Efforts are increasingly being made to classify the world’s wetland resources, an important ecosystem and habitat that is diminishing in abundance. There are multiple remote sensing classification methods, including a suite of nonparametric classifiers such as decision-tree (DT), rule-based (RB), and random forest (RF). High-resolution satellite imagery can provide more specificity to the classified end product, and ancillary data layers such as the Normalized Difference Vegetation Index, and hydrogeomorphic layers such as distance-to-a-stream can be coupled to improve overall accuracy (OA) in wetland studies. In this paper, we contrast three nonparametric machine-learning algorithms (DT, RB, and RF) using a large field-based dataset (n = 228) from the Selenga River Delta of Lake Baikal, Russia. We also explore the use of ancillary data layers selected to improve OA, with a goal of providing end users with a recommended classifier to use and the most parsimonious suite of input parameters for classifying wetland-dominated landscapes. Though all classifiers appeared suitable, the RF classification outperformed both the DT and RB methods, achieving OA >81%. Including a texture metric (homogeneity) substantially improved the classification OA. However, including vegetation/soil/water metrics (based on WorldView-2 band combinations), hydrogeomorphic data layers, and elevation data layers to increase the descriptive content of the input parameters surprisingly did not markedly improve the OA. We conclude that, in most cases, RF should be the classifier of choice. The potential exception to this recommendation is under the circumstance where the end user requires narrative rules to best manage his or her resource. Though not useful in this study, continuously increasing satellite imagery resolution and band availability suggests the inclusion of ancillary contextual data layers such as soil metrics or elevation data, the granularity of which may define its utility in subsequent wetland classifications.

Although remote sensing technology has long been used in wetland inventory and monitoring, the accuracy and detail level of wetland maps derived with moderate resolution imagery and traditional techniques have been limited and often unsatisfactory. We explored and evaluated the utility of a newly launched high-resolution, eight-band satellite system (Worldview-2; WV2) for identifying and classifying freshwater deltaic wetland vegetation and aquatic habitats in the Selenga River Delta of Lake Baikal, Russia, using a hybrid approach and a novel application of Indicator Species Analysis (ISA). We achieved an overall classification accuracy of 86.5% (Kappa coefficient: 0.85) for 22 classes of aquatic and wetland habitats and found that additional metrics, such as the Normalized Difference Vegetation Index and image texture, were valuable for improving the overall classification accuracy and particularly for discriminating among certain habitat classes. Our analysis demonstrated that including WV2’s four spectral bands from parts of the spectrum less commonly used in remote sensing analyses, along with the more traditional bandwidths, contributed to the increase in the overall classification accuracy by ~4% overall, but with considerable increases in our ability to discriminate certain communities. The coastal band improved differentiating open water and aquatic (i.e., vegetated) habitats, and the yellow, red-edge, and near-infrared 2 bands improved discrimination among different vegetated aquatic and terrestrial habitats. The use of ISA provided statistical rigor in developing associations between spectral classes and field-based data. Our analyses demonstrated the utility of a hybrid approach and the benefit of additional bands and metrics in providing the first spatially explicit mapping of a large and heterogeneous wetland system.

Wetland ecosystems straddle both terrestrial and aquatic habitats, performing many ecological functions directly and indirectly benefitting humans. However, global wetland losses are substantial. Satellite remote sensing and classification informs wise wetland management and monitoring. Both pixel- and object-based classification approaches using parametric and non-parametric algorithms may be effectively used in describing wetland structure and habitat, but which approach should one select? We conducted both pixel- and object-based image analyses (OBIA) using parametric (Iterative Self-Organizing Data Analysis Technique, ISODATA, and maximum likelihood, ML) and non-parametric (random forest, RF) approaches in the Barguzin Valley, a large wetland (~500 km²) in the Lake Baikal, Russia, drainage basin. Four Quickbird multispectral bands plus various spatial and spectral metrics (e.g., texture, Non-Differentiated Vegetation Index, slope, aspect, etc.) were analyzed using field-based regions of interest sampled to characterize an initial 18 ISODATA-based classes. Parsimoniously using a three-layer stack (Quickbird band 3, water ratio index (WRI), and mean texture) in the analyses resulted in the highest accuracy, 87.9% with pixel-based RF, followed by OBIA RF (segmentation scale 5, 84.6% overall accuracy), followed by pixel-based ML (83.9% overall accuracy). Increasing the predictors from three to five by adding Quickbird bands 2 and 4 decreased the pixel-based overall accuracy while increasing the OBIA RF accuracy to 90.4%. However, McNemar’s chi-square test confirmed no statistically significant difference in overall accuracy among the classifiers (pixel-based ML, RF, or object-based RF) for either the three- or five-layer analyses. Although potentially useful in some circumstances, the OBIA approach requires substantial resources and user input (such as segmentation scale selection—which was found to substantially affect overall accuracy). Hence, we conclude that pixel-based RF approaches are likely satisfactory for classifying wetland-dominated landscapes.

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’s and producer’s 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.