30 January 2021 | New Scientist | 13WARMING temperatures and
changing rainfall patterns may
reduce diet diversity among
children around the world – and
may even undermine efforts
to improve food security.
Meredith Niles at the
University of Vermont and her
colleagues analysed the results
of health surveys from more
than 107,000 children in
19 countries – in Asia; North,
south-east and West Africa;
and Central and South America.
The surveys were conducted
between 2005 and 2009.
In the surveys, the diversity
of a child’s diet was quantified
with a score based on their
intake of foods from different
food groups, including cereal
grains, dairy products and meat.
The data included details of
each child’s diet the day before
they were surveyed.
On average, the children –
aged 5 and under – ate food from
3.2 food groups out of a possible- But there was variation from
country to country. Children
in Colombia ate from 4.8 food
groups on average, while those
in Lesotho ate from just 1.8.
To study whether climate
affected the diversity of the
children’s diets, the researchers
linked the results from each
country to 30 years of rainfall
and temperature data in
the surveyed regions. They
found that higher long-termtemperatures were associated
with lower overall diet diversity
for children everywhere except
Central America.
There were shorter-term
trends too. In North Africa
and South America, there was
typically a reduction in diet
diversity in countries that
experienced higher-than-
average temperatures in the
year prior to the survey. In
Central America and West
Africa, diets typically became
more diverse in countries that
experienced above-average
rainfall in the previous year.
The researchers controlled for
geographic and socio-economicfactors that could affect diet
diversity, such as household
wealth, and population and
livestock density.
In some countries, the
researchers say that the
negative effect of climate
change on diet diversity was
so great that it outweighed
the beneficial impact of
development efforts focused
on education, improved
toilet facilities and poverty
reduction. These negative
impacts may even undermine
efforts to improve food security,
the researchers suggest
(Environmental Research Letters,
doi.org/frkx).
Diet diversity is a useful
metric for regions with high
rates of child malnutrition,
says Daniel Mason-D’Croz at
the Commonwealth Scientific
and Industrial Research
Organisation in Australia.
“That they’re getting a fruit or
a vegetable or animal product in
addition to the rice or the maize
[staple] – that’s an important
thing to know,” he says.
Mason-D’Croz points out that
the years the health surveys
were done coincided with the
2007 to 2008 world food price
crisis, during which food
became much more expensive.
The crisis was caused by many
factors and not just climate
change, and may have affected
diets across the world.
“There were food riots in
some of the countries that
were in the study,” says Mason-
D’Croz. A follow-up study with
more recent data could confirm
more authoritatively the effect
of climate in reducing diet
diversity, he says. ❚ARTIFICIAL intelligence has learned
to identify the songs someone is
listening to from their brain readings.
Derek Lomas at Delft University
of Technology in the Netherlands
and his colleagues asked 20 people
to listen to 12 songs through
headphones. The volunteers did this
blindfolded and in a dimly lit room
to minimise the effect of their other
senses on the results. Each person’s
brainwaves were recorded using an
electroencephalography (EEG) cap
that detects electrical activity.
The EEG readings from each
person were cut into short segments
and used along with the matching
music clip to train an AI to spot
patterns between the two. The AI
was then tested on unseen portions
of the data, identifying songs with
an accuracy of 85 per cent.
But the software struggles
if it is trained on EEG data from
one person and then attempts to
identify a song when someone else
listens to it. Accuracy in such tests
dropped below 10 per cent (CODS
COMAD 2021, doi.org/frks).
The researchers believe that this
is due to each person’s aesthetic
response to a song being unique
and people tending to focus on
different elements of the music
during training. Ultimately,
however, they aim to identify
aspects of EEG responses to music
that are common to all humans.
Lomas hopes that this will further
our understanding of the brain, as
well as boost knowledge of how
and why humans consume music.
“I think it’s really provocative to
think about how the combination of
machine learning and high-density
data from EEG can be combined
to bring insights into moving
emotional experiences, but also
to figure out what’s going on
inside your head,” he says.
Music is ultimately “just voltage
fluctuations”, he says. “And it’s the
same with the EEG.” ❚A woman selecting
corn at a market in
Kathmandu, NepalArtificial intelligence NutritionMatthew Sparkes Donna LuPRAK
ASH^ MAT
HE
MA/AFP^ VIA^ GET
TY
IMAGES19
countries included in the study,
in Asia, Africa and the AmericasClimate may undermine
food security efforts
Machine identifies
songs from people’s
brainwaves