Understanding the role of training sample size in the uncertainty of high-resolution LULC mapping using random forest

Abriha D, Srivastava PK, Szabó S (2023) Smaller is better? Unduly nice accuracy assessments in roof detection using remote sensing data with machine learning and k-fold cross-validation. Heliyon 9:1–17. https://doi.org/10.1016/j.heliyon.2023.e14045 Anderson JR, Hardy EE, Roach JT, Witmer RE (1976) A land use and land cover classification system for use with remote sensor data. US Geol Surv Prof Paper 964:28 Aune-Lundberg L, Strand G-H (2014) Environ Model Softw 61:87–97. https://doi.org/10.1016/j.envsoft.2014.07.001. Comparison of variance estimation methods for use with two-dimensional systematic sampling of land use/land cover data Belgiu M, Drăgu L (2016) Random forest in remote sensing: a review of applications and future directions. ISPRS J Photogrammetry Remote Sens 114:24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011 Bobalova H, Benová A, Kožuch M (2021) Hierarchical object-based mapping of Urban Land Cover using Sentinel-2 data: a case study of six cities in Central Europe. PFG–Journal of Photogrammetry Remote Sensing and Geoinformation Science 89:15–31. https://doi.org/10.1007/s41064-020-00135-8 Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324 Bui DH, Mucsi L (2022) Predicting the future land-use change and evaluating the change in landscape pattern in Binh Duong province, Vietnam. Hung Geographical Bull 71:349–364. https://doi.org/10.15201/hungeobull.71.4.3 Burai P, Deák B, Valkó O, Tomor T (2015) Classification of herbaceous vegetation using airborne hyperspectral imagery. Remote Sens 7:2046–2066. https://doi.org/10.3390/rs70202046 Chatziantoniou A, Petropoulos GP, Psomiadis E (2017) Co-Orbital Sentinel 1 and 2 for LULC mapping with emphasis on wetlands in a mediterranean setting based on machine learning. Remote Sens 9:1259. https://doi.org/10.3390/rs9121259 Cheng KS, Ling JY, Lin TW et al (2021) Quantifying uncertainty in Land-Use/Land-Cover classification accuracy: a Stochastic Simulation Approach. Front Environ Sci 9:1–18. https://doi.org/10.3389/fenvs.2021.628214 Congalton RG (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37:35–46. https://doi.org/10.1016/0034-4257(91)90048-B Cutler DR, Edwards TC Jr, Beard KH et al (2007) Random forests for classification in ecology. Ecology 88:2783–2792. https://doi.org/10.1890/07-0539.1 Ebrahimy H, Mirbagheri B, Matkan AA, Azadbakht M (2021) Per-pixel land cover accuracy prediction: a random forest-based method with limited reference sample data. ISPRS J Photogrammetry Remote Sens 172:17–27. https://doi.org/10.1016/j.isprsjprs.2020.11.024 ESRI (2022) ArcGIS Desktop Software (Version 10.4) Everitt JH, Yang C, Fletcher R, Deloach CJ (2008) Comparison of QuickBird and SPOT 5 satellite imagery for mapping giant reed. J Aquat Plant Manag 46:77–82 Foody GM, Mathur A, Sanchez-Hernandez C, Boyd DS (2006) Training set size requirements for the classification of a specific class. Remote Sens Environ 104:1–14. https://doi.org/10.1016/j.rse.2006.03.004 Gascon F, Ramoino F (2017) Sentinel-2 data exploitation with ESA’s Sentinel-2 Toolbox. In: EGU General Assembly Conference Abstracts. p 19548 Gudmann A, Mucsi L (2022) Pixel and object-based Land Cover Mapping and Change Detection from 1986 to 2020 for Hungary using Histogram-based gradient boosting classification Tree Classifier. Geogr Pannonica 26:165–175. https://doi.org/10.5937/gp26-37720 Heydari SS, Mountrakis G (2018) Effect of classifier selection, reference sample size, reference class distribution and scene heterogeneity in per-pixel classification accuracy using 26 landsat sites. Remote Sens Environ 204:648–658. https://doi.org/10.1016/j.rse.2017.09.035 Higgs C, van Niekerk A (2022) Impact of Training Set Configurations for differentiating Plantation Forest Genera with Sentinel-2 Imagery and Machine Learning. Remote Sens 14:3992. https://doi.org/10.3390/rs14163992 Huang C, Asner GP (2009) Applications of remote sensing to alien invasive plant studies. Sensors 9:4869–4889. https://doi.org/10.3390/s90604869 Jensen JR, Cowen DC (1999) Remote sensing of urban/suburban infrastructure and socio-economic attributes. Photogramm Eng Remote Sensing 65:611–622 Jia Y, Ge Y, Ling F et al (2018) Urban land use mapping by combining remote sensing imagery and mobile phone positioning data. Remote Sens 10:446. https://doi.org/10.3390/rs10030446 Jonckheere AR (1954) A distribution-free k-sample test against ordered alternatives. Biometrika 41:133–145. https://doi.org/10.2307/2333011 Khatami R, Mountrakis G, Stehman SV (2016) A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: General guidelines for practitioners and future research. Remote Sens Environ 177:89–100. https://doi.org/10.1016/j.rse.2016.02.028 Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet Classification with Deep Convolutional Neural Networks. In: Advances in Neural Information Processing Systems 25. pp 1–9 Kruskal WH, Wallis WA (1952) Use of ranks in one-criterion variance analysis. J Am Stat Assoc 47:583–621. https://doi.org/10.1080/01621459.1952.10483441 Kuhn M, Wing S, Weston A, Williams C et al (2023) Caret: classification and regression training. R Package Version 6:0–94. https://github.com/topepo/caret/ Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33:159–174. https://doi.org/10.2307/2529310 Liaw A, Wiener M (2002) Classification and regression by randomForest. R news 2:18–22 Luo X, Tong X, Hu Z, Wu G (2020) Improving urban land cover/use mapping by integrating a hybrid convolutional neural network and an automatic training sample expanding strategy. Remote Sens 12:2292. https://doi.org/10.3390/rs12142292 Ma L, Li M, Ma X et al (2017) A review of supervised object-based land-cover image classification. ISPRS J Photogrammetry Remote Sens 130:277–293. https://doi.org/10.1016/j.isprsjprs.2017.06.001 Matcı DK, Avdan U (2022) Data-driven automatic labelling of land cover classes from remotely sensed images. Earth Sci Inform 15:1059–1071. https://doi.org/10.1007/s12145-022-00788-6 Maxwell AE, Strager MP, Warner TA et al (2019) Large-Area, high spatial Resolution Land Cover Mapping using Random forests, GEOBIA, and NAIP Orthophotography: findings and recommendations. Remote Sens 11:1409. https://doi.org/10.3390/rs11121409 Mazeka B, Phinzi K, Sutherland C (2021) Monitoring changing Land Use-Land Cover Change to reflect the impact of Urbanisation on Environmental Assets in Durban, South Africa. Sustainable Urban futures in Africa. Routledge, pp 132–158. https://doi.org/10.4324/9781003181484-7 Millard K, Richardson M (2015) On the importance of training data sample selection in random forest image classification: a case study in peatland ecosystem mapping. Remote Sens 7:8489–8515. https://doi.org/10.3390/rs70708489 Myburgh G, Van Niekerk A (2013) Effect of feature dimensionality on object-based land cover classification: a comparison of three classifiers. South Afr J Geomatics 2:13–27 Nagel P, Yuan F (2016) High-resolution land cover and impervious surface classifications in the twin cities metropolitan area with NAIP imagery. Photogramm Eng Remote Sensing 82:63–71. https://doi.org/10.14358/PERS.83.1.63 Padmanaban R, Bhowmik AK, Cabral P (2019) Satellite image fusion to detect changing surface permeability and emerging urban heat islands in a fast-growing city. PLoS ONE 14:1–20. https://doi.org/10.1371/journal.pone.0208949 Pawłuszek K, Marczak S, Borkowski A, Tarolli P (2019) Multi-aspect analysis of object-oriented landslide detection based on an extended set of LiDAR-derived terrain features. ISPRS Int J Geoinf 8:321. https://doi.org/10.3390/ijgi8080321 Podsiadlo I, Paris C, Bruzzone L (2021) An approach based on low resolution land-cover-maps and domain adaptation to define representative training sets at large scale. In: International Geoscience and Remote Sensing Symposium (IGARSS). Institute of Electrical and Electronics Engineers Inc., pp 313–316. https://doi.org/10.1109/IGARSS47720.2021.9553498 Qian Y, Zhou W, Yan J et al (2015) Comparing machine learning classifiers for object-based land cover classification using very high resolution imagery. Remote Sens 7:153–168. https://doi.org/10.3390/rs70100153 R Core Team (2021) R: a language and environment for statistical computing. R Foundation for statistical computing, Vienna Ramezan CA, Warner TA, Maxwell AE, Price BS (2021) Effects of training set size on supervised machine-learning land-cover classification of large-area high-resolution remotely sensed data. Remote Sens 13:368. https://doi.org/10.3390/rs13030368 Shang M, Wang S-X, Zhou Y, Du C (2018) Effects of Training samples and classifiers on classification of Landsat-8 imagery. J Indian Soc Remote Sens 46:1333–1340. https://doi.org/10.1007/s12524-018-0777-z Shao Y, Cooner AJ, Walsh SJ (2021) Assessing deep convolutional neural networks and assisted machine perception for urban mapping. Remote Sens 13:1523. https://doi.org/10.3390/rs13081523 Statistics South Africa (2011) “Greater Kokstad Municipality”. https://www.statssa.gov.za/?page_id=993&id=greater-kokstad-municipality. Accessed on 22 August 2023 Talukdar S, Singha P, Mahato S et al (2020) Land-use land-cover classification by machine learning classifiers for satellite observations—a review. Remote Sens 12:1135. https://doi.org/10.3390/rs12071135 Terpstra TJ (1952) The asymptotic normality and consistency of Kendall’s test against trend, when ties are present in one ranking. Indagationes Math 14:327–333 Thanh NP, Kappas M (2017) Comparison of Random Forest, k-Nearest neighbor, and support Vector Machine Classifiers for Land Cover classification using Sentinel-2 imagery. Sensors 18:18. https://doi.org/10.3390/s18010018 Therneau T, Atkinson B, Ripley B (2022) rpart: Recursive partitioning and regression trees. R package version 4.1.19. https://cran.r-project.org/package=rpart Topaloğlu RH, Sertel E, Musaoğlu N (2016) Int archives photogrammetry remote Sens Spat Inform Sci 41:12–49. https://doi.org/10.5194/isprsarchives-XLI-B8-1055-2016. assessment of classification accuracies of Sentinel-2 and landsat-8 data for land cover/use mapping Ustuner M, Sanli FB, Abdikan S (2016) Balanced vs imbalanced training data: classifying RapidEye data with support vector machines. Int Archives Photogrammetry Remote Sens Spat Inform Sci 41:379–384. https://doi.org/10.5194/isprs-archives-XLI-B7-379-2016 Van Niel TG, McVicar TR, Datt B (2005) On the relationship between training sample size and data dimensionality: Monte Carlo analysis of broadband multi-temporal classification. Remote Sens Environ 98:468–480. https://doi.org/10.1016/j.rse.2005.08.011