Predicting Vascular Plant Richness in a Heterogeneous Wetland Using Spectral and Textural Features and a Random Forest Algorithm

Cabezas, Julián; Galleguillos, Mauricio; Perez‐Quezada, Jorge F.

doi:10.1109/lgrs.2016.2532743

Cited by 19 publications

(16 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the textural metrics, Laurin et al [24] in the Gola Rainforest National Park, obtained good predictions (R 2 = 0.84) using these type of metrics to estimate diversity based on hyperspectral data. Species richness predictions, using textural predictors, were reported by Cabezas et al [19] in an anthropogenic peatland divided into two zones with different types of management: productive (with Sphagnum extraction) and conservation (corresponding to peatland P2 in this study). In summary, spatial resolution of the scenes seems to be important for the analysis, especially in peatlands.…”

Section: Satellite Sensor Comparisonmentioning

confidence: 54%

“…This can turn into a major problem in the validation process, when the bootstrap method is implemented and sub-samples are chosen, reducing the input observations used in the model. In spite of these limitations, studies using RF to predict species richness obtained accurate predictions with similar field samples as the one used in this study [19,24], and demonstrated to be an important tool for modeling α-diversity. This study shows that both GLM and RF are valid methods for predicting α-diversity with similar performance; nonetheless, according to Latifi et al [21] and Lopatin et al [33], GLM proved to be a more parsimonious approach, since it was easier to interpret, required less computation time, and fewer predictors.…”

Section: Model Comparisonsmentioning

confidence: 90%

“…Finally, three sets of predictors were obtained, with a total of 148, 360, and 724 predictors for the OLI, ASTER, and MSI models, respectively. Reflectance values at the plot locations were obtained by bilinear interpolation [19]. Tasseled Cap Transformation TCT = Greenness, Brightness, and Wetness [40] x x…”

Section: Remote Sensing Predictorsmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Vascular Plant Diversity in Anthropogenic Peatlands: Comparison of Modeling Methods with Free Satellite Data

et al. 2017

Self Cite

View full text Add to dashboard Cite

Peatlands are ecosystems of great relevance, because they have an important number of ecological functions that provide many services to mankind. However, studies focusing on plant diversity, addressed from the remote sensing perspective, are still scarce in these environments. In the present study, predictions of vascular plant richness and diversity were performed in three anthropogenic peatlands on Chiloé Island, Chile, using free satellite data from the sensors OLI, ASTER, and MSI. Also, we compared the suitability of these sensors using two modeling methods: random forest (RF) and the generalized linear model (GLM). As predictors for the empirical models, we used the spectral bands, vegetation indices and textural metrics. Variable importance was estimated using recursive feature elimination (RFE). Fourteen out of the 17 predictors chosen by RFE were textural metrics, demonstrating the importance of the spatial context to predict species richness and diversity. Non-significant differences were found between the algorithms; however, the GLM models often showed slightly better results than the RF. Predictions obtained by the different satellite sensors did not show significant differences; nevertheless, the best models were obtained with ASTER (richness: R 2 = 0.62 and %RMSE = 17.2, diversity: R 2 = 0.71 and %RMSE = 20.2, obtained with RF and GLM respectively), followed by OLI and MSI. Diversity obtained higher accuracies than richness; nonetheless, accurate predictions were achieved for both, demonstrating the potential of free satellite data for the prediction of relevant community characteristics in anthropogenic peatland ecosystems.

show abstract

Section: Satellite Sensor Comparisonmentioning

confidence: 54%

Section: Model Comparisonsmentioning

confidence: 90%

See 1 more Smart Citation

Predicting Vascular Plant Diversity in Anthropogenic Peatlands: Comparison of Modeling Methods with Free Satellite Data

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Specifically, variation and heterogeneity in spectral reflectance increased with increasing Shannon diversity among plots. Increasing spectral heterogeneity has been previously used as a proxy for diversity in studies that have mapped peatland ecological diversity using remote sensing [91][92][93]. This type of study is based on the species-area relationship in which species richness increases with scale across a heterogeneous landscape [94].…”

Section: Remote Sensing Of Boreal Peatland Species Diversitymentioning

confidence: 99%

Characterizing Boreal Peatland Plant Composition and Species Diversity with Hyperspectral Remote Sensing

et al. 2019

View full text Add to dashboard Cite

Peatlands, which account for approximately 15% of land surface across the arctic and boreal regions of the globe, are experiencing a range of ecological impacts as a result of climate change. Factors that include altered hydrology resulting from drought and permafrost thaw, rising temperatures, and elevated levels of atmospheric carbon dioxide have been shown to cause plant community compositional changes. Shifts in plant composition affect the productivity, species diversity, and carbon cycling of peatlands. We used hyperspectral remote sensing to characterize the response of boreal peatland plant composition and species diversity to warming, hydrologic change, and elevated CO2. Hyperspectral remote sensing techniques offer the ability to complete landscape-scale analyses of ecological responses to climate disturbance when paired with plot-level measurements that link ecosystem biophysical properties with spectral reflectance signatures. Working within two large ecosystem manipulation experiments, we examined climate controls on composition and diversity in two types of common boreal peatlands: a nutrient rich fen located at the Alaska Peatland Experiment (APEX) in central Alaska, and an ombrotrophic bog located in northern Minnesota at the Spruce and Peatland Responses Under Changing Environments (SPRUCE) experiment. We found a strong effect of plant functional cover on spectral reflectance characteristics. We also found a positive relationship between species diversity and spectral variation at the APEX field site, which is consistent with other recently published findings. Based on the results of our field study, we performed a supervised land cover classification analysis on an aerial hyperspectral dataset to map peatland plant functional types (PFTs) across an area encompassing a range of different plant communities. Our results underscore recent advances in the application of remote sensing measurements to ecological research, particularly in far northern ecosystems.

show abstract

“…The Grey Level Co-occurrence Matrix (GLCM) is a commonly used method of analyzing texture and has proven an effective approach when applied to vegetation classification [14,15]. Based on GLCM's popularity in vegetation classification, some researchers [16,17] have attempted to classify wetland vegetation using texture obtained from the approach. Berberoglu et al [18] studied the land-use/cover change dynamics of a Mediterranean coastal wetland based on extraction of vegetation from Landsat TM images using GLCM.…”

Section: Introductionmentioning

confidence: 99%

Assessing Texture Features to Classify Coastal Wetland Vegetation from High Spatial Resolution Imagery Using Completed Local Binary Patterns (CLBP)

et al. 2018

View full text Add to dashboard Cite

Abstract:Coastal wetland vegetation is a vital component that plays an important role in environmental protection and the maintenance of the ecological balance. As such, the efficient classification of coastal wetland vegetation types is key to the preservation of wetlands. Based on its detailed spatial information, high spatial resolution imagery constitutes an important tool for extracting suitable texture features for improving the accuracy of classification. In this paper, a texture feature, Completed Local Binary Patterns (CLBP), which is highly suitable for face recognition, is presented and applied to vegetation classification using high spatial resolution Pléiades satellite imagery in the central zone of Yancheng National Natural Reservation (YNNR) in Jiangsu, China. To demonstrate the potential of CLBP texture features, Grey Level Co-occurrence Matrix (GLCM) texture features were used to compare the classification. Using spectral data alone and spectral data combined with texture features, the image was classified using a Support Vector Machine (SVM) based on vegetation types. The results show that CLBP and GLCM texture features yielded an accuracy 6.50% higher than that gained when using only spectral information for vegetation classification. However, CLBP showed greater improvement in terms of classification accuracy than GLCM for Spartina alterniflora. Furthermore, for the CLBP features, CLBP_magnitude (CLBP_m) was more effective than CLBP_sign (CLBP_s), CLBP_center (CLBP_c), and CLBP_s/m or CLBP_s/m/c. These findings suggest that the CLBP approach offers potential for vegetation classification in high spatial resolution images.

show abstract

Predicting Vascular Plant Richness in a Heterogeneous Wetland Using Spectral and Textural Features and a Random Forest Algorithm

Cited by 19 publications

References 31 publications

Predicting Vascular Plant Diversity in Anthropogenic Peatlands: Comparison of Modeling Methods with Free Satellite Data

Predicting Vascular Plant Diversity in Anthropogenic Peatlands: Comparison of Modeling Methods with Free Satellite Data

Characterizing Boreal Peatland Plant Composition and Species Diversity with Hyperspectral Remote Sensing

Assessing Texture Features to Classify Coastal Wetland Vegetation from High Spatial Resolution Imagery Using Completed Local Binary Patterns (CLBP)

Contact Info

Product

Resources

About