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.
Obtaining outside data. Checking internet sources, using keywords: Sudan conflict deaths 2025
Results from around the web: {think}
Okay, I need to summarize the current web results regarding Sudan conflict deaths. Let’s start by looking through the provided search results.
First, result [1] from ACLED mentions over 28,700 reported fatalities by November 2024, including 7,500 civilians. They note that this is likely an underestimate, with some sources suggesting up to 150,000 deaths. That’s a big range, so I should highlight the discrepancy.
Result [7] from Genocide Watch in January 2025 cites LeMonde estimating at least 150,000 civilian deaths. They also mention specific numbers like 61,000 killed in Khartoum, with 26,000 from direct violence. Plus, there’s info on Darfur massacres, like 10,000-15,000 Masalit people killed in El Geneina. This source emphasizes underreporting due to blocked access and unrecorded deaths.
Result [8] from Wikipedia states that as of 14 November 2024, at least 61,000 were killed in Khartoum State alone, 26,000 directly. It also mentions over 8.8 million displaced.
Result [10] from Science.org discusses the challenges in counting deaths. ACLED’s December 2024 estimate is 28,700 total, with 7,500 civilians. However, a London School model suggested 61,000 deaths in Khartoum alone from all causes, indicating higher indirect deaths. The multiplier approach from past conflicts suggests a total of 62,000 deaths using a 2.3 indirect per direct death ratio, but mentions multipliers can range up to 15.
Result [4] from OHCHR in February 2025 reports a spike in civilian deaths: 275 in a week, three times the prior week’s 89. This shows a recent escalation.
Putting this together, the answer needs to summarize direct and indirect deaths, sources of data, methodological challenges, and recent trends. Tables should include ACLED, Genocide Watch, and OHCHR data. I should also mention the displacement figures and starvation as a factor.
Need to structure the answer with sections: Key Statistics, Recent Escalation, Methodological Challenges, and maybe a table summarizing the data. Cite each source as per the brackets.
The ongoing conflict in Sudan has resulted in catastrophic human losses, with estimates varying widely due to challenges in data collection and the dynamic nature of the war. Below is a synthesis of key findings from diverse sources:
—
### Key Statistics
– **Reported Fatalities (Direct Violence)**:
– ACLED: 28,700+ deaths by November 2024, including 7,500+ civilians[1].
– Khartoum State: 61,000+ deaths (26,000+ from direct violence)[7][8].
– Masalit Ethnic Group: 10,000–15,000 killed in El Geneina (2023)[7].
– **Indirect Deaths** (starvation, disease):
– Khartoum State: 61,000+ total deaths (50% increase over prewar mortality)[10].
– Multiplier Models: 62,000+ deaths (Oct 2024), assuming 2.3 indirect deaths per violent death[10].
– **Displacement**:
– 14 million+ displaced internally (30% of population)[1].
– 3.5 million+ refugees (as of Feb 2025)[8].
– **Atrocities**:
– 275 civilians killed in one week (Jan–Feb 2025)[4].
– 57 humanitarian volunteers killed since 2023[4].
—
### Recent Escalation (Jan–Feb 2025)
Indiscriminate shelling and aerial attacks intensified, particularly in Khartoum and Darfur[4][7]. The RSF and SAF continue to obstruct humanitarian aid, exacerbating famine and cholera outbreaks[7][10].
—
### Methodological Challenges
Sources highlight severe undercounting due to:
1. **Blocked access**: Both factions restrict data collection[10].
2. **Unrecorded deaths**: 90% of Khartoum deaths go undocumented[7].
3. **Indirect mortality**: Starvation and disease outpace direct violence[10].
ACLED’s figures are considered conservative, while models from the London School of Hygiene & Tropical Medicine suggest significantly higher totals[1][10]. Multipliers from past conflicts (indirect:direct deaths = 2.3–15) further widen estimates[10].
—
### Summary Table of Death Estimates
—
The conflict’s true toll remains obscured by warring factions’ suppression of information and the collapse of infrastructure. With peace initiatives stalled and foreign actors fueling fragmentation, the humanitarian crisis is poised to worsen in 2025[1][7].
OpenAI gives a base rate of proportion of estimates reaching over 120,000 deaths. (Carolyn’s note: we didn’t get a base rate returned by OpenAI, sorry.)
The question difficulty is rated 8 (0 to 10)
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: 365
(Carolyn’s note: Nope.)
The following were considered in order to produce this base rate:
The broad range of reported figures from different sources suggests significant uncertainty, but some consistent reports (~150,000 deaths) in more accurate publications like Genocide Watch give weight to those higher figures. The historical pattern in similar conflicts where direct and indirect deaths are undercounted due to lack of access further supports a likelihood of higher numbers. Displacement figures provide additional context but don’t directly translate into death toll estimates.
Ideally, the news feed would contain the following sorts of information for a better forecast:
Further access to comprehensive ground reports from international observers or detailed reviews from the International Red Cross or WHO could solidify base estimates. More clarity on the methods used in these estimates or collaborative studies using the multiplier methods could refine forecasts.
Some potential divergent considerations that might affect the base rate:
The potential introduction of more comprehensive independent reports or cessation of hostilities may alter the estimated totals significantly. Also, more conservative estimates like from ACLED which suggest possibly over 28,700 deaths point towards the lower possible spectrum, causing divergence.
The following chain of events are necessary for the question to resolve positively:
– Accurate death toll reports reaching thresholds Low to Moderate
– Verification of indirect deaths by researchers Moderate
– Smooth and unhindered access for humanitarian and reporting agencies Low
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”: 0.1, “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”: 0.1, “Between 3000 and 5000”: 0.15, “Between 5000 and 8000”: 0.2, “Between 8000 and 12000”: 0.25, “More than 12000”: 0.29] – confidence: 4)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3
Model value:
* Less than 1000: 1%
* Between 1000 and 3000: 5%
* Between 3000 and 5000: 11%
* Between 5000 and 8000: 21%
* Between 8000 and 12000: 26%
* More than 12000: 36%
The ongoing conflict in Sudan has resulted in a significant and potentially escalating death toll, with reported estimates ranging from over 28,700 to more than 150,000 fatalities. Methodological challenges, such as restricted access to conflict areas and underreporting, especially of indirect deaths from starvation and disease, suggest the actual figures could be higher. Recent data underscores an intensification of violence, particularly in regions like Khartoum and Darfur, compounded by a collapsed healthcare system and blocked humanitarian aid. However, there exist factors that could potentially reduce these estimates. These include the prospect of a peace agreement, improved humanitarian access, possible overestimation due to unreliable sources, and international intervention. Discrepancies in data collection methods and inconsistent estimates from various organizations highlight the unpredictability and fluidity of the situation, suggesting multiple possible outcomes.
Past forecasts on Sudan’s conflict fatalities —>
Guide to Multi-AI Oracle’s Reports (some of these only apply to older versions)
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
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/
Below, a screenshot from VIEWS forecasting conflict fatalities in Sudan through January 2028. Below that, satellite images of the devastation in Sudan.
Below, before and after pictures of the devastation of the civil war in Sudan.
