<p>Rural migration responses to drought are complex, context specific, and multi-directional. Migration is one of many possible adaptive responses to drought, and is typically initiated only after other, less disruptive strategies have been attempted. The potential for drought to stimulate migration or displacement is inversely related to the range of alternative adaptation options available to households, and is lowered through coordinated vulnerability-reduction mechanisms such as institutional water-management regimes and crop insurance programs. When drought-related migration does occur, it tends to flow along pre-existing social networks to known destinations, which are usually urban centres within the same state/country or in contiguous ones. Using a mixed-methods approach that combines geospatial tools, quantitative methods (i.e. random forest and spatial regression) and qualitative data gathered through archival research and local interviews, we have generated detailed models of the changing influence over time of drought on rural population patterns on the North American Great Plains. In this presentation we highlight key findings from our work, describe data needs and limitations, discuss the predictive power of various quantitative methods, identify non-climatic variables that mediate migration outcomes, and emphasize the importance of mixed-methods approaches.</p>
Machine learning techniques have to date not been widely used in population-environment research, but represent a promising tool for identifying relationships between environmental variables and population outcomes. They may be particularly useful for instances where the nature of the relationship is not obvious or not easily detected using other methods, or where the relationship potentially varies across spatial scales within a given study unit. Machine learning techniques may also help the researcher identify the relative strength of influence of specific variables within a larger set of interacting ones, and so provide a useful methodological approach for exploratory research. In this study, we use machine learning techniques in the form of random forest and regression tree analyses to look for possible connections between drought and rural population loss on the North American Great Plains between 1970 and 2020. In doing so, we analyzed four decades of population count data (at county-size spatial scales), monthly climate data, and Palmer Drought Severity Index scores for Canada and the USA at multiple spatial scales (regional, sub-regional, national, and county/census division levels), along with county level irrigation data. We found that in some parts of Saskatchewan and the Dakotas − particularly those areas that fall within more temperate/less arid ecological sub-regions − drought conditions in the middle years of the 1970s had a significant association with rural population losses. A similar but weaker association was identified in a small cluster of North Dakota counties in the 1990s. Our models detected few links between drought and rural population loss in other decades or in other parts of the Great Plains. Based on R-squared results, models for US portions of the Plains generally exhibited stronger drought-population loss associations than did Canadian portions, and temperate ecological sub-regions exhibited stronger associations than did more arid sub-regions. Irrigation rates showed no significant influence on population loss. This article focuses on describing the methodological steps, considerations, and benefits of employing this type of machine learning approach to investigating connections between drought and rural population change. Supplementary Information The online version contains supplementary material available at 10.1007/s11111-022-00399-9.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.