Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (randomForest)

Lawrence, Rick L.; Wood, Shana D.; Sheley, Roger L.

doi:10.1016/j.rse.2005.10.014

Cited by 605 publications

(355 citation statements)

References 31 publications

Supporting

Mentioning

335

Contrasting

Unclassified

Order By: Relevance

“…Random forests' machine-learning algorithms have proved their ability to handle very complex and highdimensional remote-sensing datasets (Cutler et al 2007;Lawrence et al 2006;Stumpf and Kerle 2011;Watts et al 2009). Most of the previously cited studies used the initial implementation of the random forest algorithm (Breiman 2001) in the R software.…”

Section: Selection Of Variables By the Use Of Random Forestmentioning

confidence: 99%

Classification of riparian forest species and health condition using multi-temporal and hyperspatial imagery from unmanned aerial system

Michez

Piégay

Lisein

et al. 2016

Environ Monit Assess

204

179

View full text Add to dashboard Cite

Riparian forests are critically endangered many anthropogenic pressures and natural hazards. The importance of riparian zones has been acknowledged by European Directives, involving multi-scale monitoring. The use of this very-high-resolution and hyperspatial imagery in a multi-temporal approach is an emerging topic. The trend is reinforced by the recent and rapid growth of the use of the unmanned aerial system (UAS), which has prompted the development of innovative methodology. Our study proposes a methodological framework to explore how a set of multi-temporal images acquired during a vegetative period can differentiate some of the deciduous riparian forest species and their health conditions. More specifically, the developed approach intends to identify, through a process of variable selection, which variables derived from UAS imagery and which scale of image analysis are the most relevant to our objectives.The methodological framework is applied to two study sites to describe the riparian forest through two fundamental characteristics: the species composition and the health condition. These characteristics were selected not only because of their use as proxies for the riparian zone ecological integrity but also because of their use for river management.The comparison of various scales of image analysis identified the smallest object-based image analysis (OBIA) objects (ca. 1 m 2 ) as the most relevant scale. Variables derived from spectral information (bands ratios) were identified as the most appropriate, followed by variables related to the vertical structure of the forest. Classification results show good overall accuracies for the species composition of the riparian forest (five classes, 79.5 and 84.1 % for site 1 and site 2). The classification scenario regarding the health condition of the black alders of the site 1 performed the best (90.6 %).The quality of the classification models developed with a UAS-based, cost-effective, and semi-automatic approach competes successfully with those developed using more expensive imagery, such as multi-spectral and hyperspectral airborne imagery. The high overall accuracy results obtained by the classification of the diseased alders open the door to applications dedicated to monitoring of the health conditions of riparian forest. Our methodological framework will allow UAS users to manage large imagery metric datasets derived from those dense time series.

show abstract

Section: Selection Of Variables By the Use Of Random Forestmentioning

confidence: 99%

Classification of riparian forest species and health condition using multi-temporal and hyperspatial imagery from unmanned aerial system

Michez

Piégay

Lisein

et al. 2016

Environ Monit Assess

204

179

View full text Add to dashboard Cite

show abstract

“…It has proven effective for classifying highly dimensional data (i.e., many input variables) from a variety of sensors [23][24][25][26], and has been shown to outperform conventional parametric classifiers, including Maximum Likelihood [23,[27][28][29]. This is particularly relevant with respect to the classification of SAR data, since backscatter values are not typically normally distributed when represented in linear power format [11].…”

Section: The Random Forest Classifiermentioning

confidence: 99%

Assessing the Potential to Operationalize Shoreline Sensitivity Mapping: Classifying Multiple Wide Fine Quadrature Polarized RADARSAT-2 and Landsat 5 Scenes with a Single Random Forest Model

et al. 2015

View full text Add to dashboard Cite

Abstract:The Random Forest algorithm was used to classify 86 Wide Fine Quadrature Polarized RADARSAT-2 scenes, five Landsat 5 scenes, and a Digital Elevation Model covering an area approximately 81,000 km 2 in size, and representing the entirety of Dease Strait, Coronation Gulf and Bathurst Inlet, Nunavut. The focus of this research was to assess the potential to operationalize shoreline sensitivity mapping to inform oil spill response and contingency planning. The impact of varying the training sample size and reducing model data load were evaluated. Results showed that acceptable accuracies could be achieved with relatively few training samples, but that higher accuracies and greater probabilities of correct class assignment were observed with larger sample sizes. Additionally, the number of inputs to the model could be greatly reduced without impacting overall performance. Optimized models reached independent accuracies of 91% for seven land cover types, and classification probabilities between 0.77 and 0.98 (values for latter represent per-class averages generated from independent validation sites). Mixed OPEN ACCESSRemote Sens. 2015, 7 13529 results were observed when assessing the potential for remote predictive mapping by simulating transferability of the model to scenes without training data.

show abstract

“…We used NDVI and MSAVI 2 separately as predictors for vegetation cover in our random-forest regression analyses. The random-forest approach has been successfully used to analyze RS data (Lawrence et al 2006;Rodriguez-Galiano et al 2012;Feilhauer et al 2014). From (2003), we tested other values, but the default parameterization produced the best results.…”

Section: Multispectral Data and Analysismentioning

confidence: 99%

Remote Sensing for Grassland Management in the Arid Southwest

Marsett¹,

Heilman

et al. 2006

Rangeland Ecology & Management

215

View full text Add to dashboard Cite

Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (randomForest)

Cited by 605 publications

References 31 publications

Classification of riparian forest species and health condition using multi-temporal and hyperspatial imagery from unmanned aerial system

Classification of riparian forest species and health condition using multi-temporal and hyperspatial imagery from unmanned aerial system

Assessing the Potential to Operationalize Shoreline Sensitivity Mapping: Classifying Multiple Wide Fine Quadrature Polarized RADARSAT-2 and Landsat 5 Scenes with a Single Random Forest Model

Remote Sensing for Grassland Management in the Arid Southwest

Contact Info

Product

Resources

About