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 1,000: 1%
* Between 1,000 and 3,000: 5%
* Between 3,000 and 5,000: 16%
* Between 5,000 and 8,000: 26%
* Between 8,000 and 12,000: 36%
* More than 12,000: 16%
11–13 minutes read
Obtaining outside data.
Checking internet sources, using keywords: ACLED Sudan conflict 2025
News from various sources:
The content extracted from the ‘ACLED Sudan conflict 2025’ web page covers the ongoing conflict in Sudan, specifically highlighting information from the Armed Conflict Location and Event Data Project (ACLED). Key points include:
1. **Human Impact and Displacement**: It is reported that 11 million people in Sudan, nearly one-third of the population, have been affected by the conflict between the Sudanese Armed Forces (SAF) and the paramilitary Rapid Support Forces (RSF). The violence has resulted in nearly 12 million people being displaced, making this the highest number of internally displaced persons globally.
2. **Conflict Analysis**: Since the conflict began on April 15, 2023, there have been over 6,200 incidents of political violence, with more than 17,000 deaths. The conflict initially involved the central Sudanese government and rebel groups but has since expanded into a civil war involving various local militias and foreign backers. Communities and ethnic militias, particularly in Darfur and Kordofan, have taken up arms and experienced fragmentation and intragroup conflict.
3. **Violence Trends**: Save the Children’s report from February 2025 highlights a recent spike in violence, noting over 700 violent events targeting civilians recorded in the last quarter of 2024. December alone saw 199 incidents, and the trend continues into 2025 with 208 such events in January, including significant attacks on civilian infrastructures like hospitals and schools in regions like North Darfur.
4. **Regional Dynamics**: The conflict exacerbates existing ethnic tensions, with alliances and allegiances shifting, notably in regions such as Darfur and Kordofan. In North Darfur, aligned and rival Arab militias have clashed over resources despite shared affiliations with RSF.
5. **Humanitarian Impact**: The continuing violence in Sudan has resulted in alarming levels of hunger and health crises, with famine-like conditions in at least five areas. Civilians, particularly children, are suffering from malnutrition and diseases like cholera and measles due to inadequate humanitarian access and ongoing fighting.
6. **Calls for Peace and Ceasefire**: There’s an emphasis on the need for a ceasefire, with RSF expressing an openness to ceasefire talks. However, despite this expressed willingness, the situation remains dire, with ongoing power struggles and violence that have made peace elusive.
The data provided by ACLED and reviewed by various organizations underscores the complexity and severity of Sudan’s current crisis, highlighting not only the human cost but the geopolitical implications of the continuing conflict.
Fact-checking news summary:
To address the question regarding the number of state-based conflict deaths that ACLED will report in Sudan in 2025, let’s extract specific facts from the summary provided. We’ll evaluate each fact for correctness, importance, and relevance to the question:
1. **Fact**: 11 million people in Sudan, nearly one-third of the population, have been affected by the conflict between the SAF and the RSF.
– Correctness: True (internally consistent with the scope of ongoing conflict reports).
– Importance: Lesser.
– Relevance: False (does not directly relate to conflict death counts).
2. **Fact**: Nearly 12 million people have been displaced due to the conflict in Sudan.
– Correctness: True (reasonable estimation based on the description of the conflict).
– Importance: Lesser.
– Relevance: False (displacement data does not directly relate to conflict deaths).
3. **Fact**: Since April 15, 2023, over 6,200 incidents of political violence have occurred, with more than 17,000 deaths.
– Correctness: True (consistent with conflict reports of high violence and death rates).
– Importance: Critical.
– Relevance: True (relevant to estimating future conflict deaths).
4. **Fact**: Over 700 violent events targeting civilians were recorded in the last quarter of 2024, with 199 incidents in December alone and 208 events in January 2025.
– Correctness: True (assuming this report’s credibility and internal consistency).
– Importance: Important.
– Relevance: True (indicates trend and severity that can affect death tolls).
5. **Fact**: In North Darfur, aligned and rival Arab militias have clashed over resources despite shared affiliations with RSF.
– Correctness: True (consistent with known regional dynamics and militia behavior).
– Importance: Important.
– Relevance: True (regional dynamics can influence conflict-related deaths).
6. **Fact**: The conflict has led to famine-like conditions in at least five areas, with civilians facing malnutrition and diseases due to inadequate humanitarian access.
– Correctness: True (reflects known humanitarian impacts of ongoing violent conflicts).
– Importance: Lesser.
– Relevance: False (indirectly related to death counts through health crises).
7. **Fact**: RSF expressed openness to ceasefire talks despite ongoing power struggles and violence.
– Correctness: True (typical considering the diplomatic stance of involved parties).
– Importance: Lesser.
– Relevance: False (potential ceasefire influence on deaths not clear).
The critical and relevant facts are primarily those that provide information about ongoing violence and incident counts, as these most directly impact estimates of state-based conflict deaths. Analysis should focus on trends over time and reported incident/death rates from authoritative sources like ACLED.
Fact-checked summary:
To estimate state-based conflict deaths that ACLED will report in Sudan in 2025, important and relevant facts include the occurrence of over 6,200 incidents of political violence since April 15, 2023, resulting in more than 17,000 deaths, highlighting the high violence and death rates in the region. Additionally, over 700 violent events targeting civilians were recorded in the last quarter of 2024, with 199 incidents in December and 208 events in January 2025, indicating an ongoing trend of violence that could affect future death tolls. Furthermore, clashes over resources in North Darfur among aligned and rival Arab militias, despite shared affiliations with the RSF, illustrate regional dynamics that can influence conflict-related deaths. These facts are critical and relevant in understanding the potential scale of conflict deaths to be reported by ACLED.
OpenAI gives a base rate of (Carolyn‘s note: OpenAI failed to return a value.)
The question difficulty is rated 8 (0 to 10)
Historical weighted factors include:
Recent incidents of political violence since April 2023, 0.7
Quarterly violent events targeting civilians, 0.6
Clashes in North Darfur involving militias, 0.5
A Bayesian calculation could be performed as follows:
Using the historical factors table, we assign a weight to each factor based on its influence on conflict deaths. We ascertain the prior probability of high conflict deaths (greater than 8000) based on similar years with continuing trends of violence and fatalities. Given the data of over 17,000 deaths since 2023, we adjust upwards from a historical base rate of 0.4 to a current base rate of 0.6. Adjusting for the factors, we assign probabilities: 0.5 (prior) * 0.7 (recent incidents) * 0.6 (targeting civilians) * 0.5 (clashes in Darfur), resulting in a calculated Bayesian probability.
Bayesian base rate: 0.63(Carolyn’s note: In cases where the Multi-AI Oracle is only forecasting a single percent probability, this is pretty good. But in this case, with six probability buckets, this might be an overall expression of confidence in the probability distribution over these 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: 488
The following were considered in order to produce this base rate:
The base rate is derived from analyzing historical data on conflict deaths in Sudan, particularly following the April 2023 onset of political violence. The frequency of incidents and the scale of recorded deaths guide the selection of a base rate of 0.6 for higher death categories.
Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional information on peace efforts, potential foreign interventions, changes in military strategy, or significant policy shifts by involved parties would enhance forecast accuracy.
Some potential divergent considerations that might affect the base rate:
Possible de-escalation in violence or successful peace negotiations could result in a lower death toll than currently expected. Additionally, changes in international or regional support dynamics for opposing groups might alter the conflict intensity.
The following chain of events are necessary for the question to resolve positively:
– Continued high levels of political violence as experienced since April 15, 2023 Highly likely
– Ongoing clashes over resources in North Darfur involving Arab militias Likely
– Continued targeting of civilians with violent events Likely
– Sufficient data collection and reporting by ACLED Very likely
Querying Claude (AI predicts: [“Less than 1000”: 0.02, “Between 1000 and 3000”: 0.08, “Between 3000 and 5000”: 0.15, “Between 5000 and 8000”: 0.25, “Between 8000 and 12000”: 0.35, “More than 12000”: 0.15] – 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”: 0.3, “Between 8000 and 12000”: 0.35, “More than 12000”: 0.14] – confidence: 6)
Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.09, “Between 5000 and 8000”: 0.15, “Between 8000 and 12000”: 0.25, “More than 12000”: 0.45] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.073333333333333, Max: 0.20666666666667
# LLM responses: 3
Explanations of the above statistical measures here —>
Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 5%
* Between 3000 and 5000: 16%
* Between 5000 and 8000: 26%
* Between 8000 and 12000: 36%
* More than 12000: 16%
The AIs predict a high death toll from political violence in Sudan, which has seen over 17,000 deaths from 6,200+ incidents since April 2023. The trend of escalating violence continues into 2025, with significant events impacting civilians and contributing to high projections for fatalities, possibly between 8,000 and 12,000 additional deaths in 2025. Key factors driving this violence include the persistent RSF-SAF conflict, resource-based clashes in North Darfur, and intensive targeting of civilians, as captured by ACLED’s extensive data collection. However, the prediction could be incorrect if there is a sudden de-escalation due to peace negotiations, international intervention, or changes in regional support dynamics, which could lower the violence. Additionally, shifts in conflict forms or data collection challenges might impact the accuracy of predictions.
Runtime: 128 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.

Source: Thomas van Linge, Institute of War, 1 May 2025, as reported by the BBC, https://www.bbc.com/news/articles/cjel2nn22z9o