(Department of Electrical Engineering,
Universitas Ahmad Dahlan, Yogyakarta, Indonesia)(2) Jihad Rahmawan
(Department of Informatics,
Universitas Ahmad Dahlan, Yogyakarta, Indonesia)(3) Etika Dyah Puspitasari
(Department of Biology Education,
Universitas Ahmad Dahlan, Yogyakarta, Indonesia)(4) Anton Yudhana
(Department of Electrical Engineering,
Universitas Ahmad Dahlan, Yogyakarta, Indonesia)(5) Novi Febrianti
(Department of Biology Education,
Universitas Ahmad Dahlan, Yogyakarta, Indonesia)*corresponding author
AbstractMelon cultivation is highly vulnerable to abiotic and biotic stress, and early detection remains difficult when monitoring relies on a single sensing modality. This study investigated a multimodal stress-classification framework that combined root-zone measurements and canopy reflectance descriptors for melon monitoring under greenhouse conditions. Soil pH, nitrogen, phosphorus, potassium, and temperature were acquired using an RS485 multi-parameter sensor, while canopy images were captured using a Raspberry Pi NoIR camera and converted into Normalized Difference Vegetation Index features. Each synchronized observation was represented as a graph with fixed variable nodes and correlation-based edges, enabling relation-aware learning through a Graph Convolutional Network. The proposed model was evaluated using cross-validation and compared against conventional machine learning and non-graph deep learning baselines. The graph-based model achieved the best overall classification performance, indicating that explicit modeling of soil-canopy dependencies improved discrimination between healthy and stressed plants. The results suggest that graph-structured multimodal fusion is a promising strategy for AI-assisted crop stress monitoring.
KeywordsMelon plant; Abiotic and biotic stress; Graph convolutional network (GCN); Raspberry Pi NoIR camera;
|
DOIhttps://doi.org/10.26555/ijain.v12i2.2237 |
Article metricsAbstract views : 151 | PDF views : 7 |
Cite |
Full Text Download
|
References
[1] A. Hussain et al., “Physicochemical and phytochemical analysis of three melon fruit (canary melon, watermelon, and muskmelon) peels, and their valorization in biscuits development,” Front. Sustain. Food Syst., vol. 8, no. 1444017, pp. 1–17, 2024, doi: 10.3389/fsufs.2024.1444017.
[2] Y. Jang, D.-Y. Ko, J. Ryu, M. Kang, J. Han, and K. Ku, “Quality Evaluation and Shipping Export Potential of ‘Eliteggul’ Korean Melon (Cucumis melo var. makuwa) to Singapore Using MAP Technology,” Horticulturae, vol. 10, no. 12, p. 1354, Dec. 2024, doi: 10.3390/horticulturae10121354.
[3] H. U. Rahim et al., “Abiotic stresses in soils, their effects on plants, and mitigation strategies: a literature review,” Chem. Ecol., vol. 41, no. 4, pp. 552–585, Apr. 2025, doi: 10.1080/02757540.2024.2439830.
[4] L. Wang, C. Ju, C. Han, Z. Yu, M. Bai, and C. Wang, “The interaction of nutrient uptake with biotic and abiotic stresses in plants,” J. Integr. Plant Biol., vol. 67, no. 3, pp. 455–487, 2025, doi: 10.1111/jipb.13827.
[5] S. Choudhury and D. Moulick, Response of Field Crops to Abiotic Stress, vol. 15, no. 1391051. Boca Raton: CRC Press, 2022, doi: 10.1201/9781003258063.
[6] J. Iqbal et al., “Sustainable Rice Production Under Biotic and Abiotic Stress Challenges,” in Sustainable Agriculture in the Era of the OMICs Revolution, C. S. Prakash, S. Fiaz, M. A. Nadeem, F. S. Baloch, and A. Qayyum, Eds. Cham: Springer International Publishing, 2023, pp. 241–268.[Onlinr]. Available at: https://link.springer.com/10.1007/978-3-031-15568-0_11.
[7] U. Mittal, V. Kumar, S. Kukreja, B. Singh, N. K. Pandey, and U. Goutam, “Role of Beneficial Elements in Developing Resilience to Abiotic and Biotic Stresses in Plants: Present Status and Future Prospects,” J. Plant Growth Regul., vol. 42, no. 6, pp. 3789–3813, 2023, doi: 10.1007/s00344-022-10840-w.
[8] S. Biswas and R. Das, “Organic farming to mitigate biotic stresses under climate change scenario,” Bull. Natl. Res. Cent., vol. 48, no. 1, p. 71, 2024, doi: 10.1186/s42269-024-01226-x.
[9] A. Bera, D. Bhattacharjee, and O. Krejcar, “PND-Net: plant nutrition deficiency and disease classification using graph convolutional network,” Sci. Rep., vol. 14, no. 1, p. 15537, Jul. 2024, doi: 10.1038/s41598-024-66543-7.
[10] R. Abbasi, P. Martinez, and R. Ahmad, “Crop diagnostic system: A robust disease detection and management system for leafy green crops grown in an aquaponics facility,” Artif. Intell. Agric., vol. 10, no. 001, pp. 1–12, Dec. 2023, doi: 10.1016/j.aiia.2023.09.001.
[11] N. Paul, G. C. Sunil, D. Horvath, and X. Sun, “Deep learning for plant stress detection: A comprehensive review of technologies, challenges, and future directions,” Comput. Electron. Agric., vol. 229, no. 109734, p. 109734, Feb. 2025, doi: 10.1016/j.compag.2024.109734.
[12] P. Goyal, R. Sharda, M. Saini, and M. Siag, “A deep learning approach for early detection of drought stress in maize using proximal scale digital images,” Neural Comput. Appl., vol. 36, no. 4, pp. 1899–1913, 2024, doi: 10.1007/s00521-023-09219-z.
[13] M. Cándido-Mireles, R. Hernández-Gama, and J. Salas, “Detecting vineyard plants stress in situ using deep learning,” Comput. Electron. Agric., vol. 210, p. 107837, 2023, doi: 10.1016/j.compag.2023.107837.
[14] J. Zapata-Londoño, J. Botero-Valencia, V. García-Pineda, E. Reyes-Vera, and R. Hernández-García, “A Comprehensive Review of Optical and AI-Based Approaches for Plant Growth Assessment,” Agronomy, vol. 15, no. 8, p. 1781, Jul. 2025, doi: 10.3390/agronomy15081781.
[15] A. Nițu, C. Florea, M. Ivanovici, and A. Racoviteanu, “NDVI and Beyond: Vegetation Indices as Features for Crop Recognition and Segmentation in Hyperspectral Data,” Sensors, vol. 25, no. 12, p. 3817, Jun. 2025, doi: 10.3390/s25123817.
[16] Z. Wei and W. Fang, “UV-NDVI for real-time crop health monitoring in vertical farms,” Smart Agric. Technol., vol. 8, p. 100462, 2024, doi: 10.1016/j.atech.2024.100462.
[17] Q. Liu, F. Yao, A. Garcia-garcia, J. Zhang, J. Li, and S. Ma, “The response and sensitivity of global vegetation to water stress : A comparison of different satellite-based NDVI products,” Int. J. Appl. Earth Obs. Geoinf., vol. 120, no. 103341, 2023, doi: 10.1016/j.jag.2023.103341.
[18] K. Yan et al., “A global systematic review of the remote sensing vegetation indices,” Int. J. Appl. Earth Obs. Geoinf., vol. 139, no. 104560, 2025, doi: 10.1016/j.jag.2025.104560.
[19] J. Cooper, K. Propst, and C. D. Hirsch, “Current methods and future needs for visible and non-visible detection of plant stress responses,” Front. Plant Sci., vol. 16, no. 1585413, 2025, doi: 10.3389/fpls.2025.1585413.
[20] J. W. Choi et al., “Application of multimodal data fusion and explainable AI for classifying water stress in sweet potatoes,” Front. Plant Sci., vol. 16, no. 1681915, 2025, doi: 10.3389/fpls.2025.1681915.
[21] J. Li, L. Wang, J. Liu, and J. Tang, “ViST : A Ubiquitous Model with Multimodal Fusion for Crop Growth Prediction,” ACM Trans. Sens. Networks, vol. 20, no. 1, 2024, doi: 10.1145/3627707.
[22] L. Waikhom and R. Patgiri, “A survey of graph neural networks in various learning paradigms: methods, applications, and challenges,” Artif. Intell. Rev., vol. 56, no. 7, pp. 6295–6364, 2023, doi: 10.1007/s10462-022-10321-2.
[23] V. Ponzi, “Graph Neural Networks : Architectures , Applications , and Future Directions,” IEEE Access, vol. 13, pp. 62870–62891, 2025, doi: 10.1109/ACCESS.2025.3558752.
[24] A. M. Malla and A. A. Banka, “Comprehensive Review of Graph Neural Networks: Challenges, Classification, Architectures, Applications, and Potential Utility in Bioinformatics,” Expert Syst., vol. 42, no. 8, p. e70091, Aug. 2025, doi: 10.1111/exsy.70091.
[25] F. Lu et al., “A Spatiotemporal Attention-Guided Graph Neural Network for Precise Hyperspectral Estimation of Corn Nitrogen Content,” Agronomy, vol. 15, no. 5, p. 1041, Apr. 2025, doi: 10.3390/agronomy15051041.
[26] L. Wang, Z. Chen, W. Liu, and H. Huang, “A Temporal–Geospatial Deep Learning Framework for Crop Yield Prediction,” Electronics, vol. 13, no. 21, p. 4273, Oct. 2024, doi: 10.3390/electronics13214273.
[27] T. He, M. Li, and D. Jin, “Deep learning-based time series prediction for precision field crop protection,” Front. Plant Sci., vol. 16, no. 15775796, pp. 1–23, Jun. 2025, doi: 10.3389/fpls.2025.1575796.
[28] S. Liu, Y. Ampatzidis, C. Zhou, and W. Suk, “AI-driven time series analysis for predicting strawberry weekly yields integrating fruit monitoring and weather data for optimized harvest planning,” Comput. Electron. Agric., vol. 233, no. 110212, 2025, doi: 10.1016/j.compag.2025.110212.
[29] I. Fuentes et al., “The normalised difference vegetation index as an analytic tool for wheat crop yield prediction: A review and meta-analysis,” Precis. Agric., vol. 26, no. 4, p. 55, 2025, doi: 10.1007/s11119-025-10247-z.
[30] J. M. Siqueira et al., “Estimation of Kcb for Irrigated Melon Using NDVI Obtained Through UAV Imaging in the Brazilian Semiarid Region,” AgriEngineering, vol. 7, no. 10, p. 340, Oct. 2025, doi: 10.3390/agriengineering7100340.
[31] H. Santo and F. H. Barrios-masias, “Melon Grafting Effects on Plant Performance and Yield in the High Desert,” HortScience, vol. 59, no. 8, pp. 1143–1149, 2024, doi: 10.21273/HORTSCI17850-24.
[32] E. Ozdemir, M. Kulak, and A. Sekertekin, “Bibliometric Analysis of Monitoring and Mapping of Soil Salinity Using Remote Sensing Approaches: Reports from the Past Three Decades,” Eurasian Soil Sci., vol. 58, no. 11, p. 141, 2025, doi: 10.1134/S1064229325601027.
[33] A. Upadhyay et al., “Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture,” Artif. Intell. Rev., vol. 58, no. 3, p. 92, 2025, doi: 10.1007/s10462-024-11100-x.
[34] R. Raju and T. M. Thasleema, “Advancements in Automated Plant Disease Detection: a Comprehensive Review of Imaging Technologies and Deep Learning Applications,” J. Crop Heal., vol. 77, no. 6, p. 185, 2025, doi: 10.1007/s10343-025-01247-0.
[35] M. Shoaib et al., “An advanced deep learning models-based plant disease detection: A review of recent research,” Front. Plant Sci., vol. 14, no. 1158933, pp. 1–22, Mar. 2023, doi: 10.3389/fpls.2023.1158933.
[36] G. Tuteja et al., “CNNAttLSTM: an attention-enhanced CNN–LSTM architecture for high-precision jackfruit leaf disease classification,” Front. Plant Sci., vol. 16, no. 1720471, pp. 1–21, Jan. 2026, doi: 10.3389/fpls.2025.1720471.
[37] R. Singh, R. Nisha, R. Naik, K. Upendar, C. Nickhil, and S. C. Deka, “Sensor fusion techniques in deep learning for multimodal fruit and vegetable quality assessment: A comprehensive review,” J. Food Meas. Charact., vol. 18, no. 9, pp. 8088–8109, 2024, doi: 10.1007/s11694-024-02789-z.
[38] H. Li, L. Yue, and S. Luo, “Estimating the full-period rice leaf area index using CNN-LSTM-Attention and multispectral images from unmanned aerial vehicles,” Front. Plant Sci., vol. 16, no. 1636967, pp. 1–18, Sep. 2025, doi: 10.3389/fpls.2025.1636967.
[39] A. Singh and K. Gaurav, “Deep learning and data fusion to estimate surface soil moisture from multi-sensor satellite images,” Sci. Rep., vol. 13, no. 1, p. 2251, Feb. 2023, doi: 10.1038/s41598-023-28939-9.
[40] S. Li, P. Zhu, N. Song, C. Li, and J. Wang, “Regional Soil Moisture Estimation Leveraging Multi-Source Data Fusion and Automated Machine Learning,” Remote Sens., vol. 17, no. 5, p. 837, Feb. 2025, doi: 10.3390/rs17050837.
[41] S. Kaur and H. Sharma, “Multimodal graph neural networks for earth observation and sustainable resource management: a comprehensive review and research roadmap,” Discov. Sustain., vol. 7, no. 1, p. 21, Dec. 2025, doi: 10.1007/s43621-025-02317-z.
[42] Y. Yang, J. Liu, and W. Wan, “Regularizing Softmax With Graph Similarity for Enhanced Node Classification in Semisupervised Settings,” Int. J. Intell. Syst., vol. 2025, no. 1, p. 8861477, Jan. 2025, doi: 10.1155/int/8861477.
[43] K. Mallick et al., “Net fluxes of broadband shortwave and photosynthetically active radiation complement NDVI and near infrared reflectance of vegetation to explain gross photosynthesis variability across ecosystems and climate,” Remote Sens. Environ., vol. 307, p. 114123, 2024, doi: 10.1016/j.rse.2024.114123.
[44] M. Diykh et al., “Empirical curvelet transform based deep DenseNet model to predict NDVI using RGB drone imagery data,” Comput. Electron. Agric., vol. 221, no. 108964, p. 108964, Jun. 2024, doi: 10.1016/j.compag.2024.108964.
[45] A. de la I. Martinez and S. M. Labib, “Demystifying normalized difference vegetation index (NDVI) for greenness exposure assessments and policy interventions in urban greening,” Environ. Res., vol. 220, no. 115155, p. 115155, Mar. 2023, doi: 10.1016/j.envres.2022.115155.
[46] A. Rehman et al., “Differential Response of Two Contrasting Melon ( Cucumis melo L .) Genotypes to Drought Stress,” J. Plant Biol., vol. 66, pp. 519–534, 2023, doi: 10.1007/s12374-023-09398-1.
[47] G. S. Mirbehbahani, F. Soltani Salehabadi, and M. Shokrpour, “Differential Assessment of Growth, Physiological Parameters, and Leaf Responses to Salinity Stress in Inbred Melon Lines,” Gesunde Pflanz., vol. 75, no. 6, pp. 2623–2638, 2023, doi: 10.1007/s10343-023-00877-6.
[48] M. Nandan, “GraphXAI : a survey of graph neural networks (GNNs) for explainable AI (XAI),” Neural Comput. Appl., vol. 37, pp. 10949–11000, 2025, doi: 10.1007/s00521-025-11054-3.
[49] R. Ying, “GNNExplainer : Generating Explanations for Graph Neural Networks,” 33rd Conference on Neural Information Processing Systems (NeurIPS), pp. 1 - 13, 2019. [Online]. Available at: https://share.google/udB6r1XQduLu1hjg5
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0