Majority Filter For Enhancing Pixel-Based Random Forest Land Cover Classification In Sukajaya District, Bogor Regency
https://doi.org/10.24057/2071-9388-2025-4183
Abstract
High-quality land cover data are essential for environmental policy, spatial planning, and ecosystem monitoring. However, pixel-based classification methods, while widely used due to their practicality, often suffer from salt-and-pepper noise, which undermines map reliability. This study aimed to integrate Random Forest (RF) classification and majority filtering to enhance the quality of land cover mapping in Sukajaya District, Bogor Regency. RF was applied to Sentinel-2 image data with varying numbers of trees (ntree) to determine the optimal model performance. Subsequently, majority filtering was applied to each classification result to reduce noise and improve spatial coherence. The evaluation employed multiple accuracy metrics, including User’s Accuracy (UA), Producer’s Accuracy (PA), F1-Score, Overall Accuracy (OA), and Kappa Coefficient (KC). Comprehensive accuracy increased with the ntree until reaching an optimal point. Beyond this point, additional ntree resulted in diminishing returns. Applying majority filtering as a post-processing procedure led to further improvements in classification accuracy. While majority filtering can reduce classification noise and improve the visual quality of land cover maps, it also carries the risk of removing small, accurately classified land cover patches. This consequence is rarely discussed in similar studies. These findings highlight the importance of integrating pixel-based machine learning classification with majority filtering in land cover classification workflows, while emphasising a trade-off that tends to favour visual accuracy over the preservation of spatial detail.
About the Authors
Fathan Aldi Rivai
Department of Soil Science and Land Resources, Faculty of Agriculture, IPB University
Indonesia
Indonesia
Boedi Tjahjono
Department of Soil Science and Land Resources, Faculty of Agriculture, IPB University
Indonesia
Indonesia
Khursatul Munibah
Department of Soil Science and Land Resources, Faculty of Agriculture, IPB University
Indonesia
Indonesia
Adenan Yandra Nofrizal
Department of Applied Geoinformatics and Cartography, Faculty of Science, Charles University
Czech Republic
Czech Republic
Albertov 6, 128 43, Prague
References
1. Adhikari J.N., Bhattarai B.P., Rokaya M.B. and Thapa T.B. (2022). Land use/land cover changes in the central part of the Chitwan Annapurna Landscape, Nepal. PeerJ, 10, e13435. DOI: 10.7717/peerj.13435
2. Aji A., Husna V.N. and Purnama S.M. (2024). Multi-Temporal data for land use change analysis using a machine learning approach (google earth engine). International Journal of Geoinformatics, 20(4), 19–28. DOI: 10.52939/ijg.v20i4.3145
3. Al-Aarajy K.H.A., Zaeen A.A. and Abood K.I. (2024). Supervised classification accuracy assessment using remote sensing and geographic information system. TEM Journal, 13(1), 396–403. DOI: 10.18421/TEM131-41
4. Altman N. and Krzywinski M. (2017). Ensemble methods: bagging and random forests. Nature Methods, 14(10), 933–934. DOI: 10.1038/nmeth.4438
5. Amin G., Imtiaz I., Haroon E., Saqib N. us, Shahzad M.I. and Nazeer M. (2024). Assessment of machine learning algorithms for land cover classification in a complex mountainous landscape. Journal of Geovisualization and Spatial Analysis, 8(34), 1–19. DOI: 10.1007/s41651-02400195-z
6. Anthony T., Shohan A.A.A., Oludare A., Alsulamy S., Kafy A. Al and Khedher K.M. (2024). Spatial analysis of land cover changes for detecting environmental degradation and promoting sustainability. Kuwait Journal of Science, 51(100197). DOI: 10.1016/j.kjs.2024.100197
7. Aslam R.W., Shu H., Naz I., Quddoos A., Yaseen A., Gulshad K. and Alarifi S.S. (2024). Machine learning-based wetland vulnerability assessment in the Sindh Province Ramsar site using remote sensing data. Remote Sens., 16(928). DOI: 10.3390/rs16050928
8. Ávila-Mosqueda S.V., van Tussenbroek B.I. and Garza-Pérez J.R. (2025). Changes in seagrass landscape configuration in a Caribbean Reef Lagoon indicate an ecosystem shift after repeated disturbances. Coasts, 5(8). DOI: 10.3390/coasts5010008
9. Bayazit M., Dönmez C. and Berberoglu S. (2025). Assessing the efficiency of pixel-based and object-based image classification using deep learning in an agricultural Mediterranean plain. Environ. Monit. Assess., 197(155), 1–20. DOI: 10.1007/s10661-024-13431-2
10. Behera D.K., Pujar G.S., Kumar R. and Singh S.K. (2024). A comprehensive approach towards enhancing land use land cover classification through machine learning and object-based image analysis. Journal of the Indian Society of Remote Sensing, 53, 731–749. DOI: 10.1007/s12524-024-01997-w
11. Belay T. and Mengistu D.A. (2021). Impacts of land use/land cover and climate changes on soil erosion in Muga watershed, Upper Blue Nile basin (Abay), Ethiopia. Ecological Processes, 10(1). DOI: 10.1186/s13717-021-00339-9
12. Breiman L. (2001). Random forests. Machine Learning, 45, 5–32.
13. Chahal A., Gulia P., Gill N.S., Yahya M., Haq M.A., Aleisa M., Alenizi A., Khan A.A. and Shukla P.K. (2024). Predictive analytics technique based on hybrid sampling to manage unbalanced data in smart cities. Heliyon, 10(e39275). DOI: 10.1016/j.heliyon.2024.e39275
14. Chen J., Sasaki J., Guo Z. and Endo M. (2023). UAV-based seagrass wrack orthophotos classification for estimating blue carbon. Estuarine, Coastal and Shelf Science, 293. DOI: 10.1016/j.ecss.2023.108476
15. Chen W., Yuan Y., Gu T., Ma H. and Zeng J. (2025). What factors drove the global cropland expansion into highlands? Earth’s Future, 13, e2024EF005337. DOI: 10.1029/2024EF005337
16. Darem A.A., Alhashmi A.A., Almadani A.M., Alanazi A.K. and Sutantra G.A. (2023). Development of a map for land use and land cover classification of the Northern Border Region using remote sensing and GIS. Egyptian Journal of Remote Sensing and Space Science, 26(2), 341–350. DOI: 10.1016/j.ejrs.2023.04.005
17. Du H., Li M., Xu Y. and Zhou C. (2023). An ensemble learning approach for land use/land cover classification of arid regions for climate simulation: A case study of Xinjiang, Northwest China. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 2413–2426. DOI: 10.1109/JSTARS.2023.3247624
18. Ebrahimy H., Mirbagheri B., Matkan A.A. and Azadbakht M. (2021). Per-pixel land cover accuracy prediction: A random forestbased method with limited reference sample data. ISPRS Journal of Photogrammetry and Remote Sensing, 172, 17–27. DOI: 10.1016/j.isprsjprs.2020.11.024
19. Edosa B.T. and Erena M.G. (2024). Wildlife habitat suitability analysis and mapping the former dhidhessa wildlife sanctuary using GISbased analytical hierarchal process and weighted linear combination methods. Heliyon, 10(e33921). DOI: 10.1016/j.heliyon.2024.e33921
20. El-Deen Taha L.G. and Mandouh A.A. (2024). Assessment of Random Forest and Neural Network for improving land use/ land cover mapping from LIDAR data and RGB image: A case study of Magaga-El-Menia Governorate, Egypt. Geoplanning: Journal of Geomatics and Planning, 11(1), 17–30. DOI: 10.14710/geoplanning.11.1.17-30
21. Elmahdy S.I. and Mohamed M.M. (2023). Regional mapping and monitoring land use/land cover changes: a modified approach using an ensemble machine learning and multitemporal Landsat data. Geocarto International, 38(1). DOI: 10.1080/10106049.2023.2184500
22. Fu B., Wang Y., Campbell A., Li Y., Zhang B., Yin S., Xing Z. and Jin X. (2017). Comparison of object-based and pixel-based random forest algorithm for wetland vegetation mapping using high spatial resolution GF-1 and SAR data. Ecological Indicators, 73, 105–117. DOI: 10.1016/j.ecolind.2016.09.029
23. Hakim A.M.Y., Matsuoka M., Baja S., Rampisela D.A. and Arif S. (2020). Predicting land cover change in the Mamminasata area, Indonesia, to evaluate the spatial plan. ISPRS Int. J. Geo-Inf., 9(481). DOI: 10.3390/ijgi9080481
24. Ibrahim M. (2023). Evolution of random forest from decision tree and bagging: A bias-variance perspective. DUJASE, 7(1), 66–71. DOI: 10.3329/dujase.v7i1.62888
25. Ismail M.H., Aik D.H.J., Alias M.A., Muharam F.M. and Zaki P.H. (2021). Land Use/Land Cover (LULC) Changes in Cameron Highlands, Malaysia: Explore the Impact of the LULC Changes on Land Surface Temperature (LST) Using Remote Sensing. In: Climate Impacts on Sustainable Natural Resource Management , 279–301. wiley. DOI: 10.1002/9781119793403.ch14
26. Joseph V.R. (2022). Optimal ratio for data splitting. Stat. Anal. Data Min.: The ASA Data Sci. Journal, 15, 531–538. DOI: 10.1002/sam.11583
27. Kaur H., Tyagi S., Mehta M. and Singh D. (2023). Time series (2001/2002–2021) analysis of earth observation data using Google Earth Engine (GEE) for detecting changes in Land Use Land Cover (LULC) with specific reference to forest cover in East Godavari Region, Andhra Pradesh, India. J. Earth Syst. Sci., 132(86), 1–16. DOI: 10.1007/s12040-023-02099-w
28. Kuntla S.K. and Manjusree P. (2020). Development of an automated tool for delineation of flood footprints from SAR imagery for rapid disaster response: a case study. Journal of the Indian Society of Remote Sensing, 48(6), 935–944. DOI: 10.1007/s12524-020-01125-4
29. Li B. V, Jenkins C.N. and Xu W. (2022). Strategic protection of landslide vulnerable mountains for biodiversity conservation under landcover and climate change impacts. PNAS, 19(2), e22113416118. DOI: 10.1073/pnas.2113416118/-/DCSupplemental
30. Liu D., Zhang X., Zheng T., Shi Q., Cui Y., Wang Y. and Liu L. (2021). Optimisation and evaluation of the random forest model in the efficacy prediction of chemoradiotherapy for advanced cervical cancer based on radiomics signature from high-resolution T2 weighted images. Archives of Gynecology and Obstetrics, 303, 811–820. DOI: 10.1007/s00404-020-05908-5
31. Liu S. and Gu G. (2017). Improving the impervious surface estimation from hyperspectral images using a spectral-spatial feature sparse representation and post-processing approach. Remote Sens., 9(456). DOI: 10.3390/rs9050456
32. Maleki R., Wu F., Oubara A., Fathollahi L. and Yang G. (2024). Refinement of cropland data layer with effective confidence layer interval and image filtering. Agriculture, 14(1285). DOI: 10.3390/agriculture14081285
33. Manafifard M. (2024). A new hyperparameter to random forest: application of remote sensing in yield prediction. Earth Science Informatics, 17(1), 63–73. DOI: 10.1007/s12145-023-01156-8
34. Mensah J.K., Ofosu E.A., Yidana S.M., Akpoti K. and Kabo-bah A.T. (2022). Integrated modeling of hydrological processes and groundwater recharge based on land use land cover, and climate changes: a systematic review. Environmental Advances, 8(100224). DOI: 10.1016/j.envadv.2022.100224
35. Olariu H.G., Malambo L., Popescu S.C., Virgil C. and Wilcox B.P. (2022). Woody plant encroachment: Evaluating methodologies for semiarid woody species classification from drone images. Remote Sens., 14(1665). DOI: 10.3390/rs14071665
36. Pramesti T.V., Rushayati S.B. and Prasetyo L.B. (2025). Evaluating ecosystem recovery on degraded lands restoration using satellite-based spatial indicators in Mount Halimun Salak National Park, Indonesia. Ecological Engineering & Environmental Technology, 26(8), 363–374. DOI: 10.12912/27197050/208417
37. Probst P. and Boulesteix A.-L. (2018). To tune or not to tune the number of trees in random forest. Journal of Machine Learning Research, 18, 1–18. http://jmlr.org/papers/v18/17-269.html.
38. Qacami M., Khattabi A., Lahssini S., Rifai N. and Meliho M. (2023). Land-cover/land-use change dynamics modeling based on land change modeler. Annals of Regional Science, 70, 237–258. DOI: 10.1007/s00168-022-01169-z
39. Ratnayake S.S., Reid M., Larder N., Hunter D., Ranagalage M., Kogo B., Dharmasena P.B. and Kariyawasam C.S. (2024). Knowing the lay of the land: changes to land use and cover and landscape pattern in village tank cascade systems of Sri Lanka. Frontiers in Environmental Science, 12, 1353459. DOI: 10.3389/fenvs.2024.1353459
40. Rivai F.A., Asy’ari R., Fadhil M.H., Jouhary N.A., Saenal N., Ardan F., Pohan A., Pramulya R. and Setiawan Y. (2023). Analysis of land use and land cover changes using random forest through Google Earth Engine in Depok City. SSRS Journal B: Spatial Research, 1, 1–12.
41. Salman H.A., Kalakech A. and Steiti A. (2024). Random forest algorithm overview. Babylonian Journal of Machine Learning, 2024, 69–79. DOI: 10.58496/bjml/2024/007
42. Silva C.A., Guerrisi G., Del Frate F. and Sano E.E. (2022). Near-real time deforestation detection in the Brazilian Amazon with Sentinel-1 and neural networks. European Journal of Remote Sensing, 55(1), 129–149. DOI: 10.1080/22797254.2021.2025154
43. Singh G. and Pandey A. (2021). Evaluation of classification algorithms for land use land cover mapping in the snow-fed Alaknanda River Basin of the Northwest Himalayan Region. Applied Geomatics, 13(4), 863–875. DOI: 10.1007/s12518-021-00401-3
44. Solomon N., Pabi O., Annang T., Asante I.K. and Birhane E. (2018). The effects of land cover change on carbon stock dynamics in a dry Afromontane forest in northern Ethiopia. Carbon Balance and Manage., 13(14), 1–13. DOI: 10.1186/s13021-018-0103-7
45. Sun J. and Ongsomwang S. (2023). Optimal parameters of random forest for land cover classification with suitable data type and dataset on Google Earth Engine. Frontiers in Earth Science, 11, 1188093. DOI: 10.3389/feart.2023.1188093
46. Svoboda J., Štych P., Laštovička J., Paluba D. and Kobliuk N. (2022). Random Forest classification of Land Use, Land-Use Change and Forestry (LULUCF) using Sentinel-2 data—A case study of Czechia. Remote Sensing, 14(5). DOI: 10.3390/rs14051189
47. Tempa K. and Aryal K.R. (2022). Semi-automatic classification for rapid delineation of the geohazard-prone areas using Sentinel-2 satellite imagery. SN Applied Sciences, 4(5). DOI: 10.1007/s42452-022-05028-6
48. Tjahjono B., Firdania I. and Trisasongko B.H. (2024). Modeling landslide hazard using machine learning: a case study of Bogor, Indonesia. Journal of Natural Resources and Environmental Management, 14(2), 407–414. DOI: 10.29244/jpsl.14.2.407
49. Wahyuni N.I., Soemarno and Hasyim A.W. (2025). Estimating carbondioxide emission and mitigation strategies from land use and land cover change in Banyuwangi. J-PAL, 16(1), 9–14. DOI: 10.21776/ub.jpal.2025.016.01.02
50. Ye Z., Yang K., Lin Y., Guo S., Sun Y., Chen X., Lai R. and Zhang H. (2023). A comparison between Pixel-based deep learning and Objectbased image analysis (OBIA) for individual detection of cabbage plants based on UAV Visible-light images. Computers and Electronics in Agriculture, 209. DOI: 10.1016/j.compag.2023.107822
51. Zeferino L.B., Souza L.F.T. de, Amaral C.H. do, Fernandes Filho E.I. and Oliveira T.S. de. (2020). Does environmental data increase the accuracy of land use and land cover classification? International Journal of Applied Earth Observation and Geoinformation, 91. DOI: 10.1016/j.jag.2020.102128
52. Zhang X., Estoque R.C., Murayama Y. and Ranagalage M. (2021). Capturing urban heat island formation in a subtropical city of China based on Landsat images: implications for sustainable urban development. Environmental Monitoring and Assessment, 193(3). DOI: 10.1007/s10661-021-08890-w
53. Zhu L., Xing H. and Hou D. (2022). Analysis of carbon emissions from land cover change during 2000 to 2020 in Shandong Province, China. Scientific Reports, 12(1). DOI: 10.1038/s41598-022-12080-0
Review
For citations:
Rivai F., Tjahjono B., Munibah Kh., Nofrizal A. Majority Filter For Enhancing Pixel-Based Random Forest Land Cover Classification In Sukajaya District, Bogor Regency. GEOGRAPHY, ENVIRONMENT, SUSTAINABILITY. 2025;18(4):171-182. https://doi.org/10.24057/2071-9388-2025-4183
Views:
59
JATS XML
Email this article 