How many conflict deaths will there be in Sudan in 2025?
Jeremy’s most recent version of his Multi-AI Oracle is a side competitor with the machine forecasting bots of the VIEWS competition.
Here’s what Jeremy‘s latest version of his Multi-AI Oracle predicts: (Carolyn’s note: Both Jeremy and I agree, these probabilities are, so far, just an experiment. It is too early to know how good these will turn out to be)
Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 2%
* Between 3000 and 5000: 5%
* Between 5000 and 8000: 12%
* Between 8000 and 12000: 30%
* More than 12000: 50%
Here’s how Jeremy’s Multi-AI Oracle says it arrived at these probabilities:
Obtaining outside data.
Checking internet sources, using keywords: Sudan conflict deaths 2025
Results from around the web: {think}
Okay, let’s tackle this query about the Sudan conflict deaths in 2025. The user wants current web results from news sites, official websites, and other sources, along with data tables and a list of URLs.
First, I need to check the provided search results. They range from December 2024 to February 2025, so they’re recent. The main sources are ACLED, Science.org, CFR, Genocide Watch, and another ACLED page.
Looking at the data points: ACLED mentions over 28,700 reported fatalities by November 2024, including 7,500 civilians. Science.org notes estimates from 20,000 to 150,000, with a U.S. State Department accusation of genocide. CFR reports 54 civilians killed in February 2025. Genocide Watch cites 61,000 deaths in Khartoum alone, with 90% unrecorded.
Wait, the user asked for 2025 data, but some sources are from late 2024. However, since the current date in the prompt is April 2025, these are the most recent available. Need to clarify that the latest data is up to early 2025.
Now, compiling the data into tables. The first table would summarize total deaths and sources. The second table could be a time series, but the search results don’t provide monthly breakdowns. The CFR source mentions a February 2025 incident, so maybe include that as a period. However, without more granular data, I can’t calculate mean, median, etc. So perhaps mention that detailed time series data isn’t available.
For the summary, highlight the conflicting estimates (28,700 vs. 150,000), the humanitarian crisis, and the accusation of genocide. Emphasize that numbers are likely underestimates due to unrecorded deaths.
Finally, list all the URLs used. Make sure to format tables correctly using markdown and cite each source properly. Check that all citations are included after each relevant sentence. Also, ensure the answer doesn’t start with a header and follows all formatting rules.
The ongoing conflict in Sudan has resulted in staggering civilian casualties and a severe humanitarian crisis. Reported fatalities vary widely across sources, with ACLED documenting over 28,700 deaths by November 2024 (including 7,500 civilians killed in direct attacks)[1][5], while other estimates suggest the total death toll could surpass 150,000 when accounting for indirect deaths and unrecorded cases[2][4]. The Rapid Support Forces (RSF) and Sudanese Armed Forces (SAF) have both been accused of using starvation tactics and committing mass atrocities[2][4].
### Key Statistics Table
—
## Data Comparison Table
The geometric mean of reported direct deaths (28,700) and highest estimates (150,000) is approximately ( sqrt{28,700 times 150,000} approx 65,700 ), indicating significant variance in mortality assessments. Standardized data collection remains challenging due to:[2]
– Destroyed infrastructure (90% of Khartoum deaths unrecorded)[4]
– Blocked humanitarian access[2]
– Displacement of medical personnel[2]
**Sources Used:**
1. https://acleddata.com/conflict-watchlist-2025/sudan/
2. https://www.science.org/content/article/how-many-have-died-sudan-s-civil-war-satellite-images-and-models-offer-clues
3. https://www.cfr.org/global-conflict-tracker/conflict/power-struggle-sudan
4. https://www.genocidewatch.com/single-post/sudan-genocide-emergency-january-2025
5. https://acleddata.com/africa/horn-of-africa/sudan/
Couldn’t get base forecast
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”: 0.3, “More than 12000”: 0.5] – confidence: 6)
Querying Mistral (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.1, “Between 5000 and 8000”: 0.2, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.34] – confidence: 6)
Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.01, “Between 3000 and 5000”: 0.01, “Between 5000 and 8000”: 0.1, “Between 8000 and 12000”: 0.35, “More than 12000”: 0.52] – confidence: 7)
Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.051111111111111, Max: 0.12
# LLM responses: 3
Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 2%
* Between 3000 and 5000: 5%
* Between 5000 and 8000: 12%
* Between 8000 and 12000: 30%
* More than 12000: 50%
The conflict in Sudan remains highly deadly and complex, with significant challenges in data collection and reporting contributing to a wide variance in estimated fatalities. ACLED reports over 28,700 deaths by late 2024, but other estimates, including unrecorded deaths in Khartoum, suggest the toll could be as high as 150,000. The humanitarian crisis has led to widespread displacement and severe living conditions, potentially prolonging high death rates. There is, however, a possibility for reduced fatalities if international interventions can lead to a ceasefire or if improved humanitarian access mitigates indirect deaths from starvation and disease. Despite these possibilities, the unpredictable nature of the conflict and logistical difficulties continue to complicate accurate assessments and predictions for 2025.
Past forecasts on Sudan’s conflict fatalities —>
Guide to Multi-AI Oracle’s Reports (some of these only apply to older versions)
Bayesian calculation: a mathematical technique that helps determine the conditional probability of an event based on prior knowledge and new evidence.
MAPD: Mean Absolute Percentage Deviation calculates the average percentage difference between actual values and predicted values, providing a relative measure of error.
Median: We collect the output values from the LLMs in an array. We then take the median value. This is between 0 and 1 (i.e. 0.15 = 15%).
Base rate: Currently we take OpenAI’s value as the base rate. We are working on a better value using a different prompt that takes into account process. The base rate helps to determine if the median makes sense.
SD: The standard deviation between the median and the base rate.
Confidence: We query each of the LLMs on how confident they are of their predictions (between 0 and 10) and take a median. Because the LLMs tend to be overconfident, we take anything lower than 6 as being low confidence. This factors into the overall model.
Conf Mode: Based on the confidence value. >=9 is high confidence. Below 6 is low confidence (this is also triggered by an exceptionally high SD).
Mellers: This refers to Barbara Mellers, specifically a paper she wrote that includes a formula for moving values towards an extreme (i.e. 0 or 1).
Reverse Mellers: This uses the formula from above, but with a sub-1 coefficient to move the values closer to 50%.
Theory of Mind: We ask the LLMs what they think other LLMs would predict. We hope that this makes them consider the questions more deeply.
Beta Distribution: Currently unused, but possibly of interest. This is based on the median, the base rate and the SD.
Close Type: We noticed that the appropriate base case for some questions is closer to the extremes, while others are closer to 50%. When we have a low confidence value, this helps us to determine whether to extremize or de-extremize the value. ‘A’ implies closer to zero. ‘B’ implies closer to 50%. ‘C’ implies closer to 100%.
# LLM Responses: The count of LLMs that responded. We query 5 currently, but they have a relatively high API failure rate.
Model value: For normal confidence mode, this is the median. For high confidence, this is the Mellers value. For low confidence, this is either the Mellers or Revers
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.
Background on the Sudan conflict, as evaluated by the team of Jeremy Lichtman and Carolyn Meinel:
(1) The importance of the Sahel, a region in Africa that includes Sudan:
Why the Sahel Actually Matters (Possibly To You, Too)
(2) April 29, 2024: Today, a Russian diplomat is negotiating gold mining with the Sudanese Minister of Minerals.
(3) June 3, 2024: Today the African Union Announced Plans to Mediate in Sudan’s Civil War
(4) Sept. 11, 2024 Over 100K starvation deaths 96% likely in Sudan by 1 Jan 2025
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/
