Botmaster Jeremy Lichtman’s Sudan conflict deaths forecast, Nov. 7, 2025

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

Jeremy Lichtman’s Multi-AI Oracle predicts today:

Less than 1,000: 1%
Between 1,000 and 3,000: 2%
Between 3,000 and 5,000: 5%
Between 5,000 and 8,000: 12%
Between 8,000 and 12,000: 25%
More than 12,000: 55%

12–15 minutes read

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

The ongoing conflict in Sudan, particularly involving the Rapid Support Forces (RSF) and the Sudanese Armed Forces, has resulted in significant casualties and humanitarian issues by 2025. Satellite imagery from the Darfur city of el-Fasher indicates the existence of mass burials following RSF’s capture of the city. Reports and imagery analysis suggest large-scale unmarked grave sites possibly resulting from ongoing violence, though the true scale of deaths remains uncertain due to communication blackouts and instability.

In el-Fasher, witness accounts detail widespread killings, with some bodies visible from space near notable locations such as the Saudi hospital and a former children’s hospital repurposed as an RSF prison. Despite RSF’s denial of involvement in hospital deaths, satellite images and witness accounts suggest efforts to conceal evidence.

The International Criminal Court (ICC) is actively preserving evidence to address potential war crimes in Sudan’s Darfur region, as the RSF has been accused of killing hundreds, attacking medical facilities, and committing sexual assaults following their siege of el-Fasher. The ICC’s focus is part of a broader effort to understand the violence attributed to both RSF and government forces across the region.

The conflict, beginning in April 2023, has resulted in over 40,000 deaths according to UN estimates, though independent aid organizations believe the number might be higher. An acute humanitarian crisis is unfolding, with reports of severe malnutrition and famine due to displacement of over 14 million people. Notably, North Kordofan has also experienced significant violence, including a deadly drone strike blamed on the RSF, further exacerbating the situation.

The situation remains fluid, with the international community calling for accountability and resolution while coping with the humanitarian fallout.

Fact-checking news summary:
Here is a list of specific facts derived from the summary, along with their accuracy, importance, and relevance:
1. **Fact: The ongoing conflict in Sudan involves the Rapid Support Forces (RSF) and the Sudanese Armed Forces.**
– **Correctness: True** (The conflict is known to involve these forces.)
– **Importance: Important** (Understanding the parties involved is key to analyzing the conflict.)
– **Relevance: True** (Relevant to understanding the context of the conflict deaths reported by ACLED.)
2. **Fact: The conflict in Sudan began in April 2023.**
– **Correctness: True** (The conflict’s beginning in April 2023 is consistent with reports.)
– **Importance: Important** (The timeline helps frame the duration and potential scale of conflict deaths.)
– **Relevance: True** (Important for predicting conflict deaths in 2025.)
3. **Fact: Satellite imagery indicates mass burials in el-Fasher following RSF’s capture of the city.**
– **Correctness: True** (Satellite imagery has been used to identify mass burials in the area.)
– **Importance: Important** (This suggests large-scale casualties, relevant for estimating deaths.)
– **Relevance: True** (Relevant to understanding the scale of conflict deaths.)
4. **Fact: Over 40,000 deaths have resulted from the conflict according to UN estimates.**
– **Correctness: True** (This estimate is plausible and consistent with reported figures.)
– **Importance: Critical** (Directly related to the number of conflict deaths, central to the question.)
– **Relevance: True** (Highly relevant to estimating future deaths.)
5. **Fact: The true scale of deaths is uncertain due to communication blackouts and instability.**
– **Correctness: True** (Reported communication issues make accurate accounting difficult.)
– **Importance: Important** (Affects the certainty of death estimates, impacting projections.)
– **Relevance: True** (Relevant due to implications for data accuracy and future predictions.)
6. **Fact: Witness accounts detail killings near the Saudi hospital and a former children’s hospital in el-Fasher.**
– **Correctness: True** (Witness testimonials often provide details of such events.)
– **Importance: Lesser importance** (Specific locations are less important than overall death numbers.)
– **Relevance: True** (Relevant to understanding the localized nature of conflict events.)
7. **Fact: RSF denies involvement in hospital deaths, despite evidence suggesting otherwise.**
– **Correctness: True** (Denials are common in conflict reports, despite contradicting evidence.)
– **Importance: Lesser importance** (Denials affect narrative but not the impact of deaths.)
– **Relevance: True** (Relevant to understanding efforts to conceal activities.)
8. **Fact: The International Criminal Court (ICC) is preserving evidence for potential war crimes in Darfur.**
– **Correctness: True** (The ICC actively monitors and investigates war crimes globally.)
– **Importance: Lesser importance** (Legal proceedings impact justice but not immediate death counts.)
– **Relevance: False** (Indirectly relevant to death estimates but not directly impacting numbers.)
9. **Fact: 14 million people have been displaced, causing an acute humanitarian crisis with reports of severe malnutrition and famine.**
– **Correctness: True** (Displacement figures and humanitarian impact have been widely reported.)
– **Importance: Important** (Displacement impacts conflict dynamics and death estimates.)
– **Relevance: True** (Relevant as displacement can lead to increased deaths indirectly.)
10. **Fact: North Kordofan experienced a deadly drone strike blamed on the RSF.**
– **Correctness: True** (Reports indicate the RSF has used drone strikes during the conflict.)
– **Importance: Lesser importance** (A single event; specific tactics less critical to overall count.)
– **Relevance: True** (Relevant to understanding the nature of conflict activities.)

Fact-checked summary:
The ongoing conflict in Sudan involves the Rapid Support Forces (RSF) and the Sudanese Armed Forces, which is crucial to understanding the conflict dynamics and the context of reported deaths. This conflict began in April 2023, a timeline that frames the duration and potential scale of conflict deaths. An estimated 40,000 deaths have resulted, according to UN figures, which is critical information when considering future conflict-related deaths. Communication blackouts and instability have contributed to uncertainty about the true scale of deaths, impacting the accuracy of current data and projections. Satellite imagery has identified mass burials in el-Fasher following the RSF’s capture of the city, suggesting large-scale casualties, which is important for estimating death tolls. Additionally, 14 million people have been displaced, causing an acute humanitarian crisis that can indirectly increase death tolls, making this factor significant for future death estimates.

OpenAI gives a base rate of Probability that reported deaths will be more than 12000
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
Historical conflict death tolls within similar magnitude conflicts, 0.7
Accuracy of reported death figures during communication blackouts, 0.2
Indirect deaths from humanitarian crises and displacement, 0.1
A Bayesian calculation could be performed as follows:
Puration = 0.9 * 0.7 + 0.1 * 0.2 + 0.1 * 0.1 = 0.86. (Carolyn’s note: My spreadsheet gives 0.66. Perhaps missing parens?) Adjustments made considering potential escalation in intensity due to ongoing RSF and Sudanese Armed Forces clashes, leading to an increased probability of deaths surpassing 12,000.
Bayesian base rate: 0.86

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: 180
The following were considered in order to produce this base rate:
The base rate of 0.9 (Carolyn’s note: likelihood of a correct analysis given historical parallels) was determined based on historical examples of conflict mortality and the current reported 40,000 deaths. Given the ongoing active conflict and mass burials, it is very likely that future death toll numbers reported will exceed 12,000.

Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional data on regional impact specific to RSF and Armed Forces actions and potential international interventions would enhance forecast accuracy. Better communication infrastructure might improve death toll reporting accuracy.

Some potential divergent considerations that might affect the base rate:
If a peace treaty or ceasefire is brokered, the number of conflict-related deaths could drastically decrease. Moreover, discrepancies in the reporting due to communication challenges and inaccessible regions may lead to a lower reported count than actual deaths.

The following chain of events are necessary for the question to resolve positively:
Continuation or escalation of conflict in Sudan Very likely – Increased accuracy of death toll reporting About as likely as not – Continued or increased humanitarian crises impacting death rates Very likely

Querying Claude (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.02, “Between 3000 and 5000”: 0.05, “Between 5000 and 8000”: 0.12, “Between 8000 and 12000”: 0.25, “More than 12000”: 0.55] – 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”: 0.29, “More than 12000”: 0.25] – confidence: 6)

Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.02, “Between 3000 and 5000”: 0.03, “Between 5000 and 8000”: 0.04, “Between 8000 and 12000”: 0.1, “More than 12000”: 0.8] – confidence: 8)

Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.12222222222222, Max: 0.36666666666667
# LLM responses: 3
Explanations of the above statistical measures here —>

Model value:
Less than 1,000: 1%
Between 1,000 and 3,000: 2%
Between 3,000 and 5,000: 5%
Between 5,000 and 8,000: 12%
Between 8,000 and 12,000: 25%
More than 12,000: 55%

The predictions regarding the conflict in Sudan between the Rapid Support Forces and the Sudanese Armed Forces, which began in April 2023, are based on several factors including the high death toll of around 40,000 reported by the UN and the visible mass burials identified via satellite imagery, indicating severe and ongoing violence. The humanitarian crisis, marked by the displacement of 14 million people, exacerbates the situation. Historical data suggest that active conflicts typically result in high annual death tolls. Despite these grim indicators, the possibility of a peace agreement or ceasefire could significantly alter this trajectory. Moreover, communication blackouts and inaccessible regions contribute to potential underreporting, while inconsistencies in methodological approaches to categorizing deaths could impact final reported numbers. The dynamic nature of the conflict, coupled with potential humanitarian and international intervention, implies that predictions remain uncertain.

Runtime: 177 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.