In this project, funded by an ERC Starting Grant, I investigate why agricultural productivity is especially low in developing countries and how this affects the dynamics of structural transformation and development. To provide answers to these questions, I combine novel micro panel data from Sub-Saharan Africa and Southeast Asia with an array of geospatial data on rural areas and quantitative theoretical models for structural analysis.

I focus particularly on rural areas of developing countries that typically host large shares of the population, face increasing agricultural risk from climate change and exhibit elevated poverty incidence. Answering these questions is thus crucial for poverty reduction and helps determining whether, and if yes how, policy makers should pursue policies that encourage movement of the workforce out of agriculture.

My attention focuses on three dimensions that could explain persistent agricultural productivity gaps in developing countries: (i) dynamic farm adjustments and factor misallocation; (ii) labor reallocation and domestic migration; and (iii) the impact of climate change in the presence of barriers to adaptation.

Press statements: UAB, BSE, FECYT

The MONWADES project aims to develop an automated system for assessing war-related destruction using high-resolution satellite imagery and machine learning. Current methods, which rely on manual detection and eyewitness reports, are often slow, expensive, and prone to bias. By integrating computer vision and deep learning techniques, MONWADES seeks to provide a more efficient, accurate, and cost-effective solution for damage assessment, in different conflict zones around the globe.