Multiscale quality assessment of Global Human Settlement Layer scenes against reference data using statistical learning

• Present a multi-scale quality evaluation method for the Global Human Settlement Layer.
• We use automatic and globally consistent built-up extraction methods.
• We use settlement metrics as generalization functions.
• Reference data: very high resolution cadastral map and low resolution urban layer.
• We use regression and the R squared goodness of fit metric for scene comparisons.

A method for quality assessment of the Global Human Settlement Layer scenes against reference data is presented. It relies on two settlement metrics; the local average and gradient functions that quantify the notions of settlement density and flexible settlement limits respectively. They are both utilized as generalization functions for increasing the level of abstraction of the sets under comparison. Generalization compensates for inaccuracies of the automatic target extraction method and can be computed at multiple scales. The comparison between the target built-up layers and the reference data employs an ordered multi-scale, linear regression computing the goodness of fit measure R2R2. An optimized assessment procedure is investigated in a pilot study and is further employed in a big data exercise. A newly introduced quality metric returns the agreement between automatically extracted built-up from a set of 13605 scenes and the MODIS 500 urban layer, that was found too be as high as 91% for selected sensors. A final experiment attempts a performance increase at lower scales by correlating the target layer with automatically selected training subsets. At 50 m the adjusted R2R2 increases by 3% with a mean squared error improvement of 2% compared to the performance achieved without statistical learning. The experiment suggests that the GHSL assessment at a global scale can be carried out based on limited high resolution reference data of minimal spatial coverage.