Our mission
The QuaRCS Network promotes interdisciplinary science to foster economic, social, and environmental sustainability.
The QuaRCS Network is an international and interdisciplinary research network in Quantitative Regional and Computational Science. We integrate insights from spatial data science, machine learning, and development economics to understand and inform the process of sustainable development across subnational regions and countries. Our focus spans the economic, social, and environmental dimensions of sustainable development.
The QuaRCS Network is part of the UN Sustainable Development Solutions Network (SDSN). Together, we mobilize scientific knowledge and innovation to promote sustainable development worldwide.
Five connected research lines advancing the economic, social, and environmental dimensions of sustainable development.
Integrate satellite remote sensing, spatial econometrics, and machine learning to evaluate local progress toward the Sustainable Development Goals (SDGs), quantify environmental trade-offs, and model regional resilience.
Harness Earth observation data to map subnational wealth and health globally. This approach proxies economic activity, tracks poverty dynamics, and reveals spatial inequality in data-scarce regions.
Apply econometrics and machine learning to analyze regional income convergence, identify persistent spatial poverty traps, and measure the impact of economic spillovers across national and subnational borders.
Model how localized sectoral shifts and labor productivity improvements drive regional development. This includes detecting economic clusters and mapping their evolutionary dynamics.
Quantify the spatial disparities of energy poverty and electricity access while mapping the localized socio-economic impacts of the transition to a low-carbon economy.
Geospatial big data, spatial econometrics, causal inference, and machine learning for the quantitative geography of sustainable development.
Large-scale spatial data — satellite imagery, nighttime lights, and remote sensing — processed in reproducible workflows to measure development from space.
Exploratory spatial and space-time analysis of dependence, clustering, and regional heterogeneity.
Machine-learning methods that estimate causal effects and heterogeneous treatment responses, not just prediction.
Identifying cause and effect across regions — accounting for spatial spillovers, interference, and confounding to estimate credible policy impacts.
Machine-learning models that embed spatial structure and autocorrelation to predict and explain outcomes across regions.
