1 of 22

Leveraging News Data for AI-powered Food Insecurity Forecasts

October 28 | Berkeley, CA

Ananth Balashankar (Google DeepMind, work done while at NYU)

Coauthors: Lakshminarayanan Subramanian (NYU), Samuel Fraiberger (World Bank)

Panelist

2 of 22

Challenge: crises preparedness and response in fragile contexts

Sources: McDougal & Patterson (2021), Global Network Against Food Crises (2024), The World Bank (2024)

2 billion people live in Fragility, Conflict, and Violence (FCV) settings

Estimated $367 billion spent on domestic and international humanitarian aid in 2023

Anticipatory transfers can increase impact of aid and lower humanitarian cost by up to 30%

282 million people in 59 countries experienced high acute hunger in 2023

2

3 of 22

Status quo: existing early warning tools are limited by data gaps

Expensive

Delayed

Incomplete

Survey-based

3

4 of 22

Solution: scalable AI system using news for food crisis predictions

Anticipatory signals of food crises appear in on-the-ground news before traditional data

Our forecasting model can identify +46% food crisis outbreaks up to 12 months ahead relative to existing approaches such as Lentz et al. (2019)

Our AI models can convert news data into high-frequency food crises risk indicators at the district level globally

+46% outbreaks identified

4

5 of 22

Methodology: Extracting risk factors from news

Source: Swayamdipta et al., (2017)

Cause

Keyword Effect

Semantic frame parsing

Causation frames

Peer-reviewed articles on famine

News at ADMIN-2 District Level from 2009-20

Expansion around word2vec clusters

Granger-causality with FEWS levels

5

6 of 22

Methodology: Forecasting model

Methodology: Extracting news indicator factors

6

7 of 22

Methodology: a new perspective to the study of food insecurity

Once we identify these news indicators (“News”), we combine them with traditional food insecurity indicators (“Traditional”) in forecasting models (Random Forest Regression)

7

8 of 22

Rainfall anomaly

News mentions of climate shocks

Interpretability: why and how does our approach work?

Percentile of value

IPC Phase

Legend

Extreme drought struck Ethiopia in 2009. IPC in the Majang zone raised from a normal to a crisis phase in July 2010 when the precipitation levels were normal

News mentions of climate shocks (“drought”, “failed rain”, “abnormally low rainfall”, “prolonged dry spell”, etc.) peaked 6 months before the crisis and enabled our model to correctly predict the outbreak 4 months ahead

Machine learning predictions of food crises are interpretable by enabling to trace back to the underlying cause of the outbreak mentioned in the news

Rainfall anomaly

News mentions of climate shocks

Food crisis outbreak

IPC (Ground Truth)

Traditional

Trad. + News

Trad. + News

(excl. climate terms)

8

9 of 22

AI-powered public good to better anticipate and respond to food crises; scalable, real-time, interpretable and cost-effective

Inform World Bank’s food systems resilience programs across Africa ($3 billion in 16 countries over 10 years) and the Crisis Response Window ($2.5 billion)

Prioritize allocation of emergency food assistance to improve preparedness and reduce human suffering

Complement existing data products for food security incl. Hunger Map and the Global Food and Nutrition Security Dashboard

Takeaway: better forecasting, better policies

9

10 of 22

Potential extensions: More local, and anticipatory actions

Radio mining as localized mirror of public sentiments

AI-based anticipatory cash transfers for resilience

SMS-based alerts on emerging food crises to beneficiaries

Additional languages to enhance linguistic representation

Credit: Philipp Zimmer & Samuel Fraiberger, World Bank

10

11 of 22

11

12 of 22

Appendix

12

13 of 22

13

14 of 22

Adoption: how the World Bank is now thinking about bringing the insights to policymakers

* Frontend demo with dummy data

14

15 of 22

15

16 of 22

16

17 of 22

17

18 of 22

18

19 of 22

19

20 of 22

20

21 of 22

21

22 of 22

22