This paper presents the multi-modal BigEarthNet (BigEarthNet-MM) benchmark archive made up of 590,326 pairs of Sentinel-1 and Sentinel-2 image patches to support the deep learning (DL) studies in multi-modal multi-label remote sensing (RS) image retrieval and classification. Each pair of patches in BigEarthNet-MM is annotated with multi-labels provided by the CORINE Land Cover (CLC) map of 2018 based on its thematically most detailed Level-3 class nomenclature. Our initial research demonstrates that some CLC classes are challenging to be accurately described by only considering (single-date) BigEarthNet-MM images. In this paper, we also introduce an alternative class-nomenclature as an evolution of the original CLC labels to address this problem. This is achieved by interpreting and arranging the CLC Level-3 nomenclature based on the properties of BigEarthNet-MM images in a new nomenclature of 19 classes. In our experiments, we show the potential of BigEarthNet-MM for multi-modal multi-label image retrieval and classification problems by considering several state-of-theart DL models. We also demonstrate that the DL models trained from scratch on BigEarthNet-MM outperform those pretrained on ImageNet, especially in relation to some complex classes, including agriculture and other vegetated and natural environments. We make all the data and the DL models publicly available at https://bigearth.net, offering an important resource to support studies on multi-modal image scene classification and retrieval problems in RS.

No abstract

This paper describes a general framework alternative to the traditional surveys that are commonly performed to estimate, for statistical purposes, the areal extent of predefined land cover classes across Europe. The framework has been funded by Eurostat and relies on annual land cover mapping and updating from remotely sensed and national GIS-based data followed by area estimation. Map production follows a series of steps, namely data collection, change detection, supervised image classification, rule-based image classification, and map updating/generalization. Land cover area estimation is based on mapping but compensated for mapping error as estimated through thematic accuracy assessment. This general structure was applied to continental Portugal, successively updating a map of 2010 for the following years until 2015. The estimated land cover change was smaller than expected but the proposed framework was proved as a potential for statistics production at the national and European levels. Contextual and structural methodological challenges and bottlenecks are discussed, especially regarding mapping, accuracy assessment, and area estimation.

No abstract

Abstract. A series of five land cover maps, widely known as COS (Carta de Uso e Ocupação do Solo), have been produced since 1990 for mainland Portugal. Previous to 2015, all maps were produced through photo-interpretation of orthophotos. Land cover and land use changes were detected through comparison of previous and recent orthophotos, which were used for map updating, thereby producing a new map. The remaining areas of no change were preserved across the maps for consistency. Despite the value of the maps produced, the method is very time-consuming and limited to the single-date reference of the orthophotos. From 2015 onwards, a new approach was adopted for map production. Photo-interpretation of orthophoto maps is still the basis of mapping, but assisted by products derived from satellite data. The goals are three-fold: (i) cut time production, (ii) increase map accuracy, and (iii) further detail the nomenclature. The last map published (COS 2015) benefited from change detection and classification analyses of Landsat data, namely for guiding the photo-interpretation in forest, shrublands, and mapping annual agriculture. Time production and map error have been reduced comparing to previous maps. The new 2018 map, currently in production, further explores this approach. Landsat 8 time series of 2015–2018 are used for change detection in vegetation based on NDVI differencing, thresholding and clustering. Sentinel-2 time series of 2017–2018 are used to classify Autumn/Winter crops and Spring/Summer crops based on NDVI temporal profiles and classification rules. Benefits and pitfalls of the new mapping approach are presented and discussed.