AI for an equitable, and inclusive world
Leveraging a decade of experience and expertise in geospatial analysis and sustainable development
Overview
Artificial intelligence (AI) and machine learning (ML) are transforming how data gaps are filled in developing regions, generating fine-scale estimates of poverty, health, and living conditions from satellite imagery and other big data sources. Yet these tools risk introducing new biases, including gender-related distortions that may more accurately capture men’s conditions than women’s. AidData has pioneered research on gender bias in AI-driven poverty prediction and is expanding this work to other domains—such as population health—to identify, explain, and correct these disparities.
At the same time, the growing use of AI and satellite imagery to monitor agricultural supply chains offers both promise and peril. Under regulations like the EU Deforestation Regulation (EUDR), smallholders must prove that their plots are deforestation-free, yet many AI-powered compliance tools function as costly black boxes. AidData brings over a decade of technical expertise to independently validate these tools, with pilot projects in Honduras and Ethiopia helping farmers, regulators, and exporters make informed decisions.
Through initiatives like GeoField, AidData also addresses bottlenecks in geospatial impact evaluations by integrating drone technologies and field protocols to generate high-quality training data efficiently. Finally, AidData seeks to democratize satellite-based insights—returning data to farmers and marginalized groups—so that those most affected by these technologies can use them to improve livelihoods, resilience, and environmental sustainability.
Accessible Geospatial Insights Using LLMs
We're piloting ways to extend the benefits of geospatial analysis and insights to a far greater audience
Artificial Intelligence (AI) and Large Language Models (LLMs) are driving transformative changes in the agriculture sector around the world. While there is a clear investment in AI by major commercial farming operations in the U.S., only a handful of efforts have focused on developing countries that have explored addressing small holder farming needs through LLMs and chat bots.
AidData is uniquely situated to fill a critical gap when it comes to the use of geospatial data in low- and middle-income countries, building on over a decade of experience developing accessible geospatial data platforms like GeoQuery, leveraging cutting edge AI tools for real world applications, and championing the use of Geospatial Impact Evaluations around the world.
The use of machine learning or artificial intelligence with geospatial data — referred to as GeoAI — has largely required specialized knowledge and computational resources. GeoAI is often focused on computer vision tasks leveraging satellite imagery such as object detection (trees, buildings, vehicles, etc.) or land cover classification that are not only complex to build and run, but are typically designed with a unique application in mind. The result is that while GeoAI can be immensely powerful, its use is limited to researchers and industry specialists capable of working with big data to train and refine models.
Rather than attempting to develop and train AI tools to actually understand raw geospatial data, the use of structured semantic data in a non-spatial format can leverage the growing reasoning capacity of LLMs to explore spatial relationships. By making geospatial data and analysis available via LLMs, it is possible to provide the benefits of geospatial analysis and insights to a far greater audience than previously feasible.
The combination of the broad reasoning capabilities of modern LLMs and advances in RAG and Agentic frameworks provide the potential for versatile AI applications to serve project specific needs. By incorporating geospatial information without expensive computational requirements, these LLM driven applications can become an invaluable resource. AidData aims to put the power of these tools in the hands of local personnel supporting smallholder farmers and related groups where it can make a true difference by addressing critical needs in farming communities.
Learn how AidData is making geospatial analysis accessible through LLMs.
Case Studies
How can we better evaluate gender bias in AI applications using survey data?
We're working to increase transparency and accountability in AI for global development
In partnership with Ghana Center for Democratic Development (CDD-Ghana), AidData has worked to evaluate the potential for gender bias in wealth estimates generated using artificial intelligence (AI). We're leveraging AidData’s expertise in artificial intelligence, geospatial data, and household surveys plus CDD-Ghana’s knowledge of the local context and environments to produce a novel public good to inform discussions on the growing use of AI in development.
Funded through USAID’s Equitable AI Challenge and implemented through DAI’s Digital Frontiers agreement with USAID, our project approaches a critical problem: increase the accountability and transparency of AI systems used in global development contexts.
Online Migration Research Platform
AidData is developing a one-stop-shop to advance migration scholarship, policymaking, and practice.
As migration research rapidly expands across diverse disciplines, keeping abreast of current data, methods, and findings becomes increasingly challenging.
AidData, in collaboration with Aptima, is filling the gap with an innovative online migration research platform designed to centralize resources and facilitate scholarly collaboration. The platform's development was informed by a survey of nearly 2,000 migration researchers worldwide.
Leveraging advanced AI, including large language models, the platform will offer curated access to migration data, methodologies, literature, and networking opportunities, built upon AidData’s GeoQuery system.
Planned features include:
- a centralized data and methods portal
- curated migration datasets with metadata
- an AI-enabled literature navigator
- collaborative tools for interdisciplinary researchers
- training modules
- how-to guides for students and early-career scholars
Nigeria
Providing a low-cost solution to predict the likelihood of deadly conflict
Case Study
Uncertainty limits the humanitarian response in areas with known conflicts. AidData is working to improve how existing data can be used to train convolutional neural networks that make more accurate predictions of the likelihood of a death due to conflict at a given location. To make these estimates, the algorithm analyzes landscape features detected from moderate-resolution satellite imagery the previous year. Using Nigeria as a case study, this algorithm achieves approximately 80% classification accuracy when predicting whether a location with a known conflict in 2015, 2017, 2019 was fatal based on previous year's satellite imagery, at either yearly or six month intervals.
Read the research
Download the data and technical report
Ghana
Improving the sophistication of poverty estimates
Case Study
All data sources have limitations. When it comes to measuring poverty, surveys are expensive, limited to small sample sizes, and available only for certain geographic points in certain years. Proxies for poverty such as nighttime lights are imperfect and often struggle to accurately measure populations most in need. AidData is expanding upon methods pioneered by Stanford researchers to overcome these challenges and produce next-gen measures of poverty by leveraging machine learning.
To better estimate the economic impact of improved market access from an MCC program in Ghana, AidData utilized DHS surveys and Landsat 7 satellite data along with convolutional neural networks to provides more accurate estimates of changes in average household wealth. The resulting estimates were used to compare changes in poverty over time between regions around road improvement projects and control locations that were not near improved roads.
Download the data (beta)
Featured Reports
Research Team
For technical or research inquires, contact:
For partnership and media inquiries, contact:
Alex Wooley
Director of Partnerships and Communications