Projecting armed conflict risk in Africa towards 2050 along the SSP-RCP scenarios: a machine learning approach
نویسندگان
چکیده
Abstract In the past decade, several efforts have been made to project armed conflict risk into future. This study broadens current approaches by presenting a first-of-its-kind application of machine learning (ML) methods sub-national over African continent along three Shared Socioeconomic Pathway (SSP) scenarios and Representative Concentration Pathways towards 2050. Results open-source ML framework CoPro are consistent with underlying socioeconomic storylines SSPs, resulting out-of-sample projections obtained Random Forest classifiers agree patterns observed in comparable studies. SSP1-RCP2.6, is low most regions although Horn Africa parts East continue be conflict-prone. Conflict increases more adverse SSP3-RCP6.0 scenario, especially Central large Western Africa. We specifically assessed role hydro-climatic indicators as drivers conflict. Overall, their importance limited compared main predictors but results suggest that changing climatic conditions may both increase decrease risk, depending on location: Northern Eastern climate change projected whereas for areas West northern part Sahel shifting reduce risk. With our being at forefront applications projections, we identify various challenges this arising scientific field. A major concern selection relevant quantified SSPs present. Nevertheless, models such one presented here viable scalable way forward field can help inform policy-making process respect security.
منابع مشابه
Predicting Armed Conflict, 2010–2050∗
The paper predicts changes in global and regional incidences of armed conflict for the 2010–2050 period. The predictions are based on a dynamic multinomial logit model estimation on a 1970–2009 cross-sectional dataset of changes between no armed conflict, minor conflict, and major conflict. Core exogenous predictors are population size, infant mortality rates, demographic composition, education...
متن کاملAutomatic Vandalism Detection in Wikipedia: Towards a Machine Learning Approach
Since the end of 2006 several autonomous bots are, or have been, running on Wikipedia to keep the encyclopedia free from vandalism and other damaging edits. These expert systems, however, are far from optimal and should be improved to relieve the human editors from the burden of manually reverting such edits. We investigate the possibility of using machine learning techniques to build an autono...
متن کاملthe relationship between language and social capital in ilami kurdish: a sociopragmatic approach
چکیده زبان به عنوان یک وسیله در ایجاد و بازسازی سرمایه اجتماعی در چند دهه گذشته مورد توجه بوده است. اگر چه درباره سرمایه اجتماعی و سازه های مربوط به آن زیاد نوشته شده است ولی خیلی کم بر روی اینکه چطور زبان می تواند باعث ایجاد اعتماد یا بی اعتمادی بشود مطالعه ای انجام شده است. این مطالعه به منظور تحقق دو هدف انجام گرفته است. اول تلاش خواهد شد تا یک گونه شناسی از واژگانی که مردم کرد زبان شهر ا...
15 صفحه اولDebt Collection Industry: Machine Learning Approach
Businesses are increasingly interested in how big data, artificial intelligence, machine learning, and predictive analytics can be used to increase revenue, lower costs, and improve their business processes. In this paper, we describe how we have developed a data-driven machine learning method to optimize the collection process for a debt collection agency. Precisely speaking, we create a frame...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Environmental Research Letters
سال: 2021
ISSN: ['1748-9326']
DOI: https://doi.org/10.1088/1748-9326/ac3db2