粮食安全分析和预测:马拉维南部的机器学习案例研究

IF 1.8 Q3 PUBLIC ADMINISTRATION Data & policy Pub Date : 2022-10-11 DOI:10.1017/dap.2022.25
Shahrzad Gholami, Erwin Knippenberg, James Campbell, Daniel Andriantsimba, Anusheel Kamle, Pavitraa Parthasarathy, Ria Sankar, Cameron Birge, J. L. Lavista Ferres
{"title":"粮食安全分析和预测:马拉维南部的机器学习案例研究","authors":"Shahrzad Gholami, Erwin Knippenberg, James Campbell, Daniel Andriantsimba, Anusheel Kamle, Pavitraa Parthasarathy, Ria Sankar, Cameron Birge, J. L. Lavista Ferres","doi":"10.1017/dap.2022.25","DOIUrl":null,"url":null,"abstract":"Abstract Chronic food insecurity remains a challenge globally, exacerbated by climate change-driven shocks such as droughts and floods. Forecasting food insecurity levels and targeting vulnerable households is apriority for humanitarian programming to ensure timely delivery of assistance. In this study, we propose to harness a machine learning approach trained on high-frequency household survey data to infer the predictors of food insecurity and forecast household level outcomes in near real-time. Our empirical analyses leverage the Measurement Indicators for Resilience Analysis (MIRA) data collection protocol implemented by Catholic Relief Services (CRS) in southern Malawi, a series of sentinel sites collecting household data monthly. When focusing on predictors of community-level vulnerability, we show that a random forest model outperforms other algorithms and that location and self-reported welfare are the best predictors of food insecurity. We also show performance results across several neural networks and classical models for various data modeling scenarios to forecast food security. We pose that problem as binary classification via dichotomization of the food security score based on two different thresholds, which results in two different positive class to negative class ratios. Our best performing model has an F1 of 81% and an accuracy of 83% in predicting food security outcomes when the outcome is dichotomized based on threshold 16 and predictor features consist of historical food security score along with 20 variables selected by artificial intelligence explainability frameworks. These results showcase the value of combining high-frequency sentinel site data with machine learning algorithms to predict future food insecurity outcomes.","PeriodicalId":93427,"journal":{"name":"Data & policy","volume":" ","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Food security analysis and forecasting: A machine learning case study in southern Malawi\",\"authors\":\"Shahrzad Gholami, Erwin Knippenberg, James Campbell, Daniel Andriantsimba, Anusheel Kamle, Pavitraa Parthasarathy, Ria Sankar, Cameron Birge, J. L. Lavista Ferres\",\"doi\":\"10.1017/dap.2022.25\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Chronic food insecurity remains a challenge globally, exacerbated by climate change-driven shocks such as droughts and floods. Forecasting food insecurity levels and targeting vulnerable households is apriority for humanitarian programming to ensure timely delivery of assistance. In this study, we propose to harness a machine learning approach trained on high-frequency household survey data to infer the predictors of food insecurity and forecast household level outcomes in near real-time. Our empirical analyses leverage the Measurement Indicators for Resilience Analysis (MIRA) data collection protocol implemented by Catholic Relief Services (CRS) in southern Malawi, a series of sentinel sites collecting household data monthly. When focusing on predictors of community-level vulnerability, we show that a random forest model outperforms other algorithms and that location and self-reported welfare are the best predictors of food insecurity. We also show performance results across several neural networks and classical models for various data modeling scenarios to forecast food security. We pose that problem as binary classification via dichotomization of the food security score based on two different thresholds, which results in two different positive class to negative class ratios. Our best performing model has an F1 of 81% and an accuracy of 83% in predicting food security outcomes when the outcome is dichotomized based on threshold 16 and predictor features consist of historical food security score along with 20 variables selected by artificial intelligence explainability frameworks. These results showcase the value of combining high-frequency sentinel site data with machine learning algorithms to predict future food insecurity outcomes.\",\"PeriodicalId\":93427,\"journal\":{\"name\":\"Data & policy\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2022-10-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Data & policy\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1017/dap.2022.25\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"PUBLIC ADMINISTRATION\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Data & policy","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1017/dap.2022.25","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"PUBLIC ADMINISTRATION","Score":null,"Total":0}
引用次数: 2

摘要

摘要长期粮食不安全仍然是全球面临的挑战,干旱和洪水等气候变化引发的冲击加剧了这一挑战。预测粮食不安全程度并以弱势家庭为目标,是制定人道主义方案以确保及时提供援助的先决条件。在这项研究中,我们建议利用基于高频家庭调查数据的机器学习方法来推断粮食不安全的预测因素,并近乎实时地预测家庭层面的结果。我们的实证分析利用了马拉维南部天主教救济服务机构(CRS)实施的韧性分析测量指标(MIRA)数据收集协议,该协议是一系列每月收集家庭数据的哨点。在关注社区层面脆弱性的预测因素时,我们发现随机森林模型优于其他算法,位置和自我报告的福利是粮食不安全的最佳预测因素。我们还展示了几种神经网络和各种数据建模场景的经典模型的性能结果,以预测粮食安全。我们通过基于两个不同阈值的粮食安全评分的二分法将该问题提出为二元分类,这导致了两个不同的正类与负类比率。当基于阈值16对结果进行二分时,我们的最佳表现模型在预测粮食安全结果方面的F1为81%,准确率为83%,预测特征包括历史粮食安全得分以及人工智能可解释性框架选择的20个变量。这些结果展示了将高频哨点数据与机器学习算法相结合来预测未来粮食不安全结果的价值。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Food security analysis and forecasting: A machine learning case study in southern Malawi
Abstract Chronic food insecurity remains a challenge globally, exacerbated by climate change-driven shocks such as droughts and floods. Forecasting food insecurity levels and targeting vulnerable households is apriority for humanitarian programming to ensure timely delivery of assistance. In this study, we propose to harness a machine learning approach trained on high-frequency household survey data to infer the predictors of food insecurity and forecast household level outcomes in near real-time. Our empirical analyses leverage the Measurement Indicators for Resilience Analysis (MIRA) data collection protocol implemented by Catholic Relief Services (CRS) in southern Malawi, a series of sentinel sites collecting household data monthly. When focusing on predictors of community-level vulnerability, we show that a random forest model outperforms other algorithms and that location and self-reported welfare are the best predictors of food insecurity. We also show performance results across several neural networks and classical models for various data modeling scenarios to forecast food security. We pose that problem as binary classification via dichotomization of the food security score based on two different thresholds, which results in two different positive class to negative class ratios. Our best performing model has an F1 of 81% and an accuracy of 83% in predicting food security outcomes when the outcome is dichotomized based on threshold 16 and predictor features consist of historical food security score along with 20 variables selected by artificial intelligence explainability frameworks. These results showcase the value of combining high-frequency sentinel site data with machine learning algorithms to predict future food insecurity outcomes.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
3.10
自引率
0.00%
发文量
0
审稿时长
12 weeks
期刊最新文献
Determinants for university students’ location data sharing with public institutions during COVID-19: The Italian case Bus Rapid Transit: End of trend in Latin America? Accelerating and enhancing the generation of socioeconomic data to inform forced displacement policy and response “That is why users do not understand the maps we make for them”: Cartographic gaps between experts and domestic workers and the Right to the City Analysis of spatial–temporal validation patterns in Fortaleza’s public transport systems: a data mining approach
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1