Why We Can't Yet Predict Where Millions Of Climate Refugees Will Go

Why We Can't Yet Predict Where Millions Of Climate Refugees Will Go gregorioa / shutterstock

In the near future, global warming is expected to create millions of climate refugees, and individuals and organisations are already searching for ways to help them. Some ideas are obvious, such as improving conditions in refugee camps.

But there are also more high-tech projects such as using algorithms to forecast where displaced people will travel to. Such forecasts are crucial. They can help support organisations prepare in the right places, they can evaluate current policy (by assessing a counterfactual “what if” scenario) and they can also help predict refugee populations in remote or dangerous areas where there is little empirical data.

So we can predict where climate refugees will go, right?

No. Despite bold and excitable claims that refugee forecasting is largely resolved, we are not convinced. As computer scientists who work on this exact problem, such claims seem like a painful example of running before we can walk.

Almost four years ago, we started to research how people fled from armed conflicts. Many people were displaced due to the Arab Spring and the Syrian War, but little work had been done to predict where they could end up.

Why We Can't Yet Predict Where Millions Of Climate Refugees Will Go Africa’s Sahel region contains many of the world’s most climate-vulnerable people. mbrand85 / shutterstock

With our colleague David Bell, we created a tool that could help, and published our work in Nature Scientific Reports. Our tool represents every person as an independent agent, and then uses simple rules-of-thumb derived from scientific insights – for instance “people tend to avoid travelling through mountains when it is raining” – to determine when they will move next, and to where.

This is different from “machine learning” approaches, which use historical data to “train” the algorithm to generate rules and thus predictions. So, for example, machine learning might be given this sort of data: “the number of people that arrived in a refugee camp close to a mountainous area in a conflict that occurred perhaps many years ago, or more recently but in a different country.” The main issue is that historical data used for machine learning is always quantitative, and never is about the conflict that the simulation is directly developed for.

To see how our method worked in practice, we tested our tool against UNHCR data from three recent conflicts in Burundi, the Central African Republic and Mali. Our tool correctly predicted where more than 75% of the refugees would go.

Why We Can't Yet Predict Where Millions Of Climate Refugees Will Go Network models for (a) Burundi, (b) Central African Republic and (c) Mali. Conflict zones (red circles), refugee camps (dark green circles), forwarding hubs (light green circles) and other major settlements (yellow circles). Suleimenova et al (2017)

We have since applied our analysis to refugees fleeing conflict in South Sudan, as part of the HiDALGO project. In this study, forthcoming in the Journal of Artificial Societies and Social Simulation, we also looked at how policy decisions like border closures affected the movement of refugees into neighbouring countries, such as Ethiopia or Uganda.

We found there was indeed a link – closing the Uganda border in our model causes 40% fewer “agents” to arrive in camps after 300 days, and that effect lingers even after we reopened the border on day 301. Our tool correctly predicted where 75% of the refugees would actually go in real life.

But doing a correct “retrodiction” in these historical cases does not mean that you can do a forecast. Forecasting where people will go is much harder than predicting a historical situation, for three reasons.

Why We Can't Yet Predict Where Millions Of Climate Refugees Will Go A school in Uganda for refugees from war in South Sudan. Roberto Maldeno / flickr, CC BY-NC-ND

  1. Every model makes assumptions. For instance, a model that forecasts where refugees go might makes assumptions about their mode of transport, or the likelihood that they stay overnight in a place where violence has previously occurred. When forecasting, we need to know what happens when we give these assumptions a little shake (we examine this in the VECMA project). The less evidence we have for an assumption, the more we need to shake it and analyse how our model responds. Machine learning models generate implicit (and ill-justified) assumptions automatically when they are trained – for example, chosen destinations correlate with the stock value of company X. In agent-based models, these assumptions come from physical factors like the presence of mountains or armed groups, and are explicitly testable.

  2. Forecasting one thing requires you to forecast many other things as well. When we forecast how people escape conflict, we must forecast how the conflict will evolve. And that could depend on future market prices, weather/climate effects, or political changes, all of which would need forecasting too. To be clear: we did not require any of these models when we validated our predictions against a historical situation, so we are building new models just to make forecasts possible.

  3. Forcibly displaced people are usually fleeing from unexpected and disruptive events. Here the data upon which the machine learning algorithms are “trained” is incomplete, biased or often non-existent. We argue that agent-based models are more effective because they do not need training data, and benefit from understanding the processes that drive forced displacement.

So we have not cracked it.

Yes, forecasting is hard. We do not yet know where climate refugees and other forcibly displaced people are going. We still need huge supercomputers just to forecast next week’s weather.

So it pays to be suspicious of the idea that refugee forecasting is already solved, especially if linked to claims that the “next frontier” for computer scientists is in (controversially) extracting data from vulnerable refugees who are often unaware of the privacy and security risks. Given how hard it remains to predict where the millions of climate refugees will go, the “next frontier” is still the last frontier.The Conversation

About The Author

Derek Groen, Lecturer in Simulation and Modelling, Brunel University London and Diana Suleimenova, PhD Researcher, Computer Science, Brunel University London

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Related Books

Life After Carbon: The Next Global Transformation of Cities

by Peter Plastrik , John Cleveland
1610918495The future of our cities is not what it used to be. The modern-city model that took hold globally in the twentieth century has outlived its usefulness. It cannot solve the problems it helped to create—especially global warming. Fortunately, a new model for urban development is emerging in cities to aggressively tackle the realities of climate change. It transforms the way cities design and use physical space, generate economic wealth, consume and dispose of resources, exploit and sustain the natural ecosystems, and prepare for the future. Available On Amazon

The Sixth Extinction: An Unnatural History

by Elizabeth Kolbert
1250062187Over the last half-billion years, there have been Five mass extinctions, when the diversity of life on earth suddenly and dramatically contracted. Scientists around the world are currently monitoring the sixth extinction, predicted to be the most devastating extinction event since the asteroid impact that wiped out the dinosaurs. This time around, the cataclysm is us. In prose that is at once frank, entertaining, and deeply informed, New Yorker writer Elizabeth Kolbert tells us why and how human beings have altered life on the planet in a way no species has before. Interweaving research in half a dozen disciplines, descriptions of the fascinating species that have already been lost, and the history of extinction as a concept, Kolbert provides a moving and comprehensive account of the disappearances occurring before our very eyes. She shows that the sixth extinction is likely to be mankind's most lasting legacy, compelling us to rethink the fundamental question of what it means to be human. Available On Amazon

Climate Wars: The Fight for Survival as the World Overheats

by Gwynne Dyer
1851687181Waves of climate refugees. Dozens of failed states. All-out war. From one of the world’s great geopolitical analysts comes a terrifying glimpse of the strategic realities of the near future, when climate change drives the world’s powers towards the cut-throat politics of survival. Prescient and unflinching, Climate Wars will be one of the most important books of the coming years. Read it and find out what we’re heading for. Available On Amazon

From The Publisher:
Purchases on Amazon go to defray the cost of bringing you InnerSelf.comelf.com, MightyNatural.com, and ClimateImpactNews.com at no cost and without advertisers that track your browsing habits. Even if you click on a link but don't buy these selected products, anything else you buy in that same visit on Amazon pays us a small commission. There is no additional cost to you, so please contribute to the effort. You can also use this link to use to Amazon at any time so you can help support our efforts.



follow InnerSelf on


 Get The Latest By Email



The Rise Of Solar Power
Solar power is on the rise. You can see the evidence on rooftops and in the desert, where utility-scale solar plants…
World's Largest Batteries: Pumped Storage
by Practical Engineering
The vast majority of our grid-scale storage of electricity uses this clever method.
Hydrogen Fuels Rockets, But What About Power For Daily Life?
Hydrogen Fuels Rockets, But What About Power For Daily Life?
by Zhenguo Huang
Have you ever watched a space shuttle launch? The fuel used to thrust these enormous structures away from Earth’s…
Fossil Fuel Production Plans Could Push Earth off a Climate Cliff
by The Real News Network
The United Nations is beginning its climate summit in Madrid.
Big Rail Spends More on Denying Climate Change than Big Oil
by The Real News Network
A new study concludes that rail is the industry that's injected the most money into climate change denial propaganda…
Did Scientists Get Climate Change Wrong?
by Sabine Hossenfelder
Interview with Prof Tim Palmer from the University of Oxford.
The New Normal: Climate Change Poses Challenges For Minnesota Farmers
by KMSP-TV Minneapolis-St. Paul
Spring brought a deluge of rain in southern Minnesota and it never seemed to stop.
Report: Today's Kids' Health Will Be Imperiled by Climate Change
by VOA News
An international report from researchers at 35 institutions says climate change will threaten the health and quality of…


Can Sea Water Desalination Save The World?
Today, one out of three people don’t have access to safe drinking water. And that’s the result of many things, but one…
The Rise Of Solar Power
Solar power is on the rise. You can see the evidence on rooftops and in the desert, where utility-scale solar plants…
World's Largest Batteries: Pumped Storage
by Practical Engineering
The vast majority of our grid-scale storage of electricity uses this clever method.
How Wildfire Smoke AfHow Wildfire Smoke Affects Pets And Other Animals
How Wildfire Smoke Affects Pets And Other Animals
by Stephanie Laura Bond, et al
Catastrophic fires across the globe are increasing in both frequency and magnitude. The bushfires in Australia, fuelled…
5 Ways Families Can Help Tackle Climate Change
5 Ways Families Can Help Tackle Climate Change
by Greg McDermid, et al
While many climate solutions require leadership from governments, we also need changes within regular households, which…
Geo-engineering Could Make Poor Countries Richer
Geo-engineering Could Make Poor Countries Richer
by Tim Radford
There is still no certainty that geo-engineering could save the world. But, paradoxically, if it did work it might…
Worst Marine Heatwave On Record Killed One Million Seabirds In North Pacific Ocean
Worst Marine Heatwave On Record Killed One Million Seabirds In North Pacific Ocean
by Tim Birkhead
A common guillemot colony on the Farallon Islands, California. Duncan Wright/Wikipedia, CC BY-SA The common guillemot…
Nuclear Power Cannot Rival Renewable Energy
Nuclear Power Cannot Rival Renewable Energy
by Paul Brown
Far from tackling climate change, nuclear power is an expensive distraction whose safety is threatened by wildfires and…