{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T08:27:57Z","timestamp":1745656077011,"version":"3.37.3"},"reference-count":62,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2019,3,6]],"date-time":"2019-03-06T00:00:00Z","timestamp":1551830400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"Classifying and mapping natural systems such as wetlands using remote sensing frequently relies on data derived from regions of interest (ROIs), often acquired during field campaigns. ROIs tend to be heterogeneous in complex systems with a variety of land cover classes. However, traditional supervised image classification is predicated on pure single-class observations to train a classifier. This ultimately encourages end-users to create single-class ROIs, nudging ROIs away from field-based points or gerrymandering the ROI, which may produce ROIs unrepresentative of the landscape and potentially insert error into the classification. In this study, we explored WorldView-2 images and 228 field-based data points to define ROIs of varying heterogeneity levels in terms of class membership to classify and map 22 discrete classes in a large and complex wetland system. The goal was to include rather than avoid ROI heterogeneity and assess its impact on classification accuracy. Parametric and nonparametric classifiers were tested with ROI heterogeneity that varied from 7% to 100%. Heterogeneity was governed by ROI area, which we increased from the field-sampling frame of ~100 m2 nearly 19-fold to ~2124 m2. In general, overall accuracy (OA) tended downwards with increasing heterogeneity but stayed relatively high until extreme heterogeneity levels were reached. Moreover, the differences in OA were not statistically significant across several small-to-large heterogeneity levels. Per-class user\u2019s and producer\u2019s accuracies behaved similarly. Our findings suggest that ROI heterogeneity did not harm classification accuracy unless heterogeneity became extreme, and thus there are substantial practical advantages to accommodating heterogeneous ROIs in image classification. Rather than attempting to avoid ROI heterogeneity by gerrymandering, classification in wetland environments, as well as analyses of other complex environments, should embrace ROI heterogeneity.<\/jats:p>","DOI":"10.3390\/rs11050551","type":"journal-article","created":{"date-parts":[[2019,3,7]],"date-time":"2019-03-07T15:52:22Z","timestamp":1551973942000},"page":"551","source":"Crossref","is-referenced-by-count":13,"title":["The Influence of Region of Interest Heterogeneity on Classification Accuracy in Wetland Systems"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0671-9131","authenticated-orcid":false,"given":"Tedros M.","family":"Berhane","sequence":"first","affiliation":[{"name":"Pegasus Technical Services, Inc., c\/o U.S. Environmental Protection Agency, Cincinnati, OH 45219, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6207-8223","authenticated-orcid":false,"given":"Hugo","family":"Costa","sequence":"additional","affiliation":[{"name":"Dire\u00e7\u00e3o-Geral do Territ\u00f3rio, 1099-052 Lisbon, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0066-8919","authenticated-orcid":false,"given":"Charles R.","family":"Lane","sequence":"additional","affiliation":[{"name":"Office of Research and Development, U.S. Environmental Protection Agency, Cincinnati, OH 45268, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8633-7154","authenticated-orcid":false,"given":"Oleg A.","family":"Anenkhonov","sequence":"additional","affiliation":[{"name":"Laboratory of Floristics and Geobotany, Institute of General and Experimental Biology SB RAS, Ulan-Ude 670047, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3809-7453","authenticated-orcid":false,"given":"Victor V.","family":"Chepinoga","sequence":"additional","affiliation":[{"name":"Laboratory of Physical Geography and Biogeography, V.B. Sochava Institute of Geography SB RAS, Irkutsk 664033, Russia"},{"name":"Department of Botany, Irkutsk State University, Irkutsk 664003, Russia"}]},{"given":"Bradley C.","family":"Autrey","sequence":"additional","affiliation":[{"name":"Office of Research and Development, U.S. Environmental Protection Agency, Cincinnati, OH 45268, USA"}]}],"member":"1968","published-online":{"date-parts":[[2019,3,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"5811","DOI":"10.1080\/01431161.2015.1109727","article-title":"Object-based image analysis of optical and radar variables for wetland evaluation","volume":"36","author":"Robertson","year":"2015","journal-title":"Int. J. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wu, Q. (2018). GIS and remote sensing applications in wetland mapping and monitoring. Comprehensive Geographic Information Systems, Elsevier.","DOI":"10.20944\/preprints201709.0058.v1"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/S0304-3800(03)00139-X","article-title":"A multi-scale segmentation\/object relationship modelling methodology for landscape analysis","volume":"168","author":"Burnett","year":"2003","journal-title":"Ecol. Model."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.rse.2016.12.017","article-title":"Using mixed objects in the training of object-based image classifications","volume":"190","author":"Costa","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4764","DOI":"10.3390\/s120404764","article-title":"Multiple classifier system for remote sensing image classification: A review","volume":"12","author":"Du","year":"2012","journal-title":"Sensors"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/0034-4257(87)90015-0","article-title":"The factor of scale in remote sensing","volume":"21","author":"Woodcock","year":"1987","journal-title":"Remote Sens. Environ."},{"key":"ref_7","first-page":"491","article-title":"Relating the land-cover composition of mixed pixels to artificial neural network classification output","volume":"62","author":"Foody","year":"1996","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1007\/BF01424229","article-title":"Fully fuzzy supervised classification of land cover from remotely sensed imagery with an artificial neural network","volume":"5","author":"Foody","year":"1997","journal-title":"Neural Comput. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.1016\/j.rse.2009.06.013","article-title":"The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas","volume":"113","author":"Dalponte","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1016\/S0167-8655(96)00095-5","article-title":"Incorporating mixed pixels in the training, allocation and testing stages of supervised classifications","volume":"17","author":"Foody","year":"1996","journal-title":"Pattern Recognit. Lett."},{"key":"ref_11","first-page":"391","article-title":"Classification of remotely sensed data by an artificial neural network: Issues related to training data characteristics","volume":"61","author":"Foody","year":"1995","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/S0304-3800(99)00100-3","article-title":"Support vector machines for optimal classification and spectral unmixing","volume":"120","author":"Brown","year":"1999","journal-title":"Ecol. Model."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.rse.2006.04.001","article-title":"The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM","volume":"103","author":"Foody","year":"2006","journal-title":"Remote Sens. Environ."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Foody, G.M., Mathur, A., Sanchez-Hernandez, C., and Boyd, D.S. (2006). Training set size requirements for the classification of a specific class. Remote Sens. Environ., 104.","DOI":"10.1016\/j.rse.2006.03.004"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1023\/A:1020908432489","article-title":"Satellite remote sensing of wetlands","volume":"10","author":"Ozesmi","year":"2002","journal-title":"Wetlands Ecol. Manag."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Berhane, T., Lane, C., Wu, Q., Autrey, B., Anenkhonov, O., Chepinoga, V., and Liu, H. (2018). Decision-tree, rule-based, and random forest classification of high-resolution multispectral imagery for wetland mapping and inventory. Remote Sens., 10.","DOI":"10.3390\/rs10040580"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1007\/s11273-014-9369-z","article-title":"Classification and inventory of freshwater wetlands and aquatic habitats in the Selenga River Delta of Lake Baikal, Russia, using high-resolution satellite imagery","volume":"23","author":"Lane","year":"2015","journal-title":"Wetlands Ecol. Manag."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1007\/s11273-014-9340-z","article-title":"Remote Sensing-derived hydroperiod as a predictor of floodplain vegetation composition","volume":"23","author":"Wolski","year":"2015","journal-title":"Wetlands Ecol. Manag."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"6380","DOI":"10.3390\/rs70506380","article-title":"Object-based image analysis in wetland research: A review","volume":"7","author":"Dronova","year":"2015","journal-title":"Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"7615","DOI":"10.3390\/rs70607615","article-title":"A collection of SAR methodologies for monitoring wetlands","volume":"7","author":"White","year":"2015","journal-title":"Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"916","DOI":"10.3390\/rs10060916","article-title":"TerraSAR-X and wetlands: A review","volume":"10","author":"Wohlfart","year":"2018","journal-title":"Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Guo, M., Li, J., Sheng, C., Xu, J., and Wu, L. (2017). A Review of wetland remote sensing. Remote Sens., 17.","DOI":"10.3390\/s17040777"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Amancio, D.R., Comin, C.H., Casanova, D., Travieso, G., Bruno, O.M., Rodrigues, F.A., and da Fontoura Costa, L. (2014). A systematic comparison of supervised classifiers. PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0094137"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"12187","DOI":"10.3390\/rs61212187","article-title":"Improved wetland classification using eight-band high resolution satellite imagery and a hybrid approach","volume":"6","author":"Lane","year":"2014","journal-title":"Remote Sens."},{"key":"ref_25","first-page":"561","article-title":"Current state of the Selenga River waters in the Russian territory concerning major components and trace elements","volume":"20","author":"Chebykin","year":"2012","journal-title":"Chem. Sustain. Dev."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1134\/S0016702908030051","article-title":"Development of the chemical characteristics of ground water at the delta of the Selenga River","volume":"46","author":"Plyusnin","year":"2008","journal-title":"Geochem. Int."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1023\/B:WARE.0000021575.23690.9d","article-title":"Fractal dimension of the channel network structure of Selenga River Delta","volume":"31","author":"Balkhanov","year":"2004","journal-title":"Water Resour."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1007\/s12665-014-3106-z","article-title":"Spatio-temporal variation of sediment transport in the Selenga River Basin, Mongolia and Russia","volume":"73","author":"Chalov","year":"2015","journal-title":"Environ. Earth Sci."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Lychagin, M., Chalov, S., Kasimov, N., Shinkareva, G., Jarsj\u00f6, J., and Thorslund, J. (2016). Surface water pathways and fluxes of metals under changing environmental conditions and human interventions in the Selenga River system. Environ. Earth Sci., 76.","DOI":"10.1007\/s12665-016-6304-z"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1953","DOI":"10.1016\/j.jhydrol.2014.09.074","article-title":"Evolution of the hydro-climate system in the Lake Baikal basin","volume":"519","author":"Bring","year":"2014","journal-title":"J. Hydrol."},{"key":"ref_31","unstructured":"Tulochonov, A.K., and Plusnin, A.M. (2008). The Selenga River Delta\u2014Natural Biofilter and Indicator of the Condition of Lake Baikal, Publishing House of the Siberian Branch of the Russian Academy of Sciences. (In Russian)."},{"key":"ref_32","first-page":"14","article-title":"Clarification of the actual portion of Lake Baikal\u2019s water in the world freshwater supply","volume":"3","author":"Ivanov","year":"2009","journal-title":"Bull. Utiliz. Prot. Nat. Resour. Russia"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1134\/S1875372812030079","article-title":"Changes in the summertime atmospheric circulation over East Asia and formation of long-lasting low-water periods within the Selenga river basin","volume":"33","author":"Berezhnykh","year":"2012","journal-title":"Geogr. Nat. Resour."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2039","DOI":"10.1007\/s10113-016-0996-1","article-title":"The Selenga River delta: A geochemical barrier protecting Lake Baikal waters","volume":"17","author":"Chalov","year":"2016","journal-title":"Reg. Environ. Chang."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/s11442-008-0319-7","article-title":"Seasonal and spatial distribution of heavy metals in the Selenga River Delta","volume":"18","author":"Khazheeva","year":"2008","journal-title":"J. Geogr. Sci."},{"key":"ref_36","first-page":"58","article-title":"Probable biological and ecological consequences of hydropower plant constructing on the Selenga River and its tributaries in Mongolia","volume":"12","author":"Ubugunov","year":"2015","journal-title":"Bull. Irkutsk State Univ. Ser Biol. Ecol."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Venables, W.N., and Ripley, B.D. (2002). Time series analysis. Modern Applied Statistics with S, Springer.","DOI":"10.1007\/978-0-387-21706-2"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Friedman, J., Hastie, T., and Tibshirani, R. (2010). Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw., 33.","DOI":"10.18637\/jss.v033.i01"},{"key":"ref_39","unstructured":"Czarnecki, W., Jastrzebski, S., Data, M., Sieradzki, I., Bruno-Kaminski, M., Jurek, K., Kowenzowski, P., Pletty, M., Talik, K., and Zgliczynski, M. (2018, July 01). gmum.r: GMUM Machine Learning Group Package. Available online: https:\/\/github.com\/gmum\/gmum.r."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wright, M.N., and Ziegler, A. (2017). ranger: A fast implementation of random forests for high dimensional data in C++ and R. J. Stat. Softw., 77.","DOI":"10.18637\/jss.v077.i01"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/S0304-3800(99)00092-7","article-title":"Artificial neural networks as a tool in ecological modelling, an introduction","volume":"120","author":"Lek","year":"1999","journal-title":"Ecol. Model."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.isprsjprs.2013.11.013","article-title":"Detecting Sirex noctilio grey-attacked and lightning-struck pine trees using airborne hyperspectral data, random forest and support vector machines classifiers","volume":"88","author":"Mutanga","year":"2014","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.1109\/TGRS.2004.827257","article-title":"A relative evaluation of multiclass image classification by support vector machines","volume":"42","author":"Foody","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2440","DOI":"10.3390\/rs3112440","article-title":"An object-based classification of mangroves using a hybrid decision tree\u2014Support vector machine approach","volume":"3","author":"Heumann","year":"2011","journal-title":"Remote Sens."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.isprsjprs.2010.11.001","article-title":"Support vector machines in remote sensing: A review","volume":"66","author":"Mountrakis","year":"2011","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Berhane, T., Lane, C., Wu, Q., Anenkhonov, O., Chepinoga, V., Autrey, B., and Liu, H. (2017). Comparing pixel- and object-based approaches in effectively classifying wetland-dominated landscapes. Remote Sens., 10.","DOI":"10.3390\/rs10010046"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.3390\/rs5073212","article-title":"Influence of multi-source and multi-temporal remotely sensed and ancillary data on the accuracy of random forest classification of wetlands in Northern Minnesota","volume":"5","author":"Corcoran","year":"2013","journal-title":"Remote Sens."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Tian, S., Zhang, X., Tian, J., and Sun, Q. (2016). Random forest classification of wetland landcovers from multi-sensor data in the arid region of Xinjiang, China. Remote Sens., 8.","DOI":"10.3390\/rs8110954"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isprsjprs.2016.01.011","article-title":"Random forest in remote sensing: A review of applications and future directions","volume":"114","author":"Belgiu","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/s10462-010-9192-8","article-title":"Combining bagging, boosting, rotation forest and random subspace methods","volume":"35","author":"Kotsiantis","year":"2010","journal-title":"Artif. Intell. Rev."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1016\/j.rse.2009.03.014","article-title":"Classification accuracy comparison: Hypothesis tests and the use of confidence intervals in evaluations of difference, equivalence and non-inferiority","volume":"113","author":"Foody","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"ref_53","unstructured":"Carroll, L. (1871). Through the Looking-Glass, and What Alice Found There, MacMillan."},{"key":"ref_54","first-page":"1335","article-title":"Derivation and applications of probabilistic measures of class membership from the maximum-likelihood classification","volume":"58","author":"Foody","year":"1992","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_55","unstructured":"Jensen, J.R. (2007). Remote Sensing of the Environment: An Earth Resource Perspective, Prentice-Hall, Inc."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1080\/01431160701294661","article-title":"Multispectral landuse classification using neural networks and support vector machines: One or the other, or both?","volume":"29","author":"Dixon","year":"2008","journal-title":"Int. J. Remote Sens."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"3440","DOI":"10.1080\/01431161.2014.903435","article-title":"Land-use\/cover classification in a heterogeneous coastal landscape using RapidEye imagery: Evaluating the performance of random forest and support vector machines classifiers","volume":"35","author":"Adam","year":"2014","journal-title":"Int. J. Remote Sens."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1080\/01431160412331269698","article-title":"Random forest classifier for remote sensing classification","volume":"26","author":"Pal","year":"2005","journal-title":"Int. J. Remote Sens."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"2885","DOI":"10.1080\/01431160903140803","article-title":"The multispectral separability of Costa Rican rainforest types with support vector machines and Random Forest decision trees","volume":"31","author":"Sesnie","year":"2010","journal-title":"Int. J. Remote Sens."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"2746","DOI":"10.1080\/01431161.2018.1430398","article-title":"Active learning for object-based image classification using predefined training objects","volume":"39","author":"Ma","year":"2018","journal-title":"Int. J. Remote Sens."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1038\/ngeo3041","article-title":"Enhancing protection for vulnerable waters","volume":"10","author":"Creed","year":"2017","journal-title":"Nat. Geosci."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/516031a","article-title":"Climate change: Protect the world\u2019s deltas","volume":"516","author":"Giosan","year":"2014","journal-title":"Nature"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/5\/551\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T09:30:25Z","timestamp":1718530225000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/5\/551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,6]]},"references-count":62,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2019,3]]}},"alternative-id":["rs11050551"],"URL":"https:\/\/doi.org\/10.3390\/rs11050551","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2019,3,6]]}}}