Sudan updates from AI Botmaster Phil Godzin of April 21, 2025

How many conflict deaths will there be in Sudan in 2025?

Phil’s pgodzinai, a multi-GenAI bot, is a side competitor with the machine forecasting bots of the VIEWS competition.

Here’s what Phil’s pgodzinai predicts today:

* Less than 1000: 1%
* Between 1000 and 3000: 3%
* Between 3000 and 5000: 11%
* Between 5000 and 8000: 26%
* Between 8000 and 12000: 35%
* More than 12000: 24%

Model’s Answer: # Analysis of Conflict Deaths in Sudan for 2025
## Understanding the Current Context
The conflict in Sudan has been ongoing since April 2023, primarily between the Sudanese Armed Forces (SAF) and the Rapid Support Forces (RSF). Based on the most recent reports from April 2025, the situation remains extremely volatile with concerning escalations, particularly in Darfur and North Sudan.

Several key data points emerge from the research assistants’ reports:
1. **Recent death tolls**: Multiple sources confirm over 300 civilians killed in just two days (April 14-15, 2025) during RSF attacks on displacement camps in North Darfur. This indicates an extremely high casualty rate during periods of intense fighting.
2. **Cumulative deaths**: UN sources cite at least 24,000 confirmed deaths since the conflict began in April 2023, though some humanitarian organizations estimate the total could be as high as 150,000 due to underreporting and limited access to conflict zones.
3. **Escalating violence**: The conflict shows clear signs of intensification in April 2025, with reports of “unprecedented” and “spiraling” violence, particularly following the SAF’s recapture of Khartoum in late March 2025.
4. **Humanitarian catastrophe**: The crisis is compounded by widespread food insecurity affecting 24.6 million people, with famine declared in 10 regions. Around 12.4 million people have been displaced, with 450,000 fleeing in April 2025 alone.

## Forecasting Methodology
To forecast conflict deaths for the remainder of 2025, I’ll consider:
1. **Extrapolating from recent trends**: The high casualty rate of 300+ deaths in just two days suggests periods of intense violence. If this rate continued uninterrupted, it would result in over 45,000 deaths for the remainder of 2025 (approximately 150 deaths per day × 255 days left in 2025). However, such sustained high intensity is unlikely.
2. **Historical averages**: Reports suggest approximately 24,000-150,000 total deaths over two years (April 2023-April 2025), averaging 12,000-75,000 per year. One source mentioned an average of 50 deaths per day in 2023-2024, which would translate to about 18,250 deaths annually.
3. **Current trajectory**: Recent reports indicate an escalation in violence with daily death rates reportedly tripling in February 2025 to around 267 civilians per week, or about 38 per day. If this rate continued, it would yield approximately 9,700 additional deaths in 2025.
4. **Compounding factors**: The deteriorating humanitarian situation, including widespread famine and destruction of 70% of healthcare infrastructure, suggests indirect conflict deaths will likely increase.

## Time Considerations
As of today (April 21, 2025), approximately 3.5 months of 2025 have elapsed, with 8.5 months remaining until the resolution date (January 1, 2026). This means:
1. **Deaths already occurred in 2025**: If we assume the conflict has maintained the intensity reported for February-April (approximately 38 deaths per day), around 3,800 conflict deaths may have already occurred in 2025.
2. **Projection for remainder of 2025**: The evidence suggests the conflict is escalating rather than abating. With no signs of successful peace negotiations, continued or increased violence is likely for the remainder of the year.


## Range Estimations
Given the evidence, I’ll assess each range option:
1. **Less than 1000**: Extremely unlikely given that we’re already in April with escalating violence and reports suggesting possibly thousands of deaths have already occurred in 2025.
2. **Between 1000 and 3000**: Also very unlikely. Reports of 300+ deaths in just two days and consistent violence suggest this threshold has likely already been approached or surpassed by April.
3. **Between 3000 and 5000**: Somewhat unlikely. If even moderate intensity fighting continues, this range will likely be exceeded, especially considering we still have over 8 months left in the year.
4. **Between 5000 and 8000**: Plausible. This range would align with a scenario where the current level of violence moderates somewhat but continues throughout the year.
5. **Between 8000 and 12000**: Highly plausible. This aligns with both historical averages and recent escalations, especially if the intensity seen in April continues with some fluctuations.
6. **More than 12000**: Plausible if recent escalations continue or intensify further. The reported 300+ deaths in two days demonstrates the potential for extreme spikes in violence that could push totals above this threshold.

## Sources of Uncertainty
Several factors create considerable uncertainty in this forecast:
1. **Reporting limitations**: Access constraints and the chaotic nature of the conflict mean actual death tolls are likely underreported.
2. **Potential for mediation**: While current reports suggest resistance to peace talks, international pressure could potentially lead to ceasefire agreements later in the year.
3. **Seasonal factors**: Patterns of fighting may vary with seasonal changes, particularly during the rainy season.
4. **Indirect deaths**: The forecast must account for deaths indirectly caused by the conflict, such as those from famine and lack of medical care, which are difficult to quantify precisely.

## Final Probability Assessment
Based on the comprehensive analysis of recent developments, historical patterns, and the current trajectory of the conflict, I assign the following probabilities:

* Less than 1000: 1%
* Between 1000 and 3000: 3%
* Between 3000 and 5000: 11%
* Between 5000 and 8000: 26%
* Between 8000 and 12000: 35%
* More than 12000: 24%

Details on how Phil’s pgodzinai arrived at the above forecasts –>

Past forecasts by both Phil and Jeremy on Sudan’s conflict fatalities —>

Background on VIEWS: Near the end of 2024, the latest forecasting competition of the Violence and Impacts Early-Warning System (VIEWS) was launched. On Dec. 4, 2024, during a telecon, a group of machine forecasting experts involved in VIEWS observed Jeremy’s demonstration of his Multi-AI Oracle. Although it was too late for Jeremy to sign up as a VIEWS competitor, they urged him to run a side competition for everyone’s benefit. Jeremy chose their Sudan conflict deaths question.

Below, map of control in Sudan’s civil war as of April 15, 2025.

Below, before and after pictures of the devastation of the civil war in Sudan.


Carolyn has checked Sudan’s news sites below to ensure that they are still in operation. However, given the widespread violence in Sudan, any of these could go offline without warning.

https://www.alnilin.com/
https://www.alrakoba.net/
https://www.altaghyeer.info/ar/
https://www.altaghyeer.info/en/
https://www.alttahrer.com/
https://www.alzaeemsd.com/
https://www.assayha.net
https://www.cover-sd.com/
https://kushnews.net/
https://rakobanews.com
https://www.sudanakhbar.com/
https://sudanjem.com/
https://suna-sd.net/en
https://sudantimes.net/
https://www.sudantribune.net/
https://www.sudantribune.com/
https://sudaneseonline.com/
https://www.sudanile.com/
https://sudanow-magazine.net/
https://www.sudaress.com/
https://www.tagpress.net/

Author