R Libraries for Remote Sensing Data Classification by K-Means Clustering and NDVI Computation in Congo River Basin, DRC
Source abstract
Abstract
In this paper, an image analysis framework is formulated for Landsat-8 Operational Land Imager and Thermal Infrared Sensor (OLI/TIRS) scenes using the R programming language. The libraries of R are shown to be effective in remote sensing data processing tasks, such as classification using k-means clustering and computing the Normalized Difference Vegetation Index (NDVI). The data are processed using an integration of the RStoolbox, terra, raster, rgdal and auxiliary packages of R. The proposed approach to image processing using R is designed to exploit the parameters of image bands as cues to detect land cover types and vegetation parameters corresponding to the spectral reflectance of the objects represented on the Earth’s surface. Our method is effective at processing the time series of the images taken at various periods to monitor the landscape dynamics in the middle part of the Congo River basin, Democratic Republic of the Congo (DRC). Whereas previous approaches primarily used Geographic Information System (GIS) software, we proposed to explicitly use the scripting methods for satellite image analysis by applying the extended functionality of R. The application of scripts for geospatial data is an effective and robust method compared with the traditional approaches due to its high automation and machine-based graphical processing. The algorithms of the R libraries are adjusted to spatial operations, such as projections and transformations, object topology, classification and map algebra. The data include Landsat-8 OLI-TIRS covering the three regions along the Congo river, Bumba, Basoko and Kisangani, for the years 2013, 2015 and 2022. We also validate the performance of graphical data handling for cartographic visualization using R libraries for visualising changes in land cover types by k-means clustering and calculation of the NDVI for vegetation analysis.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing in Agriculture · Land Use and Ecosystem Services · Remote Sensing and LiDAR Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Laboratory of Image Synthesis and Analysis (LISA), École Polytechnique de Bruxelles (EPB, Brussels Faculty of Engineering), Université Libre de Bruxelles (ULB), Building L, Campus de Solbosch, ULB—LISA CP165/57, Avenue Franklin D. Roosevelt 50, B-1050 Brussels, Belgium
Funding
Federal Public Planning Service Science Policy
References (100+)
Show source-provided references
1. Lillesand, T., Kiefer, R.W., and Chipman, J. (2015). Remote Sensing and Image Interpretation, Wiley. [7th ed.].
2. Land Use and Land Cover Mapping in Europe. Practices & Trends
3. Miombo woodland, an ecosystem at risk of disappearance in the Lufira Biosphere Reserve (Upper Katanga, DR Congo)? A 39-years analysis based on Landsat images
4. Deforestation in Central Africa: Estimates at regional, national and landscape levels by advanced processing of systematically-distributed Landsat extracts10.1016/j.rse.2007.07.026 ↗
5. Ygorra, B., Frappart, F., Wigneron, J.P., Moisy, C., Catry, T., Baup, F., Hamunyela, E., and Riazanoff, S. (2021, January 11–16). Deforestation Monitoring Using Sentinel-1 SAR Images in Humid Tropical Areas. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.10.1109/IGARSS47720.2021.9554698 ↗
6. Sentinel-2 for High Resolution Mapping of Slope-Based Vegetation Indices Using Machine Learning by SAGA GIS
7. Dalimier, J., Claverie, M., Goffart, B., Jungers, Q., Lamarche, C., De Maet, T., and Defourny, P. (2021, January 11–16). Characterizing the Congo Basin Forests by a Detailed Forest Typology Enriched with Forest Biophysical Variables. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.10.1109/IGARSS47720.2021.9553905 ↗
8. Tracking small-scale tropical forest disturbances: Fusing the Landsat and Sentinel-2 data record10.1016/j.rse.2021.112470 ↗
9. Sub-annual tropical forest disturbance monitoring using harmonized Landsat and Sentinel-2 data
10. Verhegghen, A., Hugh, E., and Achard, F. (2015, January 26–31). Assessing forest degradation from selective logging using time series of fine spatial resolution imagery in Republic of Congo. Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy.10.1109/IGARSS.2015.7326202 ↗
11. Haarpaintner, J., Einzmann, K., Pedrazzani, D., Mateos San Juan, M., Gómez Giménez, M., Heinzel, J., Enßle, F., and Mane, L. (2012, January 22–27). Tropical forest remote sensing services for the Democratic Republic Of Congo case inside the EU FP7 ‘ReCover’ project (1st iteration). Proceedings of the 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany.10.1109/IGARSS.2012.6352722 ↗
12. Sakurai-Amano, T., Onuki, S., and Takagi, M. (2002, January 24–28). Automatic extraction of rivers in tropical rain forests from JERS-1 SAR images using spectral and spatial information. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Toronto, ON, Canada.
13. Floury, N., Le Toan, T., Jeanjean, H., Beaudoin, A., and Hamel, O. (1995, January 10–14). L and C-band multipolarized backscatter responses of eucalyptus plantations in Congo. Proceedings of the 1995 International Geoscience and Remote Sensing Symposium, IGARSS ’95. Quantitative Remote Sensing for Science and Applications, Firenze, Italy.
14. Zhang, H., Bauters, M., Boeckx, P., and Van Oost, K. (2021). Mapping Canopy Heights in Dense Tropical Forests Using Low-Cost UAV-Derived Photogrammetric Point Clouds and Machine Learning Approaches. Remote Sens., 13.10.3390/rs13183777 ↗
15. Jiménez, A., Hernández, A.J., and Rodríguez-Espinosa, V.M. (2020). Integration of Geospatial Tools and Multi-source Geospatial Data to Evaluate the Tropical Forest Cover Change in Central America and Its Methodological Replicability in Brazil and the DRC. Remote Sens., 12.10.3390/rs12172705 ↗
16. Mapping tree height distributions in Sub-Saharan Africa using Landsat 7 and 8 data10.1016/j.rse.2016.02.023 ↗
17. De Grandi, E.C., Mitchard, E.T.A., Woodhouse, I.H., Verhegghen, A., and Muirhead, F. (2015, January 26–31). Statistics of TanDEM-X DSM, coherence and backscatter for the characterization of tropical forest structural configuration. Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy.10.1109/IGARSS.2015.7326141 ↗
18. Mapping forest windthrows using high spatial resolution multispectral satellite images
19. Forest height mapping using inventory and multi-source satellite data over Hunan Province in southern China10.1016/j.fecs.2022.100006 ↗
20. Mapping a- and b-diversity of mangrove forests with multispectral and hyperspectral images10.1016/j.rse.2022.113021 ↗
21. Overview of the radiometric and biophysical performance of the MODIS vegetation indices10.1016/S0034-4257(02)00096-2 ↗
22. Development of a two-band enhanced vegetation index without a blue band10.1016/j.rse.2008.06.006 ↗
23. A soil-adjusted vegetation index (SAVI)10.1016/0034-4257(88)90106-X ↗
24. Ground-based Network of NDVI measurements for tracking temporal dynamics of canopy structure and vegetation phenology in different biomes10.1016/j.rse.2012.03.012 ↗
25. Hyperspectral Vegetation Indices Calculated by Qgis Using Landsat Tm Image: A Case Study of Northern Iceland10.2478/arls-2020-0021 ↗
26. Seaquist, J.W., Chappell, A., and Eklundh, L. (2002, January 24–28). Exploring and improving NOAA AVHRR NDVI image quality for African drylands. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Toronto, ON, Canada.
27. Evaluation of the potential of MODIS satellite data to predict vegetation phenology in different biomes: An investigation using ground-based NDVI measurements10.1016/j.rse.2013.01.010 ↗
28. Evolution of drivers of deforestation and forest degradation in the Congo Basin forests: Exploring possible policy options to address forest loss10.1016/j.landusepol.2015.11.024 ↗
29. Kasekete, D.K., Ligot, G., Mweru, J.P.M., Drouet, T., Rousseau, M., Moango, A., and Bourland, N. (2022). Growth, Productivity, Biomass and Carbon Stock in Eucalyptus saligna and Grevillea robusta Plantations in North Kivu, Democratic Republic of the Congo. Forests, 13.10.3390/f13091508 ↗
30. Deforestation and timber production in Congo after implementation of sustainable forest management policy10.1016/j.landusepol.2015.11.028 ↗
31. Do forest-management plans and FSC certification help avoid deforestation in the Congo Basin?10.1016/j.ecolecon.2020.106660 ↗
32. Impacts of Road Expansion on Deforestation and Biological Carbon Loss in the Democratic Republic of Congo10.1007/s10640-014-9775-y ↗
33. The Deforestation of Rural Areas in the Lower Congo Province10.1007/s10661-004-4028-0 ↗
34. Economic activities and deforestation in the Congo basin: An environmental kuznets curve framework analysis10.1016/j.envc.2022.100553 ↗
35. Hufkens, K., de Haulleville, T., Kearsley, E., Jacobsen, K., Beeckman, H., Stoffelen, P., Vandelook, F., Meeus, S., Amara, M., and Van Hirtum, L. (2020). Historical Aerial Surveys Map Long-Term Changes of Forest Cover and Structure in the Central Congo Basin. Remote Sens., 12.10.3390/rs12040638 ↗
36. Kabuanga, J.M., Kankonda, O.M., Saqalli, M., Maestripieri, N., Bilintoh, T.M., Mweru, J.P.M., Liama, A.B., Nishuli, R., and Mané, L. (2021). Historical Changes and Future Trajectories of Deforestation in the Ituri-Epulu-Aru Landscape (Democratic Republic of the Congo). Land, 10.10.20944/preprints202103.0461.v1 ↗
37. Mapping tropical deforestation in Central Africa
38. Mukenza, M.M., Muteya, H.K., Nghonda, D.D.N., Sambiéni, K.R., Malaisse, F., Kaleba, S.C., Bogaert, J., and Sikuzani, Y.U. (2022). Uncontrolled Exploitation of Pterocarpus tinctorius Welw. and Associated Landscape Dynamics in the Kasenga Territory: Case of the Rural Area of Kasomeno (DR Congo). Land, 11.10.3390/land11091541 ↗
39. Forest condition in the Congo Basin for the assessment of ecosystem conservation status10.1016/j.ecolind.2020.107268 ↗
40. Forest cover affects gully expansion at the tropical watershed scale: Case study of Luzinzi in Eastern DR Congo10.1016/j.tfp.2021.100083 ↗
41. Tropical deforestation and species endangerment: The role of remote sensing10.1007/BF00131173 ↗
42. Ma, H., Song, J., Wang, J., and Hua, Y. (2012, January 22–27). Comparison of the inversion ability in extrapolating forest canopy height by integration of LiDAR data and different optical remote sensing products. Proceedings of the 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany.10.1109/IGARSS.2012.6350700 ↗
43. Keil, M., Akgoz, E., Carl, S., Forster, B., Hausler, T., Johlige, A., Lautner, M., and Martin, K. (July, January 28). Use of SIR-C/X-SAR and Landsat TM data for vegetation mapping in the Bavarian Forest national park and in the Ore Mountains. Proceedings of the IEEE 1999 International Geoscience and Remote Sensing Symposium, IGARSS’99 (Cat. No.99CH36293), Hamburg, Germany.
44. Evaluating seasonal effect on forest leaf area index mapping using multi-seasonal high resolution satellite pléiades imagery
45. Hoan, N.T., Tateishi, R., Bayan, A., Ngigi, T.G., and Lan, M. (2011, January 24–29). Improving tropical forest mapping using combination of optical and microwave data of ALOS. Proceedings of the 2011 IEEE International Geoscience and Remote Sensing Symposium, Vancouver, BC, Canada.10.1109/IGARSS.2011.6049235 ↗
46. Scale considerations for integrating forest inventory plot data and satellite image data for regional forest mapping10.1016/j.rse.2013.08.048 ↗
47. Dupuis, C., Lejeune, P., Michez, A., and Fayolle, A. (2020). How Can Remote Sensing Help Monitor Tropical Moist Forest Degradation?—A Systematic Review. Remote Sens., 12.10.3390/rs12071087 ↗
48. Dynamics of land-use and land-cover change in tropical regions10.1146/annurev.energy.28.050302.105459 ↗
49. De Grandi, G.F., Mayaux, P., Massart, M., Baraldi, A., and Sgrenzaroli, M. (2001, January 9–13). A vegetation map of the Central Congo basin derived from microwave and optical remote sensing data using a variable resolution classification approach. Proceedings of the Geoscience and Remote Sensing Symposium, 2001. IGARSS ’01, Sydney, NSW, Australia.
50. Lamulamu, A., Ploton, P., Birigazzi, L., Xu, L., Saatchi, S., and Kibambe Lubamba, J.P. (2022). Assessing the Predictive Power of Democratic Republic of Congo’s National Spaceborne Biomass Map over Independent Test Samples. Remote Sens., 14.10.3390/rs14164126 ↗
51. Laporte, N., and Lin, T.S. (2003, January 21–25). Monitoring logging in the tropical forest of Republic of Congo with Landsat imagery. Proceedings of the IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477), Toulouse, France.
52. A GIS-based assessment on the vulnerability and future extent of the tropical forests of the Congo basin10.1007/s10661-006-2015-3 ↗
53. Global, Landsat-based forest-cover change from 1990 to 200010.1016/j.rse.2014.08.017 ↗
54. Haarpaintner, J., and Hindberg, H. (2019). Multi-Temporal and Multi-Frequency SAR Analysis for Forest Land Cover Mapping of the Mai-Ndombe District (Democratic Republic of Congo). Remote Sens., 11.10.3390/rs11242999 ↗
55. Simard, M., Saatchi, S., and DeGrandi, G. (2000, January 24–28). Comparison of a decision tree and maximum likelihood classifiers: Application to SAR image of tropical forest. Proceedings of the IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120), Honolulu, HI, USA.
56. Antropov, O., Rauste, Y., Seifert, F.M., and Häme, T. (2015, January 26–31). Selective logging of tropical forests observed using L- and C-band SAR satellite data. Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy.10.1109/IGARSS.2015.7326669 ↗
57. Einzmann, K., Haarpaintner, J., and Larsen, Y. (2012, January 22–27). Forest monitoring in Congo Basin with combined use of SAR C- & L-band. Proceedings of the 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany.10.1109/IGARSS.2012.6352093 ↗
58. Deutscher, J., Gutjahr, K., Perko, R., Raggam, H., Hirschmugl, M., and Schardt, M. (2017, January 27–29). Humid tropical forest monitoring with multi-temporal L-, C- and X-band SAR data. Proceedings of the 2017 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp), Brugge, Belgium.10.1109/Multi-Temp.2017.8035264 ↗
59. A method for integrating MODIS and Landsat data for systematic monitoring of forest cover and change in the Congo Basin10.1016/j.rse.2007.11.012 ↗
60. Mapping annual forest cover by fusing PALSAR/PALSAR-2 and MODIS NDVI during 2007–201610.1016/j.rse.2019.01.038 ↗
61. SatRed: New classification land use/land cover model based on multi-spectral satellite images and neural networks applied to a semiarid valley of Patagonia
62. Unsupervised deep learning of landscape typologies from remote sensing images and other continuous spatial data10.1016/j.envsoft.2022.105462 ↗
63. Fitness landscape analysis of convolutional neural network architectures for image classification10.1016/j.ins.2022.07.040 ↗
64. Zhang, X.Q., Yang, G.D., Chen, S.B., Fan, J.Z., and Wei, X.H. (2011, January 24–26). RS image batch processing in grid. Proceedings of the 2011 19th International Conference on Geoinformatics, Shanghai, China.10.1109/GeoInformatics.2011.5981114 ↗
65. Pyeo: A Python package for near-real-time forest cover change detection from Earth observation using machine learning10.1016/j.cageo.2022.105192 ↗
66. Impact of land use/land cover changes on groundwater resources in Al Ain region of the United Arab Emirates using remote sensing and GIS techniques10.1016/j.gsd.2021.100587 ↗
67. Asuquo Enoh, M., Ebere Njoku, R., and Chinenye Okeke, U. (Adv. Space Res., 2022). Modeling and mapping the spatial–temporal changes in land use and land cover in Lagos: A dynamics for building a sustainable urban city, Adv. Space Res., in press.10.1016/j.asr.2022.07.042 ↗
68. Monitoring land use/cover change using remote sensing and GIS techniques: A case study of Hawalbagh block, district Almora, Uttarakhand, India
69. Land use and land cover (LULC) change analysis using TM, ETM+ and OLI Landsat images in district of Okara, Punjab, Pakistan10.1016/j.pce.2022.103117 ↗
70. Coastal and landuse changes of Burullus Lake, Egypt: A comparison using Landsat and Sentinel-2 satellite images
71. Paddy lands detection using Landsat-8 satellite images and object-based classification in Rasht city, Iran
72. R Core Team (2022). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing.
73. de Wasseige, C., Devers, D., De, P., Ebaá Atyi, R., Nasi, R., and Mayaux, P. (2009). Les Forêts du Bassin du Congo—Etat des Forêts 2008, Office des Publications de Lúnion Européenne.
74. Lescuyer, G., Cerutti, P.O., Essiane Mendoula, E., Eba’a Atyi, R., and Nasi, R. (2010). An appraisal of chainsaw milling in the Congo Basin. The forests of the Congo Basin: State of the forest 2010, Publications Office of the European Union. Tropenbos International.
75. Drivers of deforestation and degradation for 28 tropical conservation landscapes10.1007/s13280-020-01325-9 ↗
76. Quantifying forest cover loss in Democratic Republic of the Congo, 2000–2010, with Landsat ETM+ data10.1016/j.rse.2011.08.027 ↗
77. Using fragmentation to assess degradation of forest edges in Democratic Republic of Congo10.1186/s13021-016-0054-9 ↗
78. Leutner, B., Horning, N., Schwalb-Willmann, J., and Hijmans, R.J. (2022). Package ‘RStoolbox’, German Aerospace Center (DLR).
79. Hijmans, R.J., Bivand, R., Forner, K., Ooms, J., Pebesma, E., and Sumner, M.D. (2022). Package ‘Terra’, Maintainer.
80. Hijmans, R.J. (2022, October 05). Raster: Geographic Data Analysis and Modeling. R Package Version 2.6-7. Available online: https://CRAN.R-project.org/package=raster.
81. Neuwirth, E. (2022, October 05). RColorBrewer: ColorBrewer Palettes. R Package Version 1.1-2. Available online: https://CRAN.R-project.org/package=RColorBrewer.
82. Garnier, S., Ross, N., Rudis, R., Sciaini, M., Camargo, A.P., and Scherer, C. (2021). Viridis—Colorblind-Friendly Color Maps for R, New Jersey Institute of Technology. R Package Version 0.6.2.2021.
83. Assessment of basin-scale soil erosion within the Congo River Basin: A review10.1016/j.catena.2019.02.030 ↗
84. Mapping of Central Africa Forested Wetlands Using Remote Sensing10.1109/JSTARS.2013.2269733 ↗
85. Congo Basin rainfall climatology: Can we believe the climate models?10.1098/rstb.2012.0296 ↗
86. Sayer, J. (1992). Zaïre. The Conservation Atlas of Tropical Forests Africa, Palgrave Macmillan.10.1007/978-1-349-12961-4 ↗
87. Mendako, R.K., Tian, G., Ullah, S., Sagali, H.L., and Kipute, D.D. (2022). Assessing the Economic Contribution of Forest Use to Rural Livelihoods in the Rubi-Tele Hunting Domain, DR Congo. Forests, 13.10.3390/f13010130 ↗
88. Batra, N., Yang, Y.C.E., Choi, H.I., Kumar, P., Cai, X., and De Fraiture, C. (2008, January 7–11). Understanding Hydrological Cycle Dynamics Due to Changing Land Use and Land Cover: Congo Basin Case Study. Proceedings of the IGARSS 2008—2008 IEEE International Geoscience and Remote Sensing Symposium, Boston, MA, USA.10.1109/IGARSS.2008.4780136 ↗
89. Remote sensing imagery for resource inventories in central Africa: The importance of detailed field data10.1007/BF02168858 ↗
90. The Congo Basin forests in a changing climate: Policy discourses on adaptation and mitigation (REDD+)10.1016/j.gloenvcha.2011.08.001 ↗
91. Adapting the Congo Basin forests management to climate change: Linkages among biodiversity, forest loss, and human well-being10.1016/j.forpol.2014.05.010 ↗
92. Morgan, E.A., Bush, G., Mandea, J.Z., Kermarc, M., and Mackey, B. (2022). Comparing Community Needs and REDD+ Activities for Capacity Building and Forest Protection in the Équateur Province of the Democratic Republic of Congo. Land, 11.10.3390/land11060918 ↗
93. Governing knowledge transfer for deforestation monitoring: Insights from REDD+ projects in the Congo Basin region10.1016/j.forpol.2019.102081 ↗
94. Cornerstones and epilogue of the GRFM Africa project: A gallery of regional scale vegetation maps10.1109/IGARSS.2002.1025720 ↗
95. Preliminary estimation of above-ground carbon storage in cocoa agroforests of Bengamisa-Yangambi forest landscape (Democratic Republic of Congo)10.1007/s10457-021-00657-z ↗
96. African Climate Change: Taking the Shorter Route10.1175/BAMS-87-10-1355 ↗
97. Engebretson, C. (2022, October 05). Landsat 8-9 Operational Land Imager (OLI)—Thermal Infrared Sensor (TIRS) Collection 2 Level 1 (L1) Data Format Control Book (DFCB). Online, 2020. LSDS-1822 Version 6.0, USGS. Available online: https://earth.esa.int/eogateway/documents/20142/0/Landsat-8-9-OLI-TIRS-Collection-2-Level-1-Data-Format-Control-Book-DFCB.pdf.
98. Lemenkova, P. (2022). Handling Dataset with Geophysical and Geological Variables on the Bolivian Andes by the GMT Scripts. Data, 7.10.3390/data7060074 ↗
99. Lemenkova, P. (2022). Mapping Climate Parameters over the Territory of Botswana Using GMT and Gridded Surface Data from TerraClimate. ISPRS Int. J. Geo-Inf., 11.10.3390/ijgi11090473 ↗
100. Lemenkova, P. (2022). Console-Based Mapping of Mongolia Using GMT Cartographic Scripting Toolset for Processing TerraClimate Data. Geosciences, 12.10.3390/geosciences12030140 ↗