Scenario projections of South Asian migration patterns amidst environmental and socioeconomic change

Datos Bibliográficos

ID12262147
AutoresSophie de Bruin (0000-0003-3429-349X, Vrije Universiteit Amsterdam, autor de correspondencia), Jeffrey Hoch (0000-0003-3570-6436, At Bristol), Jens de Bruijn (0000-0003-3961-6382, International Institute for Applied Systems Analysis), Kathleen Hermans (0000-0002-8475-9019, Leibniz Institute of Agricultural Development in Transition Economies), Amina Maharjan (0000-0003-4002-3242, International Centre for Integrated Mountain Development), Matti Kummu (0000-0001-5096-0163, Aalto University), Jasper van Vliet (0000-0002-3996-5278, Vrije Universiteit Amsterdam)
Año2024
Volumen88
Páginas102920-102920
Fecha de publicación2024-09-01
Open AccessSí
TipoARTICLE
RevistaGlobal Environmental Change (JOURNAL)
Identificadores de la revistaISSN: 0959-3780 • E-ISSN: 1872-9495
EditorialElsevier BV (PUBLISHER)
DOI10.1016/j.gloenvcha.2024.102920
OpenAlexW4402119375
IdiomaEN
Referencias citadas69

Projecting migration is challenging, due to the context-specific and discontinuous relations between migration and the socioeconomic and environmental conditions that drive this process. Here, we investigate the usefulness of Machine Learning (ML) Random Forest (RF) models to develop three net migration scenarios in South Asia by 2050 based on historical patterns (2001–2019). The model for the direction of net migration reaches an accuracy of 75%, while the model for the magnitude of migration in percentage reaches an R2 value of 0.44. The variable importance is similar for both models: temperature and built-up land are of primary importance for explaining net migration, aligning with previous research. In all scenarios we find hotspots of in-migration North-western India and hotspots of out-migration in eastern and northern India, parts of Nepal and Sri Lanka, but with disparities across scenarios in other areas. These disparities underscore the challenge of obtaining consistent results from different approaches, which complicates drawing firm conclusions about future migration trajectories. We argue that the application of multi-model approaches is a useful avenue to project future migration dynamics, and to gain insights into the uncertainty and range of plausible outcomes of these processes

Climate change · Context (archaeology · Economic geography · Environmental change · Environmental planning · Geography · Human migration · Net migration rate · Population · Population growth · Range (aeronautics · Socioeconomic status · Sociology · Sri lanka · Variable (mathematics · Climate Change, Adaptation, Migration · Demography · Engineering · Migration and Labor Dynamics · Migration, Aging, and Tourism Studies · Ecology