Search

This paper presents an assessment of the performance of a hybrid method that allows a simultaneous retrieval of land-surface temperature (LST) and emissivity (LSE) from remotely-sensed data. The proposed method is based on a synergistic usage of the split-window (SW) algorithm and the two-temperature method (TTM) and combines the advantages of both procedures while mitigating their drawbacks. The method was implemented for thermal channels 76 (10.56 µm) and 78 (11.72 µm) of the Airborne Hyperspectral Scanner (AHS), which was flown over the Barrax test site (Albacete, Spain) in the second week of July 2005, within the framework of the Sentinel-2 and Fluorescence Experiment (SEN2FLEX) field campaign. A set of radiometric measurements was performed in the thermal infrared region in coincidence with aircraft overpasses for different surface types, e.g. bare soil, water body, corn, wheat, grass. The hybrid method was tested and compared with a standard SW algorithm and the results obtained show that the hybrid method is able to provide better estimates of LST, with values of bias (RMSE) of the order of 0.8 K (1.9 K), i.e. about one third (one half) of the corresponding values of 2.7 K (3.4 K) that were obtained for bias (RMSE) when using the SW algorithm. These figures provide a sound indication that the developed hybrid method is particularly useful for surface and atmospheric conditions where SW algorithms cannot be accurately applied. [ABSTRACT FROM AUTHOR]

This paper explores the potential of an artificial immune-based supervised classification algorithm for land-cover classification. This classifier is inspired by the human immune system and possesses properties similar to nonlinear classification, self/non-self identification, and negative selection. Landsat ETM+ data of an area lying in Eastern England near the town of Littleport are used to study the performance of the artificial immune-based classifier. A univariate decision tree and maximum likelihood classifier were used to compare its performance in terms of classification accuracy and computational cost. Results suggest that the artificial immune-based classifier works well in comparison with the maximum likelihood and the decision-tree classifiers in terms of classification accuracy. The computational cost using artificial immune based classifier is more than the decision tree but less than the maximum likelihood classifier. Another data set from an area in Spain is also used to compare the performance of immune based supervised classifier with maximum likelihood and decision-tree classification algorithms. Results suggest an improved performance with the immune-based classifier in terms of classification accuracy with this data set, too. The design of an artificial immune-based supervised classifier requires several user-defined parameters to be set, so this work is extended to study the effect of varying the values of six parameters on classification accuracy. Finally, a comparison with a backpropagation neural network suggests that the neural network classifier provides higher classification accuracies with both data sets, but the results are not statistically significant. [ABSTRACT FROM AUTHOR]