Reliability assessment for remote sensing data: Beyond Cohen's kappa

Kerr, Grégoire; Fischer, Christian; Reulke, Ralf

doi:10.1109/igarss.2015.7326954

Cited by 11 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Os resultados das classificações foram avaliados a partir da matriz de confusão, para quantificar os erros de omissão e comissão de cada classe, e coeficiente kappa (CONGALTON, 1991). Apesar das limitações do kappa terem sido, amplamente, discutidas pela literatura (FOODY, 2020;KERR;FISCHER;REULKE, 2015;PONTIUS JR;MILLONES, 2011), não existe uma concordância entre os pesquisadores sobre possíveis substitutos. Além disso, uma gama de pesquisas ainda utiliza o kappa para quantificar acurácia de mapeamentos temáticos por GEOBIA (MAXWELL et al, 2019;PRADO;RUIZ, 2019;COLARES et al, 2015;BELGIU;STROBL, 2014;FRANCISCO;KIM et al, 2011).…”

Section: Avaliação E Comparação Dos Resultadosunclassified

Análise De Imagens Baseada Em Objetos Geográficos: Comparação De Regras De Classificação Da Cobertura Da Terra

Araujo

Filho

2023

Revista RAEGA

View full text Add to dashboard Cite

Os níveis de automação do processo de classificação das imagens de satélite variam muito entre as diferentes pesquisas. Contudo, inúmeros trabalhos demonstraram que os procedimentos semiautomáticos, como a Análise de Imagens Baseada em Objetos Geográficos (GEOBIA), produzem melhores resultados. Este artigo tem como objetivo comparar os parâmetros de classificação desenvolvidos por quatro analistas distintos, que se basearam na mesma chave de interpretação, aplicados em duas cenas de Marília - SP. Visa avaliar o potencial de transferência das regras de classificação entre as diferentes áreas. Os resultados mostraram que os analistas optaram por diferentes: conjuntos de regras, atributos quantificáveis, limiares e níveis hierárquicos. No entanto, os índices kappa das classificações foram considerados muito bons. E, os conjuntos de regras produzidos por três analistas apresentaram elevada capacidade de transferência entre as cenas analisadas. Essa constatação ressalta a relevância de criar bibliotecas específicas para compartilhar os referidos procedimentos.

show abstract

Section: Avaliação E Comparação Dos Resultadosunclassified

Análise De Imagens Baseada Em Objetos Geográficos: Comparação De Regras De Classificação Da Cobertura Da Terra

Araujo

Filho

2023

Revista RAEGA

View full text Add to dashboard Cite

show abstract

“…(1) ALS data allowed for an automated and more accurate identification of AAL in terms of classification accuracy (>90%) and spatial resolution (<1.0 m) than did other RS platforms [53][54][55][56][57][58][59][60][61][62][63][64]. Potential improvements in process of AAL identification may be achieved using some qualitative variable of ALS data (e.g., intensity) or alternatively through multispectral ALS data [65][66][67][68].…”

Section: Discussionmentioning

confidence: 99%

“…The accuracy of the ALS-based spatial identification of AAL was assessed by an error matrix, including calculations of the producer's, user's, and overall accuracies, as well as the Cohen's kappa [55]. We used five reference areas (1 × 1 km) located in the center, northwest, northeast, southwest, and southeast of the study area (Figure 1).…”

Section: Validation Of the Models And Mapsmentioning

confidence: 99%

Mapping Aboveground Woody Biomass on Abandoned Agricultural Land Based on Airborne Laser Scanning Data

2020

View full text Add to dashboard Cite

Mapping aboveground woody biomass (AGB) on abandoned agricultural land (AAL) is required by relevant stakeholders to monitor the spatial dynamics of farmland afforestation, to assess the carbon sequestration, and to set the appropriate management of natural resources. The objective of this study was, therefore, to present and assess a workflow consisting of (1) the spatial identification of AAL based on a combination of airborne laser scanning (ALS) data, cadastral data, and Land Parcel Identification System data, and (2) the prediction of AGB on AAL using an area-based approach and a nonparametric random forest (RF) model based on a combination of field and ALS data. Part of the second objective was also to evaluate the applicability of (1) the author-developed algorithm for the calculation of ALS metrics and (2) a single comprehensive RF model for the whole area of interest. The study was conducted in the forest management unit Vígľaš (Slovakia, Central Europe) covering a total area of 12,472 ha. Specifically, five reference areas consisting of 11,194 reference points were used to assess the accuracy of the spatial identification of AAL, and seventy-five ground reference plots were used for the development of the ALS-based AGB model and for assessing the accuracy of the AGB map. The overall accuracy of the spatial identification of AAL was found to be 93.00% (Cohen’s kappa = 0.82). The difference between ALS-predicted and ground-observed AGB reached a relative root mean square error (RMSE) at 26.1%, 33.1%, and 21.3% for the whole sample size, plots dominated by shrub species, and plots dominated by tree species, respectively.

show abstract

“…Usually they aim to outperform Kappa and correct some of its associated problems. These include, among others, the F-Score (Pérez-Hoyos et al 2020), Scott's pi statistic (Gwet 2002) and Krippendorff's a-coefficient (Kerr et al 2015). These metrics are not widely used and they provide similar information to Kappa, which is why we do not recommend that they be used in a standard LUC validation exercise.…”

Section: Validation Of Single Land Use Cover Mapsmentioning

confidence: 99%

Validation of Land Use Cover Maps: A Guideline

Olmedo

García-Álvarez

Gallardo

et al. 2022

Land Use Cover Datasets and Validation Tools

View full text Add to dashboard Cite

This chapter offers a general overview of the available tools and strategies for validating Land Use Cover (LUC) data—specifically LUC maps—and Land Use Cover Change Modelling (LUCCM) exercises. We give readers some guidelines according to the type of maps they want to validate: single LUC maps (Sect. 3), time series of LUC maps (Sect. 4) or the results of LUCCM exercises (Sect. 5). Despite the fact that some of the available methods are applicable to all these maps, each type of validation exercise has its own particularities which must be taken into account. Each section of this chapter starts with a brief introduction about the specific type of maps (single, time series or modelling exercises) and the reference data needed to validate them. We also present the validation methods/functions and the corresponding exercises developed in Part III of this book. To this end, we address, in this order, the tools for validating Land Use Cover data based on basic and Multiple-Resolution Cross-Tabulation (see chapter “Basic and Multiple-Resolution Cross Tabulation to Validate Land Use Cover Maps”), metrics based on the Cross-Tabulation matrix (see chapter “Metrics Based on a Cross-Tabulation Matrix to Validate Land Use Cover Maps”), Pontius Jr. methods based on the Cross-Tabulation matrix (see chapter “Pontius Jr. Methods Based on a Cross-Tabulation Matrix to Validate Land Use Cover Maps”), validation practices with soft maps produced by Land Use Cover models (see chapter “Validation of Soft Maps Produced by a Land Use Cover Change Model”), spatial metrics (see chapter “Spatial Metrics to Validate Land Use Cover Maps”), advanced pattern analysis (see chapter “Advanced Pattern Analysis to Validate Land Use Cover Maps”) and geographically weighted methods (see chapter “Geographically Weighted Methods to Validate Land Use Cover Maps”).

show abstract

Reliability assessment for remote sensing data: Beyond Cohen's kappa

Cited by 11 publications

References 12 publications

Análise De Imagens Baseada Em Objetos Geográficos: Comparação De Regras De Classificação Da Cobertura Da Terra

Análise De Imagens Baseada Em Objetos Geográficos: Comparação De Regras De Classificação Da Cobertura Da Terra

Mapping Aboveground Woody Biomass on Abandoned Agricultural Land Based on Airborne Laser Scanning Data

Validation of Land Use Cover Maps: A Guideline

Contact Info

Product

Resources

About