Significance: This paper illustrates the potential of machine learning-based classification of multisensor, multitemporal satellite data for the remote detection and mapping of archaeological mounded settlements in arid environments. Our research integrates multitemporal synthetic-aperture radar and multispectral bands to produce a highly accurate probability field of mound signatures. The results largely expand the known concentration of Indus settlements in the Cholistan Desert in Pakistan ( ca . 3300 to 1500 BC), with the detection of hundreds of new sites deeper in the desert than previously suspected including several large-sized (>30 ha) urban centers. These distribution patterns have major implications regarding the influence of climate change and desertification in the collapse of the largest of the Old-World Bronze Age civilizations.

Remote sensing has considerable potential to contribute to the identification and reconstruction of lost hydrological systems and networks. Remote sensing-based reconstructions of palaeo-river networks have commonly employed single or limited time-span imagery, which limits their capacity to identify features in complex and varied landscape contexts. This paper presents a seasonal multi-temporal approach to the detection of palaeo-rivers over large areas based on long-term vegetation dynamics and spectral decomposition techniques. Twenty-eight years of Landsat 5 data, a total of 1711 multi-spectral images, have been bulk processed using Google Earth Engine^© Code Editor and cloud computing infrastructure. The use of multi-temporal data has allowed us to overcome seasonal cultivation patterns and long-term visibility issues related to recent crop selection, extensive irrigation and land-use patterns. The application of this approach on the Sutlej-Yamuna interfluve (northwest India), a core area for the Bronze Age Indus Civilisation, has enabled the reconstruction of an unsuspectedly complex palaeo-river network comprising more than 8000 km of palaeo-channels. It has also enabled the definition of the morphology of these relict courses, which provides insights into the environmental conditions in which they operated. These new data will contribute to a better understanding of the settlement distribution and environmental settings in which this, often considered riverine, civilisation operated.

The pollen analysis of a new sedimentary sequence performed at the Bosc dels Estanyons peat bog (2180 m a.s.l., Eastern Pyrenees, Andorra) is presented. Seven radiocarbon measurements and complementary macro-charcoal, stomata, and pollen influx analyses are employed to illustrate the dynamics of high-mountain vegetal communities since the end of the Late Glacial period. This high-resolution pollen analysis outlines the evolution of human activities since the Mesolithic–Early Neolithic transition for the first time in this area.

Historical maps present a unique depiction of past landscapes, providing evidence for a wide range of information such as settlement distribution, past land use, natural resources, transport networks, toponymy and other natural and cultural data within an explicitly spatial context. Maps produced before the expansion of large‐scale mechanized agriculture reflect a landscape that is lost today. Of particular interest to us is the great quantity of archaeologically relevant information that these maps recorded, both deliberately and incidentally. Despite the importance of the information they contain, researchers have only recently begun to automatically digitize and extract data from such maps as coherent information, rather than manually examine a raster image. However, these new approaches have focused on specific types of information that cannot be used directly for archaeological or heritage purposes. This paper provides a proof of concept of the application of deep learning techniques to extract archaeological information from historical maps in an automated manner. Early twentieth century colonial map series have been chosen, as they provide enough time depth to avoid many recent large‐scale landscape modifications and cover very large areas (comprising several countries). The use of common symbology and conventions enhance the applicability of the method. The results show deep learning to be an efficient tool for the recovery of georeferenced, archaeologically relevant information that is represented as conventional signs, line‐drawings and text in historical maps. The method can provide excellent results when an adequate training dataset has been gathered and is therefore at its best when applied to the large map series that can supply such information. The deep learning approaches described here open up the possibility to map sites and features across entire map series much more quickly and coherently than other available methods, opening up the potential to reconstruct archaeological landscapes at continental scales.