ABSTRACT
Changes in land-use practices have been a central element of human adaptation to Holocene climate change. Many practices that result in the short-term stabilization of socio-natural systems, however, have longer-term, unanticipated consequences that present cascading challenges for human subsistence strategies and opportunities for subsequent adaptations. Investigating complex sequences of interaction between climate change and human land-use in the past-rather than short-term causes and effects-is therefore essential for understanding processes of adaptation and change, but this approach has been stymied by a lack of suitably-scaled paleoecological data. Through a high-resolution paleoecological analysis, we provide a 7000-year history of changing climate and land management around Lake Acopia in the Andes of southern Peru. We identify evidence of the onset of pastoralism, maize cultivation, and possibly cultivation of quinoa and potatoes to form a complex agrarian landscape by c. 4300 years ago. Cumulative interactive climate-cultivation effects resulting in erosion ended abruptly c. 2300 years ago. After this time, reduced sedimentation rates are attributed to the construction and use of agricultural terraces within the catchment of the lake. These results provide new insights into the role of humans in the manufacture of Andean landscapes and the incremental, adaptive processes through which land-use practices take shape.
ABSTRACT
Archaeology has long faced fundamental issues of sampling and scalar representation. Traditionally, the local-to-regional-scale views of settlement patterns are produced through systematic pedestrian surveys. Recently, systematic manual survey of satellite and aerial imagery has enabled continuous distributional views of archaeological phenomena at interregional scales. However, such "brute force" manual imagery survey methods are both time- and labor-intensive, as well as prone to inter-observer differences in sensitivity and specificity. The development of self-supervised learning methods (e.g., contrastive learning) offers a scalable learning scheme for locating archaeological features using unlabeled satellite and historical aerial images. However, archaeological features are generally only visible in a very small proportion relative to the landscape, while the modern contrastive-supervised learning approach typically yields an inferior performance on highly imbalanced datasets. In this work, we propose a framework to address this long-tail problem. As opposed to the existing contrastive learning approaches that typically treat the labeled and unlabeled data separately, our proposed method reforms the learning paradigm under a semi-supervised setting in order to fully utilize the precious annotated data (<7% in our setting). Specifically, the highly unbalanced nature of the data is employed as the prior knowledge in order to form pseudo negative pairs by ranking the similarities between unannotated image patches and annotated anchor images. In this study, we used 95,358 unlabeled images and 5,830 labeled images in order to solve the issues associated with detecting ancient buildings from a long-tailed satellite image dataset. From the results, our semi-supervised contrastive learning model achieved a promising testing balanced accuracy of 79.0%, which is a 3.8% improvement as compared to other state-of-the-art approaches.
