Sudan updates from AI Botmaster Jeremy Lichtman of April 18, 2025

How many conflict deaths will there be in Sudan in 2025?

Jeremy’s 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)
* Less than 1000: 1%
* Between 1000 and 3000: 2%
* Between 3000 and 5000: 5%
* Between 5000 and 8000: 12%
* Between 8000 and 12000: 25%
* More than 12000: 55%

Here’s what his Multi-AI Oracle says about how it created these forecasts: Obtaining outside data. Checking internet sources, using keywords: Sudan conflict 2025/ Results from around the web:
{think}

Okay, I need to address the user’s query about Sudan conflict deaths in 2025 using the provided search results. Let me start by going through each source carefully to extract relevant information.

First, looking at source [1], it mentions that as of December 2024, ACLED estimated 28,700 deaths from intentional injuries, including 7,500 civilians. However, other studies suggest the toll is much higher, with some estimates up to 150,000 when including indirect causes like starvation and disease. The Yale lab’s satellite imagery shows destroyed infrastructure and potential mass graves, which implies higher casualties than reported.

Source [2] from ACLED’s Conflict Watchlist 2025 confirms the 28,700 figure by November 2024, noting it’s an underestimate, with some sources claiming up to 150,000 deaths. It also describes the ongoing conflict dynamics, including foreign involvement and regional fragmentation, which likely contribute to the rising death toll into 2025.

Source [3] by CFR mentions the former U.S. envoy’s estimate of 150,000 killed since the conflict began in 2023. It also highlights the displacement crisis and humanitarian issues exacerbating mortality rates. The article updates military actions into early 2025, suggesting continued violence and casualties.

Source [4] from USCRI in April 2025 reports the U.S. State Department’s determination of genocide by the RSF, emphasizing atrocities and the blockage of aid leading to famine and disease. While it doesn’t give exact 2025 figures, the context indicates that deaths from indirect causes are significant.

Source [5] (NRC) states over 150,000 deaths and 14 million displaced as of April 2025, aligning with the higher estimates from other sources. This provides a more recent figure, reinforcing the severity of the crisis.

Source [6] (Simple Wikipedia) offers a timeline but lists lower figures (12,000 killed by December 2023), which are outdated compared to other sources. However, it provides background context on the conflict’s origins and key players.

Sources [7], [9], and [10] are either about BTC forecasts or the South Sudanese Civil War and don’t contribute to Sudan’s 2025 death toll. Source [8] discusses the Darfur conflict up to 2005, which is historical and not directly relevant to the current query.

Putting this together, the key points are the discrepancy between direct conflict deaths (around 28,700) and total deaths including indirect causes (up to 150,000). The Yale lab’s methods using satellite data and ground reports suggest underreporting, especially in 2025. The ACLED and NRC figures from late 2024 to April 2025 indicate that the death toll continues to rise, with famine and disease playing a major role.

The user also requested tables. I’ll create a table summarizing the estimates from different sources, highlighting the range and causes. Since time-series data isn’t explicitly provided in the sources, I’ll note that detailed periodic data isn’t available but mention the overall trends. The death toll in Sudan’s ongoing civil war remains highly contested, with estimates varying widely depending on methodology and sources. As of April 2025:

**Direct conflict deaths**
– ACLED reports **28,700+ intentional injury deaths** (including 7,500 civilians) through November 2024[1][2].
– London School of Hygiene & Tropical Medicine models suggest **26,000+ direct deaths** in Khartoum state alone between April 2023–June 2024[1].

**Total excess deaths**
– Multiple sources estimate **150,000+ total deaths** when including indirect causes like starvation and disease[1][5].
– CFR cites U.S. envoy figures of **150,000 killed** since the war began in April 2023[3].

### Key Mortality Drivers

### Data Limitations
– No authoritative real-time tracking exists due to:
– **Reporting gaps**: 30% population displaced[4], aid workers targeted[1]
– **Method variances**: ACLED uses verified incident reports vs. epidemiological models[1][2]
– **Political obfuscation**: Both sides restrict access to conflict zones[3][5]

While precise 2025 figures are unavailable, all sources agree mortality accelerated through early 2025 with:
– SAF recapturing Khartoum suburbs intensifying urban combat[3]
– RSF maintaining siege tactics in Darfur[2][8]
– Rainy season (June–Sept 2025) expected to worsen disease spread[1][4]

OpenAI gives a base rate of probability that total deaths will be more than 12,000.
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: reference_class
Expected time (days) until question close: 257

The following were considered in order to produce this base rate:
The base rate is derived from recent estimates that suggest total deaths, including indirect causes like starvation and disease, have surpassed 150,000 as of April 2025. Given that direct conflict deaths are reported at around 28,700 through late 2024 and the ongoing severity of the conflict, the probability of deaths continuing to exceed 12,000 in 2025 is very high.

Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional information on peace efforts, potential ceasefire agreements, and updated humanitarian intervention successes would be valuable. More frequent and real-time updates on the situation from impartial sources would aid in refining the forecast.

Some potential divergent considerations that might affect the base rate:
Factors that could lower the death toll include successful peace negotiations, increased humanitarian access, and effective international intervention to mitigate famine and disease impacts.

The following chain of events are necessary for the question to resolve positively:
– Continuation of the Sudan conflict throughout 2025 Highly Likely
– Continued underreporting of indirect causes of death Likely
– Ongoing famine and disease conditions Highly Likely
– Restricted access to conflict zones, limiting accurate data collection 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”: 0.1, “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”: 0.02, “Between 3000 and 5000”: 0.02, “Between 5000 and 8000”: 0.05, “Between 8000 and 12000”: 0.1, “More than 12000”: 0.8] – confidence: 7)

Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.10222222222222, Max: 0.30666666666667
# LLM responses: 3

Model value:
* Less than 1000: 0.01%
* Between 1000 and 3000: 2%
* Between 3000 and 5000: 5%
* Between 5000 and 8000: 12%
* Between 8000 and 12000: 25%
* More than 12000: 55%
The ongoing conflict in Sudan has resulted in a significant death toll, with over 150,000 total deaths reported by April 2025, including 28,700 direct conflict-related deaths. The crisis is exacerbated by urban warfare, sieges, weaponized food blockades, and the collapse of medical infrastructure, which contribute to growing fatalities from famine and disease—especially during the rainy season. However, there are potential mitigating factors that could alter the situation and reduce mortality rates. These include successful peace negotiations, increased humanitarian aid and access, effective international intervention, and possible inaccuracies in current death estimates due to underreporting and data collection challenges. If these interventions occur or the conflict dynamics change, the projected death toll could be significantly lower, although the outlook remains dire without such changes.

Past forecasts on Sudan’s conflict fatalities —>

Guide to Multi-AI Oracle’s Reports (some of these only apply to older versions)
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.

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/