{"resourceId":"brown-vanderbilt-deepandes-workbench-schmidt-ai-archaeology-20261102","versions":[{"version":"external-206f8af3f42c0b62170fd161f8b94df301d295c4515b9926f670b08611a15046","resource":{"id":"brown-vanderbilt-deepandes-workbench-schmidt-ai-archaeology-20261102","title":"Brown and Vanderbilt receive $732,574 from Schmidt Sciences to build DeepAndes Workbench, an agent-queried AI survey tool for Andean archaeology","organization":"Brown University (Parker VanValkenburgh); Vanderbilt University (Steven Wernke, Yuankai Huo); Oak Ridge National Laboratory; Schmidt Sciences","sector":"University humanities and social-science research (AI-assisted archaeological survey)","geography":"United States, with collaborators in Peru, Chile and Australia","publishedAt":"2 November 2026 (Brown University news)","publicationDate":"2026-11-02","eventDate":null,"sourceName":"Brown University","sourceLabel":"Brown University, \"Brown archaeologist to co-lead AI project to advance understanding of ancient Andean empires,\" 2 Nov 2026","sourceUrl":"https://www.brown.edu/news/2026-11-02/vanvalkenburgh-schmidt-sciences-grant","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["knowledge-work","infrastructure","operating-model"],"finding":"Brown associate professor Parker VanValkenburgh and Vanderbilt researchers Steven Wernke and Yuankai Huo received $732,574 from Schmidt Sciences for \"Scaling Archaeological Vision: Imperial Landscapes of the Andes through AI-Assisted Survey.\" They will build DeepAndes Workbench, which lets archaeologists query an agent with images and verbal prompts to find specific feature types, with expert feedback used to improve the models. It builds on GeoPACHA, their satellite-imagery and AI mapping platform. The team includes about 15 collaborators across the US, Peru, Chile and Australia plus Oak Ridge National Laboratory researchers; Schmidt Sciences also provides in-kind supercomputing. VanValkenburgh described it as a tool to extend researchers' vision, not an all-seeing eye.","sledRelevance":"Shows AI-for-research funding and national-lab compute reaching the humanities, a segment research computing groups often under-serve. It is also an example of philanthropic in-kind compute supplementing campus resources.","evidence":"Read the full release. This is an award announcement; no model performance, accuracy or user data are given. Expected outputs (continental-scale maps) are aspirations.","architectureImplications":"Image-search-style agent over satellite imagery with expert feedback loops, backed by external supercomputing from a philanthropy and ORNL collaboration.","governanceImplications":"International collaboration on cultural heritage data raises questions about site-location sensitivity and partner-country data rights, not addressed.","securityPrivacyImplications":"Precise archaeological site maps can enable looting; release controls are not discussed.","caveats":"University award announcement (institutional self-report, classed as operator claim); no results yet. Humanities use case with distinctive data; transfer to other fields is limited.","streamIds":["research"],"roles":{"sales":"Lead with research computing support for humanities AI. Brown said on 2 November that a Brown-Vanderbilt team won $732,574 from Schmidt Sciences to build DeepAndes Workbench, an agent that archaeologists query with images and prompts, backed by in-kind supercomputing and Oak Ridge collaborators. Research computing directors and humanities deans should see this demand coming. Offer a bounded review of how campus services support externally funded humanities AI projects. Do not claim the tool works yet; no results are published.","engineering":"Frame fit around geospatial imagery pipelines with expert-in-the-loop model improvement. DeepAndes Workbench extends GeoPACHA, using satellite imagery, an agent interface for image and text queries, and expert feedback to retrain models, with external supercomputing. Prerequisites are large imagery storage, GPU access for vision models and annotation tooling. Validate by measuring precision and recall of feature detection against expert-labelled survey areas and checking that sensitive site coordinates are controlled.","delivery":"Treat delivery as support for a multi-institution grant. Work covers data management plans, imagery storage, compute access across Brown, Vanderbilt and external providers, and annotation workflows for about 15 international collaborators. Ownership sits with the principal investigators, supported by research computing and research data services. Governance checkpoints cover partner-country data agreements and site-location release rules. Acceptance criteria are proposals, such as documented detection accuracy on labelled regions, not reported results."},"roleDetails":{"sales":{"customerProblem":"Humanities teams winning AI grants need imagery storage, compute and data governance that campus services rarely tailor to them.","stakeholders":["Research computing director","Dean of humanities or social sciences","Sponsored programs office","Principal investigators"],"discoveryQuestions":["How do you support externally funded humanities AI projects?","Where will large imagery datasets live?","Who governs sensitive site-location data?"],"valueHypothesis":"Planned support for storage, compute and data agreements may let humanities AI projects start faster.","potentialEngagement":"A review of campus support for one externally funded humanities AI project.","unsupportedClaims":["The tool detects features accurately","Campus compute is required","Continental-scale maps will be delivered"]},"engineering":{"fit":"Fits geospatial computer-vision projects with expert annotation and external compute.","architectureIntegration":"Satellite imagery store, vision models, an agent query interface and expert feedback loop, with philanthropic supercomputing.","prerequisites":["Imagery storage","GPU access","Annotation tooling"],"constraints":["Partner-country data rights","Sensitive site locations","Unreported model performance"],"security":"Restrict precise site coordinates to authorized researchers to reduce looting risk.","proofOfValue":["Precision and recall on expert-labelled areas","Expert feedback turnaround","Access control test on site data"]},"delivery":{"work":"Data management, storage, multi-site compute access, annotation workflows and collaborator onboarding.","dependencies":["Schmidt Sciences compute","ORNL collaboration","International partners"],"ownership":"Principal investigators with research computing and data services support.","skillsAdoption":"Archaeologists learn to query and correct the agent; staff learn geospatial AI support.","governanceCheckpoints":["Partner data agreements","Site-location release review","Grant reporting"],"acceptanceCriteria":["Documented detection accuracy on labelled regions (proposal)","Collaborators onboarded","Data plan approved"],"risks":["Model errors misdirect fieldwork","Site data leakage","Dependence on in-kind compute"]}},"retrievedAt":"2026-11-02T22:07:31-06:00","enrichedAt":"2026-11-02T22:07:32-06:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Expert users provide feedback that trains the models, adding annotation work for scholars.","procurementImplications":"Compute comes in kind from Schmidt Sciences rather than campus purchase.","operatingModelImplications":"Multi-institution, international team with external compute; campus research computing role is unclear.","peerReview":"unknown","sourceVerification":{"openedUrl":"https://www.brown.edu/news/2026-11-02/vanvalkenburgh-schmidt-sciences-grant","referenceExcerpt":"were awarded $732,574 for their project, “Scaling Archaeological Vision: Imperial Landscapes of the Andes through AI-Assisted Survey.”","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}