Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Machine learning can guide food security efforts when primary data are not available

Nature Food volume 3, pages 716–728 (2022)Cite this article

Subjects

Abstract

Estimating how many people are food insecure and where they are is of fundamental importance for governments and humanitarian organizations to make informed and timely decisions on relevant policies and programmes. In this study, we propose a machine learning approach to predict the prevalence of people with insufficient food consumption and of people using crisis or above-crisis food-based coping when primary data are not available. Making use of a unique global dataset, the proposed models can explain up to 81% of the variation in insufficient food consumption and up to 73% of the variation in crisis or above food-based coping levels. We also show that the proposed models can nowcast the food security situation in near real time and propose a method to identify which variables are driving the changes observed in predicted trends—which is key to make predictions serviceable to decision-makers.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Predicted versus observed values in the test set for each of the four models.
Fig. 2: Comparison between near-real time monitoring of insufficient food consumption and predicted trends.
Fig. 3: Comparison between near-real time monitoring of crisis or above food-based coping and predicted trends.
Fig. 4: Error classification for real time monitoring predictions.
Fig. 5: Explanation of a single prediction of insufficient food consumption and of crisis or above food-based coping.
Fig. 6: Explanation of changes in predicted trends between two dates.

Similar content being viewed by others

Data availability

The data that support the findings of this study are available in a Zenodo repository: https://zenodo.org/record/6953981.

Code availability

The code used to generate the results reported in this study is available in a Zenodo repository: https://zenodo.org/record/6953981.

References

  1. Food Security Analysis (World Food Programme, 2022); https://www.wfp.org/food-security-analysis

  2. Blumenstock, J., Cadamuro, G. & On, R. Predicting poverty and wealth from mobile phone metadata. Science 350, 1073–1076 (2015).

    Article  ADS  CAS  Google Scholar 

  3. Jean, N. et al. Combining satellite imagery and machine learning to predict poverty. Science 353, 790–794 (2016).

    Article  ADS  CAS  Google Scholar 

  4. Steele, J. E. et al. Mapping poverty using mobile phone and satellite data. J. R. Soc. Interface 14, 20160690 (2017).

    Article  Google Scholar 

  5. Pokhriyal, N. & Jacques, D. C. Combining disparate data sources for improved poverty prediction and mapping. Proc. Natl Acad. Sci. USA 114, E9783–E9792 (2017).

    Article  ADS  CAS  Google Scholar 

  6. Engelmann, G., Smith, G. & Goulding, J. The unbanked and poverty: predicting area-level socio-economic vulnerability from m-money transactions. In 2018 IEEE International Conference on Big Data 1357–1366 (IEEE, 2018).

  7. Sheehan, E. et al. Predicting economic development using geolocated Wikipedia articles. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2698–2706 (ACM, 2019).

  8. Kondmann, L., Haeberle, M. & Zhu, X. X.Combining Twitter and Earth observation data for local poverty mapping. In NeuRIPS Machine Learning for the Developing World Workshop 1–5 (NeurIPS, 2020).

  9. Fatehkia, M. et al. Mapping socioeconomic indicators using social media advertising data. EPJ Data Sci. 9, 22 (2020).

    Article  Google Scholar 

  10. IFAD, UNICEF, WFP & WHO. The State of Food Security and Nutrition in the World 2021. Transforming Food Systems for Food Security, Improved Nutrition and Affordable Healthy Diets for All (FAO, 2021).

  11. FSIN. Global Report on Food Crises 2020 (FSIN, 2020); https://www.wfp.org/publications/2020-global-report-food-crises

  12. Emergency Operations Division WFP Global Operational Response Plan: Update #3–November 2021 (WFP, 2021); https://www.wfp.org/publications/wfp-global-operational-response-plan-update-3-november-2021

  13. Declaration of the World Summit on Food Security (FAO, 2009).

  14. Vaitla, B. et al. The measurement of household food security: correlation and latent variable analysis of alternative indicators in a large multi-country dataset. Food Policy 68, 193–205 (2017).

    Article  Google Scholar 

  15. Lobell, D. B. et al. Prioritizing climate change adaptation needs for food security in 2030. Science 319, 607–610 (2008).

    Article  CAS  Google Scholar 

  16. Zufiria, P. J. et al. Identifying seasonal mobility profiles from anonymized and aggregated mobile phone data. Application in food security. PloS ONE 13, e0195714 (2018).

    Article  Google Scholar 

  17. Napoli, M. Towards a Food Insecurity Multidimensional Index (FIMI). MSc thesis, Roma Tre Univ. (2011).

  18. Caccavale, O. M. & Giuffrida, V. The proteus composite index: towards a better metric for global food security. World Dev. 126, 104709 (2020).

    Article  Google Scholar 

  19. Okori, W. & Obua, J. Machine learning classification technique for famine prediction. In Proceedings of the World Congress on Engineering, Vol. 2 4–9 (Citeseer, 2011).

  20. Andree, B. P. J., Chamorro, A., Kraay, A., Spencer, P. & Wang, D. Predicting Food Crises (World Bank, 2020).

  21. Wang, D., Andree, B. P. J., Chamorro, A. F. & Girouard Spencer, P. Stochastic Modeling of Food Insecurity (World Bank, 2020).

  22. Lentz, E., Michelson, H., Baylis, K. & Zhou, Y. A data-driven approach improves food insecurity crisis prediction. World Dev.122, 399–409 (2019).

    Article  Google Scholar 

  23. Westerveld, J. J. et al. Forecasting transitions in the state of food security with machine learning using transferable features. Sci. Total Environ. 786, 147366 (2021).

    Article  ADS  CAS  Google Scholar 

  24. Deléglise, H. et al. Food security prediction from heterogeneous data combining machine and deep learning methods. Expert Syst. Appl. 190, 116189 (2021).

    Article  Google Scholar 

  25. Chen, T. & Guestrin, C. Xgboost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Pages 785–794 (ACM, 2016).

  26. Funk, C. et al. Recognizing the famine early warning systems network: over 30 years of drought early warning science advances and partnerships promoting global food security. Bull. Am. Meteorol. Soc. 100, 1011–1027 (2019).

    Article  ADS  Google Scholar 

  27. HungerMap LIVE (WFP, 2022); https://hungermap.wfp.org/

  28. Lundberg, S. M. & Lee, S.-I. in Advances in Neural Information Processing Systems, Vol. 30 4765-4774 (eds Guyon, I. et al.) (Curran Associates Inc., 2017).

  29. Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2, 2522–5839 (2020).

    Article  Google Scholar 

  30. HungerMap LIVE: Global Insights and Key Trends (WFP, 2022); https://static.hungermapdata.org/insight-reports/latest/global-summary.pdf

  31. Blumenstock, J. E. Estimating economic characteristics with phone data. AEA Pap. Proc. 108, 72–76 (2018).

    Article  Google Scholar 

  32. Singh, S., Nourozi, S., Acharya, L. & Thapa, S. Estimating the potential effects of COVID-19 pandemic on food commodity prices and nutrition security in Nepal. J. Nutr. Sci. 9, E51 (2020).

    Article  CAS  Google Scholar 

  33. Jelilov, G., Iorember, P. T., Usman, O. & Yua, P. M. Testing the nexus between stock market returns and inflation in Nigeria: does the effect of COVID-19 pandemic matter? J. Public Aff. 20, e2289 (2020).

    PubMed  PubMed Central  Google Scholar 

  34. Ogunleye, A. & Wang, Q.-G. Xgboost model for chronic kidney disease diagnosis. IEEE/ACM Trans. Comput. Biol. Bioinf. 17, 2131–2140 (2019).

    Article  Google Scholar 

  35. Zhang, Y. & Hamori, S. Forecasting crude oil market crashes using machine learning technologies. Energies 13, 2440 (2020).

    Article  CAS  Google Scholar 

  36. Smith, G., Mansilla, R. & Goulding, J. Model class reliance for random forests. In Ao, I.S. et al. (eds) Adv. Neural Inf. Process. Syst. 33 22305-22315 Newswood Limited (2020). http://www.iaeng.org/publication/WCE2011/#:~:text=The%20WCE%202011%20takes%20place,engineering%20and%20computer%20science%20subjects

  37. Kumar, I. E., Venkatasubramanian, S., Scheidegger, C. & Friedler, S. Problems with Shapley-value-based explanations as feature importance measures. In International Conference on Machine Learning 5491–5500 (PMLR, 2020).

  38. Food Consumption Analysis Calculation and Use of the Food Consumption Score in Food Security Analysis (WFP, 2008); https://documents.wfp.org/stellent/groups/public/documents/manual_guide_proced/wfp197216.pdf

  39. The Coping Strategies Index: Field Methods Manual (WFP, 2008); https://documents.wfp.org/stellent/groups/public/documents/manual_guide_proced/wfp211058.pdf

  40. Bowling, A. Mode of questionnaire administration can have serious effects on data quality. J. Public Health 27, 281–291 (2005).

    Article  Google Scholar 

  41. The World Food Programme’s Real-Time Monitoring Systems: Approaches and Methodologies (WFP, 2021); https://docs.wfp.org/api/documents/WFP-0000135070/download/

  42. Technical Manual Version 3.0. Evidence and Standards for Better Food Security and Nutrition Decisions (IPC, 2019).

  43. Chan, J. Y.-L. et al. Mitigating the multicollinearity problem and its machine learning approach: a review. Mathematics 10, 1283 (2022).

    Article  Google Scholar 

  44. Calculation and Use of the Alert for Price Spikes (ALPS) Indicator, Technical Guidance Note (WFP, 2014); https://documents.wfp.org/stellent/groups/public/documents/manual_guide_proced/wfp264186.pdf

  45. WFP Food Price Forecasting and Alert for Price Spikes (WFP, 2022); https://dataviz.vam.wfp.org/economic_explorer/price-forecasts-alerts

  46. Trading Economics (Trading Economics, 2022); https://tradingeconomics.com/

  47. WFP Economic Explorer (WFP, 2022); https://dataviz.vam.wfp.org/economic_explorer/macro-economics/exchange_rate

  48. WFP Seasonal Explorer (WFP, 2022); https://dataviz.vam.wfp.org/seasonal_explorer/rainfall_vegetation/visualizations

  49. Funk, C. C. et al. A quasi-global precipitation time series for drought monitoring. US Geol. Surv. Data Series 832, 4 (2014).

    Google Scholar 

  50. MODIS Vegetation Index Products (NDVI and EVI) (NASA, 2022); https://modis.gsfc.nasa.gov/data/dataprod/mod13.php

  51. Data Export Tool (ACLED, 2022); https://acleddata.com/data-export-tool/

  52. Dowd, C. in Cahill, B.H. and Lawton, J. (eds) A Skein of Thought 119–132 (Fordham Univ. Press, 2020).

  53. Food and Agriculture Organization Corporate Statistical Database (FAOSTAT, 2022); http://www.fao.org/faostat

  54. Gridded Population of the World version 4 (GPWv4): Population Density, Revision 11 (NASA, 2018); https://doi.org/10.7927/H49C6VHW

  55. Friedman, J. H. Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232 (2001).

    Article  MathSciNet  Google Scholar 

  56. Lundberg, S. SHAP Documentation (Read the Docs, 2018); https://shap.readthedocs.io/

Download references

Acknowledgements

We thank our colleagues at WFP in headquarters, regional bureaus and country offices for the fruitful discussions, and Alibaba Cloud for initial contribution in terms of data infrastructure and modelling approach.

Author information

Authors and Affiliations

  1. World Food Programme, Research, Assessment and Monitoring Division (RAM), Rome, Italy

    Giulia Martini, Alberto Bracci, Lorenzo Riches, Sejal Jaiswal, Matteo Corea, Jonathan Rivers, Arif Husain & Elisa Omodei

  2. Department of Mathematics, University of London, London, UK

    Alberto Bracci

  3. Department of Network and Data Science, Central European University, Vienna, Austria

    Elisa Omodei

Authors
  1. Giulia Martini
    View author publications

    Search author on:PubMed Google Scholar

  2. Alberto Bracci
    View author publications

    Search author on:PubMed Google Scholar

  3. Lorenzo Riches
    View author publications

    Search author on:PubMed Google Scholar

  4. Sejal Jaiswal
    View author publications

    Search author on:PubMed Google Scholar

  5. Matteo Corea
    View author publications

    Search author on:PubMed Google Scholar

  6. Jonathan Rivers
    View author publications

    Search author on:PubMed Google Scholar

  7. Arif Husain
    View author publications

    Search author on:PubMed Google Scholar

  8. Elisa Omodei
    View author publications

    Search author on:PubMed Google Scholar

Contributions

E.O., L.R. and J.R. conceptualized the study and G.M. and A.B. contributed to its further design. G.M., L.R. and E.O. analysed the data. G.M., A.B., S.J., M.C., L.R. and E.O. designed and developed the Python code used in the work. E.O. supervised the research. E.O., G.M. and A.B. wrote the manuscript, and all authors reviewed and approved it.

Corresponding author

Correspondence to Elisa Omodei.

Ethics declarations

Competing interests

The authors declare no competing interests. The content and views expressed in this paper are solely those of the authors and do not necessarily reflect the official views of the UN World Food Programme.

Peer review

Peer review information

Nature Food thanks Erin Lentz, Gavin Smith and James Goulding for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Martini, G., Bracci, A., Riches, L. et al. Machine learning can guide food security efforts when primary data are not available. Nat Food 3, 716–728 (2022). https://doi.org/10.1038/s43016-022-00587-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s43016-022-00587-8

This article is cited by

Search

Advanced search

Quick links

Nature Briefing AI and Robotics

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing: AI and Robotics