geoLab: 2021 Annual Report Permalink
Our annual report for the year 2021.
Themes
Security
Predicting road quality using high resolution satellite imagery: A transfer learning approach Permalink
In this paper, we present a test of the use of transfer learning in convolutional neural networks in conjunction with high resolution satellite imagery of ro...
China’s BRI in Latin America: Case Study – Hydropower in Ecuador Permalink
This Tearline article discusses findings from a project which utilizes open-source data collection and imagery analysis to study the impacts of Chinese devel...
Hydropower in Bolivia - Monitoring Chinese Activities from Space Permalink
This Tearline article examines evidence of six Chinese BRI hydroelectric power projects in Bolivia.
geoLab: 2020 Annual Report Permalink
Our annual report for the year 2020.
Caroline Morin explores research passion through geoParsing, publishes papers on Chinese development financing
Multiple articles using high resolution satellite imagery to track Chinese activities.
Recently funded roadRunner project launches competition to build best convolution neural network
Six-university collaboration on estimating road quality from space.
Monitoring Sustainable Energy in Cuba with High Resolution Satellite Imagery Permalink
The article uses the Chinese financing of sustainable energy projects in Cuba as a case study, analyzing why energy projects have been sustainable in Cuba an...
Using Ultra-high Resolution Satellite Imagery to Monitor China’s BRI in Latin America: Ports Permalink
Across seven BRI port projects in Central America and the Caribbean, we find evidence that the project partnerships between China and recipient countries var...
A convolutional neural network approach to predict non-permissive environments from moderate-resolution imagery Permalink
This article explores a CNN-based approach leveraging Landsat 8 imagery to predict locations of conflict-related deaths.
The Global Administrative Database: Accurate, open-source guide to subnational borders
An introduction to the geoBoundaries dataset.
geoLab: 2019 Annual Report Permalink
Our annual report for the year 2019.
Satellite Data Poisoning Project (SDPP)
As the volume of satellite imagery has increased, so too has our need to use machine learning models to mine that data for meainingful, decision-relevant inf...
Migration and Machine Learning (MML) Project
Core Contribution - Improving our understanding of the highly non-linear impact of climate on human migratory decisions across multiple countries in Latin Am...
geoInt
The geoInt project focuses on better understanding the evolution of international actors programs using high resolution satellite imagery. Through qualitati...
Deep Learning for Satellite Imagery (DL4SAT)
Deep learning techniques have revolutionized a number of fields, predominantly based on research from the computer vision community. The vast majority of li...
Sustainability
Using Satellite Data and Deep Learning to Estimate Educational Outcomes in Data Sparse Environments. Permalink
In this article, we present a case study estimating school test scores based solely on publicly available imagery in both the Philippines (2010, 2014) and Br...
Toponym-assisted map georeferencing: Evaluating the use of toponyms for the digitization of map collections Permalink
This paper introduces a fully automated method based on map toponym (place name) labels. It is the first study to demonstrate these methods across a wide ran...
geoLab: 2021 Annual Report Permalink
Our annual report for the year 2021.
Predicting road quality using high resolution satellite imagery: A transfer learning approach Permalink
In this paper, we present a test of the use of transfer learning in convolutional neural networks in conjunction with high resolution satellite imagery of ro...
geoLab students research COVID-19’s impacts on biodiversity through internships with the Global Environment Facility
Studying health outcomes related to environmental interventions.
geoLab: 2020 Annual Report Permalink
Our annual report for the year 2020.
The Global Administrative Database: Accurate, open-source guide to subnational borders
An introduction to the geoBoundaries dataset.
The Use of Remote Sensing Analysis for Evaluating the Impact of Development Projects in the Yellow Sea Large Marine Ecosystem Permalink
his study uses remote sensing ocean color products to evaluate the impact on reducing marine pollution of the Global Environment Facility’s (GEF) portfolio o...
Evaluating the Impact of Environmental Interventions during a Global Quarantine Permalink
In this brief overview of an article recently published in the journal Sustainability, we showcase one way we’re engaged with continuing operations while und...
Exploring the Socioeconomic Co-benefits of Global Environment Facility Projects in Uganda Using a Quasi-Experimental Geospatial Interpolation (QGI) Approach Permalink
Leveraging a novel database on the geographic location of GEF project interventions in Uganda, this paper explores the impact of GEF projects on household as...
geoLab: 2019 Annual Report Permalink
Our annual report for the year 2019.
Value for Money Analysis of GEF Interventions in Support of Sustainable Forest Management Permalink
This study is the first Value for Money analysis undertaken by the IEO to assess the impact and global environmental benefits of GEF investments and technica...
Migration and Machine Learning (MML) Project
Core Contribution - Improving our understanding of the highly non-linear impact of climate on human migratory decisions across multiple countries in Latin Am...
Global Education Observatory
The Global Education Observatory focuses on collecting, disseminating, and imputing information about school test scores in underserved environments. Our st...
Climate Intervention Effectiveness Programme (CIEP)
The Climate Intervention Effectiveness Programme conducts analyses (and collects data) to help better inform global climate change mitigation efforts. CIEP ...
Vibrancy
geoBoundaries 4.0 Release
The fourth iteration of our original dataset.
Using Satellite Data and Deep Learning to Estimate Educational Outcomes in Data Sparse Environments. Permalink
In this article, we present a case study estimating school test scores based solely on publicly available imagery in both the Philippines (2010, 2014) and Br...
Toponym-assisted map georeferencing: Evaluating the use of toponyms for the digitization of map collections Permalink
This paper introduces a fully automated method based on map toponym (place name) labels. It is the first study to demonstrate these methods across a wide ran...
geoLab: 2021 Annual Report Permalink
Our annual report for the year 2021.
geoLab: 2020 Annual Report Permalink
Our annual report for the year 2020.
The Global Administrative Database: Accurate, open-source guide to subnational borders
An introduction to the geoBoundaries dataset.
geoBoundaries: A global database of political administrative boundaries. Permalink
We present the geoBoundaries Global Administrative Database (geoBoundaries): an online, open license resource of the geographic boundaries of political admin...
geoLab: 2019 Annual Report Permalink
Our annual report for the year 2019.
geoLab: Students use satellites & AI to make a better world
A brief origin story of the geoLab.
Global Education Observatory
The Global Education Observatory focuses on collecting, disseminating, and imputing information about school test scores in underserved environments. Our st...
What’s New in HPC Research: Thrill for Big Data, Scaling Resilience and More Permalink
Highlight of the geoQuery data platform by HPCWire.
geoBoundaries
Produced and maintained by the William & Mary geoLab since 2017, the geoBoundaries Global Database of Political Administrative Boundaries Database is an ...
geoFellows
The geoFellows program has three core goals, focused on increasing the diversity of leaders in the computational sciences:
Deep Learning for Satellite Imagery (DL4SAT)
Deep learning techniques have revolutionized a number of fields, predominantly based on research from the computer vision community. The vast majority of li...