Sudan updates from AI Botmaster Phil Godzin of April 19, 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: (Carolyn’s note: These probabilities are experimental. It is too early to know how accurate these will turn out to be. However, speaking as one of RAND’s top ranked pro forecasters, I  substantially agree with pgodzinai’s results.)
* Less than 1000: 1%
* Between 1000 and 3000: 3%
* Between 3000 and 5000: 5%
* Between 5000 and 8000: 12%
* Between 8000 and 12000: 24%
* More than 12000: 55%

Model’s Answer: # Analysis of Sudan Conflict Deaths in 2025
To forecast the number of conflict deaths in Sudan for 2025, I need to carefully analyze recent developments alongside historical patterns while considering we’re already in mid-April 2025, with approximately 8.5 months remaining in the year.

## Current State of the Conflict
The Sudan conflict, which began in April 2023, is now in its third year with no signs of resolution. Multiple sources confirm that the situation remains severe:
1. **Death Toll to Date**: Sources indicate that cumulative deaths since the conflict began in April 2023 range from 24,000 (UN’s conservative count) to approximately 150,000 (higher estimates from MEI and CFR). This discrepancy likely reflects differences in counting methodology, with the UN typically reporting only verified deaths.
2. **Recent Escalation**: Particularly concerning is the report of over 300 civilian deaths in just two days in North Darfur in mid-April 2025. This suggests an intensification of violence. Additional reports mention 57 deaths in El Fasher and 400 killed in recent attacks.
3. **Territorial Control**: The SAF has regained control of Khartoum, while the RSF controls most of Darfur and parts of the south. This territorial split increases the likelihood of continued fighting.
4. **Humanitarian Crisis**: Famine has been declared in North Darfur, with 30.4 million people needing aid and 3.2 million children facing acute malnutrition. These conditions typically increase mortality beyond direct combat deaths.

## Death Rate Estimation
To estimate the 2025 death toll, I need to consider:
1. **Deaths Already Occurred**: Since we’re in mid-April, approximately 3.5 months of 2025 have elapsed. If we assume the conflict has maintained relatively consistent intensity, a significant portion of the annual death toll has already occurred.
2. **Recent Death Rate**: The report of 300+ deaths in two days indicates a potential rate of 150 deaths per day in high-intensity periods. While this rate may not be sustained throughout the year, it suggests that even brief periods of intense fighting can substantially increase the death toll.
3. **Indirect Deaths**: The famine and collapse of healthcare systems will contribute to the overall death toll, though these may be counted differently depending on the source.

## Calculation Approach
Let’s consider different scenarios:
1. **Conservative Scenario**: Assuming a lower average of 30 direct conflict deaths per day for the remainder of 2025 (about 20% of the recently reported peak):
– 30 deaths/day × 255 days remaining ≈ 7,650 deaths
– Plus an estimated 3,000-4,000 deaths from January through mid-April
– Total: 10,650-11,650 deaths
2. **Moderate Scenario**: Assuming an average of 50 direct conflict deaths per day:
– 50 deaths/day × 255 days remaining ≈ 12,750 deaths
– Plus an estimated 5,000-6,000 deaths from January through mid-April
– Total: 17,750-18,750 deaths
3. **High-Intensity Scenario**: Assuming periods of intense fighting similar to recent reports:
– 75 deaths/day × 255 days remaining ≈ 19,125 deaths
– Plus an estimated 7,000-9,000 deaths from January through mid-April
– Total: 26,125-28,125 deaths

Given the recent escalation, territorial divisions, and humanitarian crisis, I believe the moderate to high-intensity scenarios are more likely than the conservative one.

## Forecast Confidence and Adjustments
Several factors increase uncertainty in this forecast:
1. **Potential Peace Process**: Although unlikely given recent reports, a successful peace agreement could dramatically reduce deaths in the latter part of 2025.
2. **Seasonal Variations**: Conflict intensity may vary with seasonal factors like weather conditions.
3. **Data Reliability**: The significant discrepancy between reported death counts (24,000 vs. 150,000) indicates substantial uncertainty in mortality data.
4. **Humanitarian Crisis Acceleration**: The worsening famine could cause indirect deaths to increase exponentially.
Given these uncertainties and to avoid overconfidence, I need to distribute probability across multiple outcomes while weighing heavily toward the higher death toll ranges given recent trends.

## Final Forecast
Based on the analysis of recent developments, historical patterns, and the current trajectory of the conflict, my forecast for Sudan conflict deaths in 2025 is:
Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 3%
* Between 3000 and 5000: 5%
* Between 5000 and 8000: 12%
* Between 8000 and 12000: 24%
* More than 12000: 55%

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