Predicting physiological health states of tropical papaya using UAV multispectral imagery for precision agriculture monitoring

Abstract

Spatial heterogeneity in crop physiological performance remains a major constraint to efficient management in tropical horticultural systems. This study evaluated the capability of UAV-based multispectral imagery to predict intrinsically derived physiological health states of tropical papaya by integrating canopy spectral predictors with multivariate plant functional measurements. Field observations were conducted on 103 papaya trees in a commercial plantation in Yogyakarta, Indonesia. Six physiological indicators, namely SPAD chlorophyll meter value, stomatal conductance (gsw), electron transport rate (etr), maximum fluorescence (Fm), steady-state fluorescence (Fs), and effective quantum yield of photosystem II (ΦPSII), were used to derive intrinsic health states through K-means clustering after z-score standardization. Candidate cluster numbers ( K = 2–5) were evaluated using inertia, silhouette coefficient, Calinski–Harabasz index, and Davies–Bouldin index. Although K = 2 yielded the most compact statistical partition, K = 3 was retained to preserve agronomically interpretable Healthy, Moderate, and Stressed physiological states. A total of 124 UAV-derived spectral predictors were constructed at the plant level and sequentially reduced to 21 predictors through correlation pruning and recursive feature elimination with cross-validation (RFECV). Random Forest classification using the selected predictors achieved a training accuracy of 0.958, testing accuracy of 0.903, and 5-fold cross-validation accuracy of 0.96 ± 0.02. Model interpretability identified GBNDVI_max, GBNDVI_mean, rho_green_min, MGRVI_std, RTVI_max, and MGRVI_min as key spectral features, while partial dependence analysis showed stronger threshold-like relationships with stomatal conductance than with ΦPSII. These findings indicate that UAV multispectral sensing can capture physiologically meaningful within-field heterogeneity in tropical papaya and support management-priority monitoring in precision agriculture.

Keywords

UAV multispectral imagery / Physiological health states / Tropical papaya / Random forest classification / Precision agriculture

References

[1] D.J. Mulla, Twenty five years of remote sensing in precision agriculture: key advances and remaining knowledge gaps, Biosyst. Eng. 114 (2013) 358-371, https://doi.org/10.1016/j.biosystemseng.2012.08.009.

[2] J.P. Pennacchi, J.M.S. Lira, M. Rodrigues, F.H.S. Garcia, A.M. das C. Mendonça, J.P.R.A.D. Barbosa, A systemic approach to the quantification of the phenotypic plasticity of plant physiological traits: the multivariate plasticity index, J. Exp. Bot. 72 (2021) 1864-1878, https://doi.org/10.1093/jxb/eraa545.

[3] C. Zheng, A. Abd-Elrahman, V. Whitaker, C. Dalid, Prediction of strawberry dry biomass from UAV multispectral imagery using multiple machine learning methods, Remote Sens. 14 (2022) 4511, https://doi.org/10.3390/rs14184511.

[4] F. Alliaume, G. Echeverria, M. Ferrer, P. González Barrios, A Study of the multivariate spatial variability of soil properties, and their association with Vine vigor growing on a clayish soil, J. Soil Sci. Plant Nutr. 24 (2024) 3282-3297, https://doi.org/10.1007/s42729-024-01751-8.

[5] X. Mo, H. Peng, J. Xin, S. Wang, Analysis of urea nitrogen leaching under high-intensity rainfall using HYDRUS-1D, J. Environ. Manag. 312 (2022) 114900, https://doi.org/10.1016/j.jenvman.2022.114900.

[6] M. Lechenet, F. Dessaint, G. Py, D. Makowski, N. Munier-Jolain, Reducing pesticide use while preserving crop productivity and profitability on arable farms, Nat. Plants 3 (2017) 17008, https://doi.org/10.1038/nplants.2017.8.

[7] C. Georgi, D. Spengler, S. Itzerott, B. Kleinschmit, Automatic delineation algorithm for site-specific management zones based on satellite remote sensing data, Precis. Agric. 19 (2018) 684-707, https://doi.org/10.1007/s11119-017-9549-y.

[8] J. Uddling, J. Gelang-Alfredsson, K. Piikki, H. Pleijel, Evaluating the relationship between leaf chlorophyll concentration and SPAD-502 chlorophyll meter readings, Photosynth. Res. 91 (2007) 37-46, https://doi.org/10.1007/s11120-006-9077-5.

[9] T. Lawson, S. Vialet-Chabrand, Speedy stomata, photosynthesis and plant water use efficiency, New Phytol. 221 (2019) 93-98, https://doi.org/10.1111/nph.15330.

[10] Q. Jiao, X. Hu, Recent advances and emerging trends in chlorophyll fluorescence parameter, Phyton 94 (2025) 2615-2630, https://doi.org/10.32604/phyton.2025.069246.

[11] L.J. Velazquez-Chavez, A. Daccache, A.Z. Mohamed, M. Centritto, Plant-based and remote sensing for water status monitoring of orchard crops: systematic review and meta-analysis, Agric. Water Manag. 303 (2024) 109051, https://doi.org/10.1016/j.agwat.2024.109051.

[12] R.P. Sishodia, R.L. Ray, S.K. Singh, Applications of remote sensing in precision agriculture: a review, Remote Sens. 12 (2020) 3136, https://doi.org/10.3390/rs12193136.

[13] W.H. Maes, K. Steppe, Perspectives for remote sensing with unmanned aerial vehicles in precision agriculture, Trends Plant Sci. 24 (2019) 152-164, https://doi.org/10.1016/j.tplants.2018.11.007.

[14] R. Zhang, X. Wu, J. Li, P. Zhao, Q. Zhang, L. Wuri, D. Zhang, Z. Zhang, L. Yang, A bibliometric review of deep learning in crop monitoring: trends, challenges, and future perspectives, Front. Artif. Intell. 8 (2025) 1636898, https://doi.org/10.3389/frai.2025.1636898.

[15] A.A. Gitelson, Wide dynamic range vegetation index for remote quantification of biophysical characteristics of vegetation, J. Plant Physiol. 161 (2004) 165-173, https://doi.org/10.1078/0176-1617-01176.

[16] J. Xue, B. Su, Significant remote sensing vegetation indices: a review of developments and applications, J. Sens. 2017 (2017) 1-17, https://doi.org/10.1155/2017/1353691.

[17] Z. Fu, J. Jiang, Y. Gao, B. Krienke, M. Wang, K. Zhong, Q. Cao, Y. Tian, Y. Zhu, W. Cao, X. Liu, Wheat growth monitoring and yield estimation based on multi-rotor unmanned aerial vehicle, Remote Sens. 12 (2020) 508, https://doi.org/10.3390/rs12030508.

[18] X. Zhou, H.B. Zheng, X.Q. Xu, J.Y. He, X.K. Ge, X. Yao, T. Cheng, Y. Zhu, W.X. Cao, Y.C. Tian, Predicting grain yield in rice using multi-temporal vegetation indices from UAV-based multispectral and digital imagery, ISPRS J. Photogramm. Remote Sens. 130 (2017) 246-255, https://doi.org/10.1016/j.isprsjprs.2017.05.003.

[19] L. Wan, Y. Li, H. Cen, J. Zhu, W. Yin, W. Wu, H. Zhu, D. Sun, W. Zhou, Y. He, Combining UAV-Based vegetation indices and image classification to estimate flower number in oilseed rape, Remote Sens. 10 (2018) 1484, https://doi.org/10.3390/rs10091484.

[20] K. Berger, M. Machwitz, M. Kycko, S.C. Kefauver, S. Van Wittenberghe, M. Gerhards, et al., Multi-sensor spectral synergies for crop stress detection and monitoring in the optical domain: a review, Remote Sens. Environ. 280 (2022) 113198, https://doi.org/10.1016/j.rse.2022.113198.

[21] G. Sapes, L. Schroeder, A. Scott, I. Clark, J. Juzwik, R.A. Montgomery, J.A. Guzmán Q, J. Cavender-Bares, Mechanistic links between physiology and spectral reflectance enable previsual detection of oak wilt and drought stress, Proc. Natl. Acad. Sci. 121 (2024) e2316164121, https://doi.org/10.1073/pnas.2316164121.

[22] M. Moustakas, I. Sperdouli, J. Moustaka, Early drought stress warning in plants: color pictures of photosystem II photochemistry, Climate 10 (2022) 179, https://doi.org/10.3390/cli10110179.

[23] T. Swoczyna, H.M. Kalaji, F. Bussotti, J. Mojski, M. Pollastrini, Environmental stress - what can we learn from chlorophyll a fluorescence analysis in woody plants? A review, Front. Plant Sci. 13 (2022), https://doi.org/10.3389/fpls.2022.1048582.

[24] N. Vilfan, C. van der Tol, W. Verhoef, Estimating photosynthetic capacity from leaf reflectance and Chl fluorescence by coupling radiative transfer to a model for photosynthesis, New Phytol. 223 (2019) 487-500, https://doi.org/10.1111/nph.15782.

[25] A. Matese, S.F. Di Gennaro, Practical applications of a multisensor UAV platform based on multispectral, thermal and RGB high resolution images in precision viticulture, Agriculture 8 (2018) 116, https://doi.org/10.3390/agriculture8070116.

[26] B. Wang, Y. Yan, J. Zhao, R. Kaousar, Y. Lan, Status and prospect of the application of UAV remote sensing technology in smart orchard management, Crop Prot. 195 (2025) 107240, https://doi.org/10.1016/j.cropro.2025.107240.

[27] R.I. Pratiwi, S. Suminah, E. Widiyanti, Motivasi Petani dalam Budidaya Tanaman Pepaya (Carica papaya L.) di Kecamatan Mojosongo Kabupaten Boyolali , AGRITEXTS: Journal of Agricultural Extension 46 (2023) 108, https://doi.org/10.20961/agritexts.v46i2.67123.

[28] C.C. Pham, W.C. Lin, Development and field evaluation of a UWB-IMU navigated autonomous spraying robot for papaya greenhouses, Smart Agric. Technol. 12 (2025) 101267, https://doi.org/10.1016/j.atech.2025.101267.

[29] N. Bagheri, H. Ahmadi, S.K. Alavipanah, M. Omid, Multispectral remote sensing for site-specific nitrogen fertilizer management, Pesqui. Agropecu. Bras. 48 (2013) 1394-1401, https://doi.org/10.1590/S0100-204X2013001000011.

[30] A. Risal, H. Niu, J.L. Landivar-Scott, M.M. Maeda, C.W. Bednarz, J. Landivar-Bowles, N. Duffield, P. Payton, P. Pal, R.J. Lascano, T. Goebel, M. Bhandari, Improving irrigation management of cotton with small Unmanned Aerial Vehicle (UAV) in Texas High Plains, Water (Basel) 16 (2024) 1300, https://doi.org/10.3390/w16091300.

[31] L.N. Lacerda, J. Snider, Y. Cohen, V. Liakos, M.R. Levi, G. Vellidis, Correlation of UAV and satellite-derived vegetation indices with cotton physiological parameters and their use as a tool for scheduling variable rate irrigation in cotton, Precis. Agric. 23 (2022) 2089-2114, https://doi.org/10.1007/s11119-022-09948-6.

[32] S.B. Khose, D.R. Mailapalli, UAV-based multispectral image analytics and machine learning for predicting crop nitrogen in rice, Geocarto Int. 39 (2024) 2373867, https://doi.org/10.1080/10106049.2024.2373867.

[33] A. Wiratmoko, A.P. Nugroho, M.S. Muna, M. Syarovy, Sukarman Suwardi, L. Sutiarso, Development of cloud-based decision support system for fertilizer management - a case study in Wilmar oil palm plantation, in: Proceedings of the International Conference on Sustainable Environment, Agriculture and Tourism (ICOSEAT 2022), Atlantis Press, 2023, https://doi.org/10.2991/978-94-6463-086-2_69.

[34] H. Lyu, T. Watanabe, Y. Ota, A. Hartono, M. Anda, R.A. Dahlgren, S. Funakawa, Climatic controls on soil clay mineral distributions in humid volcanic regions of Sumatra and Java, Indonesia, Geoderma 425 (2022) 116058, https://doi.org/10.1016/j.geoderma.2022.116058.

[35] S.A.H. Mohsan, N.Q.H. Othman, Y. Li, M.H. Alsharif, M.A. Khan, Unmanned aerial vehicles (UAVs): practical aspects, applications, open challenges, security issues, and future trends, Intell. Serv. Robot. 16 (2023) 109-137, https://doi.org/10.1007/s11370-022-00452-4.

[36] T.G. Shibaeva, A.V. Mamaev, E.G. Sherudilo, Evaluation of a SPAD-502 plus chlorophyll meter to estimate chlorophyll content in leaves with interveinal chlorosis, Russ. J. Plant Physiol. 67 (2020) 690-696, https://doi.org/10.1134/S1021443720040160.

[37] M.S. Muna, A.P. Nugroho, M. Syarovy, A. Wiratmoko, Suwardi, L. Sutiarso, Development of automatic counting system for palm oil tree based on remote sensing imagery. https://doi.org/10.2991/978-94-6463-086-2_68, 2022.

[38] J.R. Pleban, C.R. Guadagno, D.S. Mackay, C. Weinig, B.E. Ewers, Rapid chlorophyll a fluorescence light response curves mechanistically inform photosynthesis modeling, Plant Physiol. 183 (2020) 602-619, https://doi.org/10.1104/pp.19.00375.

[39] M. Lu, P. Gao, J. Hu, J. Hou, D. Wang, A classification method of stress in plants using unsupervised learning algorithm and chlorophyll fluorescence technology, Front. Plant Sci. 14 (2023) 1202092, https://doi.org/10.3389/fpls.2023.1202092.

[40] T. Souza, Principal Component Analysis (PCA), in: Advanced Statistical Analysis for Soil Scientists, Springer Nature Switzerland, Cham, 2025, pp. 43-56, https://doi.org/10.1007/978-3-031-88161-9_4.

[41] I.T. Jolliffe, Principal Component Analysis, Springer-Verlag, New York, 2002, https://doi.org/10.1007/b98835.

[42] S. Sankaran, J. Zhou, L.R. Khot, J.J. Trapp, E. Mndolwa, P.N. Miklas, High-throughput field phenotyping in dry bean using small unmanned aerial vehicle based multispectral imagery, Comput. Electron. Agric. 151 (2018) 84-92, https://doi.org/10.1016/j.compag.2018.05.034.

[43] S. Liu, B. Zhang, W. Yang, T. Chen, H. Zhang, Y. Lin, J. Tan, X. Li, Y. Gao, S. Yao, Y. Lan, L. Zhang, Quantification of physiological parameters of rice varieties based on multi-spectral remote sensing and machine learning models, Remote Sens. 15 (2023) 453, https://doi.org/10.3390/rs15020453.

[44] S. Zhang, X. Wang, H. Lin, Y. Dong, Z. Qiang, A review of the application of UAV multispectral remote sensing technology in precision agriculture, Smart Agric. Technol. 12 (2025) 101406, https://doi.org/10.1016/j.atech.2025.101406.

[45] Y. Lan, Z. Huang, X. Deng, Z. Zhu, H. Huang, Z. Zheng, B. Lian, G. Zeng, Z. Tong, Comparison of machine learning methods for citrus greening detection on UAV multispectral images, Comput. Electron. Agric. 171 (2020) 105234, https://doi.org/10.1016/j.compag.2020.105234.

[46] K.M. Sujon, R. Hassan, K. Choi, M.A. Samad, Accuracy, precision, recall, f1-score, or MCC? Empirical evidence from advanced statistics, ML, and XAI for evaluating business predictive models, J. Big Data 12 (2025) 268, https://doi.org/10.1186/s40537-025-01313-4.

[47] S. Nembrini, I.R. König, M.N. Wright, The revival of the Gini importance? Bioinformatics 34 (2018) 3711-3718, https://doi.org/10.1093/bioinformatics/bty373.

[48] A. Koushik, M. Manoj, N. Nezamuddin, SHapley Additive exPlanations for explaining artificial neural network based mode choice models, Transp. Dev. Econ. 10 (2024) 12, https://doi.org/10.1007/s40890-024-00200-6.

[49] C. Kirabo, S. Murindanyi, N.P. Kirabo, K.M. Hasib, G. Marvin, SHapley Additive exPlanations for machine emotion intelligence in CNNs, pp. 657-671, https://doi.org/10.1007/978-981-97-3526-6_50, 2024.

[50] S. Candiago, F. Remondino, M. De Giglio, M. Dubbini, M. Gattelli, Evaluating multispectral images and vegetation indices for precision farming applications from UAV images, Remote Sens. 7 (2015) 4026-4047, https://doi.org/10.3390/rs70404026.

[51] P.J. Zarco-Tejada, A. Hornero, R. Hernández-Clemente, P.S.A. Beck, Understanding the temporal dimension of the red-edge spectral region for forest decline detection using high-resolution hyperspectral and Sentinel-2a imagery, ISPRS J. Photogrammetry Remote Sens. 137 (2018) 134-148, https://doi.org/10.1016/j.isprsjprs.2018.01.017.

[52] S.B. Opiyo, L. Pienaar, S.J. Piketh, R.P. Burger, H. Chikoore, H. Havenga, Assessment of vegetation density trends in response to long-term climate change impacts in Western South Africa (1962-2022) using SPEI and NDVI time series, Discover Forests 1 (2025) 29, https://doi.org/10.1007/s44415-025-00030-3.

[53] A. Gitelson, A. Viña, A. Solovchenko, T. Arkebauer, Y. Inoue, Derivation of canopy light absorption coefficient from reflectance spectra, Remote Sens. Environ. 231 (2019) 111276, https://doi.org/10.1016/j.rse.2019.111276.

[54] Z. Jiang, A. Huete, K. Didan, T. Miura, Development of a two-band enhanced vegetation index without a blue band, Remote Sens. Environ. 112 (2008) 3833-3845, https://doi.org/10.1016/j.rse.2008.06.006.

[55] A.A. Gitelson, Y. Peng, J.G. Masek, D.C. Rundquist, S. Verma, A. Suyker, J.M. Baker, J.L. Hatfield, T. Meyers, Remote estimation of crop gross primary production with Landsat data, Remote Sens. Environ. 121 (2012) 404-414, https://doi.org/10.1016/j.rse.2012.02.017.

[56] S. Gao, K. Yan, J. Liu, J. Pu, D. Zou, J. Qi, X. Mu, G. Yan, Assessment of remote-sensed vegetation indices for estimating forest chlorophyll concentration, Ecol. Indic. 162 (2024) 112001, https://doi.org/10.1016/j.ecolind.2024.112001.

[57] A. Huete, K. Didan, T. Miura, E.P. Rodriguez, X. Gao, L.G. Ferreira, Overview of the radiometric and biophysical performance of the MODIS vegetation indices, Remote Sens. Environ. 83 (2002) 195-213, https://doi.org/10.1016/S0034-4257(02)00096-2.

[58] C. Wongoutong, The impact of neglecting feature scaling in k-means clustering, PLoS One 19 (2024) e0310839, https://doi.org/10.1371/journal.pone.0310839.

[59] J. Calder, P.J. Olver, Principal component analysis, 311-356, https://doi.org/10.1007/978-3-031-93764-4_8, 2025.

[60] A.P. Nugroho, A. Wiratmoko, U.D. Oktasari, R.F. Kusumawardani, F.A. Pradana, L. Sutiarso, Suwardi Sukarman, S. Primananda, T. Okayasu, A confidence-weighted decision framework for on-site fertilizer quality screening and off-spec detection in smart agricultural systems using low-cost macronutrient sensors, Smart Agric. Technol. (2026) 102103, https://doi.org/10.1016/j.atech.2026.102103.

[61] A.P. Nugroho, A. Wiratmoko, D. Nugraha, S. Markumningsih, L. Sutiarso, M.A.F. Falah, T. Okayasu, Development of a low-cost thermal imaging system for water stress monitoring in indoor farming, Smart Agric. Technol. 11 (2025) 101048, https://doi.org/10.1016/j.atech.2025.101048.