Machine learning-ready remote sensing data for Maya archaeology.

In our study, we set out to collect a multimodal annotated dataset for remote sensing of Maya archaeology, that is suitable for deep learning. The dataset covers the area around Chactún, one of the largest ancient Maya urban centres in the central Yucatán Peninsula. The dataset includes five types of data records: raster visualisations and canopy height model from airborne laser scanning (ALS) data, Sentinel-1 and Sentinel-2 satellite data, and manual data annotations. The manual annotations (used as binary masks) represent three different types of ancient Maya structures (class labels: buildings, platforms, and aguadas - artificial reservoirs) within the study area, their exact locations, and boundaries. The dataset is ready for use with machine learning, including convolutional neural networks (CNNs) for object recognition, object localization (detection), and semantic segmentation. We would like to provide this dataset to help more research teams develop their own computer vision models for investigations of Maya archaeology or improve existing ones.

Archaeological landscape, settlement dynamics, and sociopolitical organization in the Chactún area of the central Maya Lowlands.

Until recently, an extensive area in the central lowlands of the Yucatán peninsula was completely unexplored archaeologically. In 2013 and 2014, during initial surveys in the northern part of the uninhabited Calakmul Biosphere Reserve in eastern Campeche, Mexico, we located Chactún, Tamchén and Lagunita, three major Maya centers with some unexpected characteristics. Lidar data, acquired in 2016 for a larger area of 240 km2, revealed a thoroughly modified and undisturbed archaeological landscape with a remarkably large number of residential clusters and widespread modifications related to water management and agriculture. Substantial additional information was obtained through field surveys and test excavations in 2017 and 2018. While hydraulic and agricultural features and their potential for solving various archaeologically relevant questions were discussed in a previous publication, here we examine the characteristics of settlement patterns, architectural remains, sculpted monuments, and ceramic evidence. The early Middle Preclassic (early first millennium BCE) material collected in stratigraphic pits at Tamchén and another locale constitutes the earliest evidence of colonization known so far in a broader central lowland area. From then until the Late Classic period, which was followed by a dramatic demographic decline, the area under study witnessed relatively constant population growth and interacted with different parts of the Maya Lowlands. However, a number of specific and previously unknown cultural traits attest to a rather distinctive regional development, providing novel information about the extent of regional variation within the Maya culture. By analyzing settlement pattern characteristics, inscriptional data, the distribution of architectural volumes and some other features of the currently visible archaeological landscape, which largely reflects the Late Classic situation, we reconstruct several aspects of sociopolitical and territorial organization in that period, highlighting similarities with and differences from what has been evidenced in the neighboring Río Bec region and elsewhere in the Maya area.