Afghanistan: The “Fighting Season” & Detecting Seasonality Using Facebook’s Prophet (Working Draft)
Disclaimer: This is a working draft, i.e., research in progress and is such, published to elicit comments/advice/recommendations and to encourage debate. The views expressed in this article are solely mine, and do not represent the views of my employer.
On October 7, 2001, the United States launched combat operations under Operation Enduring Freedom to topple the Taliban regime and eliminate al Qaeda. The Taliban regime fell quickly and U.S. officials declared an end to major combat operations on May 1, 2003. However, over a decade and a half later, the United States and its NATO allies are still there, mired in a seemingly endless conflict that has consumed innumerable lives.
Currently (March 12, 2019), as Taliban negotiators entered a third week of talks with American diplomats in Qatar, the New York Times reported that Taliban forces had killed or captured an entire Afghan National Army company of more than 50 soldiers in northwestern Badghis Province.
Given the importance of the ongoing conflict, I wanted to write several articles on Afghanistan. This first article will be focusing on identifying the existence of seasonality (aka the ‘fighting season”) in Afghan conflict fatality data.
Afghanistan’s “Fighting Season”
Since the United States first foray into Afghanistan, the idea of the so-called “fighting season” has been well established. The fighting season is the term used to describe the seasonality in armed offensives by different militant groups, and in particular, the Taliban. The Taliban’s annual Spring offensive, often actually announced in statements, comes with an escalation of violence around Afghanistan.
Barnett Koven, a Senior Researcher at the University of Maryland’s National Consortium for the Study of Terrorism and Responses to Terrorism (START), summarised it succintly on the Small Wars Journal: “a confluence of three factors — the conclusion of poppy cultivation, improved weather conditions and recesses in madrassas in neighboring Pakistan — have made spring Afghanistan’s ‘fighting season.’”
Here, Figure 1 shows the statistics; daily total fatalities based on recorded armed clashes between the beginning of 2017 to March 2019.
However, Koven also argued that the Taliban’s fighting season may be ending. Based on statistics from the Global Terrorism Database, Koven found that “2016 marked the first year, since insurgent violence first surged in 2006, where the arrival of spring did not correlate with an increase in insurgent attacks.”
This warrants an interesting question. Has Afghanistan’s fighting season ended, or does seasonality still exist in the conflict? This article aims to address this question by utilizing daily fatality data from Afghanistan, and applying conventional techniques to detect seasonality.
Methodology
Data Description
In this analysis, I use statistics from the Armed Conflict Location & Event Data Project (“ACLED”). ACLED is a disaggregated conflict collection, analysis and crisis mapping project that collects the dates, actors, types of violence, locations, and fatalities of all reported political violence and protest events across the globe. In this specific instance, I am utilizing ACLED’s data for Afghanistan from 2017 to March 2019, as shown in Table 1.
Bar charts & Box plots
In order to identify the existance of seasonality in Afghan daily fatality data, we will first explore characteristics in the data by visually examining mean monthly fatality data. Here, Figure 2 shows the mean monthly fatality data for Afghanistan. It’s possible to discern some seasonality in the monthly mean, for example May, July and August have the highest monthly means.
Figure 3, shows a boxplot of the daily fatality data grouped by month. The boxplot includes the mean, median, max, min, percentiles, and the outliers. By examining the boxplots, it is possible to visually discern some evidence of a seasonal pattern. Outlier data points are highest among the “fighting season”, and median daily fatality for each month are similarly seasonal. The boxplot also shows that the distribution varies by month. For example, daily fatality data in July has significant skew. Overall, the boxplots seem to support the hypothesis that Afghan fatality data have an annual seasonal pattern with higher levels between May-August, and lower levels between November-February.
However, it is also clear that June has a consistently lower total fatality level in Afghanistan. It it thus important to consider the effect of certain Islamic observances such as Ramadan that may potentially be affecting the data. Ramadan occurs on the ninth month of the Islamic calendar, and is observed by Muslims worldwide as a month of fasting (Sawm). Typically, Ramadan occurs sometime between the months of May and June in the Gregorian calendar (used here), and lasts 29–30 days. As the observance of Ramadan may reduce the frequency of armed clashes between different actors, it is important to take into account such effects when examining seasonality in the data.
Facebook’s Prophet: Fourier Order for Seasonalities
Prophet is an open source forecasting procedure released by Facebook’s Core Data Science team. It provides a completely automated forecast of time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. Prophet is also robust to missing data and shifts in the trend, and typically handles outliers well.
Prophet relies on a Fourier series to provide a flexible model of periodic effects (Taylor & Letham, 2017). A Fourier series is basically a way to represent a function as the sum of simple sine waves. Prophet utilizes it to estimates seasonality in the time series data. A partial Fourier sum can approximate an arbitrary periodic signal, and the numbers of terms in the partial sum (the order) is a parameter that determines how quickly the seasonality can change. For this article, Prophet was implemented using R.
Figure 4 above shows the initial forecast from Prophet. However, this plot doesn’t show seasonality. By using the ‘prophets_plot_components()’ function, the forecast can be broken down into its individual components.
Here, Figure 5 shows the daily fatality data from Afghanistan broken down into its individual components: trend, weekly seasonality, and yearly seasonality. The ‘yearly’ component shows strong evidence of seasonality, with the fatality numbers increasing during the spring and summer seasons, then decreasing during the winter. The frequency of fatalities from armed clashes between Afghan security forces and militia groups clearly varies in a seasonal pattern, and strongly corresponds with the historic fighting season.
Interestingly enough, there also seems to be evidence of weekly seasonality, with Saturday to Monday having the highest fatality numbers. Additionally, the trend component shows the forecast of total fatality numbers to be on the rise.
Concluding remarks
In short, Afghanistan’s daily total fatality data from ACLED seems to show no apparent decline to the seasonality in fighting. Prophet disaggregated the Afghan data into individual components, showing both yearly and weekly seasonality. The yearly component showed that the historic fighting season from May to August was still apparent, with the caveat of a decrease during religious observances. There was also evidence of weekly seasonality, with Saturday to Monday having higher levels of fatalities.
Nevertheless, with rising global temperatures due to climate change, it is unclear whether the fighting season will continue into the near future. Furthermore, the prospects of a potential peace deal between the U.S. and the Taliban may present a future where the fighting season is no longer necessary.
References
- Taylor SJ, Letham B. 2017. Forecasting at scale. PeerJ Preprints 5:e3190v2 https://doi.org/10.7287/peerj.preprints.3190v2
- THE END OF AFGHANISTAN’S SPRING FIGHTING SEASONS AND THE DEMISE OF THE AFGHAN NATIONAL SECURITY FORCES https://smallwarsjournal.com/jrnl/art/the-end-of-afghanistan’s-spring-fighting-seasons-and-the-demise-of-the-afghan-national-secu
