NOAA AVHRR satellite infra-red data are used to display the surface radiant temperature heat islands of Vancouver, British Columbia, Seattle, Washington, and Los Angeles, California. Heat island intensities are largest in the day-time and in the warm season. Day-time intra-urban thermal patterns are strongly correlated with land-use; industrial areas are warmest and vegetated, riverine or coastal areas are coolest. Nocturnal heat island intensities and the correlation of the surface radiant temperature distribution with land use are less. This is the reverse of the known characteristics of near-surface air temperature heat islands. Several questions relating to the interpretation and limitations of satellite data in heat island analysis and urban climate modelling are addressed.

In this paper, we propose two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification. Based on predefined heuristics, the classifier ranks the unlabeled pixels and automatically chooses those that are considered the most valuable for its improvement. Once the pixels have been selected, the analyst labels them manually and the process is iterated. Starting with a small and nonoptimal training set, the model itself builds the optimal set of samples which minimizes the classification error. We have applied the proposed algorithms to a variety of remote sensing data, including very high resolution and hyperspectral images, using support vector machines. Experimental results confirm the consistency of the methods. The required number of training samples can be reduced to 10% using the methods proposed, reaching the same level of accuracy as larger data sets. A comparison with a state-of-the-art active learning method, margin sampling, is provided, highlighting advantages of the methods proposed. The effect of spatial resolution and separability of the classes on the quality of the selection of pixels is also discussed.