of Healthy, Infected and Dry Leaves. Remote Sensing, 12, Article 2101. https://doi.org/10.3390/rs12132101
[26]
Song, Z., Liu, Y., Yu, J., Guo, Y., Jiang, D., Zhang, Y., et al. (2024) Estimation of Chlorophyll Content in Apple Leaves Infected with Mosaic Disease by Combining Spectral and Textural Information Using Hyperspectral Images. Remote Sensing, 16, Article 2190. https://doi.org/10.3390/rs16122190
[27]
Aka Romain, A., Klotioloma, C., Pierre N’Guessan, W., Kouakou, K., Gnion Mathias, T., F. N’Guessan, K., et al. (2020) Cocoa Swollen Shoot Disease in C？te d’Ivoire: History of Expansion from 2008 to 2016. International Journal of Sciences, 9, 52-60. https://doi.org/10.18483/ijsci.2203
[28]
Kamate, A., Soro, P.A., Zoro-Diama, E.G., Diomande, K.S. and Adohi-Krou, A.V. (2023) Water Stress Early Detection of Eggplant Plants by Hyperspectral Fluorescence Spectroscopy. Open Journal of Applied Sciences, 13, 343-354. https://doi.org/10.4236/ojapps.2023.133028
[29]
Isaksson, T. and N？s, T. (1988) The Effect of Multiplicative Scatter Correction (MSC) and Linearity Improvement in NIR Spectroscopy. Applied Spectroscopy, 42, 1273-1284. https://doi.org/10.1366/0003702884429869
[30]
Yang, H., Chen, Q., Qian, J., Li, J., Lin, X., Liu, Z., et al. (2024) Determination of Dry-Matter Content of Kiwifruit before Harvest Based on Hyperspectral Imaging. AgriEngineering, 6, 52-63. https://doi.org/10.3390/agriengineering6010004
[31]
Barnes, R.J., Dhanoa, M.S. and Lister, S.J. (1989) Standard Normal Variate Transformation and De-Trending of Near-Infrared Diffuse Reflectance Spectra. Applied Spectroscopy, 43, 772-777. https://doi.org/10.1366/0003702894202201
[32]
Savitzky, A. and Golay, M.J.E. (1964) Smoothing and Differentiation of Data by Simplified Least Squares Procedures. Analytical Chemistry, 36, 1627-1639. https://doi.org/10.1021/ac60214a047
[33]
Demetriades-Shah, T.H., Steven, M.D. and Clark, J.A. (1990) High Resolution Derivative Spectra in Remote Sensing. Remote Sensing of Environment, 33, 55-64. https://doi.org/10.1016/0034-4257(90)90055-q
[34]
Gewers, F.L., Ferreira, G.R., Arruda, H.F.D., Silva, F.N., Comin, C.H., Amancio, D.R., et al. (2021) Principal Component Analysis: A Natural Approach to Data Exploration. ACM Computing Surveys, 54, 1-34. https://doi.org/10.1145/3447755
[35]
Vigni, M.L., Durante, C. and Cocchi, M. (2013) Exploratory Data Analysis. In: DataHandlinginScienceandTechnology, Elsevier, 55-126. https://doi.org/10.1016/b978-0-444-59528-7.00003-x
[36]
Thorp, K.R. (2024) Vegspec: A Compilation of Spectral Vegetation Indices and Transformations in Python. SoftwareX, 28, Article 101928. https://doi.org/10.1016/j.softx.2024.101928
[37]
Bi, P., Yu, L., Zhou, Q., Kuang, J., Tang, R., Ren, L., et al. (2024) Early Detection of Dendroctonus Valens Infestation with UAV-Based Thermal and Hyperspectral Images. Remote Sensing, 16, Article 3840. https://doi.org/10.3390/rs16203840
[38]
Gao, B., Yu, L., Ren, L., Zhan, Z. and Luo, Y. (2023) Early Detection of Dendroctonus Valens Infestation at Tree Level with a Hyperspectral UAV Image. Remote Sensing, 15, Article 407. https://doi.org/10.3390/rs15020407
[39]
Vera-Esmeraldas, A., Pizarro-Oteíza, S., Labbé, M., Rojo, F. and Salazar, F. (2025) UAV-Based Spectral and Thermal Indices in Precision Viticulture: A Review of NDVI, NDRE, SAVI, GNDVI, and CWSI. Agronomy, 15, Article 2569. https://doi.org/10.3390/agronomy15112569
[40]
Rouse, J.W., Haas, R.H., Deering, D.W., Schell, J.A. and Harlan, J.C. (1974) Monitoring the Vernal Advancement and Retrogradation (Green Wave Effect) of Natural Vegetation. Rapport Final NASA/GSFC Type III, NASA-CR-144661, Greenbelt, Maryland, USA: NASA/GSFC, 390p. https://skclivinglandscapes.org/remote_sensing/resources/Section6Resources/Rouse_et_al.1974NDVI.pdf
[41]
Gitelson, A.A. and Merzlyak, M.N. (1997) Remote Estimation of Chlorophyll Content in Higher Plant Leaves. International Journal of Remote Sensing, 18, 2691-2697. https://doi.org/10.1080/014311697217558
[42]
Datt, B. (1998) Remote Sensing of Chlorophyll A, Chlorophyll B, Chlorophyll A+B, and Total Carotenoid Content in Eucalyptus Leaves. Remote Sensing of Environment, 66, 111-121. https://doi.org/10.1016/s0034-4257(98)00046-7
[43]
Carter, G.A. (1994) Ratios of Leaf Reflectances in Narrow Wavebands as Indicators of Plant Stress. International Journal of Remote Sensing, 15, 697-703. https://doi.org/10.1080/01431169408954109
[44]
Merzlyak, M.N., Gitelson, A.A., Chivkunova, O.B. and Rakitin, V.Y. (1999) Non-Destructive Optical Detection of Pigment Changes during Leaf Senescence and Fruit Ripening. Physiologia Plantarum, 106, 135-141. https://doi.org/10.1034/j.1399-3054.1999.106119.x
[45]
Penuelas, J., Baret, F. and Filella, I. (1995) Semi-Empirical Indices to Assess Carotenoids/Chlorophyll A Ratio from Leaf Spectral Reflectance. Photosynthetica, 31, 221-230.
[46]
Gamon, J.A., Pe？uelas, J. and Field, C.B. (1992) A Narrow-Waveband Spectral Index That Tracks Diurnal Changes in Photosynthetic Efficiency. Remote Sensing of Environment, 41, 35-44. https://doi.org/10.1016/0034-4257(92)90059-s
[47]
Lichtenthaler, H.K., Lang, M., Sowinska, M., Heisel, F. and Miehé, J.A. (1996) Detection of Vegetation Stress via a New High Resolution Fluorescence Imaging System. Journal of Plant Physiology, 148, 599-612. https://doi.org/10.1016/s0176-1617(96)80081-2
[48]
Shapiro, S.S. and Wilk, M.B. (1965) An Analysis of Variance Test for Normality (Complete Samples). Biometrika, 52, 591-611. https://doi.org/10.1093/biomet/52.3-4.591
[49]
Schultz, B.B. (1985) Levene’s Test for Relative Variation. Systematic Zoology, 34, 449-456. https://doi.org/10.2307/2413207
[50]
Kruskal, W.H. and Wallis, W.A. (1952) Use of Ranks in One-Criterion Variance Analysis. Journal of the American Statistical Association, 47, 583-621. https://doi.org/10.1080/01621459.1952.10483441
Zhang, C., Liu, Y. and Tie, N. (2023) Forest Land Resource Information Acquisition with Sentinel-2 Image Utilizing Support Vector Machine, K-Nearest Neighbor, Random Forest, Decision Trees and Multi-Layer Perceptron. Forests, 14, Article 254. https://doi.org/10.3390/f14020254
[53]
Anku, K., Percival, D. and Heung, B. (2025) Field Assessment Strategies: Assessing and Classifying Blight Disease in Wild Blueberry Populations Using Multispectral and Hyperspectral Sensors. Remote Sensing, 17, Article 3074. https://doi.org/10.3390/rs17173074
[54]
Macedo, F.L., Nóbrega, H., de Freitas, J.G.R. and Pinheiro de Carvalho, M.A.A. (2025) Assessment of Vegetation Indices Derived from UAV Imagery for Weed Detection in Vineyards. Remote Sensing, 17, Article 1899. https://doi.org/10.3390/rs17111899
[55]
Marin, D.B., Ferraz, G.A.E.S., Santana, L.S., Barbosa, B.D.S., Barata, R.A.P., Osco, L.P., et al. (2021) Detecting Coffee Leaf Rust with UAV-Based Vegetation Indices and Decision Tree Machine Learning Models. Computers and Electronics in Agriculture, 190, Article 106476. https://doi.org/10.1016/j.compag.2021.106476
[56]
Akbulut, Y., Sengur, A., Guo, Y. and Smarandache, F. (2017) NS-k-NN: Neutrosophic Set-Based K-Nearest Neighbors Classifier. Symmetry, 9, Article 179. https://doi.org/10.3390/sym9090179
[57]
Hatem, M.Q. (2022) Skin Lesion Classification System Using a K-Nearest Neighbor Algorithm. Visual Computing for Industry, Biomedicine, and Art, 5, Article No. 7. https://doi.org/10.1186/s42492-022-00103-6
[58]
Ahmad, M., Aftab, S., Salman, M., Hameed, N., Ali, I. and Nawaz, Z. (2018) SVM Optimization for Sentiment Analysis. International Journal of Advanced Computer Science and Applications, 9, 393-398. https://doi.org/10.14569/ijacsa.2018.090455
[59]
Müller, K., Mika, S., Tsuda, K. and Sch？lkopf, K. (2018) An Introduction to Kernel-Based Learning Algorithms. In: Handbook of Neural Network Signal Processing, CRC Press, 94-133. https://doi.org/10.1201/9781315220413-4
[60]
Pradhan, B. (2013) A Comparative Study on the Predictive Ability of the Decision Tree, Support Vector Machine and Neuro-Fuzzy Models in Landslide Susceptibility Mapping Using GIS. Computers&Geosciences, 51, 350-365. https://doi.org/10.1016/j.cageo.2012.08.023
[61]
Zuntz, J., Lanusse, F., Malz, A.I., Wright, A.H., Slosar, A., Abolfathi, B., et al. (2021) The LSST-DESC 3x2pt Tomography Optimization Challenge. The Open Journal of Astrophysics, 4, 30. https://doi.org/10.21105/astro.2108.13418
[62]
Sheykhmousa, M., Mahdianpari, M., Ghanbari, H., Mohammadimanesh, F., Ghamisi, P. and Homayouni, S. (2020) Support Vector Machine versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 6308-6325. https://doi.org/10.1109/jstars.2020.3026724
[63]
Alabede, T.E., Bunakiye, J.R., Ishima, M.D. and Abdulazeez, A.O. (2025) A Machine Learning Approach to Predicting High Blood Pressure Using Predictive Modeling on Local and Global Datasets to Enhance Patient Safety. International Journal of Applied Information Systems, 13, 72-85. https://doi.org/10.5120/ijais2025452036
[64]
Sims, D.A. and Gamon, J.A. (2002) Relationships between Leaf Pigment Content and Spectral Reflectance across a Wide Range of Species, Leaf Structures and Developmental Stages. Remote Sensing of Environment, 81, 337-354. https://doi.org/10.1016/s0034-4257(02)00010-x
[65]
Ashourloo, D., Mobasheri, M.R. and Huete, A. (2014) Evaluating the Effect of Different Wheat Rust Disease Symptoms on Vegetation Indices Using Hyperspectral Measurements. Remote Sensing, 6, 5107-5123. https://doi.org/10.3390/rs6065107
[66]
Song, G. and Wang, Q. (2022) Developing Hyperspectral Indices for Assessing Seasonal Variations in the Ratio of Chlorophyll to Carotenoid in Deciduous Forests. Remote Sensing, 14, Article 1324. https://doi.org/10.3390/rs14061324
