About

Parker VanValkenburgh is an Associate Professor of Anthropology and Archaeology and the Ancient World at Brown University. His research employs archaeological methods to explore anthropological questions, with a focus on the long-term impacts of colonialism and imperialism on Indigenous peoples and environments in the Peruvian Andes. He investigates how relationships between people, institutions, and environments are transformed through imperial histories by analyzing diverse materials such as architecture, ceramics, environmental datasets, and archival documents. VanValkenburgh aims to understand community strategies of survival and resilience passed down across generations, contributing approaches applicable to the study of empire beyond the Andean region and fostering interdisciplinary understanding of imperial legacies in the modern world. He integrates digital methodologies, including geographic information systems (GIS), to map and analyze social, political, and environmental change over space and time, and critically examines how digital media and techniques influence archaeological scholarship and collaboration. He holds a Ph.D. from Harvard University and has held academic positions at the University of Vermont and Washington University in St. Louis. VanValkenburgh is a co-director of the Paisajes Arqueológicos de Chachapoyas (PACha) project, investigating long-term human-environment interactions in Peru's Chachapoyas region through archaeological survey, archival research, remote sensing, and community engagement. He also co-directs GeoPACHA, a geospatial platform for Andean culture and archaeology, and collaborates on projects examining historical trauma in Tulsa and colonial impacts on landscapes in Peru. At Brown, he directs the Brown Digital Archaeology Laboratory and teaches courses on GIS, cartography, digital archaeology, the politics of space and landscape, historical anthropology, and Andean archaeology.

Research topics

• Geography
• Archaeology
• Computer Science
• Engineering
• Remote sensing
• Data Mining
• Cartography
• History
• Data science
• Geodesy
• Geology

Selected publications

• Enduring Traditions of Indigenous Mound Building along the Upper Paraguai River (Mato Grosso, Brazil)

  Ethnoarchaeology · 2026-01-10

  article
  PublisherDOI

• Indigenous labor and the circulation of majolica in the colonial Andes

  UNC Libraries · 2025-04-04

  articleOpen accessSenior author
  PublisherDOI

• Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration

  2025-06-10 · 2 citations

  article

  Point cloud completion helps restore partial incomplete point clouds suffering occlusions. Current self-supervised methods fail to give high fidelity completion for large objects with missing surfaces and unbalanced distribution of available points. In this paper, we present a novel method for restoring large-scale point clouds with limited and unbalanced ground-truth. Using rough boundary annotations for a region of interest, we project the original point clouds into a multiple-center-of-projection (MCOP) image, where fragments are projected to images of 5 channels (RGB, depth, and rotation). Completion of the original point cloud is reduced to inpainting the missing pixels in the MCOP images. Due to lack of complete structures and an unbalanced distribution of existing parts, we develop a self-supervised scheme which learns to infill the MCOP image with points resembling existing "complete" patches. Special losses are applied to further enhance the regularity and consistency of completed MCOP images, which is mapped back to 3D to form final restoration. Extensive experiments demonstrate the superiority of our method in completing 600+ incomplete and unbalanced archaeological structures in Peru.

  PublisherDOI

• Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration

  ArXiv.org · 2025-03-06

  preprintOpen access

  Point cloud completion helps restore partial incomplete point clouds suffering occlusions. Current self-supervised methods fail to give high fidelity completion for large objects with missing surfaces and unbalanced distribution of available points. In this paper, we present a novel method for restoring large-scale point clouds with limited and imbalanced ground-truth. Using rough boundary annotations for a region of interest, we project the original point clouds into a multiple-center-of-projection (MCOP) image, where fragments are projected to images of 5 channels (RGB, depth, and rotation). Completion of the original point cloud is reduced to inpainting the missing pixels in the MCOP images. Due to lack of complete structures and an unbalanced distribution of existing parts, we develop a self-supervised scheme which learns to infill the MCOP image with points resembling existing "complete" patches. Special losses are applied to further enhance the regularity and consistency of completed MCOP images, which is mapped back to 3D to form final restoration. Extensive experiments demonstrate the superiority of our method in completing 600+ incomplete and unbalanced archaeological structures in Peru.

  PublisherOA PDFDOI

• Vision Foundation Models in Remote Sensing: A survey

  IEEE Geoscience and Remote Sensing Magazine · 2025-03-07 · 61 citations

  article

  Artificial intelligence (AI) technologies have profoundly transformed the field of remote sensing (RS), revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, RS research has been significantly enhanced by the advent of foundation models (FMs)—large-scale pretrained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency. This article provides a comprehensive survey of FMs in the RS domain. We categorize these models based on their architectures, pretraining datasets, and methodologies. Through detailed performance comparisons, we highlight emerging trends and the significant advancements achieved by those FMs. Additionally, we discuss technical challenges, practical implications, and future research directions, addressing the need for high-quality data, computational resources, and improved model generalization. Our research also finds that pretraining methods, particularly self-supervised learning (SSL) techniques like contrastive learning (CL) and masked autoencoders (MAEs), remarkably enhance the performance and robustness of FMs. This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for the continued development and application of FMs in RS.

  PublisherDOI

• DeepAndes: A Self-Supervised Vision Foundation Model for Multispectral Remote Sensing Imagery of the Andes

  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 2025-01-01 · 2 citations

  articleOpen access

  By mapping sites at large scales using remotely sensed data, archaeologists can generate unique insights into long-term demographic trends, inter-regional social networks, and human adaptations in the past. Remote sensing surveys complement field-based approaches, and their reach can be especially great when combined with deep learning and computer vision techniques. However, conventional supervised deep learning methods face challenges in annotating fine-grained archaeological features at scale. In addition, while recent vision foundation models have shown remarkable success in learning large-scale remote sensing data with minimal annotations, most off-the-shelf solutions are designed for RGB images rather than multi-spectral satellite imagery, such as the 8-band data used in our study. In this paper, we introduce DeepAndes, a transformer-based vision foundation model trained on three million multi-spectral satellite images, specifically tailored for Andean archaeology. DeepAndes incorporates a customized DINOv2 self-supervised learning algorithm optimized for 8-band multi-spectral imagery, marking the first foundation model designed explicitly for the Andes region. We evaluate its image understanding performance through imbalanced image classification, image instance retrieval, and pixel-level semantic segmentation tasks. Our experiments show that DeepAndes achieves superior F1 scores, mean average precision, and Dice scores in few-shot learning scenarios, significantly outperforming models trained from scratch or pre-trained on smaller datasets. This underscores the effectiveness of large-scale self-supervised pre-training in archaeological remote sensing. Codes will be available on <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/geopacha/DeepAndes</uri>.

  PublisherDOI

• Vision Foundation Models in Remote Sensing: A Survey

  arXiv (Cornell University) · 2024-08-06 · 7 citations

  preprintOpen access

  Artificial Intelligence (AI) technologies have profoundly transformed the field of remote sensing, revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, remote sensing research has been significantly enhanced by the advent of foundation models-large-scale, pre-trained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency. This paper provides a comprehensive survey of foundation models in the remote sensing domain. We categorize these models based on their architectures, pre-training datasets, and methodologies. Through detailed performance comparisons, we highlight emerging trends and the significant advancements achieved by those foundation models. Additionally, we discuss technical challenges, practical implications, and future research directions, addressing the need for high-quality data, computational resources, and improved model generalization. Our research also finds that pre-training methods, particularly self-supervised learning techniques like contrastive learning and masked autoencoders, remarkably enhance the performance and robustness of foundation models. This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for continued development and application of foundation models in remote sensing.

  PublisherOA PDFDOI

• Assessing Conservation Conditions at La Fortaleza de Kuelap, Peru, Based on Integrated Close-Range Remote Sensing and Near-Surface Geophysics

  Remote Sensing · 2024-03-16 · 1 citations

  articleOpen access

  We combined datasets from multiple research projects and remote sensing technologies to evaluate conservation conditions at La Fortaleza de Kuelap, a pre-Hispanic site in Peru that suffered significant damage under heavy seasonal rains in April 2022. To identify the causes of the collapse and where the monument is at further risk, we modeled surface hydrology using a DTM derived from drone LiDAR data, reconstructed a history of collapses, and calculated the volume of the most recent by fusing terrestrial LiDAR and photogrammetric datasets. In addition, we examined subsurface water accumulation with electrical resistivity, reconstructed the stratification of the monument with seismic refraction, and analyzed vegetation loss and ground moisture accumulation using satellite imagery. Our results point to rainwater infiltration as the most significant source of risk for La Fortaleza’s perimeter walls. Combined with other adverse natural conditions and contemporary conservation interventions, this led to the 2022 collapse. Specialists need to consider these factors when tasked with conserving monuments located in comparable high-altitude perhumid environments. This integration of analytical results demonstrates how multi-scalar and multi-instrumental approaches provide comprehensive and timely assessments of conservation needs.

  PublisherOA PDFDOI

• Wet and dry events influenced colonization of a mid-elevation Andean forest

  Quaternary Science Reviews · 2024-02-02 · 4 citations

  articleOpen access
  PublisherOA PDFDOI

• Assessing Conservation Conditions at La Fortaleza De Kuelap, Peru Based on Integrated Close-Range Remote Sensing and Near-Surface Geophysics

  Preprints.org · 2024-01-04 · 1 citations

  preprintOpen access

  In this article, we combine datasets from multiple research projects and remote sensing tech-nologies to evaluate the conservation conditions of La Fortaleza de Kuelap, a pre-Hispanic monument in Peru’s northeastern Andes that suffered significant damage during historically high seasonal rains in April 2022. Our analyses seek to identify the main causes of the collapse and locate places where the monument is likely at risk of further deterioration. To do so, we model surface hydrology using a digital elevation model (DEM) derived from drone LiDAR data, re-construct a history of previous collapses, and calculate the volume of the most recent by fusing terrestrial LiDAR and photogrammetric datasets. In addition, we examine subsurface water ac-cumulation through electrical resistivity data, reconstruct the stratification of the monument from seismic refraction data, and analyze vegetation loss and ground moisture accumulation using high resolution satellite imagery. Our results point to water accumulation as the most significant source of risk for La Fortaleza’s perimeter walls. Combined with adverse contemporary conser-vation interventions and natural conditions, this led to the collapse of April 2022. This integration of analytical results demonstrates how multi-scalar and multi-instrumental approaches provide comprehensive and timely assessments of conservation needs.

  PublisherOA PDFDOI

Frequent coauthors

• Jeffrey Quilter

  Harvard University Press

  12 shared

• Sarah J. Kelloway

  University of Sydney

  11 shared

• Steven A. Wernke

  Vanderbilt University

  10 shared

• Daniel Plekhov

  8 shared

• Matthias Kucera

  8 shared

• Sarah A. Kennedy

  Carleton College

  6 shared

• Bartłomiej Ćmielewski

  Wrocław University of Science and Technology

  6 shared

• Jacek Kościuk

  University of Warsaw

  6 shared

Education

• Ph.D.

  Harvard University

• M.A., Anthropology

  University of Vermont

• B.A., Anthropology

  University of Vermont