Quantifying Categorical Information Loss in Forest Compositional Mapping: Implications for the Accuracy of Forest Assessment in Lualaba Province (DR Congo) - 2026
Quantifying Categorical Information Loss in Forest Compositional Mapping: Implications for the Accuracy of Forest Assessment in Lualaba Province (DR Congo)
[en] Forests of Lualaba Province (DR Congo) form a compositionally complex mosaic of dry dense forest, gallery forest, and Miombo woodland. Yet, categorical land-cover maps impose discrete boundaries on these inherently continuous vegetation gradients, systematically discarding subpixel compositional information critical for forest monitoring and carbon accounting. The magnitude of this information loss at the landscape scale, however, remains largely unquantified. In this study, we train a Multi-Output Neural Network (MONN) using Sentinel-2 spectral and textural predictors (2025) to estimate the proportional cover of three forest types across the province. Model performance is benchmarked against a normalised Random Forest (RF) using spatial block cross-validation. Categorical information loss is quantified pixel-wise using two complementary metrics, dominant class proportion and Shannon compositional entropy, alongside a derived interpretive quantity, categorical information loss. The MONN slightly outperformed RF (R2 = 0.648 vs. 0.630; RMSE = 0.224 vs. 0.229), yet the results reveal a fundamentally heterogeneous landscape structure. The mean dominant-class proportion was only 56.2%, indicating that categorical maps discard, on average, 43.8% of compositional information per pixel. Only 7.9% of forested pixels exceeded the 75% dominance threshold, while Shannon entropy reached 74.1% of its theoretical maximum, indicating that forest types coexist in near-equal proportions across most pixels. This renders categorical attribution structurally inadequate for most of the forested landscape. Across 92.1% of forested pixels, no single forest type achieved clear dominance. These results show that compositional mixing is the dominant structural condition of the landscape, and that compositional mapping is essential for representing tropical forest structure in heterogeneous drylands. By formally quantifying categorical information loss at the landscape scale, this study shows that continuous compositional mapping converts this structural ambiguity into a spatially explicit ecological signal, with direct implications for monitoring vegetation dynamics and biodiversity, suggesting a structural source of error in carbon stock estimation in tropical dry forests that warrants empirical validation.
Disciplines :
Environmental sciences & ecology
Author, co-author :
Mpanda Mukenza, Médard ; Teaching and Research Center (TERRA), Gembloux Agro-Bio Tech—Université de Liège, Gembloux, Belgium
Kikuni Tchowa, John ; Teaching and Research Center (TERRA), Gembloux Agro-Bio Tech—Université de Liège, Gembloux, Belgium
Nantenaina Ramalason, Felana; Mention Foresterie et Environnement, École Supérieure des Sciences Agronomiques (ESSA-Forêts), Université d’Antananarivo, Antananarivo, Madagascar
Khoji Muteya, Heritier ; Ecology, Ecological Restoration and Landscape Unit, Faculty of Agronomic Sciences, University of Lubumbashi, Lubumbashi P.O. Box 1825, Democratic Republic of the Congo
Bogaert, Jan ; Teaching and Research Center (TERRA), Gembloux Agro-Bio Tech—Université de Liège, Gembloux, Belgium
Useni Sikuzani, Yannick ; Ecology, Ecological Restoration and Landscape Unit, Faculty of Agronomic Sciences, University of Lubumbashi, Lubumbashi P.O. Box 1825, Democratic Republic of the Congo
Bastin, Jean-François ; Université de Liège - ULiège > TERRA Research Centre > Biodiversité, Ecosystème et Paysage (BEP)
Language :
English
Title :
Quantifying Categorical Information Loss in Forest Compositional Mapping: Implications for the Accuracy of Forest Assessment in Lualaba Province (DR Congo)
Publication date :
June 2026
Journal title :
Remote Sensing
eISSN :
2072-4292
Publisher :
Multidisciplinary Digital Publishing Institute (MDPI)
Buchhorn M. Lesiv M. Tsendbazar N.-E. Herold M. Bertels L. Smets B. Copernicus Global Land Cover Layers—Collection 2 Remote Sens. 2020 12 1044 10.3390/rs12061044
Brown C.F. Brumby S.P. Guzder-Williams B. Birch T. Hyde S.B. Mazzariello J. Czerwinski W. Pasquarella V.J. Haertel R. Ilyushchenko S. et al. Dynamic World, near real-time global 10 m land use land cover mapping Sci. Data 2022 9 251 10.1038/s41597-022-01307-4
Useni Sikuzani Y. Mpanda Mukenza M. Kikuni Tchowa J. Kabamb Kanyimb D. Malaisse F. Bogaert J. Hierarchical analysis of Miombo woodland spatial dynamics in Lualaba Province (Democratic Republic of the Congo), 1990–2024: Integrating remote sensing and landscape ecology techniques Remote Sens. 2024 16 3903 10.3390/rs16203903
Tyukavina A. Hansen M.C. Potapov P. Parker D. Okpa C. Stehman S.V. Kommareddy I. Turubanova S. Congo basin forest loss dominated by increasing smallholder clearing Sci. Adv. 2018 4 eaat2993 10.1126/sciadv.aat2993 30417092
Picard J. Nungi-Pambu Dembi M.M. Barbier N. Cornu G. Couteron P. Forni E. Gibbon G. Lim F. Ploton P. Pouteau R. et al. Combining satellite and field data reveals Congo’s forest types structure, functioning and composition Remote Sens. Ecol. Conserv. 2025 11 200 220 10.1002/rse2.419
Sexton J.O. Song X.-P. Feng M. Noojipady P. Anand A. Huang C. Kim D.-H. Collins K.M. Channan S. DiMiceli C. et al. Global, 30-m resolution continuous fields of tree cover Int. J. Digit. Earth 2013 6 427 448 10.1080/17538947.2013.786146
Castle S.E. Newton P. Oldekop J.A. Baylis K. Miller D.C. Global forest dataset incongruence creates high uncertainties for conservation, climate, and development policy One Earth 2026 9 101558 10.1016/j.oneear.2025.101558
Bastin J.-F. Berrahmouni N. Grainger A. Maniatis D. Mollicone D. Moore R. Patriarca C. Picard N. Sparrow B. Abraham E.M. The extent of forest in dryland biomes Science 2017 356 635 638 10.1126/science.aam6527
Ryan C.M. Williams M. Grace J. Above- and belowground carbon stocks in a miombo woodland landscape of Mozambique Biotropica 2011 43 423 432 10.1111/j.1744-7429.2010.00713.x
White F. The Vegetation of Africa UNESCO Paris, France 1983
Abdou Amadou S. Lawali D. Bastin J.-F. Bogaert J. Michez A. Meersmans J. Effect of Spatial Resolution on Land Cover Mapping in an Agropastoral Area of Niger (Aguié and Mayahi) Using Sentinel-2 and Landsat 8 Imagery Within a Random Forest Regression Framework Remote Sens. 2026 18 750 10.3390/rs18050750
Atkinson P.M. Resolution manipulation and sub-pixel mapping Remote Sensing Image Analysis: Including the Spatial Domain De Jong S.M. Van der Meer F.D. Springer Dordrecht, The Netherlands 2004 51 70
Keshava N. Mustard J.F. Spectral unmixing IEEE Signal Process. Mag. 2002 19 44 57 10.1109/79.974727
Foody G.M. Atkinson P.M. Uncertainty in Remote Sensing and GIS Wiley Chichester, UK 2002 10.1002/0470035269
DiMiceli C. Carroll M. Sohlberg R. Kim D. Kelly M. Townshend J. MOD44B MODIS/Terra Vegetation Continuous Fields Yearly L3 Global 250m SIN Grid V006 NASA EOSDIS Land Processes DAAC Sioux Falls, SD, USA 2015 10.5067/MODIS/MOD44B.006
Hansen M.C. Potapov P.V. Moore R. Hancher M. Turubanova S.A. Tyukavina A. Thau D. Stehman S.V. Goetz S.J. Loveland T.R. et al. High-resolution global maps of 21st-century forest cover change Science 2013 342 850 853 10.1126/science.1244693
Belgiu M. Drăguț L. Random forest in remote sensing: A review of applications and future directions ISPRS J. Photogramm. Remote Sens. 2016 114 24 31 10.1016/j.isprsjprs.2016.01.011
Reiner F. Brandt M. Tong X. Skole D. Kariryaa A. Ciais P. Davies A. Hiernaux P. Chave J. Mugabowindekwe M. et al. More than one quarter of Africa’s tree cover is found outside areas previously classified as forest Nat. Commun. 2023 14 2258 10.1038/s41467-023-37880-4
Reichstein M. Camps-Valls G. Stevens B. Jung M. Denzler J. Carvalhais N. Prabhat Deep learning and process understanding for data-driven Earth system science Nature 2019 566 195 204 10.1038/s41586-019-0912-1
Kattenborn T. Leitloff J. Schiefer F. Hinz S. Review on convolutional neural networks (CNN) in vegetation remote sensing ISPRS J. Photogramm. Remote Sens. 2021 173 24 49 10.1016/j.isprsjprs.2020.12.010
Allred B.W. Bestelmeyer B.T. Boyd C.S. Brown C. Davies K.W. Duniway M.C. Ellsworth L.M. Erickson T.A. Fuhlendorf S.D. Griffiths T.V. et al. Improving Landsat predictions of rangeland fractional cover with multitask learning and uncertainty Methods Ecol. Evol. 2021 12 841 849 10.1111/2041-210X.13564
Schug F. Pfoch K.A. Pham V.-D. van der Linden S. Okujeni A. Frantz D. Radeloff V.C. Land cover fraction mapping across global biomes with Landsat data, spatially generalized regression models and spectral-temporal metrics Remote Sens. Environ. 2024 311 114260 10.1016/j.rse.2024.114260
Pan Y. Birdsey R.A. Fang J. Houghton R. Kauppi P.E. Kurz W.A. Phillips O.L. Shvidenko A. Lewis S.L. Canadell J.G. et al. A large and persistent carbon sink in the world’s forests Science 2011 333 988 993 10.1126/science.1201609
Olander L.P. Gibbs H.K. Steininger M. Swenson J.J. Murray B.C. Reference scenarios for deforestation and forest degradation in support of REDD Environ. Res. Lett. 2008 3 025011 10.1088/1748-9326/3/2/025011
Olofsson P. Foody G.M. Herold M. Stehman S.V. Woodcock C.E. Wulder M.A. Good practices for estimating area and assessing accuracy of land change Remote Sens. Environ. 2014 148 42 57 10.1016/j.rse.2014.02.015
Colditz R.R. An evaluation of different training sample allocation schemes for discrete and continuous land cover classification using decision tree-based algorithms Remote Sens. 2015 7 9655 9681 10.3390/rs70809655
Roberts D.R. Bahn V. Ciuti S. Boyce M.S. Elith J. Guillera-Arroita G. Hauenstein S. Lahoz-Monfort J.J. Schröder B. Thuiller W. et al. Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure Ecography 2017 40 913 929 10.1111/ecog.02881
Valavi R. Elith J. Lahoz-Monfort J.J. Guillera-Arroita G. blockCV: An R package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models Methods Ecol. Evol. 2019 10 225 232 10.1111/2041-210X.13107
FAO Global Forest Resources Assessment 2020: Main Report Food and Agriculture Organization of the United Nations Rome, Italy 2020
Timberlake J. Chidumayo E. Sawadogo L. Distribution and characteristics of African dry forests and woodlands The Dry Forests and Woodlands of Africa: Managing for Products and Services Chidumayo E.N. Gumbo D.J. Earthscan London, UK 2010 11 42
Vrieling A. Meroni M. Darvishzadeh R. Skidmore A.K. Wang T. Zurita-Milla R. Oosterbeek K. O’Connor B. Paganini M. Vegetation phenology from Sentinel-2 and field cameras for a Dutch barrier island Remote Sens. Environ. 2018 215 517 529 10.1016/j.rse.2018.03.014
Bey A. Sánchez-Paus Díaz A. Maniatis D. Marchi G. Mollicone D. Ricci S. Bastin J.-F. Moore R. Federici S. Rezende M. et al. Collect Earth: Land Use and Land Cover Assessment through Augmented Visual Interpretation Remote Sens. 2016 8 807 10.3390/rs8100807
Colditz R.R. Schmidt M. Conrad C. Hansen M.C. Dech S. Land cover classification with coarse spatial resolution data to derive continuous and discrete maps for complex regions Remote Sens. Environ. 2011 115 3264 3275 10.1016/j.rse.2011.07.010
Gorelick N. Hancher M. Dixon M. Ilyushchenko S. Thau D. Moore R. Google Earth Engine: Planetary-scale geospatial analysis for everyone Remote Sens. Environ. 2017 202 18 27 10.1016/j.rse.2017.06.031
Hastie T. Tibshirani R. Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction 2nd ed. Springer New York, NY, USA 2009
Georganos S. Grippa T. Vanhuysse S. Lennert M. Shimoni M. Kalogirou S. Wolff E. Less is more: Optimizing classification performance through feature selection in a very-high-resolution remote sensing object-based urban application GIScience Remote Sens. 2018 55 221 242 10.1080/15481603.2017.1408892
Wright M.N. Ziegler A. ranger: A fast implementation of random forests for high dimensional data in C++ and R J. Stat. Softw. 2017 77 1 17 10.18637/jss.v077.i01
Breiman L. Random forests Mach. Learn. 2001 45 5 32 10.1023/A:1010933404324
Probst P. Wright M.N. Boulesteix A.-L. Hyperparameters and tuning strategies for random forest WIREs Data Min. Knowl. Discov. 2019 9 e1301 10.1002/widm.1301
Aitchison J. The Statistical Analysis of Compositional Data Chapman & Hall London, UK 1986
Ioffe S. Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift Proceedings of the 32nd International Conference on Machine Learning (ICML) Lille, France 6–11 July 2015 448 456
Srivastava N. Hinton G. Krizhevsky A. Sutskever I. Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting J. Mach. Learn. Res. 2014 15 1929 1958
Goodfellow I. Bengio Y. Courville A. Deep Learning MIT Press Cambridge, MA, USA 2016
Kingma D.P. Ba J. Adam: A method for stochastic optimization Proceedings of the 3rd International Conference on Learning Representations (ICLR) San Diego, CA, USA 7–9 May 2015
Willmott C.J. Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance Clim. Res. 2005 30 79 82 10.3354/cr030079
Foody G.M. Status of land cover classification accuracy assessment Remote Sens. Environ. 2002 80 185 201 10.1016/S0034-4257(01)00295-4
Fisher P.F. The pixel: A snare and a delusion Int. J. Remote Sens. 1997 18 679 685 10.1080/014311697219015
Cracknell A.P. Synergy in remote sensing—what’s in a pixel? Int. J. Remote Sens. 1998 19 2025 2047 10.1080/014311698214848
Fernandes R. Fraser R. Latifovic R. Cihlar J. Beaubien J. Du Y. Approaches to fractional land cover and continuous field mapping: A comparative assessment over the BOREAS study region Remote Sens. Environ. 2004 89 234 251 10.1016/j.rse.2002.06.006
Shannon C.E. A mathematical theory of communication Bell Syst. Tech. J. 1948 27 379 423 10.1002/j.1538-7305.1948.tb01338.x
Pielou E.C. The measurement of diversity in different types of biological collections J. Theor. Biol. 1966 13 131 144 10.1016/0022-5193(66)90013-0
Lluïsà J. Ogaya R. Sardans J. Peñuelas J. Mapping tree species fractions in temperate mixed forests using Sentinel-2 time series and synthetically mixed training data Remote Sens. Environ. 2025 323 114740 10.1016/j.rse.2025.114740
Somers B. Asner G.P. Tits L. Coppin P. Endmember variability in spectral mixture analysis: A review Remote Sens. Environ. 2011 115 1603 1616 10.1016/j.rse.2011.03.003
Zhu Z. Zhang J. Yang Z. Aljaddani A.H. Cohen W.B. Qiu S. Zhou C. Continuous monitoring of land disturbance based on Landsat time series Remote Sens. Environ. 2020 238 111116 10.1016/j.rse.2019.03.009
Herold M. Mayaux P. Woodcock C.E. Baccini A. Schmullius C. Some challenges in global land cover mapping: An assessment of agreement and accuracy in existing 1 km datasets Remote Sens. Environ. 2008 112 2538 2556 10.1016/j.rse.2007.11.013
Potapov P. Hansen M.C. Pickens A. Hernandez-Serna A. Tyukavina A. Turubanova S. Zalles V. Li X. Khan A. Stolle F. et al. The global 2000–2020 land cover and land use change dataset derived from the Landsat archive: The GLC-SHARE dataset Front. Remote Sens. 2022 3 856903 10.3389/frsen.2022.856903
Gal Y. Ghahramani Z. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning Proceedings of the 33rd International Conference on Machine Learning (ICML) New York, NY, USA 19–24 June 2016 1050 1059
Meyer H. Reudenbach C. Wollauer S. Nauss T. Importance of spatial predictor variable selection in machine learning applications—Moving from data reproduction to spatial prediction Ecol. Model. 2018 411 108815 10.1016/j.ecolmodel.2019.108815
Wadoux A.M.J.-C. Heuvelink G.B.M. De Bruin S. Brus D.J. Spatial cross-validation is not the right way to evaluate map accuracy Ecol. Model. 2021 457 109692 10.1016/j.ecolmodel.2021.109692
Réjou-Méchain M. Barbier N. Couteron P. Ploton P. Vincent G. Herold M. Mermoz S. Saatchi S. Chave J. de Boissieu F. et al. Upscaling forest biomass from field to satellite measurements: Sources of errors and ways to reduce them Surv. Geophys. 2019 40 881 911 10.1007/s10712-019-09532-0
Higginbottom T.P. Symeonakis E. Assessing land degradation and desertification using vegetation index data: Current frameworks and future directions Remote Sens. 2014 6 9552 9575 10.3390/rs6109552
Grantham H.S. Duncan A. Evans T.D. Jones K.R. Beyer H.L. Schuster R. Walston J. Ray J.C. Robinson J.G. Callow M. et al. Anthropogenic modification of forests means only 40% of remaining forests have high ecosystem integrity Nat. Commun. 2020 11 5978 10.1038/s41467-020-19493-3
Wan L. Ciais P. de Truchis A. Sean E. Fischer F.J. Purnell D. Ploton P. Satellite-based mapping of annual canopy height and aboveground biomass in African dense forests Front. Remote Sens. 2025 6 1724950 10.3389/frsen.2025.1724950
Duncanson L. Kellner J.R. Armston J. Dubayah R. Minor D.M. Hancock S. Healey S.P. Patterson P.L. Saarela S. Marselis S. et al. Aboveground biomass density models for NASA’s Global Ecosystem Dynamics Investigation (GEDI) lidar mission Remote Sens. Environ. 2022 270 112845 10.1016/j.rse.2021.112845
