This paper presents the performance and evaluation of a number of machine learning classifiers for the discrimination between the vegetation physiognomic classes using the satellite based time-series of the surface reflectance data. Discrimination of six vegetation physiognomic classes, Evergreen Coniferous Forest, Evergreen Broadleaf Forest, Deciduous Coniferous Forest, Deciduous Broadleaf Forest, Shrubs, and Herbs, was dealt with in the research. Rich-feature data were prepared from time-series of the satellite data for the discrimination and cross-validation of the vegetation physiognomic types using machine learning approach. A set of machine learning experiments comprised of a number of supervised classifiers with different model parameters was conducted to assess how the discrimination of vegetation physiognomic classes varies with classifiers, input features, and ground truth data size. The performance of each experiment was evaluated by using the 10-fold cross-validation method. Experiment using the Random Forests classifier provided highest overall accuracy (0.81) and kappa coefficient (0.78). However, accuracy metrics did not vary much with experiments. Accuracy metrics were found to be very sensitive to input features and size of ground truth data. The results obtained in the research are expected to be useful for improving the vegetation physiognomic mapping in Japan.
Irrespective of several attempts to land use/cover mapping at local, regional, or global scales, mapping of vegetation physiognomic types is limited and challenging. The main objective of the research is to produce an accurate nationwide vegetation physiognomic map by using automated machine learning approach with the support of reference data. A time-series of the multi-spectral and multi-indices data derived from Moderate Resolution Imaging Spectroradiometer (MODIS) were exploited along with the land-surface slope data. Reliable reference data of the vegetation physiognomic types were prepared by refining the existing vegetation survey data available in the country. The Random Forests based mapping framework adopted in the research showed high performance (Overall accuracy = 0.82, Kappa coefficient = 0.79) using 148 optimum number of features out of 231 featured used. A nationwide vegetation physiognomic map of year 2013 was produced in the research. The resulted map was compared to the existing MODIS Land Cover Type (MCD12Q1) product of year 2013. A huge difference was found between two maps. Validation with the reference data showed that the MCD12Q1 product did not work satisfactorily in Japan. The outcome of the research highlights the possibility of improving the accuracy of the MCD12Q1 product with special focus on reference data.
This paper presents an improved classification and mapping of vegetation types for all of Japan by utilizing the Moderate-resolution Imaging Spectroradiometer (MODIS) data. The Nadir BRDF-Adjusted Reflectance (MCD43A4 product) data were compared to the conventional Surface Reflectance (MOD09A1/MOY09A1 products) data for the classification of vegetation types: evergreen coniferous forest, evergreen broadleaf forest, deciduous coniferous forest, deciduous broadleaf forest, shrubs, herbaceous, arable; and non-vegetation. Very rich spectral and temporal features were prepared from MCD43A4 and MOD09A1/MOY09A1 products. Random Forests classifier was employed for the classification of vegetation types with the support of ground truth data prepared in the research. Accuracy metrics-confusion matrix, overall accuracy, and kappa coefficient calculated through 10-fold cross-validation approach-were used for quantitative comparison of MCD43A4 and MOD09A1/MOY09A1 products. The cross-validation results indicated better performance of the MCD43A4 (Overall accuracy = 0.73; Kappa coefficient = 0.69) product than conventional MOD09A1/MOY09A1 products (Overall accuracy = 0.70; Kappa coefficient = 0.66) for the classification. McNemar's test was also used to confirm a significant difference (p-value = 0.0003) between MCD43A4 and MOD09A1/MOY09A1 products. Based on these results, by utilizing the MCD43A4 features, a new vegetation map was produced for all of Japan. The newly produced map showed better accuracy than the extant, MODIS Land Cover Type product (MCD12Q1) and Global Land Cover by National Mapping Organizations (GLCNMO) product in Japan.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.