Curriculum learning-based strategy for low-density archaeological mound detection from historical maps in India and Pakistan.

This paper presents two algorithms for the large-scale automatic detection and instance segmentation of potential archaeological mounds on historical maps. Historical maps present a unique source of information for the reconstruction of ancient landscapes. The last 100 years have seen unprecedented landscape modifications with the introduction and large-scale implementation of mechanised agriculture, channel-based irrigation schemes, and urban expansion to name but a few. Historical maps offer a window onto disappearing landscapes where many historical and archaeological elements that no longer exist today are depicted. The algorithms focus on the detection and shape extraction of mound features with high probability of being archaeological settlements, mounds being one of the most commonly documented archaeological features to be found in the Survey of India historical map series, although not necessarily recognised as such at the time of surveying. Mound features with high archaeological potential are most commonly depicted through hachures or contour-equivalent form-lines, therefore, an algorithm has been designed to detect each of those features. Our proposed approach addresses two of the most common issues in archaeological automated survey, the low-density of archaeological features to be detected, and the small amount of training data available. It has been applied to all types of maps available of the historic 1″ to 1-mile series, thus increasing the complexity of the detection. Moreover, the inclusion of synthetic data, along with a Curriculum Learning strategy, has allowed the algorithm to better understand what the mound features look like. Likewise, a series of filters based on topographic setting, form, and size have been applied to improve the accuracy of the models. The resulting algorithms have a recall value of 52.61% and a precision of 82.31% for the hachure mounds, and a recall value of 70.80% and a precision of 70.29% for the form-line mounds, which allowed the detection of nearly 6000 mound features over an area of 470,500 km2, the largest such approach to have ever been applied. If we restrict our focus to the maps most similar to those used in the algorithm training, we reach recall values greater than 60% and precision values greater than 90%. This approach has shown the potential to implement an adaptive algorithm that allows, after a small amount of retraining with data detected from a new map, a better general mound feature detection in the same map.

Potential of deep learning segmentation for the extraction of archaeological features from historical map series.

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.

Automated detection of archaeological mounds using machine-learning classification of multisensor and multitemporal satellite data.

This paper presents an innovative multisensor, multitemporal machine-learning approach using remote sensing big data for the detection of archaeological mounds in Cholistan (Pakistan). The Cholistan Desert presents one of the largest concentrations of Indus Civilization sites (from ca 3300 to 1500 BC). Cholistan has figured prominently in theories about changes in water availability, the rise and decline of the Indus Civilization, and the transformation of fertile monsoonal alluvial plains into an extremely arid margin. This paper implements a multisensor, multitemporal machine-learning approach for the remote detection of archaeological mounds. A classifier algorithm that employs a large-scale collection of synthetic-aperture radar and multispectral images has been implemented in Google Earth Engine, resulting in an accurate probability map for mound-like signatures across an area that covers ca 36,000 km2 The results show that the area presents many more archaeological mounds than previously recorded, extending south and east into the desert, which has major implications for understanding the archaeological significance of the region. The detection of small (<5 ha) to large mounds (>30 ha) suggests that there were continuous shifts in settlement location. These shifts are likely to reflect responses to a dynamic and changing hydrological network and the influence of the progressive northward advance of the desert in a long-term process that culminated in the abandonment of much of the settled area during the Late Harappan period.

Shipping amphorae and shipping sheep? Livestock mobility in the north-east Iberian peninsula during the Iron Age based on strontium isotopic analyses of sheep and goat tooth enamel.

Animal mobility is a common strategy to overcome scarcity of food and the related over-grazing of pastures. It is also essential to reduce the inbreeding rate of animal populations, which is known to have a negative impact on fertility and productivity. The present paper shows the geographic range of sheep provisioning in different phases of occupation at the Iron Age site of Turó de la Font de la Canya (7th to 3rd centuries BC). Strontium isotope ratios from 34 archaeological sheep and goat enamel, two archaeological bones and 14 modern tree leaves are presented. The isotopic results suggest that sheep and goats consumed at the site were reared locally (within a few kilometres radius) during the whole period of occupation. The paper discusses the isotopic results in light of the socio-political structure of this period, as complex, strongly territorial societies developed during the Iron Age in the north-east Iberian Peninsula.

Multi-scale relief model (MSRM): a new algorithm for the visualization of subtle topographic change of variable size in digital elevation models.

Morphological analysis of landforms has traditionally relied on the interpretation of imagery. Although imagery provides a natural view of an area of interest (AOI) images are largely hindered by the environmental conditions at the time of image acquisition, the quality of the image and, mainly, the lack of topographical information, which is an essential factor for a correct understanding of the AOI's geomorphology. More recently digital surface models (DSMs) have been incorporated into the analytical toolbox of geomorphologists. These are usually high-resolution models derived from digital photogrammetric processes or LiDAR data. However, these are restricted to relatively small areas and are expensive or complex to acquire, which limits widespread implementation. In this paper, we present the multi-scale relief model (MSRM), which is a new algorithm for the visual interpretation of landforms using DSMs. The significance of this new method lies in its capacity to extract landform morphology from both high- and low-resolution DSMs independently of the shape or scale of the landform under study. This method thus provides important advantages compared to previous approaches as it: (1) allows the use of worldwide medium resolution models, such as SRTM, ASTER GDEM, ALOS, and TanDEM-X; (2) offers an alternative to traditional photograph interpretation that does not rely on the quality of the imagery employed nor on the environmental conditions and time of its acquisition; and (3) can be easily implemented for large areas using traditional GIS/RS software. The algorithm is tested in the Sutlej-Yamuna interfluve, which is a very large low-relief alluvial plain in northwest India where 10 000 km of palaeoriver channels have been mapped using MSRM. The code, written in Google Earth Engine's implementation of JavaScript, is provided as Supporting Information for its use in any other AOI without particular technical knowledge or access to topographical data. © 2017 The Authors. Earth Surface Processes and Landforms published by John Wiley & Sons Ltd.