KLASIFIKASI BERBASIS PIKSEL UNTUK IDENTIFIKASI DAN PEMETAAN GULMA PADA LAHAN PADI SAWAH MENGGUNAKAN CITRA DRONE MULTISPEKTRAL DAN PEMBELAJARAN MESIN

Muhammad Ardiansyah; Khursatul Munibah; Syakira Rizqa Zakiyah

doi:10.29244/jitl.28.2.80-90

Authors

Muhammad Ardiansyah Center for Climate Risk and Opportunity Management in Southeast Asia and Pacific, IPB University, Jl. Pajajaran – Kampus IPB Baranangsiang, Bogor, West Java 16143
Khursatul Munibah Departemen Ilmu Tanah dan Sumberdaya Lahan, Fakultas Pertanian, IPB University, Jl. Meranti – Kampus IPB Dramaga, Bogor, Jawa Barat 16680
Syakira Rizqa Zakiyah Departemen Ilmu Tanah dan Sumberdaya Lahan, Fakultas Pertanian, IPB University, Jl. Meranti – Kampus IPB Dramaga, Bogor, Jawa Barat 16680

DOI:

https://doi.org/10.29244/jitl.28.2.80-90

Keywords:

multispectral UAV, random forest, support vector machine, weeds

Abstract

Weeds are one of the major constraints in lowland rice cultivation because they compete with rice plants for essential growth resources and may reduce crop productivity. Rapid and accurate weed identification and mapping are therefore needed to support effective weed management. This study aimed to analyze the reflectance patterns of weeds and rice plants and to evaluate the performance of pixel-based classification using Random Forest (RF) and Support Vector Machine (SVM) algorithms on multispectral Unmanned Aerial Vehicle (UAV) imagery. The study was conducted in a 1,300 m² lowland rice field in Ciherang Village, Ciomas District, Bogor Regency, using multispectral UAV imagery acquired on October 4, 2023, before weed cleaning, and October 13, 2023, after weed cleaning. The imagery consisted of green, red, red-edge, and near-infrared (NIR) bands. Pixel samples representing weed and non-weed classes, including rice, soil, and water bodies, were selected using purposive sampling. The pixel data were then divided into training and validation datasets at a 70:30 ratio and classified using RF and SVM with default parameters in the Dzetsaka plugin. The results showed that weeds generally had higher reflectance values than rice plants, particularly in the red-edge and NIR bands, providing spectral separability that could be exploited for pixel-based classification. RF achieved 100% Overall Accuracy (OA), User's Accuracy (UA), and Producer's Accuracy (PA) on both observation dates. SVM achieved an OA of 100% on October 4, 2023, which decreased to 92.13% on October 13, 2023, with a PA of 81.65% for the weed class. Weed area estimates also differed between the two algorithms, with the average weed area estimated by RF decreasing from 5.75% to 2.50%, while that estimated by SVM decreased from 3.06% to 2.76% after weed cleaning. These findings indicate that multispectral UAV imagery combined with pixel-based classification can be used to identify and map weeds in lowland rice fields, with RF showing more consistent performance than SVM under the conditions of this study.

Downloads

Download data is not yet available.

References

Ashraf, T., and Khan, Y. N. (2020). Weed density classification in rice crop using computer vision. Computers and Electronics in Agriculture, 175, 105590. https://doi.org/10.1016/j.compag.2020.105590.

[BPS] Badan Pusat Statistik. (2024). Statistik Indonesia: Statistical Yearbook of Indonesia Vol. 52. Jakarta (ID): BPS-Statistics Indonesia.

Chauhan, B. S. (2020). Grand challenges in weed management. Frontiers in Agronomy, 1, 3. https://doi.org/10.3389/fagro.2019.00003.

Ghosh, A., Ankit, R. K. Singh, and O. N. Singh. 2021. Crop-weed competition in aerobic rice (Oryza sativa) – serious concern in nitrogen fertilizer management. The Indian Journal of Agricultural Sciences, 91(7): 985–989. https://doi.org/10.56093/ijas.v91i7.115107.

Islam, N., Rashid, M. M., Wibowo, S., Xu, C.-Y., Morshed, A., Wasimi, S. A., Moore, S., and Rahman, S. M.. (2021). Early weed detection using image processing and machine learning techniques in an Australian chilli farm. Agriculture, 11(5), 387. https://doi.org/10.3390/agriculture11050387.

Juwono, F. H., Wong, W. K., Verma, S., Shekhawat, N., Lease, B. A., and Apriono, C. (2023). Machine learning for weed–plant discrimination in agriculture 5.0: An in-depth review. Artificial Intelligence in Agriculture, 10, 13–25. https://doi.org/10.1016/j.aiia.2023.09.002.

Okamoto, Y., Mccarthy, C., Mahinda, A., Iskandar, W., Mishra, A. K., and Funakawa, S. (2017). Applicability of the Multicopter (Unmanned Aerial Vehicle) and Aerial Photograph in the Experiental Station, Kyoto Japan in International Symposium on Global Environmental Studies Education and Research in Asia and the 11th Inter-University Workshop on Education and Research Collaboration in the Indochina Region, Bangkok, Thailand, November 13-15, 2016.

Rahaman, F., Juraimi, A. S., Rafii, M. Y., Uddin, K., Hassan, L., Chowdhury, A. K., Karim, S. M. R., Rini, B. Y., Yusuff, O., Bashar, H. M. K., and Hossain, A. (2022). Allelopathic potential in rice – a biochemical tool for plant defence against weeds. Frontiers in Plant Science, 13, 1072723. https://doi.org/10.3389/fpls.2022.1072723.

Rai, N., Zhang, Y., Ram, B. G., Schumacher, L., Yellavajjala, R. K., Bajwa, S., and Sun, X. (2023). Applications of deep learning in precision weed management: A review. Computers and Electronics in Agriculture, 206, 107698. https://doi.org/10.1016/j.compag.2023.107698.

Serra Serra, N., Shanmuganathan, R., and Becker, C. (2021). Allelopathy in rice: A story of momilactones, kin recognition, and weed management. Journal of Experimental Botany, 72(11), 4022–4037. https://doi.org/10.1093/jxb/erab084.

Shahi, T. B., Xu, C. Y., Neupane, A., and Guo, W. (2022. Machine learning methods for precision agriculture with UAV imagery: A review. Electronic Research Archive, 30(12), 4277–4317. https://doi.org/10.3934/era.2022218.

Shekhawat, K., Rathore, S. S., and Chauhan, B. S. (2020). Weed management in dry direct-seeded rice: A review on challenges and opportunities for sustainable rice production. Agronomy, 10(9), 1264. https://doi.org/10.3390/agronomy10091264.

Su, J., Yi, D., Coombes, M., Liu, C., Zhai, X., McDonald-Maier, K., and Chen, W. H. (2022). Spectral analysis and mapping of blackgrass weed by leveraging machine learning and UAV multispectral imagery. Computers and Electronics in Agriculture, 192, 106621. https://doi.org/10.1016/j.compag.2021.106621.

Ubben, N., Pukrop, M., and Jarmer, T. (2024). Spatial resolution as a factor for efficient UAV-based weed mapping—A soybean field case study. Remote Sensing, 16(10), 1778. https://doi.org/10.3390/rs16101778.

Wang, C. (2021). At-sensor radiometric correction of a multispectral camera (RedEdge) for UAS vegetation mapping. Sensors, 21(24), 8224. https://doi.org/10.3390/s21248224.

Xu, B., Meng, R., Chen, G., Liang, L., Lv, Z., Zhou, L., Sun, R., Zhaom F., and Yang, W. (2023). Improved weed mapping in corn fields by combining UAV-based spectral, textural, structural, and thermal measurements. Pest Management Science, 79(7), 2591–2602. https://doi.org/10.1002/ps.7443.

Yu, F., Jin, Z., Guo, S., Guo, Z., Zhang, H., Xu, T., and Chen, C. (2022). Research on weed identification method in rice fields based on UAV remote sensing. Frontiers in Plant Science, 13, 1037760. https://doi.org/10.3389/fpls.2022.1037760.

Zhang, Y., Yan, Z., Gao, J., Shen, Y., Zhou, H., W. Tang, Y. Lu, and Y. Yang. 2024. UAV imaging hyperspectral for barnyard identification and spatial distribution in paddy fields. Expert Systems with Applications, 255, 124771. https://doi.org/10.1016/j.eswa.2024.124771.

Zhu, W., Sun, Z., Yang, T., Li, J., Peng, J., Zhu, K., Li, S., Gong, H., Lyu, Y., Li, B., and Liao, X. (2020). Estimating leaf chlorophyll content of crops via optimal unmanned aerial vehicle hyperspectral data at multi-scales. Computers and Electronics in Agriculture, 178, 105786. https://doi.org/10.1016/j.compag.2020.105786.