Tim Busker, Bart van den Hurk, Hans de Moel, Marc van den Homberg, Chiem van Straaten, Rhoda A. Odongo, Jeroen C. J. H. Aerts
{"title":"利用机器学习预测非洲之角的粮食安全危机","authors":"Tim Busker, Bart van den Hurk, Hans de Moel, Marc van den Homberg, Chiem van Straaten, Rhoda A. Odongo, Jeroen C. J. H. Aerts","doi":"10.1029/2023EF004211","DOIUrl":null,"url":null,"abstract":"<p>In this study, we present a machine-learning model capable of predicting food insecurity in the Horn of Africa, which is one of the most vulnerable regions worldwide. The region has frequently been affected by severe droughts and food crises over the last several decades, which will likely increase in future. Therefore, exploring novel methods of increasing early warning capabilities is of vital importance to reducing food-insecurity risk. We present a XGBoost machine-learning model to predict food-security crises up to 12 months in advance. We used >20 data sets and the FEWS IPC current-situation estimates to train the machine-learning model. Food-security dynamics were captured effectively by the model up to 3 months in advance (<i>R</i><sup>2</sup> > 0.6). Specifically, we predicted 20% of crisis onsets in pastoral regions (<i>n</i> = 96) and 20%–50% of crisis onsets in agro-pastoral regions (<i>n</i> = 22) with a 3-month lead time. We also compared our 8-month model predictions to the 8-month food-security outlooks produced by FEWS NET. Over a relatively short test period (2019–2022), results suggest the performance of our predictions is similar to FEWS NET for agro-pastoral and pastoral regions. However, our model is clearly less skilled in predicting food security for crop-farming regions than FEWS NET. With the well-established FEWS NET outlooks as a basis, this study highlights the potential for integrating machine-learning methods into operational systems like FEWS NET.</p>","PeriodicalId":48748,"journal":{"name":"Earths Future","volume":"12 8","pages":""},"PeriodicalIF":7.3000,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2023EF004211","citationCount":"0","resultStr":"{\"title\":\"Predicting Food-Security Crises in the Horn of Africa Using Machine Learning\",\"authors\":\"Tim Busker, Bart van den Hurk, Hans de Moel, Marc van den Homberg, Chiem van Straaten, Rhoda A. Odongo, Jeroen C. J. H. Aerts\",\"doi\":\"10.1029/2023EF004211\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>In this study, we present a machine-learning model capable of predicting food insecurity in the Horn of Africa, which is one of the most vulnerable regions worldwide. The region has frequently been affected by severe droughts and food crises over the last several decades, which will likely increase in future. Therefore, exploring novel methods of increasing early warning capabilities is of vital importance to reducing food-insecurity risk. We present a XGBoost machine-learning model to predict food-security crises up to 12 months in advance. We used >20 data sets and the FEWS IPC current-situation estimates to train the machine-learning model. Food-security dynamics were captured effectively by the model up to 3 months in advance (<i>R</i><sup>2</sup> > 0.6). Specifically, we predicted 20% of crisis onsets in pastoral regions (<i>n</i> = 96) and 20%–50% of crisis onsets in agro-pastoral regions (<i>n</i> = 22) with a 3-month lead time. We also compared our 8-month model predictions to the 8-month food-security outlooks produced by FEWS NET. Over a relatively short test period (2019–2022), results suggest the performance of our predictions is similar to FEWS NET for agro-pastoral and pastoral regions. However, our model is clearly less skilled in predicting food security for crop-farming regions than FEWS NET. With the well-established FEWS NET outlooks as a basis, this study highlights the potential for integrating machine-learning methods into operational systems like FEWS NET.</p>\",\"PeriodicalId\":48748,\"journal\":{\"name\":\"Earths Future\",\"volume\":\"12 8\",\"pages\":\"\"},\"PeriodicalIF\":7.3000,\"publicationDate\":\"2024-08-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2023EF004211\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Earths Future\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1029/2023EF004211\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Earths Future","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1029/2023EF004211","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0
摘要
非洲之角是全球最脆弱的地区之一,在本研究中,我们提出了一个能够预测非洲之角粮食不安全状况的机器学习模型。在过去的几十年里,该地区经常受到严重干旱和粮食危机的影响,这种情况在未来可能还会加剧。因此,探索提高预警能力的新方法对于降低粮食不安全风险至关重要。我们提出了一个 XGBoost 机器学习模型,用于提前 12 个月预测粮食不安全危机。我们使用了 20 个数据集和 FEWS IPC 当前形势估计来训练机器学习模型。该模型可提前 3 个月有效捕捉粮食安全动态(R2 为 0.6)。具体来说,在 3 个月的准备时间内,我们预测了牧区 20% 的危机发生率(n = 96)和农牧区 20%-50% 的危机发生率(n = 22)。我们还将 8 个月的模型预测与 FEWS NET 制作的 8 个月粮食安全展望进行了比较。在相对较短的测试期(2019-2022 年)内,结果表明我们的预测在农牧区和牧区的表现与 FEWS NET 相似。然而,我们的模型在预测农作物种植区的粮食安全方面显然不如 FEWS NET 熟练。以 FEWS NET 成熟的展望为基础,本研究强调了将机器学习方法整合到 FEWS NET 等业务系统中的潜力。
Predicting Food-Security Crises in the Horn of Africa Using Machine Learning
In this study, we present a machine-learning model capable of predicting food insecurity in the Horn of Africa, which is one of the most vulnerable regions worldwide. The region has frequently been affected by severe droughts and food crises over the last several decades, which will likely increase in future. Therefore, exploring novel methods of increasing early warning capabilities is of vital importance to reducing food-insecurity risk. We present a XGBoost machine-learning model to predict food-security crises up to 12 months in advance. We used >20 data sets and the FEWS IPC current-situation estimates to train the machine-learning model. Food-security dynamics were captured effectively by the model up to 3 months in advance (R2 > 0.6). Specifically, we predicted 20% of crisis onsets in pastoral regions (n = 96) and 20%–50% of crisis onsets in agro-pastoral regions (n = 22) with a 3-month lead time. We also compared our 8-month model predictions to the 8-month food-security outlooks produced by FEWS NET. Over a relatively short test period (2019–2022), results suggest the performance of our predictions is similar to FEWS NET for agro-pastoral and pastoral regions. However, our model is clearly less skilled in predicting food security for crop-farming regions than FEWS NET. With the well-established FEWS NET outlooks as a basis, this study highlights the potential for integrating machine-learning methods into operational systems like FEWS NET.
期刊介绍:
Earth’s Future: A transdisciplinary open access journal, Earth’s Future focuses on the state of the Earth and the prediction of the planet’s future. By publishing peer-reviewed articles as well as editorials, essays, reviews, and commentaries, this journal will be the preeminent scholarly resource on the Anthropocene. It will also help assess the risks and opportunities associated with environmental changes and challenges.