Generated by All in One SEO v5.0.1.1, this is an llms.txt file, used by LLMs to index the site. # AI and Global Development Lab ## Sitemaps - [XML Sitemap](https://aidevlab.org/sitemap.xml): Contains all public & indexable URLs for this website. ## Posts - [Platonic Representations for Poverty Mapping: Do Images and Language Share a ?](https://aidevlab.org/platonic-post/) - Listen to post 12:30 0:00 0:00 / 12:30 0.75× 1× 1.25× 1.5× 2× 15 15 Space play · ←→ seek · ↑↓ speed TL;DR. We paired ~60k African DHS clusters with satellite imagery and two flavors of place‑specific text—LLM‑only spatiotemporal descriptions (“neural memory”) and web text fetched by an AI search agent—and asked whether these - [Unshrink Tutorial](https://aidevlab.org/unshrink-tutorial/) - Tutorial for: unshrink: Package for Post-hoc Debiasing of ML Predictions for Causal Inference[Readme] [Paper] [.bib] ## Pages - [AI & GLOBAL DEVELOPMENT LAB](https://aidevlab.org/) - The AI & Global Development Lab fuses AI with Earth Observation to illuminate the causes and consequences of human development across time and space. Our interdisciplinary team, comprising data scientists, computer scientists, and social scientists, develops methods to better understand the multi-scale dynamics of pressing global issues, including poverty, conflict, sustainability, and the effectiveness of - [Horizontal Inequality & Conflict](https://aidevlab.org/horizontal-inequality-conflict-satellite/) - >>>Economic Horizontal Inequality is Linked to Conflict Persistence: High-Resolution Evidence from Satellite-Derived Wealth Measures in Africa Skip to the findings Using annual satellite-derived wealth estimates at 6.72-km resolution across Africa, this study separates the start of conflict from what happens after armed violence is underway. It finds no statistically significant onset association, but consistent links - [Debiasing ML Predictions](https://aidevlab.org/tweedie/) - Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis [PDF] [Slides] [Code] [.bib] Authors: Markus B. Pettersson | Connor T. Jerzak | Adel DaoudOral presentation at AAAI-26 Listen to Paper Listen to paper 49:48 TL;DR: Machine learning models built on satellite imagery can create - [Transcripts](https://aidevlab.org/transcripts/) - The AI & Global Development Lab uses AI and Earth‑observation data to map and analyse development at planetary scale. Here, we provide transcripts, gathering written versions of key talks from the Lab’s video library to make the content easier to review. Current transcripts include Adel Daoud’s lectures on confounding and on the overall concept of planetary - [How AI and Satellites Reveal Poverty Traps](https://aidevlab.org/how-ai-and-satellites-reveal-poverty-traps/) - Speaker: Adel Daoud at the Geo for Good Lightning Conference Despite the progress that humanity has made over the last century, many children still die globally, and that is because of poverty and unequal access to resources. Part of the problem is that communities might be trapped in so-called "poverty traps." To analyze poverty traps, - [AI & Global Development Lab Culture](https://aidevlab.org/lab-culture/) - Aims Global-development research won't build its own future. Somebody has to do it, and we'd like that to be us. We're a mixed bunch of disciplines, held together by a long time horizon. People here have room to pursue ideas that seem unlikely, and they're expected to make them happen. The horizon we're pointed at - [AI Global Development Lab: About](https://aidevlab.org/sites/) - About The AI and Global Development Lab is a network of innovation hubs that partners with organizations worldwide to apply frontier AI to the mapping and causal analysis of development, broadly defined. Drawing on expertise in causal inference, computer vision, statistics, political economy, and machine learning, each of our sites brings together researchers and engineers - [Tools](https://aidevlab.org/visualizations/) - Interactive tools of AI-driven insights on satellite data, causal methods, and ground truth validation. To learn more about the code powering these visualizations, follow us on GitHub or Hugging Face. We thank Chris Li for great work in helping build out our visualization infrastructure! - Team Members on GitHub adasgupta04 @adasgupta04 Adel Daoud @adeldaoud Amir - [Research](https://aidevlab.org/research/) - The AI & Global Development Lab’s research portfolio contains studies that apply cutting‑edge artificial intelligence, machine learning, and Earth observation to pressing social and economic problems. Recent papers tackle tasks such as debiasing machine‑learning predictions for causal inference and poverty analysis using satellite imagery, optimizing multi‑scale representations to detect effect heterogeneity, and providing a scoping - [Platonic Poverty Mapping](https://aidevlab.org/platonic/) - Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty? [PDF] [Video] [Data] [.bib] Authors: Satiyabooshan Murugaboopathy | Connor T. Jerzak | Adel Daoud TL;DR: What this poverty mapping study shows We combine satellite imagery with AI-generated text to predict household wealth across more than 60,000 African neighborhoods, using the International Wealth Index (IWI) - [Transcript: Platonic Poverty Mapping](https://aidevlab.org/transcript-platonic/) - >>>Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty? (@ICSC) [PDF] [Video] [Data] [.bib] Authors: Satiyabooshan Murugaboopathy | Connor T. Jerzak | Adel Daoud The research addresses the limitations of traditional poverty surveys, which are often costly and infrequent. The proposed solution involves fusing satellite imagery with text generated by Large Language Models - [Bibliography](https://aidevlab.org/bibliography/) - This bibliography catalogs the 40+ published articles, books, conference papers, and patents of the AI & Global Development Lab. Key research domains include planetary causal inference, satellite measurement of social phenomena, measurement error debiasing, and disaster impact evaluation. See also [Research] for more information. - [Data](https://aidevlab.org/data/) - This page hosts some of curated datasets that power our workflows. See our Hugging Face profile for more information. See also [Leaderboard]. Data for: Temporal Neighborhood-level Material Wealth Maps of Africa (1990-2019)Description: The data product consists of continent-wide maps of material-asset wealth across Africa from 1990-2019, created by using multi-temporal satellite imagery at the neighborhood - [Guest Lecture: Best Practices for Cloud-Native GeoAI (Isaac Corley)](https://aidevlab.org/cloud-geo-ai/) - Speaker: Isaac Corley Transcript: I’m Isaac. I just joined as Director of AI at Taylor Geospatial. We’re a nonprofit that pushes geospatial projects from research into production. We identified a huge gap in the geospatial industry: academics publish papers and prototypes, but they often disappear into publications and conferences, while industry teams are trying to - [Chinese vs. World Bank Development Projects](https://aidevlab.org/china-vs-wb-cv/) - Chinese vs. World Bank Development Projects: Insights from Earth Observation and Computer Vision on Wealth Gains in Africa, 2002-2013 Chinese vs. World Bank Development Projects Leverages computer vision on satellite imagery to impute wealth outcomes and control for confounding variables, enabling a continent-scale evaluation of development programs across 9,899 neighborhoods in 36 African countries and - [Interview - Satiyabooshan Murugaboopathy](https://aidevlab.org/interview-satiya/) - Today, we sit down with Satiya Murugaboopathy-- incoming research engineer in the AI & Global Development Lab, for a conversation about AI, the study of poverty at global scale, social-computer science synergies, long-term AI trends, and more. Background and first project Listen 13:23 Interviewer: Alright—let’s rapid fire. Satiya, can you tell me a little bit - [Gallery](https://aidevlab.org/gallery/) - Explore our visual archive of maps and figures combining satellite imagery, machine learning, and causal inference to study development worldwide. Each item links to the underlying paper, data, and code—making it easy to understand, reproduce, and build on the work. Explore this gallery to see how AI, remote sensing and causal inference come together to - [Partners](https://aidevlab.org/partners/) - We have maintained partnerships and collaborations with stakeholders from: Linköping University, Chalmers University of Technology, Chalmers Ventures, Harvard University, University of Texas, Triathlon Group, UNICEF, among others. - [RESEARCH](https://aidevlab.org/research-2/) - [](https://aidevlab.org/rankings/) - How Have Living Conditions Changed Across African Provinces from 1990 to 2019? Between 1990–1992 and 2017–2019, average living conditions improved in about 96% of the 855 first-level administrative regions (states/provinces) across Africa, based on the International Wealth Index (IWI). This page summarizes where progress has been fastest, where it has stalled, and how the underlying - [Funding & Support](https://aidevlab.org/support/) - The AI & Global Development Lab advances a planetary-scale, causal atlas of human development by fusing Earth-observation imagery, machine learning, and rigorous inference to map poverty dynamics and evaluate policy impacts across time and space. Our work is made possible by competitive, peer-reviewed support. [8] Swedish National Space Agency (SNSA) Research Grant (2025, 6.5 million - [CausalImages](https://aidevlab.org/code/) - To learn more about the code powering our lab, follow us on GitHub or Hugging Face. - causalimages: This package enables causal inference with image and image-sequence data—spanning Earth observation, biomedical, and social-science imagery—by turning pixels into estimands. It provides tools for image-based treatment-effect heterogeneity and image-based deconfounding, plus utilities for producing embeddings and efficiently - [Positions](https://aidevlab.org/positions/) - This page contains information about currently or recently open positions within the AI & Global Development Lab. Reach out to Adel (adel.daoud@liu.se) or Connor (connor.jerzak@austin.utexas.edu) for information about upcoming opportunities. For more information about our lab research, please see: aidevlab.org/research. Recent Job Postings [3.] Research Assistant in the AI & Global Development Lab Posted: Autumn - [Video Library](https://aidevlab.org/videos/) - Welcome to the AI for Global Development Lab's Video Library, where we share talks, demos, and tutorials on applying machine learning to global development challenges. [AI & Global Development Lab YouTube][Planetary Causal Inference YouTube][Transcripts] - - - - - - - - - - [Transcript - AI & Global Development - Harvard Astrostatistics](https://aidevlab.org/transcript-ai-global-dev-lab-harvard-astrostatistics/) - Speaker: Adel Daoud -Transcript- Organizer: Adel and I started talking to each other, and I began to learn about his work on global poverty, which you will see a great deal of today. However, the basic idea—without stealing his thunder—is that he was essentially using deep learning algorithms to connect satellite image data with ground - [](https://liu.aidevlab.org/) - Institution: Institute for Analytical Sociology at Linköping University Note for partners: The institutional indirect cost rate for the Institute for Analytical Sociology (IAS) at Linköping University, as applied to activities stemming from Swedish Research Council grants, is 24%. The rate 24% applies for and is decided by the whole department, Department of Management and Engineering, - [Test](https://aidevlab.org/test/) - Testing new features and visualization tools. For feedback, send a message to connor.jerzak@austin.utexas.edu. ## Categories - [Uncategorized](https://aidevlab.org/category/uncategorized/)