Artificial Neural Network Model for Shallot Disease Severity Prediction Using Drone Multispectral Imagery
Abstract
Shallot plant diseases can reduce yields by up to 50% of total land area. Currently, shallot plant disease identification relies on direct observation, which is less effective and efficient due to varying intensities of disease and large cultivation areas. This study aims to develop a predictive model for shallot disease severity using multispectral drone imagery, apply Artificial Neural Network (ANN) algorithm to analyze multispectral band data, and evaluate the model's performance. The study used ANN algorithm with multi-layer perceptron regressor, involving following stages such as dataset acquisition, dataset stitching, dataset filtering and feature extraction, model development, and model evaluation. Multispectral data were taken using DJI Mavic 3 Multispectral drone, resulting 696 images per bands that were stitched into orthophoto map. The filtering process of plant objects yielded better model training results compared to unfiltered data. The optimal ANN model structure was identified as 4-6-2-1, with R² value of 0.9194 and MAE value of 0.0618. Model testing results demonstrated that using four input bands (G, R, RE, NIR) provided the best performance with R² value of 0.9194, followed by combination of two bands (R, RE) with R² value of 0.8883. This indicated that the R and RE bands were most strongly correlated with shallot disease severity.
Keywords: Drone, Multi-layer perceptron, Multispectral imagery, Plant disease, Shallot.
Downloads
References
Amarillis, S., Solahudin, M., & Sucahyo, L. (2022). The Study of Shallot Seedling from TSS (True Shallot Seed) on LCAC (Low-Cost Aeroponic Chamber). Earth and Environmental Science, 1038, 1–7. https://doi.org/10.1088/1755-1315/1038/1/012013
Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science, 7, 1–24. https://doi.org/10.7717/PEERJ-CS.623
Davidson, C., Jaganathan, V., Sivakumar, A. N., Czarnecki, J. M. P., & Chowdhary, G. (2022). NDVI/NDRE prediction from standard RGB aerial imagery using deep learning. Computers and Electronics in Agriculture, 203, 107396. https://doi.org/10.1016/J.COMPAG.2022.107396
Gunardi, K., Priandana, K., Kusuma Dewi Hardhienata, M., Wulandari, & Solahudin, M. (2023). Perbandingan Algoritma Klasifikasi untuk Mendeteksi Kebutuhan Nitrogen Tanaman Padi Berdasarkan Data Citra Multi-spectral Drone. Jurnal Ilmu Komputer Dan Agri-Informatika, 10(2), 238–249. https://doi.org/10.29244/jika.10.2.238-249
Hamim. (2018). Fisiologi Tumbuhan 1: Air, Energi, dan Metabolisme Karbon (1st ed.). IPB Press.
Hersanti, Febrianti, N., & Djaya, L. (2023). Effectiveness of Nano Chitosan and Nano Silica to Suppress the Growth of Fusarium oxysporum, the Cause of Twisting Disease on Shallot. Jurnal Fitopatologi Indonesia, 19(6), 265–275. https://doi.org/10.14692/jfi.19.6.265-275
Kementerian Pertanian. (2023). Komoditas Pertanian Subsektor Hortikultura Bawang Merah (1st ed.). Pusat Data dan Sistem Informasi Pertanian.
Kesuma, I. M. S. A., Nugroho, A. S. B., & Aminullah, A. (2023). Pengaruh Variasi Hidden Layer Terhadap Nilai MAPE Pada Pengembangan Model Estimasi Biaya Menggunakan Artificial Neural Network. Jurnal Teknik Sipil, 9(2), 152–163. https://doi.org/10.31849/siklus.v9i2.14221
Kim, W. S., Lee, D. H., & Kim, Y. J. (2020). Machine vision-based automatic disease symptom detection of onion downy mildew. Computers and Electronics in Agriculture, 168(July 2019), 105099. https://doi.org/10.1016/j.compag.2019.105099
Kurniasari, D., & Ammar, M. N. (2024). Analisis Struktur Terbaik Neural Network dengan Algoritma Backpropagation dalam Memprediksi Indeks Kandungan Sulfida ( SO 2 ) di Ibu Kota Jakarta. Jurnal Sistem Dan Teknologi Informasi, 12(2), 321–329. https://doi.org/10.26418/justin.v12i2.76166
Manalu, D.R., Sebayang, J., Manullang, H.G. (2023). Klasifikasi penyakit bawang merah melalui citra daun dengan metode Kmeans. METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi, 7(1), 150-157. https://doi.org/10.46880/jmika.Vol7No1.pp150-157
Merwe, D., Burchfield, D. R., Witt, T. D., Price, K. P., & Sharda, A. (2020). Drones in agriculture. Advances in Agronomy, 162, 1–30. https://doi.org/10.1016/bs.agron.2020.03.001
Messina, G., Peña, J. M., Vizzari, M., & Modica, G. (2020). A comparison of UAV and satellites multispectral imagery in monitoring onion crop. An application in the ‘Cipolla Rossa di Tropea’ (Italy). Remote Sensing, 12(20), 1–27. https://doi.org/10.3390/rs12203424
Nurhikma, Purnawansyah, Darwis, H., & L, H. (2023). K-Nearest Neighbor dan Convolutional Neural Network pada Klasifikasi Penyakit Tanaman Bawang Merah. Techno, 22(3), 643–653.
Pertanian, K. (2023). Komoditas Pertanian Subsektor Hortikultura Bawang Merah (1st ed.). Pusat Data dan Sistem Informasi Pertanian.
Prakoso, E. B., Wiyatingsih, S., & Nirwanto, H. (2016). Uji ketahanan berbagai kultivar bawang merah ( Allium ascalonicum ) terhadap infeksi penyakit moler ( Fusarium oxysporum f . sp . cepae ). Jurnal Plumula., 5(1), 10–20. http://ejournal.upnjatim.ac.id/index.php/plumula/article/view/773
Purwansya, Y. G., Solahudin, M., & Supriyanto, S. (2024). Effect of Preprocessing and Augmentation Process in Development of a Deep Learning Model for Fusarium Detection in Shallots. Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering), 13(2), 350. https://doi.org/10.23960/jtep-l.v13i2.350-360
Sari, M. P., Hadisutrisno, B., & Suryanti, S. (2017). Penekanan Perkembangan Penyakit Bercak Ungu pada Bawang Merah oleh Cendawan Mikoriza Arbuskula. Jurnal Fitopatologi Indonesia, 12(5), 159. https://doi.org/10.14692/jfi.12.5.159
Satria, A., Badri, R. M., & Safitri, I. (2023). Prediksi Hasil Panen Tanaman Pangan Sumatera dengan Metode Machine Learning. Digital Transformation Technology, 3(2), 389–398. https://doi.org/10.47709/digitech.v3i2.2852
Sholeh, M. I., Suhartiningsih, D., & Nurcahyanti, D. (2023). Perkembangan Penyakit Moler (Fusarium oxysporum f.sp cepae) pada Sentra Produksi Bawang Merah Berkala Ilmiah Pertanian. Berkala Ilmiah Pertanian, 6(2), 56–62.
Solahudin, M., & Mutawally, F. W. (2020). Identifikasi Ganoderma Pada Tanaman Kelapa Sawit Berbasis Reflektansi Gelombang Multispektral. Jurnal Keteknikan Pertanian, 7(3), 193–200. https://doi.org/10.19028/jtep.07.3.193-200
Solahudin, M., Pramudya, B., Liyantono, Supriyanto, & Manaf, R. (2015). Gemini Virus Attack Analysis in Field of Chili (Capsicum Annuum L.) Using Aerial Photography and Bayesian Segmentation Method. Procedia Environmental Sciences, 24, 254–257. https://doi.org/10.1016/j.proenv.2015.03.033
Supriyanto, Noguchi, R., Ahamed, T., Rani, D. S., Sakurai, K., Nasution, M. A., Wibawa, D. S., Demura, M., & Watanabe, M. M. (2019). Artificial neural networks model for estimating growth of polyculture microalgae in an open raceway pond. Biosystems Engineering, 177(October), 122–129. https://doi.org/10.1016/j.biosystemseng.2018.10.002
Supyani, Poromarto, S., Supriyadi, Permatasari, F., Putri, D., Putri, D., & Hadiwiyono. (2021). Disease intensity of moler and yield losses of Shallot cv . Bima caused by Fusarium oxysporum f . sp . cepae in Brebes Central Java. Earth and Environmental Science, 905, 1–5. https://doi.org/10.1088/1755-1315/905/1/012049
Susanti, D., Mulyadi, & Wiyatiningsih, S. (2016). Karakterisasi isolat - isolat Fusarium oxysporum f.sp.cepae penyebab penyakit moler pada bawang merah dari daerah Nganjuk dan Probolinggo. Plumula, 5(2), 153–160.
Swanda, H., Sadjati, E., & Ikhwan, M. (2021). Pemanfaatan Teknologi Pesawat Tanpa Awak Untuk Identifikasi Klasifikasi Tutupan Lahan ( Studi Kasus : Kawasan Tahura SSH ). 1(1), 157–167.
