Comparative machine learning for forest landscape mapping in Mount Argapura, East Java, Indonesia
Article Sidebar
Abstract Views: 168
File Views: 106
Main Article Content
Abstract
Abstract. Wulandari PW, Hernawan E, Sumarga E, Sulistyawati E. 2026. Comparative machine learning for forest landscape mapping in Mount Argapura, East Java, Indonesia. Asian J For 10 (1): r100122. https://doi.org/10.13057/asianjfor/r100122. Monitoring land cover is essential for understanding forest landscape structure and supporting sustainable management in mountainous regions. This study mapped land cover in the Mount Argapura landscape, East Java, Indonesia, using 2024 Landsat 8/9 imagery combined with topographic variables and topographic and texture metrics. Seven land-cover classes were identified: Natural Forest, Plantation Forest, Plantation Estate, Dryland Agriculture, Open Land, Settlements, and Water Bodies. Three machine-learning classifiers Classification and Regression Tree (CART), Random Forest (RF), and Support Vector Machine (SVM) were evaluated using Overall Accuracy (OA), Kappa (κ), 95% Confidence Intervals (CI), and McNemar’s test. Results indicate that RF achieved the highest performance (OA=0.98; κ=0.97), significantly outperforming CART (OA=0.97; κ=0.96) and SVM (OA=0.87; κ=0.82). At the class level, RF showed high stability (User’s Accuracy 0.98 for forest classes), while SVM struggled with spectral confusion between plantation and Dryland Agriculture. Spatial analysis reveals a landscape dominated by managed forest systems, with Plantation Forest covering 36.3% (35,544.33 ha) and Natural Forest covering 32.7% (32,043.51 ha). Together with Plantation Estates (22.1%), these vegetated classes account for over 91% of the 97,923.33 ha study area. Comparison with the official Indonesian Ministry of Environment and Forestry (MoEF) map showed moderate agreement (OA=0.54; κ=0.30), with this study identifying a larger extent of managed plantation landscapes (35,544.33 ha vs. 12,053 ha in MoEF). This discrepancy highlights the importance of local-scale mapping for capturing site-specific details. The findings provide a robust baseline for BKSDA and Perum Perhutani in biodiversity conservation, carbon stock assessment, and agroforestry planning. Future research should incorporate multi-temporal data to better detect fine-scale forest dynamics in this complex tropical terrain.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
How to Cite
References
Al Farikhi F, Pramono RWD. 2023. Perbandingan algoritma Classification and Regression Tree (CART) dan Random Forest (RF) untuk klasifikasi penggunaan lahan pada Google Earth Engine. Jurnal Spatial Wahana Komunikasi dan Informasi Geografi 23 (2): 170-179. https://doi.org/10.21009/spatial.232.09. [Indonesian]
Alcaras E, Costantino D, Guastaferro F, Parente C, Pepe M. 2022. Normalized Burn Ratio Plus (NBR+): A new index for Sentinel-2 imagery. Remote Sens 14 (7): 1727. https://doi.org/10.3390/rs14071727.
Aldiansyah S, Saputra RA. 2022. Comparison of machine learning algorithms for land use and land cover analysis using Google Earth Engine (case study: Wanggu Watershed). Intl J Remote Sens Earth Sci 19 (2): 197-210. https://doi.org/10.30536/ijreses.v19i2.13716.
Alemayehu B, Suarez-Minguez J, Rosette J. 2024. The implications of Plantation Forest-driven land use/land cover changes for ecosystem service values in the Northwestern highlands of Ethiopia. Remote Sens 16 (22): 4159. https://doi.org/10.3390/rs16224159.
Ali U, Esau TJ, Farooque AA, Zaman QU, Abbas F, Bilodeau MF. 2022. Limiting the collection of ground truth data for land use and land cover maps with machine learning algorithms. ISPRS Intl J Geo-Inf 11 (6): 333. https://doi.org/10.3390/ijgi11060333.
Amin G, Imtiaz I, Haroon E, Saqib NUS, Shahzad MI, Nazeer M. 2024. Assessment of machine learning algorithms for land cover classification in a complex mountainous landscape. J Geovis Spatial Anal 8 (2): 34. https://doi.org/10.1007/s41651-024-00195-z.
Anderson JRA. 1976. Land Use and Land Cover Classification System for Use with Remote Sensor Data. [Professional Paper]. US Geological Survey, Virginia. https://doi.org/10.3133/pp964.
Aryal K, Apan A, Maraseni T. 2023. Comparing global and local land cover maps for ecosystem management in the Himalayas. Remote Sens Appl Soc Environ 30: 100952. https://doi.org/10.1016/j.rsase.2023.100952.
Azedou A, Amine A, Kisekka I, Lahssini S. 2025. Genetic algorithm optimization of ensemble learning approach for improved land cover and land use mapping: Application to Talassemtane National Park. Ecol Indic 177: 113776. https://doi.org/10.1016/j.ecolind.2025.113776.
Biah I, Azihou AF, Guendehou S, Sinsin B. 2024. Land use/land cover change and carbon footprint in tropical ecosystems in Benin, West Africa. Tree For People 15: 100488. https://doi.org/10.1016/j.tfp.2023.100488.
Bie Q, Shi Y, Li X, Wang Y. 2023. Contrastive analysis and accuracy assessment of three global 30 m land cover maps circa 2020 in arid land. Sustainability 15 (1): 741. https://doi.org/10.3390/su15010741.
Bimaprawira AK, Rejeki HA. 2021. Relationship of rainfall periodicity in coastal and mountain areas of East Java Province with global and regional scale weather variability. Jurnal Sains dan Teknologi Modifikasi Cuaca 22 (2): 51-59. https://doi.org/10.29122/jstmc.v22i2.4422. [Indonesian]
Boer R, Anwar S, Margono BA et al. 2022. National Forest Reference Level for Deforestation, Forest Degradation, and Enhancement of Forest Carbon Stock. FREL Indonesia, Jakarta. [Indonesian]
Bogale T, Degefa S, Dalle G, Abebe G. 2025. Machine learning-based analysis of land use and land cover trends in southeastern Ethiopia using Google Earth Engine. Discov Sustain 6 (1): 878. https://doi.org/10.1007/s43621-025-01709-5.
Bragagnolo L, da Silva RV, Grzybowski JMV. 2021. Amazon forest cover change mapping based on semantic segmentation by U-Nets. Ecol Inform 62: 101279. https://doi.org/10.1016/j.ecoinf.2021.101279.
Brito CS dos S, Beltrão NES, Pimenta LB, de Jesus NCC. 2025. Performance of random forest and CART algorithms in land-use and land-cover classification on Cotijuba Island (PA) from 1989 to 2023. Rev Gest Soc Ambient 19 (12): e014093. https://doi.org/10.24857/rgsa.v19n12-048.
Buchner J, Yin H, Frantz D, Kuemmerle T, Askerov E, Bakuradze T, Bleyhl B, Elizbarashvili N, Komarova A, Lewińska KE, Rizayeva A, Sayadyan H, Tan B, Tepanosyan G, Zazanashvili N, Radeloff VC. 2020. Land-cover change in the Caucasus Mountains since 1987 based on the topographic correction of multi-temporal Landsat composites. Remote Sens Environ 248: 111967. https://doi.org/10.1016/j.rse.2020.111967.
Buthelezi MNM, Lottering RT, Peerbhay KY, Mutanga O. 2024. Predicting land use and land cover change dynamics in the eThekwini Municipality: A machine learning approach with Landsat imagery. J Spat Sci 69 (4): 1241-1263. https://doi.org/10.1080/14498596.2024.2378362.
Carletta J. 1996. Assessing agreement on classification tasks: The kappa statistic. Comput Linguist 22 (2): 249-254.
Cheng KS, Ling JY, Lin TW, Liu YT, Shen YC, Kono Y. 2021. Quantifying uncertainty in land-use/land-cover classification accuracy: A stochastic simulation approach. Front Environ Sci 9: 628214. https://doi.org/10.3389/fenvs.2021.628214.
Chidodo S, Zhang L, Zarei A, Feger KH. 2025. Remote sensing-based assessment of four decades of land use/land cover change in the Sigi River Watershed, East Usambara Mountains, Tanzania. Front Remote Sens 6: 1594331. https://doi.org/10.3389/frsen.2025.1594331.
Chowdhury MS. 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. Environ Chall 14: 100800. https://doi.org/10.1016/j.envc.2023.100800.
Congalton RG, Green K. 2005. Assessing the Accuracy of Remotely Sensed Data: Principles and Practices. 2nd Edition, CRC Press, Taylor & Francis Group, London.
Demirović E, Lukina A, Hebrard E, Chan J, Bailey J, Leckie C, Ramamohanarao K, Stuckey PJ. 2022. MurTree: Optimal decision trees via dynamic programming and search. J Mach Learn Res 23 (26): 1-47.
Dietz J, Treydte AC, Lippe M. 2023. Exploring the future of Kafue National Park, Zambia: Scenario-based land use and land cover modelling to understand drivers and impacts of deforestation. Land Use Policy 126: 106535. https://doi.org/10.1016/j.landusepol.2023.106535.
Esri. 2025. ArcGIS Pro Personal Use. Esri, Redlands, California. https://www.esri.com/.
Fonte CC, Duarte D, Jesus I, Costa H, Benevides P, Moreira F, Caetano M. 2024. Accuracy assessment and comparison of national, European and global land use land cover maps at the national scale: Case study Portugal. Remote Sens 16 (9): 1504. https://doi.org/10.3390/rs16091504.
Foody GM. 2020. Explaining the unsuitability of the kappa coefficient in the assessment and comparison of the accuracy of thematic maps obtained by image classification. Remote Sens Environ 239: 111630. https://doi.org/10.1016/j.rse.2019.111630.
Google Developers. 2025. Landsat. Mountain View, California. https://developers.google.com/earth-engine/datasets/catalog/landsat.
Guarderas P, Smith F, Dufrene M. 2022. Land use and land cover change in a tropical mountain landscape of northern Ecuador: Altitudinal patterns and driving forces. PLoS One 17 (7): e0260191. https://doi.org/10.1371/journal.pone.0260191.
Hanum U, Dianti, Safitri RN, Pratiwi VMR, Hermawan WG, Indrawan M, Setyawan AD. 2024. Ecological change detection in PT. Semen Gresik Rembang, Indonesia (limestone mining) activities between 2016 to 2022. Intl J Trop Drylands 8: 59-68.https://doi.org/10.13057/tropdrylands/t080201.
Hariyono MI, Rokhmatulloh, Dewi RS. 2023. Land use and land cover (LULC) classification with machine learning approach using orthophoto data. Majalah Ilmiah Globe 25 (1): 87-96. [Indonesian]
Harmoko J, Munibah K, Ardiansyah M. 2025. Klasifikasi penutupan/penggunaan lahan dari citra Landsat 8 dengan pendekatan random forest dan support vector machine di Kabupaten Sumedang, Jawa Barat. Jurnal Ilmu Tanah dan Lingkungan 27 (1): 24-31. https://doi.org/10.29244/jitl.27.1.24-31. [Indonesian]
Huang C, Zhang C, He Y, Liu Q, Li H, Su F, Liu G, Bridhikitti A. 2020. Land cover mapping in cloud-prone tropical areas using Sentinel-2 data: Integrating spectral features with NDVI temporal dynamics. Remote Sens 12 (7): 1163. https://doi.org/10.3390/rs12071163.
Islam MY, Nasher NMR, Karim KHR, Rashid KJ. 2023. Quantifying forest land-use changes using remote-sensing and CA-ANN model of Madhupur Sal Forests, Bangladesh. Heliyon 9 (5): e15617. https://doi.org/10.1016/j.heliyon.2023.e15617.
Jozdani SE, Johnson BA, Chen D. 2019. Comparing deep neural networks, ensemble classifiers, and support vector machine algorithms for object-based urban land use/land cover classification. Remote Sens 11 (14): 1713. https://doi.org/10.3390/rs11141713.
Kementerian Lingkungan Hidup dan Kehutanan (KLHK). 2022. Kementerian Lingkungan Hidup dan Kehutanan Republik Indonesia menuju FOLU Net Sink 2030. Kementerian Lingkungan Hidup dan Kehutanan, Jakarta. [Indonesian]
Landis JR, Koch GG. 1977. The measurement of observer agreement for categorical data. Biometrics 33 (1): 159-174. https://doi.org/10.2307/2529310.
Lemenkova P. 2024. Support vector machine algorithm for mapping land cover dynamics in Senegal, West Africa, using Earth observation data. Earth 5 (3): 420-462. https://doi.org/10.3390/earth5030024.
Mahmoud MI, Campbell MJ, Sloan S, Alamgir M, Laurance WF. 2020. Land-cover change threatens tropical forests and biodiversity in the Littoral Region, Cameroon. Oryx 54 (6): 882-891. https://doi.org/10.1017/S0030605318000881.
Manyothwane T, Mengistu TG. 2025. Challenging global generalizations: Superior land cover mapping in Botswana with a locally trained transformer model. Front Remote Sens 6: 1654692. https://doi.org/10.3389/frsen.2025.1654692.
Melichar M, Didan K, Barreto-Muñoz A, Duberstein JN, Jiménez Hernández E, Crimmins T, Li H, Traphagen M, Thomas KA, Nagler PL. 2023. Random forest classification of multitemporal Landsat 8 spectral data and phenology metrics for land cover mapping in the Sonoran and Mojave Deserts. Remote Sens 15 (5): 1266. https://doi.org/10.3390/rs15051266.
Moreno-Pájaro ÁM, Osorio-Gastelbondo A, Moreno-Egel DA, Coronado-Hernández OE, Narváez-Cuadro MA, Saba M, Arrieta-Pastrana A. 2025. Hydrological modelling and remote sensing for assessing the impact of vegetation cover changes. Hydrology 12 (5): 107. https://doi.org/10.3390/hydrology12050107.
Muhamad D, Okubo S, Harashina K, Parikesit, Gunawan B, Takeuchi K. 2014. Living close to forests enhances people’s perception of ecosystem services in a forest-agricultural landscape of West Java, Indonesia. Ecosyst Serv 8: 197-206. https://doi.org/10.1016/j.ecoser.2014.04.003.
Ouchra H, Belangour A, Erraissi A. 2023. Machine learning algorithms for satellite image classification using Google Earth Engine and Landsat satellite data: Morocco case study. IEEE Acces 11: 71127-71142. https://doi.org/10.1109/ACCESS.2023.3293828.
Pontius Jr RG, Francis T, Millones M. 2025. A call to interpret disagreement components during classification assessment. Intl J Geogr Inf Sci 39 (7): 1373-1390. https://doi.org/10.1080/13658816.2025.2469830.
Ramezan CA, Warner TA, Maxwell AE. 2019. Evaluation of sampling and cross-validation tuning strategies for regional-scale machine learning classification. Remote Sens 11 (2): 185. https://doi.org/10.3390/rs11020185.
Rouse RWH, Haas JAW, Deering DW. 1974. Monitoring vegetation systems in the Great Plains with ERTS. Goddard Space Flight Center 3d ERTS-1 Symposium, 1, 309-317. NASA, Greenbelt, Maryland.
Roy DP, Kovalskyy V, Zhang HK, Vermote EF, Yan L, Kumar SS, Egorov A. 2016. Characterization of Landsat-7 to Landsat-8 reflective wavelength and normalized difference vegetation index continuity. Remote Sens Environ 185: 57-70. https://doi.org/10.1016/j.rse.2015.12.024.
Sari IL, Weston CJ, Newnham GJ, Volkova L. 2021. Assessing accuracy of land cover change maps derived from automated digital processing and visual interpretation in tropical forests in Indonesia. Remote Sens 13 (8): 1446. https://doi.org/10.3390/rs13081446.
Shah RK, Shah RK. 2023. Forest Cover Change Detection using Remote Sensing and GIS in Dibru-Saikhowa National Park, Assam: A Spatio-Temporal Study. Proc Natl Acad Sci India Sect B Biol Sci 93 (3): 559-564. https://doi.org/10.1007/s40011-023-01449-4.
Shahfahad, Talukdar S, Naikoo MW, Rahman A, Gagnon AS, Islam ARMT, Mosavi A. 2023. Comparative evaluation of operational land imager sensor on board Landsat 8 and Landsat 9 for land use land cover mapping over a heterogeneous landscape. Geocarto Intl 38 (1): 2152496. https://doi.org/10.1080/10106049.2022.2152496.
Shetty S, Gupta PK, Belgiu M, Srivastav SK. 2021. Assessing the effect of training sampling design on the performance of machine learning classifiers for land cover mapping using multi-temporal remote sensing data and Google Earth Engine. Remote Sens 13 (8): 1433. https://doi.org/10.3390/rs13081433.
Siddiq AM, Subchan W, Maulahila HI, Kholiq N. 2023. Habitat suitability model for banteng (Bos javanicus) in Meru Betiri National Park, Indonesia. Biodiversitas 24 (2): 1296-1302. https://doi.org/10.13057/biodiv/d240272.
Slagter B, Fesenmyer K, Hethcoat M, Belair E, Ellis P, Kleinschroth F, Peña-Claros M, Herold M, Reiche J. 2024. Monitoring road development in Congo Basin forests with multi-sensor satellite imagery and deep learning. Remote Sens Environ 315: 114380. https://doi.org/10.1016/j.rse.2024.114380.
Sovann C, Tagesson T, Vestin P, Sakhoeun S, Kim S, Kok S, Olin S. 2025. Land-cover change alters stand structure, species diversity, leaf functional traits, and soil conditions in Cambodian tropical forests. Biogeosciences 22 (18): 4649-4677. https://doi.org/10.5194/bg-22-4649-2025.
Sumarga E, Nurudin N, Suwandhi I. 2020. Land-cover and elevation-based mapping of aboveground carbon in a tropical mixed-shrub forest area in West Java, Indonesia. Forests 11 (6): 636. https://doi.org/10.3390/F11060636.
Sumarga E. 2017. Spatial indicators for human activities may explain the 2015 fire hotspot distribution in Central Kalimantan, Indonesia. Trop Conserv Sci 10: 1-10. https://doi.org/10.1177/1940082917706168.
Surasinghe TD, Singh KK, Smart LS. 2025. Leveraging phenology to assess seasonal variations of plant communities for mapping dynamic ecosystems. Remote Sens 17 (10): 1778. https://doi.org/10.3390/rs17101778.
Tan YC, Duarte L, Teodoro AC. 2024. Comparative study of random forest and support vector machine for land cover classification and post-wildfire change detection. Land 13 (11): 1878. https://doi.org/10.3390/land13111878.
Tassi A, Vizzari M. 2020. Object-oriented LULC classification in Google Earth Engine combining SNIC, GLCM, and machine learning algorithms. Remote Sens 12 (22): 3776. https://doi.org/10.3390/rs12223776.
Tewabe D, Fentahun T. 2020. Assessing land use and land cover change detection using remote sensing in the Lake Tana Basin, Northwest Ethiopia. Cogent Environ Sci 6 (1): 1778998. https://doi.org/10.1080/23311843.2020.1778998.
Trisasongko BH, Panuju DR, Karyati NE, I’anatus Sholihah R. 2022. Comparison of machine learning models for land cover classification. Intl J Remote Sens Earth Sci 19 (1): 21-29. https://doi.org/10.30536/ijreses.v19i1.13781.
Valero MJA, Alzate ABE. 2019. Comparison of maximum likelihood, support vector machines, and random forest techniques in satellite images classification. Tecnura 23 (59): 13-26. https://doi.org/10.14483/22487638.14826.
Vatitsi K, Ioannidou N, Mirli A, Siachalou S, Kagalou I, Latinopoulos D, Mallinis G. 2023. LULC change effects on environmental quality and ecosystem services using EO data in two rural river basins in Thrace, Greece. Land 12 (6): 1140. https://doi.org/10.3390/land12061140.
Velastegui-Montoya A, Montalván-Burbano N, Peña-Villacreses G, de Lima A, Herrera-Franco G. 2022. Land use and land cover in tropical forest: Global research. Forests 13 (10): 1709. https://doi.org/10.3390/f13101709.
Wang Y, Liu H, Sang L, Wang J. 2022. Characterizing forest cover and landscape pattern using multi-source remote sensing data with ensemble learning. Remote Sens 14 (21): 5470. https://doi.org/10.3390/rs14215470.
Winkler K, Fuchs R, Rounsevell M, Herold M. 2021. Global land use changes are four times greater than previously estimated. Nat Commun 12 (1): 2501. https://doi.org/10.1038/s41467-021-22702-2.
Xu H, Sun H, Xu Z, Wang Y, Zhang T, Wu D, Gao JH. 2025. kNDMI: A kernel normalized difference moisture index for remote sensing of soil and vegetation moisture. Remote Sens Environ 319: 114621. https://doi.org/10.1016/j.rse.2025.114621.
Yousefi S, Mirzaee S, Almohamad H, Al Dughairi AA, Gomez C, Siamian N, Alrasheedi M, Abdo HG. 2022. Image classification and land cover mapping using Sentinel-2 imagery: Optimization of SVM parameters. Land 11 (7): 993. https://doi.org/10.3390/land11070993.
Yuh YG, Tracz W, Matthews HD, Turner SE. 2023. Application of machine learning approaches for land cover monitoring in Northern Cameroon. Ecol Inform 74: 101955. https://doi.org/10.1016/j.ecoinf.2022.101955.
Zafar Z, Zubair M, Zha Y, Fahd S, Ahmad Nadeem A. 2024. Performance assessment of machine learning algorithms for mapping of land use/land cover using remote sensing data. Egypt J Remote Sens Space Sci 27 ( 2): 216-226. https://doi.org/10.1016/j.ejrs.2024.03.003.
Zafari A, Zurita-Milla R, Izquierdo-Verdiguier E. 2019. Evaluating the performance of a random forest kernel for land cover classification. Remote Sens 11 (5): 575. https://doi.org/10.3390/rs11050575.