September 19, 2022

Scientists propose machine learning approach to solve the world's food insecurity issue

by Central European University

Scientists Propose Machine Learning Approach to Solve the World’s Food Insecurity Issue
Machine learning can guide food security efforts when primary data are not available. Predictions that differ from the observed value by maximum ± 5 prevalence points are classified as correct. Predicted prevalence >40% (<40%) when the observed prevalence is <40% (>40%) are classified as high over-estimation (under-estimation). The other regions are classified as low under- and over-estimation. The solid black line indicates where the points would fall if all predicted values perfectly matched the observed ones, and the gray dashed diagonal lines indicate a distance of ± 5 prevalence points from it. The gray dashed horizontal and vertical lines indicate the 40% prevalence thresholds. Credit: Nature Food (2022). DOI: 10.1038/s43016-022-00587-8

Researchers of a recent paper published by Nature Food suggest a method which they claim will allow decision-makers to make more timely and informed decisions on policies and programs oriented towards the fight against hunger.

In 2021, 193 million people across 53 countries were acutely insecure. This number has been steadily increasing during the last few years also as a consequence of the COVID-19 pandemic. To address this global issue, monitoring the situation and its evolution is key.

Governments and humanitarian organizations perform assessments on a regular basis through face-to-face and remote mobile phone surveys. However, these approaches have in both monetary and human resources, and hence primary data on the food security situation is not always available for all affected areas. Yet this information is key for governments and .

To tackle this issue, researchers of the Nature Food paper propose a machine learning approach to predict the number of people with insufficient food consumption when up-to-date direct measurements are not available. "We also propose a method to identify which variables are driving the changes observed in predicted trends, which is key to making predictions serviceable to ," says Assistant Professor Elisa Omodei (Department of Network and Data Science, CEU, Vienna).

The proposed method uses a machine learning algorithm to estimate the current food insecurity situation in a given area from data on the key drivers of food insecurity: conflict, weather extremes and economic shocks. The results show that the proposed methodology can explain up to 81% of the variation in insufficient food consumption.

Researchers claim their approach opens the door to food security near-real time nowcasting on a global scale, allowing decision-makers to make more timely and on policies and programs oriented towards the fight against hunger, in the effort to try to achieve SDG 2 of the 2030 Agenda for Sustainable Development.

More information: Giulia Martini et al, Machine learning can guide food security efforts when primary data are not available, Nature Food (2022). DOI: 10.1038/s43016-022-00587-8

Journal information: Nature Food

Provided by Central European University

Citation: Scientists propose machine learning approach to solve the world's food insecurity issue (2022, September 19) retrieved 3 October 2023 from https://phys.org/news/2022-09-scientists-machine-approach-world-food.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Explore further

Hunger is increasing worldwide, but women bear the brunt of food insecurity
60 shares

Feedback to editors
Load comments (0)