Forecasting transitions in the state of food security with machine learning using transferable features

Joris J.L. Westerveld; Marc J.C. van den Homberg; Gabriela Guimarães Nobre; Dennis L.J. van den Berg; Aklilu D. Teklesadik; Sjoerd M. Stuit

doi:10.1016/j.scitotenv.2021.147366

Forecasting transitions in the state of food security with machine learning using transferable features

Joris J.L. Westerveld^*, Marc J.C. van den Homberg, Gabriela Guimarães Nobre, Dennis L.J. van den Berg, Aklilu D. Teklesadik, Sjoerd M. Stuit

^*Corresponding author for this work

Water and Climate Risk

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

Food insecurity is a growing concern due to man-made conflicts, climate change, and economic downturns. Forecasting the state of food insecurity is essential to be able to trigger early actions, for example, by humanitarian actors. To measure the actual state of food insecurity, expert and consensus-based approaches and surveys are currently used. Both require substantial manpower, time, and budget. This paper introduces an extreme gradient-boosting machine learning model to forecast monthly transitions in the state of food security in Ethiopia, at a spatial granularity of livelihood zones, and for lead times of one to 12 months, using open-source data. The transition in the state of food security, hereafter referred to as predictand, is represented by the Integrated Food Security Phase Classification Data. From 19 categories of datasets, 130 variables were derived and used as predictors of the transition in the state of food security. The predictors represent changes in climate and land, market, conflict, infrastructure, demographics and livelihood zone characteristics. The most relevant predictors are found to be food security history and surface soil moisture. Overall, the model performs best for forecasting Deteriorations and Improvements in the state of food security compared to the baselines. The proposed method performs (F1 macro score) at least twice as well as the best baseline (a dummy classifier) for a Deterioration. The model performs better when forecasting long-term (7 months; F1 macro average = 0.61) compared to short-term (3 months; F1 macro average = 0.51). Combining machine learning, Integrated Phase Classification (IPC) ratings from monitoring systems, and open data can add value to existing consensus-based forecasting approaches as this combination provides longer lead times and more regular updates. Our approach can also be transferred to other countries as most of the data on the predictors are openly available from global data repositories.

Original language	English
Article number	147366
Pages (from-to)	1-15
Number of pages	15
Journal	Science of the Total Environment
Volume	786
Early online date	27 Apr 2021
DOIs	https://doi.org/10.1016/j.scitotenv.2021.147366
Publication status	Published - 10 Sept 2021

Bibliographical note

Funding Information:
Marc van den Homberg, Gabriela Guimarães Nobre and Joris Westerveld were partly funded by the GFDRR Forecast-based financing for food security project. Marc van den Homberg, Aklilu Teklesadik and Joris Westerveld were also partly funded by the Ikea Foundation as part of the Innovative Approaches to Response Preparedness Program. Marc van den Homberg was also partly funded by the Netherlands Red Cross Princess Margriet Fund FbF methodologies project.

Publisher Copyright:
© 2021 The Authors

Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.

Keywords

Early warning systems
Extreme gradient boosting
Food security
IPC
Machine learning
Open data

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.scitotenv.2021.147366

Persistent URL (handle)

Copy link address

Cite this

@article{7fbe35ccc008438cbb3a0b8c9bd9ee32,

title = "Forecasting transitions in the state of food security with machine learning using transferable features",

abstract = "Food insecurity is a growing concern due to man-made conflicts, climate change, and economic downturns. Forecasting the state of food insecurity is essential to be able to trigger early actions, for example, by humanitarian actors. To measure the actual state of food insecurity, expert and consensus-based approaches and surveys are currently used. Both require substantial manpower, time, and budget. This paper introduces an extreme gradient-boosting machine learning model to forecast monthly transitions in the state of food security in Ethiopia, at a spatial granularity of livelihood zones, and for lead times of one to 12 months, using open-source data. The transition in the state of food security, hereafter referred to as predictand, is represented by the Integrated Food Security Phase Classification Data. From 19 categories of datasets, 130 variables were derived and used as predictors of the transition in the state of food security. The predictors represent changes in climate and land, market, conflict, infrastructure, demographics and livelihood zone characteristics. The most relevant predictors are found to be food security history and surface soil moisture. Overall, the model performs best for forecasting Deteriorations and Improvements in the state of food security compared to the baselines. The proposed method performs (F1 macro score) at least twice as well as the best baseline (a dummy classifier) for a Deterioration. The model performs better when forecasting long-term (7 months; F1 macro average = 0.61) compared to short-term (3 months; F1 macro average = 0.51). Combining machine learning, Integrated Phase Classification (IPC) ratings from monitoring systems, and open data can add value to existing consensus-based forecasting approaches as this combination provides longer lead times and more regular updates. Our approach can also be transferred to other countries as most of the data on the predictors are openly available from global data repositories.",

keywords = "Early warning systems, Extreme gradient boosting, Food security, IPC, Machine learning, Open data",

author = "Westerveld, {Joris J.L.} and {van den Homberg}, {Marc J.C.} and Nobre, {Gabriela Guimar{\~a}es} and {van den Berg}, {Dennis L.J.} and Teklesadik, {Aklilu D.} and Stuit, {Sjoerd M.}",

note = "Funding Information: Marc van den Homberg, Gabriela Guimar{\~a}es Nobre and Joris Westerveld were partly funded by the GFDRR Forecast-based financing for food security project. Marc van den Homberg, Aklilu Teklesadik and Joris Westerveld were also partly funded by the Ikea Foundation as part of the Innovative Approaches to Response Preparedness Program. Marc van den Homberg was also partly funded by the Netherlands Red Cross Princess Margriet Fund FbF methodologies project. Publisher Copyright: {\textcopyright} 2021 The Authors Copyright: Copyright 2021 Elsevier B.V., All rights reserved.",

year = "2021",

month = sep,

day = "10",

doi = "10.1016/j.scitotenv.2021.147366",

language = "English",

volume = "786",

pages = "1--15",

journal = "Science of the Total Environment",

issn = "0048-9697",

publisher = "Elsevier",

}

TY - JOUR

T1 - Forecasting transitions in the state of food security with machine learning using transferable features

AU - Westerveld, Joris J.L.

AU - van den Homberg, Marc J.C.

AU - Nobre, Gabriela Guimarães

AU - van den Berg, Dennis L.J.

AU - Teklesadik, Aklilu D.

AU - Stuit, Sjoerd M.

N1 - Funding Information: Marc van den Homberg, Gabriela Guimarães Nobre and Joris Westerveld were partly funded by the GFDRR Forecast-based financing for food security project. Marc van den Homberg, Aklilu Teklesadik and Joris Westerveld were also partly funded by the Ikea Foundation as part of the Innovative Approaches to Response Preparedness Program. Marc van den Homberg was also partly funded by the Netherlands Red Cross Princess Margriet Fund FbF methodologies project. Publisher Copyright: © 2021 The Authors Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2021/9/10

Y1 - 2021/9/10

N2 - Food insecurity is a growing concern due to man-made conflicts, climate change, and economic downturns. Forecasting the state of food insecurity is essential to be able to trigger early actions, for example, by humanitarian actors. To measure the actual state of food insecurity, expert and consensus-based approaches and surveys are currently used. Both require substantial manpower, time, and budget. This paper introduces an extreme gradient-boosting machine learning model to forecast monthly transitions in the state of food security in Ethiopia, at a spatial granularity of livelihood zones, and for lead times of one to 12 months, using open-source data. The transition in the state of food security, hereafter referred to as predictand, is represented by the Integrated Food Security Phase Classification Data. From 19 categories of datasets, 130 variables were derived and used as predictors of the transition in the state of food security. The predictors represent changes in climate and land, market, conflict, infrastructure, demographics and livelihood zone characteristics. The most relevant predictors are found to be food security history and surface soil moisture. Overall, the model performs best for forecasting Deteriorations and Improvements in the state of food security compared to the baselines. The proposed method performs (F1 macro score) at least twice as well as the best baseline (a dummy classifier) for a Deterioration. The model performs better when forecasting long-term (7 months; F1 macro average = 0.61) compared to short-term (3 months; F1 macro average = 0.51). Combining machine learning, Integrated Phase Classification (IPC) ratings from monitoring systems, and open data can add value to existing consensus-based forecasting approaches as this combination provides longer lead times and more regular updates. Our approach can also be transferred to other countries as most of the data on the predictors are openly available from global data repositories.

AB - Food insecurity is a growing concern due to man-made conflicts, climate change, and economic downturns. Forecasting the state of food insecurity is essential to be able to trigger early actions, for example, by humanitarian actors. To measure the actual state of food insecurity, expert and consensus-based approaches and surveys are currently used. Both require substantial manpower, time, and budget. This paper introduces an extreme gradient-boosting machine learning model to forecast monthly transitions in the state of food security in Ethiopia, at a spatial granularity of livelihood zones, and for lead times of one to 12 months, using open-source data. The transition in the state of food security, hereafter referred to as predictand, is represented by the Integrated Food Security Phase Classification Data. From 19 categories of datasets, 130 variables were derived and used as predictors of the transition in the state of food security. The predictors represent changes in climate and land, market, conflict, infrastructure, demographics and livelihood zone characteristics. The most relevant predictors are found to be food security history and surface soil moisture. Overall, the model performs best for forecasting Deteriorations and Improvements in the state of food security compared to the baselines. The proposed method performs (F1 macro score) at least twice as well as the best baseline (a dummy classifier) for a Deterioration. The model performs better when forecasting long-term (7 months; F1 macro average = 0.61) compared to short-term (3 months; F1 macro average = 0.51). Combining machine learning, Integrated Phase Classification (IPC) ratings from monitoring systems, and open data can add value to existing consensus-based forecasting approaches as this combination provides longer lead times and more regular updates. Our approach can also be transferred to other countries as most of the data on the predictors are openly available from global data repositories.

KW - Early warning systems

KW - Extreme gradient boosting

KW - Food security

KW - IPC

KW - Machine learning

KW - Open data

UR - http://www.scopus.com/inward/record.url?scp=85105528215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85105528215&partnerID=8YFLogxK

U2 - 10.1016/j.scitotenv.2021.147366

DO - 10.1016/j.scitotenv.2021.147366

M3 - Article

C2 - 33971600

AN - SCOPUS:85105528215

SN - 0048-9697

VL - 786

SP - 1

EP - 15

JO - Science of the Total Environment

JF - Science of the Total Environment

M1 - 147366

ER -

Forecasting transitions in the state of food security with machine learning using transferable features

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this