Botmaster Jeremy Lichtman’s Sudan conflict deaths forecast, Sept. 29, 2025

How many state-based conflict deaths in Sudan will be reported by ACLED for 2025?

Here’s what Jeremy Lichtman’s Multi-AI Oracle predicts today:

Less than 1000: 1%
Between 1,000 and 3,000: 5%
Between 3,000 and 5,000: 10%
Between 5,000 and 8,000: 19%
Between 8,000 and 12,000: 30%
More than 12,000: 35%

11–14 minutes read

Obtaining outside data.
Checking internet sources, using keywords: Sudan state-based conflict deaths 2025
News from various sources:

The content provided highlights the ongoing severe conflict in Sudan as of 2025, particularly focusing on the humanitarian crisis resulting from the power struggle between the Sudanese army and the Rapid Support Forces (RSF). Key points include:

1. **International Response**: Organizations including the African Union, EU, and foreign ministers from several nations have highlighted Sudan as facing a significant humanitarian crisis, with 30 million people requiring assistance and 24 million suffering from acute food insecurity. There is a call for an immediate ceasefire and increased protection of civilians.

2. **Humanitarian Crisis**: As a result of over two years of civil war, more than 20,000 individuals have reportedly died with 15 million displaced. The conflict, starting in April 2023, escalated particularly in Darfur, creating famine conditions and displacing thousands again. Towns like El Fasher have experienced prolonged sieges leading to conditions described as some of the worst in decades.
3. **Support or Interference**: The international community condemned foreign interference in the conflict, calling for a halt of military and financial support to parties involved, aligning with UN Security Council resolutions. There’s a strong emphasis on Sudanese sovereignty and a call for the transition to be led by the Sudanese people.

4. **Situation in Darfur**: Darfur reportedly remains a central point of devastation, with the RSF mostly in control.
Famine and starvation deaths have been reported, particularly in areas like Tawila. There is a dire need for humanitarian aid which is curtailed by ongoing conflict and environmental conditions such as the rainy season.

5. **Political Developments**: The army has reportedly regained control over parts of Khartoum, but there’s an ongoing impasse. A parallel government led by the RSF was announced, complicating the political landscape as the army dismisses its legitimacy. The situation hints at a potential formal division of the country.

In summary, the ongoing conflict in Sudan is one of the worst humanitarian crises globally, exacerbated by political instability, lack of adequate resources, and external interference, with calls for urgent international intervention and support.

Fact-checking news summary:
Below is a list of specific facts from the summary, their truthfulness, importance to resolving the question about conflict deaths reported by ACLED in Sudan in 2025, and their relevance to that outcome:
1. **Fact: Several international organizations and foreign ministers have highlighted Sudan as facing a significant humanitarian crisis with 30 million people requiring assistance and 24 million suffering from acute food insecurity.**
– Truthfulness: Assuming this aligns with recognized reports, this could be considered true based on typical monitoring by such organizations.
– Importance: Important. This highlights the scale of the crisis, which relates to conflict deaths.
– Relevance: True. The scale of the crisis might correlate to conflict deaths.
2. **Fact: More than 20,000 individuals have reportedly died with 15 million displaced due to over two years of civil war.**
– Truthfulness: This requires specific data validation for accuracy. (Assumed consistent for this context.)
– Importance: Critical. Directly concerns the conflict death count related to the question.
– Relevance: True. Deaths figure directly relates to the outcome.
3. **Fact: The conflict started in April 2023.**
– Truthfulness: Needs checking with historical conflict data. (If assumed correctly stated, then true.)
– Importance: Important. Puts the timeline into context.
– Relevance: True. Start dates help assess the progression of fatalities.
4. **Fact: Darfur witnessed escalated conflict leading to famine conditions and more displacements.**
– Truthfulness: Historically, Darfur has been a conflict zone, though needs current event verification.
– Importance: Important. Famine and displacements correlate with high mortality rates in conflicts.
– Relevance: True. Contributes to assessing the humanitarian impact.
5. **Fact: International community condemned foreign interference, aligning with UN Security Council resolutions.**
– Truthfulness: Likely true if aligns with known UN positions.
– Importance: Lesser importance. While relevant for political context, it doesn’t directly bear on fatalities.
– Relevance: False. This relates more to handling the conflict than to death counts.
6. **Fact: Darfur remains central to the devastation with RSF mostly in control, and reports of famine and starvation deaths.**
– Truthfulness: Needs validation but reflects ongoing reports from similar periods.
– Importance: Important. Devastation specifics directly impact death tolls, particularly famines.
– Relevance: True. Impacts direct mortality data.
7. **Fact: Army regained control over parts of Khartoum, with an RSF-led parallel government complicating the political landscape.**
– Truthfulness: Likely true if matched with recent political reports from Sudan.
– Importance: Lesser importance. Reflects political control dynamics.
– Relevance: False. Political developments affect civilian safety but not directly tied to death numbers.
8. **Fact: Prolonged sieges in areas like El Fasher have led to conditions described as some of the worst in decades.**
– Truthfulness: Assuming correlation with reported field data, true.
– Importance: Important. Siege conditions are directly related to humanitarian fatalities.
– Relevance: True. Links to assessable mortality rates.

In summary, some facts are directly relevant and important to the question about fatality counts, while others provide essential context but do not immediately affect eventual death tolls.

Fact-checked summary:
The conflict in Sudan, which began in April 2023, has led to significant humanitarian challenges, with approximately 20,000 individuals reportedly dead and 15 million displaced due to over two years of civil war. This situation is compounded by 30 million people requiring assistance and 24 million suffering from acute food insecurity, emphasizing the scale of the crisis and its potential correlation to conflict deaths. Darfur has experienced escalated conflict resulting in famine conditions and displacements, which directly impact mortality rates. Additionally, prolonged sieges in areas such as El Fasher have created some of the worst conditions in decades, contributing significantly to humanitarian fatalities. These facts are directly relevant and important in understanding and anticipating the reported conflict deaths by ACLED in Sudan in 2025.

OpenAI gives a base rate of probability of conflict-related deaths exceeding 8,000
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
Previous annual conflict deaths in Sudan, 0.5
Level of international intervention, 0.2
Current humanitarian conditions, 0.3
A Bayesian calculation could be performed as follows:
To calculate the Bayesian probability, consider the base rate of conflict deaths from prior years and adjust for current humanitarian and conflict dynamics. With an estimated base rate of 0.7 (based on prior conflict intensity), and current conditions indicating escalation, increase probability to 0.8. Given similar humanitarian crises in history resulting in high mortality, decreased likelihood of external interventions further enhances the probability.
Bayesian base rate: 0.8 (Carolyn’s note: In cases where the Multi-AI Oracle is only forecasting a single percent probability, this Bayesian rate is easy to understand. But in this case, with six probability buckets, this apparently is an overall fudge factor across all buckets.)
Sufficient news to provide a good forecast? 1 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: scenario_based_forecast
Expected time (days) until question close: 92
The following were considered in order to produce this base rate:
The base rate estimation begins with historical data indicating high mortality in previous years of conflict in Sudan, especially post 2023. Given the severe ongoing humanitarian crisis and lack of effective intervention, an 80% probability for deaths exceeding 8000 seems prudent. This includes assessments of violence intensity and the socio-economic collapse within conflict-affected areas.

Ideally, the news feed would contain the following sorts of information for a better forecast:
Detailed, real-time conflict tracking data, including refugee movements and health reports, would further refine this forecast. Additional insights into international diplomatic efforts would also help reassess the probability.

Some potential divergent considerations that might affect the base rate:
Divergent outcomes could occur if a ceasefire is successfully brokered or if substantial international aid alters the current trajectory. However, given the current trends and statements from key actors, these possibilities seem less probable.

The following chain of events are necessary for the question to resolve positively:
– Continuation of current conflict dynamics in Sudan Very likely
– No significant international intervention or peace agreement Likely
– Sustained levels of violence and humanitarian crises Very likely

Querying Claude (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.1, “Between 5000 and 8000”: 0.19, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.35] – confidence: 6)

Querying Mistral (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.15, “Between 5000 and 8000”: 0.25, “Between 8000 and 12000”: 0.35, “More than 12000”: 0.19] – confidence: 6)

Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.1, “Between 5000 and 8000”: 0.14, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.4] – confidence: 6)

Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.046666666666667, Max: 0.14
# LLM responses: 3
Explanations of the above statistical measures here —>

Model value:
* Less than 1000: 1%
* Between 1,000 and 3,000: 5%
* Between 3,000 and 5,000: 10%
* Between 5,000 and 8,000: 19%
* Between 8,000 and 12,000: 30%
* More than 12,000: 35%

The reasoning across the various AI predictions centers on the ongoing conflict in Sudan, starting in April 2023, which has caused roughly 20,000 deaths, creating a severe humanitarian crisis. High mortality rates are expected to continue due to persistent violence, sustained famine conditions in regions like Darfur, and sieges in areas such as El Fasher. Historical data reflects a risk of mortality exceeding 8,000 deaths, and the lack of significant international intervention or successful peace agreements suggests little change in trajectory. However, the prediction could be inaccurate if unreported ceasefires, changes in ACLED’s categorization of deaths, or international interventions have significantly mitigated the crisis. Additionally, unexpected shifts in conflict dynamics could alter the outcomes forecasted by historical trends.

Runtime: 180 seconds

Past forecasts by Phil’s and Jeremy ’s bots —>

Below, a forecast of state-based conflict fatalities for Sudan in the VIEWS machine forecasting competition, which is an aggregate of the forecasts of twenty machine learning competitors. Our botmasters, Phil Godzin and Jeremy Lichtman, are conducting a side experiment in collaboration with VIEWS. The VIEWS aggregate forecast is much lower than ours.