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 2025
Results from around the web:
Okay, let’s tackle this query about Sudan conflict deaths in 2025. The user wants current web results from various sources, including news, Wikipedia, official sites, and prediction markets. They also want tables with relevant data and time series if possible.
First, I’ll go through each of the provided search results to find information related to death tolls in Sudan’s conflict during 2025. Let’s start with the sources one by one.
Search result [1] from OHCHR dated February 2025 mentions at least 275 civilian deaths in late January to early February 2025. That’s a significant increase from the previous week’s 89 deaths. This shows a sharp escalation early in the year.
Result [4] from ACLED in December 2024 reports over 28,700 fatalities by November 2024, with 7,500 civilians killed directly. They also mention some estimates as high as 150,000, but that’s from a BBC article in November 2024. This gives a baseline going into 2025.
Result [7] by Genocide Watch in January 2025 cites LeMonde estimating 150,000 civilian deaths by November 2024. It also notes 61,000 deaths in Khartoum alone, with 26,000 from direct violence. There’s mention of underreporting, with 90% of deaths in Khartoum unrecorded. This suggests the actual numbers could be much higher.
Result [8] from Wikipedia (updated as of November 2024) states 61,000 killed in Khartoum State alone, 26,000 from direct violence. By February 2025, it mentions SAF regaining control in some areas, indicating ongoing conflict.
Result [10] from Science.org in February 2025 discusses varying estimates, from 20,000 to 150,000. It highlights that many die from starvation and disease, not just violence. ACLED’s figure here is 28,700, including 7,500 civilians. A study by Maysoon Dahab’s team estimates 26,000 intentional injury deaths in Khartoum alone from April 2023 to June 2024.
Now, looking for data tables or time series. Result [2] from Simple Wikipedia has a table with casualties: 12,000+ killed and 33,000+ injured, but this data seems outdated (as of April 2023). Result [8] has a table with 61,000 killed in Khartoum by November 2024. Result [10] mentions ACLED’s 28,700 total deaths by December 2024 and Dahab’s model suggesting 61,000 deaths in Khartoum from all causes.
I need to compile the most recent 2025 data. The OHCHR report from February 2025 is key here, showing 275 deaths in a week. However, other sources (like [4] and [7]) provide cumulative figures up to late 2024 and early 2025 but don’t have specific 2025 monthly breakdowns. The user might want the latest available, which is the February 2025 spike.
For tables, I can create one summarizing key statistics from different sources, noting the time periods. A time series would require data points over periods, but the available info is limited. The OHCHR data from January-February 2025 shows a weekly increase, so I can present that as a time series segment.
Prediction markets aren’t covered in the provided results, so I’ll note that no relevant data was found there.
In summary, the answer should highlight the escalating death toll in early 2025, the underreporting issues, sources of data discrepancies, and the humanitarian crisis exacerbated by starvation and disease. Tables will organize the stats from different reports and the time series for the OHCHR’s weekly data.
The Sudan conflict’s death toll in 2025 reflects an intensifying humanitarian catastrophe, with civilian casualties escalating sharply due to indiscriminate attacks, starvation tactics, and disease outbreaks. Key findings from recent reports include:
## Civilian Death Toll Escalation
– **February 2025 spike**: The UN documented **275 civilian deaths** from 31 January to 5 February 2025 due to artillery shelling and airstrikes in Khartoum and Darfur regions[1]. This marked a **threefold increase** from the previous week’s 89 deaths[1].
– **Cumulative estimates**:
– At least **28,700 reported fatalities** by November 2024, including **7,500 civilians killed in direct attacks**[4][10].
– Independent studies suggest **actual deaths may exceed 150,000** when accounting for indirect causes like starvation and disease[7][10].
## Mortality Drivers
– **Starvation**: 30 million Sudanese require aid, with famine conditions in five regions[7][10]. Cholera outbreaks have killed 546+ people[10].
– **Healthcare collapse**: 65% of Darfur lacks basic medical services after 145 facilities were destroyed[7].
– **Sexual violence**: Over 400 documented rape cases (April 2023–July 2024), though underreporting is rampant[7].
## Time Series: Early 2025 Casualty Surge
_Data reflects UN Human Rights Office reports[1]._
No relevant data from prediction markets (e.g., Kalshi, Polymarket) was found in the provided sources. Discrepancies in death estimates stem from restricted humanitarian access[10] and systematic underreporting, particularly in RSF-controlled areas[7].
OpenAI gives a base rate of a 40% likelihood that the death toll from the conflict in Sudan in 2025 will exceed 8000 but will not exceed 12000.
The question difficulty is rated 8 (0 to 10)
Sufficient news to provide a good forecast? 0 (0 or 1)
News is relevant, topical and unbiased? 1 (0 or 1)
Question classification: scenario_based_forecast
Expected time (days) until question close: 264
The following were considered in order to produce this base rate:
The base rate was determined by analyzing the ongoing conflict dynamics in Sudan, taking into account historical data from the end of 2024 and early 2025 reports. The reported 28,700 total fatalities by November 2024 provide a reference, with early 2025 indicating a further increase due to intensified conflict and humanitarian crises.
Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional information on the specific regions most affected by the conflict in terms of casualties beyond early 2025 would improve forecast accuracy. Regular updates from credible international agencies like the UN or Red Cross would also be valuable.
Some potential divergent considerations that might affect the base rate:
Factors causing deviation from the base rate include potential peace negotiations, international intervention, or a ceasefire. Alternatively, an escalation of violence in untargeted regions or external support to one of the militant groups could lead to an unexpected increase in fatalities.
The following chain of events are necessary for the question to resolve positively:
– Ongoing conflict in Sudan resulting in significant civilian casualties Likely
– Escalation of violence in major regions such as Khartoum and Darfur Likely
– Humanitarian crisis leading to indirect deaths from starvation and disease Very Likely
– Continued use of indiscriminate military tactics causing civilian harm Highly Likely
Querying Claude (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”: 0.4, “More than 12000”: 0.14] – confidence: 6)
Querying Mistral (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.09, “Between 3000 and 5000”: 0.2, “Between 5000 and 8000”: 0.3, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.1] – confidence: 6)
Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.08, “Between 5000 and 8000”: 0.1, “Between 8000 and 12000”: 0.36, “More than 12000”: 0.4] – confidence: 6)
Question Type: Multiple Choice
Confidence: 6
# LLM responses: 3
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: 37%
* More than 12000: 15%
The AIs reason that the ongoing conflict in Sudan, particularly in regions like Khartoum and Darfur, is likely to result in a high number of fatalities, projecting an annual death toll between 8,000 and 12,000 based on recent escalations and historical data. Key factors influencing this prediction include a sharp increase in violence, systematic underreporting of casualties, a severe humanitarian crisis, and indirect deaths from starvation and disease. However, they acknowledge the potential for significant deviations in their projections due to various factors. These include the possibility of peace agreements or ceasefires, international interventions, improved humanitarian access, and the potential for unexpected changes in conflict dynamics that might either increase or decrease the death toll. Therefore, the uncertainty around the actual impact of the conflict remains high.
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.
