In the Yangtze River Basin, the birthplace of civilization in China, it is necessary to further discover and investigate ancient remains. The archaeological site prediction model is important for discovering and investigating archaeological sites. In this paper, we focused on the ancient city sites of the Neolithic and Bronze Age in the Jianghan region located along the middle reaches of the Yangtze River, annotated the specific locations and extents of 33 ancient city sites using the Google Earth Engine (GEE) cloud platform, and proposed a machine learning-based ancient city site prediction model that couples geographic element features and temporal spectral features. The results indicated that the ancient city sites were recognizable in different geographic elements and were separable in Sentinel-2 multispectral bands and spectral indices. The coupled time series spectral features could improve the ability of the model to recognize the regions with ancient city sites. Ultimately, the percentage of pixels with a high probability of prediction (greater than 0.57) within the extent of the ancient city sites reached 80.0% and enabled to obtain high probability regions for the distribution of the ancient city site. The proposed model can be used to predict the potential geographic locations of ancient city sites and identify key areas for future archaeological field survey work.

The landscape of ancient sites has changed greatly with the passage of time. Among all of the factors, human activities and the change in natural environment are the main factors leading to the change in site landscape. The Panlongcheng site, which is located in Hubei Province, China, has a history of 3500 years with the most abundant relics in the Yangtze River Basin during the Shang Dynasty. As a near-water site, the landscape of the Panlongcheng site is greatly affected by water level changes and water conservancy activities. In this paper, by using spatial information technology, the data obtained from land and underwater archaeological exploration were integrated to restore landscapes of Panlongcheng sites in different periods. After removing modern artificial features and topsoil, the landscapes of the sites before the Shang Dynasty, in the Shang Dynasty and modern time were reconstructed. Combining historical records of water level changes, the landscape and water–land distribution of the Panlongcheng site were compared. The analysis results reflect the interaction between water level changes and human activities in this region for thousands of years, and support the archaeological findings in the near-water area of the Panlongcheng site, which provides a new idea for the landscape reconstruction and analysis of near-water sites.

The CORONA satellite image preserves the landscape from half a century ago, and has played a great role in landscape archaeology in many regions of the world. In recent years, with the rapid development of UAV (Unmanned Aerial Vehicle) Photogrammetry technology, Archaeologists can easily obtain the digital surface model (DSM)and Digital Ortho Map (DOM) of a site in the fieldwork. In the archaeological survey of bronze age sites in the middle of the Yangtze River project, we combined the UAV photogrammetry results with CORONA satellite photography, which can help us extract the surface landscape feature of the sites. This strategy has shown significant advantages in reconstructing the settlement layout, detecting the unknown linear features (such as walls, moats and canals) of sites and comparing the landscape between different sites.

Recent work at the early Shang period type site in Panlongcheng, Hubei Province, China, provides a new understanding of changes in the landscape and water environment over time. In the past few decades, the research at this site has obtained important results and shown progress in many aspects, but few scholars have discussed the geomorphological environment of Panlongcheng, especially the water environment. Researchers have long believed that the present-day environment and landscape of Panlongcheng are no different than during the early Shang period. However, recent archaeological discoveries indicate that there may still be some cultural remains underwater. Therefore, we used a combination of underwater surveys, drilling and digital mapping to expand our knowledge of the landscape of Panlongcheng during the early Shang period. This included mapping the lake basin using single-beam echo sounders and drilling to preliminarily observe the stratum and collect samples from underwater. We also conducted radiocarbon dating on the samples collected from the bottom of the lake. The results suggest that there might not have been a lake during the early Shang period. Therefore, the landscape and environment of Panlongcheng and other related issues should be reexamined. In addition, we hope the methods used in this study can provide a reference for related archaeological work in shallow water areas in inland China.