Modelling and Projecting Urban Population Growth in Somalia (1960–2050): A Comparative Analysis of Time Series Models
This study utilizes historical data from 1960 to 2024 and compares six time-series models to project Somalia's urban population, identifying TBATS and ARIMA as robust forecasting tools that predict the urban population will more than double to 22.2 million by 2050, thereby underscoring the urgent need for proactive urban planning.
Original paper licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). This is an AI-generated explanation of the paper below. It is not written or endorsed by the authors. For technical accuracy, refer to the original paper. Read full disclaimer
Imagine you are trying to predict the weather for a city that has never kept a proper diary. You know it rains a lot, sometimes floods, and the wind changes direction wildly, but you don't have a clear record of why or when these things happened in the past. This is the challenge of demographic forecasting in places like Somalia. It's a branch of science that tries to guess how many people will live in a specific area in the future. To do this, scientists use time-series models, which are like mathematical crystal balls. They look at a long line of past numbers (like the population count every year) and try to find a pattern, or a "rhythm," to see where the line is heading next. Some models are simple, like drawing a straight line through dots; others are complex, like a robot that learns to dance to the beat of the data, accounting for sudden jumps, slow climbs, and weird twists. Why does this matter? Because cities are the engines of the future. If we don't know how many people will be living there, we can't build enough schools, hospitals, or water pipes. Guessing wrong means chaos; guessing right means a chance to build a better life.
Now, let's zoom in on a specific story about a country that has been a bit of a mystery to the data world: Somalia. A researcher named Eng. Ahmed Abdirahmaan Ibrahim decided to tackle the question: "How fast is Somalia's city population growing, and where will it be in 2050?" He didn't just guess; he gathered a massive history book of numbers, tracking the urban population from 1960 all the way to 2024. That's 65 years of data, starting when the city population was just 508,138 people and ending when it had exploded to 10,382,351.
The problem was that this data wasn't a smooth, gentle hill. It was a rollercoaster. The numbers were "non-stationary," which is a fancy way of saying the trend was changing so fast that you couldn't just draw a straight line through it. It was accelerating. To fix this, the researcher had to do some mathematical "tuning," specifically using a technique called "second-order differencing." Think of it like this: if you are driving a car and you press the gas pedal harder every second, your speed isn't just going up; your acceleration is going up. The math had to account for that extra layer of speed to make sense of the curve.
Once the data was prepped, the researcher threw six different "forecasting robots" at the problem to see which one could predict the future best. These robots were named ARIMA, ETS, BATS, TBATS, Theta, and ARFIMA. To test them, the researcher hid the last 26 years of data (from 1999 to 2024) and asked the robots to guess what happened during those years. The winner? The TBATS and BATS models. They were the most accurate, missing the mark by only about 10.54% on average. The ARIMA model came in a close second for the long-term view, with an error rate of 14.62%. The other models, like Theta and ARFIMA, struggled mightily, missing the mark by huge margins (over 40% and 60% respectively), suggesting that the Somali population growth is too wild and complex for those simpler tools to handle.
So, what does the winning robot say about the future? The results are staggering. The study suggests that Somalia is in the middle of a "metropolitan revolution." By 2030, the urban population is projected to hit roughly 13.1 million people. But the real shocker is the long-term view: by 2050, the city population is expected to double again, reaching approximately 22.2 million people. That is a 113.8% increase from today's numbers.
The paper is careful to note that this isn't a guaranteed fact written in stone, but a strong projection based on the best mathematical tools available. The data suggests that the growth isn't slowing down; it's actually speeding up. This contradicts some older theories that say cities eventually stop growing and level off like a flat plateau. Instead, the Somali data looks more like a rocket that hasn't hit its brakes yet. The researcher argues that this isn't just because people are moving to cities for jobs (the "pull" factor), but also because of tough conditions in the countryside, like drought and land degradation (the "push" factor).
The takeaway is clear: if the current trend holds, Somalia's cities will be packed with twice as many people as they are today by the middle of the century. The paper suggests that without careful planning, this rapid expansion could lead to overcrowding and environmental stress, like "urban heat islands" where concrete gets too hot. However, if leaders use these numbers to plan ahead—building better infrastructure and services—this massive growth could become a powerful engine for the country's future. The math says the train is moving fast; the question is whether the tracks are ready for it.
Drowning in papers in your field?
Get daily digests of the most novel papers matching your research keywords — with technical summaries, in your language.