Evaluasi Algoritma Machine Learning untuk Klasifikasi dan Prediksi Penggunaan Lahan

https://doi.org/10.22146/mgi.99150

Fajar Nugraha(1*), Dwi Putro Tejo Baskoro(2), Suria Darma Tarigan(3)

(1) Departemen Ilmu Tanah dan Sumberdaya Lahan, Fakultas Pertanian, Institut Pertanian Bogor, Indonesia
(2) Institut Pertanian Bogor
(3) Departemen Ilmu Tanah dan Sumberdaya Lahan, Fakultas Pertanian, Institut Pertanian Bogor, Indonesia
(*) Corresponding Author

Abstract


Abstrak. Pemantauan, perencanaan, dan pengelolaan sumberdaya lahan membutuhkan data penggunaan lahan yang akurat. Banyak penelitian telah dilakukan mengenai klasifikasi dan prediksi penggunaan lahan. Namun, penelitian terkait penentuan metode klasifikasi dan prediksi yang akurat masih sangat penting. Penelitian ini bertujuan untuk mengevaluasi algoritma machine learning dalam klasifikasi dan prediksi penggunaan lahan serta menganalisis perubahan penggunaan lahan tahun 2002- 2032. Area studi penelitian ini yaitu Sub DAS Tanralili, klasifikasi menggunakan Dzetsaka dengan algoritma seperti kNN, GMM, RF, dan SVM, dan prediksi menggunakan MOLUSCE dengan model CA yang dikombinasi dengan ANN, LR, WoE, dan MCE. Model dievaluasi menggunakan overall accuracy dan kappa, akurasi tertinggi pada tahun 2002, 2012, dan 2022 masing-masing adalah kNN (kappa 0,92), SVM (kappa 0,86), dan GMM (kappa 0,74). Algoritma SVM memiliki kappa rata-rata tertinggi untuk klasifikasi sebesar 0,83, sedangkan model CA-ANN menunjukkan nilai kappa tertinggi untuk prediksi sebesar 0,65. Pada periode 2002-2022, terjadi penurunan hutan sekunder (4.184,0 ha), pertanian lahan kering (1.259,3 ha), dan badan air (328,0 ha), sedangkan peningkatan pada semak belukar (5.303,3 ha), sawah (367,0 ha), padang rumput (64,5 ha), dan permukiman (36,5 ha). Pada periode 2022-2032 menunjukkan penurunan hutan sekunder (554,2 ha), sawah (332,6 ha), padang rumput (192,8 ha), dan badan air (33,4 ha), sedangkan peningkatan pada semak belukar (700,9 ha), pertanian lahan kering (401,1 ha), dan permukiman (1,1 ha).

 

Abstract. Monitoring, planning, and managing land resources require accurate land use data. Many studies have been conducted on land use classification and prediction. However, research related to determining accurate classification and prediction methods is still very important. This study aimed to evaluate machine learning algorithms in land use classification and prediction and analyzed land use change from 2002 to 2032. The study area of this research was the Tanralili Sub Watershed, with classification using Dzetsaka and algorithms such as kNN, GMM, RF, and SVM, and prediction using MOLUSCE with the CA model combined with ANN, LR, WoE, and MCE. The models were evaluated using overall accuracy and kappa; the highest accuracy in 2002, 2012, and 2022 were kNN (kappa 0.92), SVM (kappa 0.86), and GMM (kappa 0.74), respectively. The SVM algorithm had the highest average kappa for classification at 0.83, while the CA-ANN model showed the highest kappa value for prediction at 0.65. In the period 2002-2022, there was a decrease in secondary forests (4,184.0 ha), dry land agriculture (1,259.3 ha), and water bodies (328.0 ha), while an increase in shrubs (5,303.3 ha), rice fields (367.0 ha), grasslands (64.5 ha), and settlements (36.5 ha). The 2022-2032 period predicted a decrease in secondary forests (554.2 ha), rice fields (332.6 ha), grasslands (192.8 ha), and water bodies (33.4 ha), while an increase in shrubs (700.9 ha), dry land farming (401.1 ha), and settlements (1.1 ha).

 

Submitted: 2024-08-14 Revisions:  2024-11-13 Accepted: 2025-02-17 Published: 2025-02-17

 


Keywords


Dzetsaka; Kappa; Molusce; Perencanaan; Sub DAS Tanralili



References

Ambarwulan, W., Yulianto, F., Widiatmaka, W., Rahadiati, A., Tarigan, S. D., Firmansyah, I., & Hasibuan, M. A. S. (2023). Modelling land use/land cover projection using different scenarios in the Cisadane Watershed, Indonesia: Implication on deforestation and food security. The Egyptian Journal of Remote Sensing and Space Sciences, 26(2), 273-283. https://doi.org/10.1016/j.ejrs.2023.04.002 Aryal, J., Sitaula, C., & Frery, A. C. (2023). Land use and land cover (LULC) performance modeling using machine learning algorithms: a case study of the city of Melbourne, Australia. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-40564-0 PMid:37598272 PMCid:PMC10439905 Baig, M. F., Mustafa, M. R. U., Baig, I., Takaijudin, H. B., & Zeshan, M. T. (2022). Assessment of Land Use Land Cover Changes and Future Predictions Using CA-ANN Simulation for Selangor, Malaysia. Water, 14(3). https://doi.org/10.3390/w14030402 Blissag, B., Yebdri, D., & Kessar, C. (2024). Spatiotemporal change analysis of LULC using remote sensing and CA-ANN approach in the Hodna basin, NE of Algeria. Physics and Chemistry of the Earth, 133. https://doi.org/10.1016/j.pce.2023.103535 Bounoua, L., Bachir, N., Souidi, H., Bahi, H., Lagmiri, S., Khebiza, M. Y., Nigro, J., & Thome, K. (2023). Sustainable Development in Algeria's Urban Areas: Population Growth and Land Consumption. Urban Science, 7(1). https://doi.org/10.3390/urbansci7010029 Chowdhury, M. S. (2024). Comparison of accuracy and reliability of random forest , support vector machine , artificial neural network and maximum likelihood method in land use / cover classification of urban setting. Environmental Challenges, 14.
https://doi.org/10.1016/j.envc.2023.100800 Danoedoro, P., Widayani, P., Hidayati, I. N., Kartika, C. S. D., & Alfani, F. (2024). Incorporating landscape ecological approach in machine learning classification for agricultural land-use mapping based on a single date imagery. Geocarto International, 39(1), 1-20. https://doi.org/10.1080/10106049.2024.2356844 Din, S. U., & Yamamoto, K. (2024). Urban Spatial Dynamics and Geo-informatics Prediction of Karachi from 1990-2050 Using Remote Sensing and CA-ANN Simulation. Earth Systems and Environment, 8, 849-868. https://doi.org/10.1007/s41748-024-00439-4 Ekasari, C., Barkey, R., Chairil, A., Nursaputra, M., & Pahar, S. P. P. (2021). Socioeconomic characteristics of communities utilizing land in forest areas in the Maros Watershed. IOP Conference Series: Earth and Environmental Science, 886(1).
https://doi.org/10.1088/1755-1315/886/1/012028 Eshetie, A. A., Wubneh, M. A., Kifelew, M. S., & Alemu, M. G. (2023). Application of artificial neural network ( ANN ) for investigation of the impact of past and future land use - land cover change on streamflow in the Upper Gilgel Abay watershed , Abay Basin ,. Applied Water Science, 13.
https://doi.org/10.1007/s13201-023-02003-3 Ghayour, L., Neshat, A., Paryani, S., Shahabi, H., Shirzadi, A., Chen, W., Al-Ansari, N., Geertsema, M., Amiri, M. P., Gholamnia, M., Dou, J., & Ahmad, A. (2021). Performance evaluation of sentinel-2 and landsat 8 OLI data for land cover/use classification using a comparison between machine learning algorithms. Remote Sensing, 13(7). https://doi.org/10.3390/rs13071349 Hariyanto, A. D., Yudono, A., & Wicaksono, A. D. (2024). Comparison of Land Cover Change Prediction Models: A Case Study in Kedungkandang District, Malang City. Journal of Geomatics and Planning, 11(1), 85-98.
https://doi.org/10.14710/geoplanning.11.1.85-98 Hasnawir, Kubota, T., Sanchez-Castillo, L., & Soma, A. S. (2017). The Influence of Land Use and Rainfall on Shallow Landslides in Tanralili Sub-watershed, Indonesia. Journal of the Faculty of Agriculture, Kyushu University, 62(1), 171-176.
https://doi.org/10.5109/1801778 Imran, A. N., & Djafar, M. (2020). Pengaruh Pengetahuan Ekosistem, Pengetahuan Konservasi, dan Pengetahuan Pencemaran, terhadap Sikap Memelihara Lingkungan Masyarakat di Wilayah DAS Maros Bagian Hulu Kabupaten Maros. Jurnal Eboni, 2(1), 1-11. https://ejournals.umma.ac.id/index.php/eboni/article/view/610/465 Iqbal, I. M., Balzter, H., Firdaus-e-Bareen, & Shabbir, A. (2023). Mapping Lantana camara and Leucaena leucocephala in Protected Areas of Pakistan: A Geo-Spatial Approach. Remote Sensing, 15(4). 0
https://doi.org/10.3390/rs15041020 Jamsran, B. E., Lin, C., Byambakhuu, I., Raash, J., & Akhmadi, K. (2019). Applying a support vector model to assess land cover changes in the Uvs Lake Basin ecoregion in Mongolia. Information Processing in Agriculture, 6(1), 158-169.
https://doi.org/10.1016/j.inpa.2018.07.007 Jayabaskaran, M., & Das, B. (2023). Land Use Land Cover (LULC) Dynamics by CA-ANN and CA-Markov Model Approaches: A Case Study of Ranipet Town, India. Nature Environment and Pollution Technology, 22(3), 1251-1265.
https://doi.org/10.46488/NEPT.2023.v22i03.013 Karasiak, N., & Perbet, P. (2018). Remote Sensing of Distinctive Vegetation in Guiana Amazonian Park. In N. Baghdadi, C. Mallet, & M. Zribi (Eds.), QGIS and Applications in Agriculture and Forest (pp. 215-245). John Wiley & Sons, Inc.
https://doi.org/10.1002/9781119457107.ch7 Lukas, P., Melesse, A. M., & Kenea, T. T. (2023). Prediction of Future Land Use/Land Cover Changes Using a Coupled CA-ANN Model in the Upper Omo- Gibe River Basin, Ethiopia. Remote Sensing, 15(4).
https://doi.org/10.3390/rs15041148 Mao, Y., Fan, J., Zhou, D., He, Y., Yuan, M., & Zhang, H. (2024). Community-Scale Classification and Governance Policy Implications for Demographic, Economic, and Land-Use Linkages in Mega-Cities. Land, 13(4). 1 https://doi.org/10.3390/land13040441 Muhammad, R., Zhang, W., Abbas, Z., Guo, F., & Gwiazdzinski, L. (2022). Spatiotemporal Change Analysis and Prediction of Future Land Use and Land Cover Changes Using QGIS MOLUSCE Plugin and Remote Sensing Big Data: A Case Study of Linyi, China. Land, 11(3). https://doi.org/10.3390/land11030419 Neves, J. L., Sellick, T. K., Hasan, A., & Pilesjö, P. (2023). Flood risk assessment under population growth and urban land use change in Matola, Mozambique. African Geographical Review, 42(5), 539-559.
https://doi.org/10.1080/19376812.2022.2076133 Njock, P. G. A., Shen, S.-L., Zhou, A., & Modoni, G. (2021). Artificial neural network optimized by differential evolution for predicting diameters of jet grouted columns. Journal of Rock Mechanics and Geotechnical Engineering, 13(6), 1500-1512.
https://doi.org/10.1016/j.jrmge.2021.05.009 Nkolokosa, C., Stothard, R., Jones, C. M., Stanton, M., Chirombo, J., & Tangena, J. A. (2023). Monitoring and simulating landscape changes: how do long‑term changes in land use and long‑term average climate affect regional biophysical conditions in southern Malawi? Environmental Monitoring and Assessment, 195(10), 1-16.
https://doi.org/10.1007/s10661-023-11783-9
PMid:37750982 PMCid:PMC10522741 Noi, P. T., & Kappas, M. (2017). Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery. Sensors, 18(1).
https://doi.org/10.3390/s18010018
PMid:29271909 PMCid:PMC5796274 Ogunbo, J. N., Alagbe, O. A., Oladapo, M. I., & Shin, C. (2020). N-hidden layer artificial neural network architecture computer code: geophysical application example. Heliyon, 6(6). https://doi.org/10.1016/j.heliyon.2020.e04108
PMid:32566777 PMCid:PMC7298414 Ouchra, H., Belangour, A., & Erraissi, A. (2024). Supervised Machine Learning Algorithms for Land Cover Classification in Casablanca, Morocco. International Information and Engineering Technology Assocoation, 29(1), 377-387.
https://doi.org/10.18280/isi.290137 Pande, C. B., Diwate, P., Orimoloye, I. R., Sidek, L. M., Mishra, A. P., Moharir, K. N., Pal, S. C., Alshehri, F., & Tolche, A. D. (2024). Impact of land use/land cover changes on evapotranspiration and model accuracy using Google Earth engine and classification and regression tree modeling. Geomatics, Natural Hazards and Risk, 15(1). https://doi.org/10.1080/19475705.2023.2290350 Priyanto, H., Mudjiono, & Yosomulyono, S. (2021). Koreksi Geometrik Pemetaan Tataguna Lahan di Sekitar Calon Tapak PLTN Kalimantan Barat. Jurnal Pengembangan Energi Nuklir, 23(1), 61-69.
https://doi.org/10.17146/jpen.2021.23.1.6306 Putri, E. A. W., Danoedoro, P., & Farda, M. N. (2024). Studi Komparasi Teknik Klasifikasi berbasis Objek terhadap Citra Resolusi Spasial Menengah dan Tinggi untuk Pemetaan Tutupan Lahan di Sebagian Kabupaten Kulonprogo. Majalah Geografi Indonesia, 38(1), 1-7. https://doi.org/10.22146/mgi.81374 Ramadhan, C., Dina, R., & Nurjani, E. (2023). Spatial and temporal based deforestation proclivity analysis on flood events with applying watershed scale (case study: Lasolo watershed in Southeast Sulawesi, Central Sulawesi, and South Sulawesi, Indonesia). International Journal of Disaster Risk Reduction, 93.
https://doi.org/10.1016/j.ijdrr.2023.103745 Santarsiero, V., Nolè, G., Lanorte, A., Tucci, B., Cillis, G., & Murgante, B. (2022). Remote Sensing and Spatial Analysis for Land-Take Assessment in Basilicata Region (Southern Italy). Remote Sensing, 14(7). https://doi.org/10.3390/rs14071692 Shafizadeh-Moghadam, H., Tayyebi, A., & Helbich, M. (2017). Transition index maps for urban growth simulation: application of artificial neural networks, weight of evidence and fuzzy multi-criteria evaluation. Environmental Monitoring and Assessment, 189(6). https://doi.org/10.1007/s10661-017-5986-3
PMid:28555438 Soil Survey Staff. (2022). Keys to Soil Taxonomy (13th ed.). USDA Natural Resources Conservation Service. Sparey, M., Williamson, M. S., & Cox, P. M. (2024). Machine Learning for Global Bioclimatic Classification: Enhancing Land Cover Prediction through Random Forests. Atmosphere, 15(6). https://doi.org/10.3390/atmos15060700 Surahman, S. (2017). Perubahan Penggunaan Lahan dan Dampaknya Terhadap Karakteristik Hidrologi Sub DAS Tanralili Provinsi Sulawesi Selatan Menggunakan Model Swat. Jurnal Agrotan, 3(2), 50-67. https://ejournals.umma.ac.id/index.php/agrotan/article/view/24/22 Syafri, S., Surya, B., Ridwan, R., Bahri, S., Rasyidi, E. S., & Sudarman, S. (2020). Water Quality Pollution Control and Watershed Management Based on Community Participation in Maros City, South Sulawesi, Indonesia. Sustainability, 12(24).
https://doi.org/10.3390/su122410260 Tayyebi, A., & Pijanowski, B. C. (2014). Modeling multiple land use changes using ANN, CART and MARS: Comparing tradeoffs in goodness of fit and explanatory power of data mining tools. International Journal of Applied Earth Observation and Geoinformation, 28, 102-116. https://doi.org/10.1016/j.jag.2013.11.008 Trisnaputra, A., Barus, B., & Trisasongko, B. H. (2023). Modeling land use/land cover change in Berau Pantai Forests, Berau Regency, East Kalimantan Province. Journal of Natural Resources and Environmental Management, 13(3), 386-397.
https://doi.org/10.29244/jpsl.13.3.386-397 Wang, Y., & Zeng, W. (2022). A Comparison of Three Different Group Intelligence Algorithms for Hyperspectral Imagery Classification. Processes, 10(9).
https://doi.org/10.3390/pr10091672 Widayani, P., Salsabila, H. N., & Andriantari, A. (2023). Dampak perubahan penutup lahan terhadap nilai jasa ekosistem di Kabupaten Sleman Daerah Istimewa Yogyakarta. Majalah Geografi Indonesia, 37(2), 104-113.
https://doi.org/10.22146/mgi.78192 Wolde, Z., Wei, W., Likessa, D., Omari, R., & Ketema, H. (2021). Understanding the Impact of Land Use and Land Cover Change on Water-Energy-Food Nexus in the Gidabo Watershed, East African Rift Valley. Natural Resources Research, 30(3), 2687-2702.https://doi.org/10.1007/s11053-021-09819-3 Wulder, M. A., Loveland, T. R., Roy, D. P., Crawford, C. J., Masek, J. G., Woodcock, C. E., Allen, R. G., Anderson, M. C., Belward, A. S., Cohen, W. B., Dwyer, J., Erb, A., Gao, F., Griffiths, P., Helder, D., Hermosilla, T., Hipple, J. D., Hostert, P., Hughes, M. J., … Zhu, Z. (2019). Current status of Landsat program, science, and applications. Remote Sensing of Environment, 225, 127-147.
https://doi.org/10.1016/j.rse.2019.02.015 Yue, W., Qin, C., Su, M., Teng, Y., & Xu, C. (2024). Simulation and prediction of land use change in Dongguan of China based on ANN cellular automata - Markov chain model. Environmental and Sustainability Indicators, 22.
https://doi.org/10.1016/j.indic.2024.100355 Zhang, Y., Chen, H., Yang, B., Fu, S., Yu, J., & Wang, Z. (2018). Prediction of phosphate concentrate grade based on artificial neural network modeling. Results in Physics, 11, 625-628.https://doi.org/10.1016/j.rinp.2018.10.011 Zhao, Z., Islam, F., Waseem, L. A., Tariq, A., Nawaz, M., Islam, I. U., Bibi, T., Rehman, N. U., Ahmad, W., Aslam, R. W., Raza, D., & Hatamleh, W. A. (2024). Comparison of Three Machine Learning Algorithms Using Google Earth Engine for Land Use Land Cover Classification. Rangeland Ecology & Management, 92, 129-137.
https://doi.org/10.1016/j.rama.2023.10.007



DOI: https://doi.org/10.22146/mgi.99150

Article Metrics

Abstract views : 20

Refbacks

  • There are currently no refbacks.


Bookmark and Share


Copyright (c) 2025 Fajar Nugraha, Dwi Putro Tejo Baskoro, Suria Darma Tarigan

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.


 

Accredited Journal, Based on Decree of the Minister of Research, Technology and Higher Education, Republic of Indonesia Number 164/E/KPT/2021

Volume 35 No 2 the Year 2021 for Volume 39 No 1 the Year 2025

ISSN  0215-1790 (print) ISSN 2540-945X  (online)

 

website statistics Statistik MGI