Prediksi Penyakit Mangga Menggunakan Model Klasifikasi Multi-Label Berdasarkan Data Cuaca
DOI:
https://doi.org/10.23969/infomatek.v28i1.45396Keywords:
data cuaca, klasifikasi multi-label, penyakit mangga, prediksi penyakit tanaman, random forestAbstract
Penyakit pada tanaman mangga merupakan salah satu faktor utama yang dapat menurunkan produktivitas buah tropis, sehingga diperlukan pendekatan prediksi dini yang efektif berbasis data. Penelitian ini bertujuan mengembangkan model klasifikasi multi-label untuk memprediksi risiko beberapa penyakit mangga secara simultan berdasarkan data cuaca historis. Dataset yang digunakan terdiri dari data harian suhu, kelembapan relatif, dan curah hujan di Kabupaten Majalengka, Jawa Barat selama periode 2011–2023. Proses pelabelan dilakukan menggunakan pendekatan berbasis aturan untuk menghasilkan indikator biner tiga penyakit utama yaitu antraknosa, embun tepung, dan bercak daun. Model Multi-Output Random Forest dilatih menggunakan 80% data dan diuji pada 20% data dengan evaluasi menggunakan akurasi, presisi, recall, F1-score, dan hamming loss. Hasil penelitian menunjukkan bahwa model mampu mencapai akurasi sebesar 0.8811, presisi 0.8920, recall 0.9227, F1-score 0.9062, serta hamming loss yang rendah sebesar 0.0396. Model menunjukkan performa sangat baik dalam mendeteksi embun tepung dan bercak daun, namun masih menghadapi tantangan moderat pada prediksi antraknosa akibat kemiripan pola kondisi cuaca. Penelitian ini menyimpulkan bahwa integrasi pelabelan berbasis pengetahuan domain dengan pembelajaran mesin pada data cuaca efektif untuk mendukung prediksi multi-penyakit secara simultan. Temuan ini berimplikasi pada peningkatan sistem peringatan dini dan pengambilan keputusan berbasis data dalam pengelolaan penyakit tanaman mangga.
Downloads
References
Chai, Y., Liu, H., Xu, J., Samtani, S., Jiang, Y., & Liu, H. (2023). A Multi-Label Classification with an Adversarial-Based Denoising Autoencoder for Medical Image Annotation. ACM Transactions on Management Information Systems, 14(2), 1–21. https://doi.org/10.1145/3561653
Dai, G., Fan, J., Tian, Z., & Wang, C. (2023). PPLC-Net:Neural network-based plant disease identification model supported by weather data augmentation and multi-level attention mechanism. Journal of King Saud University - Computer and Information Sciences, 35(5), 101555. https://doi.org/10.1016/j.jksuci.2023.101555
Dianda, O. Z., Wonni, I., Ouédraogo, L., Sankara, P., Tollenaere, C., Del Ponte, E. M., & Fernandez, D. (2023). Lasiodiplodia species associated with mango (Mangifera indica L.) decline in Burkina Faso and influence of climatic factors on the disease distribution. Physiological and Molecular Plant Pathology, 126, 102041. https://doi.org/10.1016/j.pmpp.2023.102041
Elbeltagi, A., Pande, C. B., Kumar, M., Tolche, A. D., Singh, S. K., Kumar, A., & Vishwakarma, D. K. (2023). Prediction of meteorological drought and standardized precipitation index based on the random forest (RF), random tree (RT), and Gaussian process regression (GPR) models. Environmental Science and Pollution Research, 30(15), 43183–43202. https://doi.org/10.1007/s11356-023-25221-3
Han, M., Wu, H., Chen, Z., Li, M., & Zhang, X. (2023). A survey of multi-label classification based on supervised and semi-supervised learning. International Journal of Machine Learning and Cybernetics, 14(3), 697–724. https://doi.org/10.1007/s13042-022-01658-9
Iqbal, S., Atiq, M., Fayyaz, M., Zakria, M., Rajput, N. A., Kachelo, G. A., Ahmad, I., Usman, M., Mehmood, A., & others. (2024). Powdery Mildew of Mango: Current Status, Perspective and Emerging Tools for Management. Agricultural Sciences Journal, 6(1), 92–101. https://doi.org/10.56520/asj.v6i1.365
Kiloes, A. M., Joyce, D. C., & Abdul Aziz, A. (2024). Exploring the Challenges and Opportunities of Mango Export from Indonesia: Insights from Stakeholder Interviews. The Qualitative Report, 29(3), 811–830. https://doi.org/10.46743/2160-3715/20246343
Kumari, N., Shukla, P. K., Singh, H., Singh, H. S., Pandey, S., & Singh, A. (2025). Identification of fungi causing pre-harvest anthracnose and anthracnose-like symptoms on mango fruits (Mangifera indica). Canadian Journal of Plant Pathology, 47(3), 210–226. https://doi.org/10.1080/07060661.2025.2461015
Kusrini, K., Suputa, S., Setyanto, A., Agastya, I. M. A., Priantoro, H., & Pariyasto, S. (2022). A comparative study of mango fruit pest and disease recognition. TELKOMNIKA (Telecommunication Computing Electronics and Control), 20(6), 1264–1275. https://doi.org/10.12928/telkomnika.v20i6.21783
Liang, Q., Pan, H., He, X., Wang, S., Hou, Y., Xiao, H., Xu, G., Yi, R., Lin, D., & Yang, Z. (2024). Population structure and genetic diversity of mango (Mangifera indica L.) germplasm resources as revealed by single-nucleotide polymorphism markers. Frontiers in Plant Science, 15. https://doi.org/10.3389/fpls.2024.1328126
Liu, J., Xu, H., Peng, X., Wang, J., & He, C. (2023). Reliable composite fault diagnosis of hydraulic systems based on linear discriminant analysis and multi-output hybrid kernel extreme learning machine. Reliability Engineering & System Safety, 234, 109178. https://doi.org/https://doi.org/10.1016/j.ress.2023.109178
Liu, Z., Bashir, R. N., Iqbal, S., Shahid, M. M. A., Tausif, M., & Umer, Q. (2022). Internet of Things (IoT) and Machine Learning Model of Plant Disease Prediction–Blister Blight for Tea Plant. IEEE Access, 10, 44934–44944. https://doi.org/10.1109/ACCESS.2022.3169147
Matengu, T. T., Bullock, P. R., Mkhabela, M. S., Zvomuya, F., Henriquez, M. A., Ojo, E. R., & Fernando, W. G. D. (2024). Weather‐based models for forecasting Fusarium head blight risks in wheat and barley: A review. Plant Pathology, 73(3), 492–505. https://doi.org/10.1111/ppa.13839
moola, swathi, & Yakubreddy, K. (2024). Predicting Earthquake Parameters Using Random Forest: A Multi-Output Approach With P-Arrival Data. SSRN Electronic Journal. https://doi.org/10.2139/SSRN.5055638
Nega, A. (2025). Climate change impacts on agriculture: A review of plant diseases and insect pests in Ethiopia and East Africa, with adaptation and mitigation strategies. Advances in Agriculture, 2025(1), 5606701. https://doi.org/10.1155/aia/5606701
Pansy, D. L., & Murali, M. (2023). UAV hyperspectral remote sensor images for mango plant disease and pest identification using MD-FCM and XCS-RBFNN. Environmental Monitoring and Assessment, 195(9), 1120. https://doi.org/10.1007/s10661-023-11678-9
Rajput, N. K., & Grover, B. A. (2022). A multi-label movie genre classification scheme based on the movie’s subtitles. Multimedia Tools and Applications, 81(22), 32469–32490. https://doi.org/10.1007/s11042-022-12961-6
Raju, C., Pazhanivelan, S., Perianadar, I. V., Kaliaperumal, R., Sathyamoorthy, N. K., & Sendhilvel, V. (2024). Climate Change as an Existential Threat to Tropical Fruit Crop Production—A Review. Agriculture; Basel, 14(11). https://doi.org/10.3390/agriculture14112018
Umar, U. D., Ahmed, N., Zafar, M. Z., Rehman, A., Naqvi, S. A. H., Zulfiqar, M. A., Malik, M. T., Ali, B., Saleem, M. H., & Marc, R. A. (2022). Micronutrients foliar and drench application mitigate mango sudden decline disorder and impact fruit yield. Agronomy, 12(10), 2449. https://doi.org/10.3390/agronomy12102449
World Meteorological Organization (WMO). (2024). Guide to Instruments and Methods of Observation (WMO-No. 8) 2024 Edition.
Yadav, S., & Tewari, A. S. (2025). CONF-RCNN: a conformer and faster region-based convolutional neural network model for multi-label classification of tomato leaves disease in real field environment. Journal of Plant Diseases and Protection, 132(2), 61. https://doi.org/10.1007/s41348-024-01057-y
Yang, B., Li, M., Li, F., Wang, Y., Liang, Q., Zhao, R., Li, C., & Wang, J. (2024). A novel plant type, leaf disease and severity identification framework using CNN and transformer with multi-label method. Scientific Reports, 14(1), 11664. https://doi.org/10.1038/s41598-024-62452-x
Zhou, C., Zhao, Z., Chen, W., Feng, Y., Song, J., & Xiang, W. (2024). Residual attention based multi-label learning for apple leaf disease identification. Journal of Agricultural Engineering, 55(4). https://doi.org/10.4081/jae.2024.1595
