Botmaster Jeremy Lichtman’s Sudan conflict deaths forecast, May 30, 2025

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 1000: 1%
* Between 1000 and 3000: 5%
* Between 3000 and 5000: 14%
* Between 5000 and 8000: 25%
* Between 8000 and 12000: 30%
* More than 12000: 25%

Obtaining outside data.
Checking internet sources, using keywords: ACLED Sudan 2025 conflict deaths
News from various sources:

The retrieved content contains detailed information on the significant underreporting of deaths in the ongoing conflict in Sudan, according to reports from multiple studies. Here is a summary of the key findings:

1. **Underreported Deaths**: The London School of Hygiene and Tropical Medicine (LSHTM) report indicates that between April 2023 and June 2024, the death toll in Sudan, particularly in Khartoum State, was greatly underreported. Over 61,000 deaths from all causes were recorded in Khartoum, with 26,000 attributed to violence alone. This is substantially higher than the 20,178 intentional-injury deaths reported for the entire country by the Armed Conflict Location and Event Data (ACLED).
2. **Indirect Mortality**: Indirect deaths due to factors like preventable disease and starvation were prevalent. Estimates suggest a total of over 62,000 deaths, combining direct conflict deaths and additional indirect deaths calculated using various multipliers.
3. **Humanitarian Crisis**: The conflict has exacerbated humanitarian issues, including ethnic cleansing, mass displacement, food scarcity, and disease spread. The United Nations and aid agencies have highlighted a severe hunger crisis, with millions on the brink of famine, particularly in Darfur.
4. **Conflict Background**: The war started in April 2023 as a struggle between the Sudanese Armed Forces and the Rapid Support Forces. The conflict has led to the displacement of over 14 million people, and widespread violence has made accurate casualty counts difficult.
5. **Methodology**: The LSHTM study utilized a capture-recapture analysis technique to estimate unrecorded deaths by comparing data from multiple sources.
6. **Humanitarian Needs**: The staggering death toll and dire humanitarian situation call for increased international aid efforts. The need for safe access to food and medical supplies is critical.
7. **International Response**: Efforts by international organizations to cease the violence have been hindered by geopolitical dynamics, including a recent UN Security Council resolution vetoed by Russia.
In essence, the conflict in Sudan has led to a far higher number of deaths than previously recorded, with many resulting from indirect causes linked to the breakdown of health care and food supply systems. The LSHTM study and others underscore the urgent need for increased humanitarian aid and international mediation to address the worsening crisis.

Fact-checking news summary:
Here is a list of specific facts from the summary and an assessment of each one:

1. **Fact**: The London School of Hygiene and Tropical Medicine (LSHTM) report indicates that between April 2023 and June 2024, over 61,000 deaths from all causes were recorded in Khartoum, with 26,000 attributed to violence.
– **Correctness**: Internally consistent given the summary but verification would need the original LSHTM report.
– **Importance**: Important, as it provides a direct estimate of underreported deaths.
– **Relevance**: True; it provides a baseline on the scale of conflict-related deaths necessary for future projections.
2. **Fact**: The Armed Conflict Location and Event Data (ACLED) reported 20,178 intentional-injury deaths for the entire country in the same period.
– **Correctness**: Needs verification with ACLED’s actual data.
– **Importance**: Important, as it highlights discrepancies in reported figures.
– **Relevance**: True; it’s relevant to assess the reporting gap.
3. **Fact**: Indirect deaths due to preventable disease and starvation were estimated to surpass 62,000.
– **Correctness**: Internally consistent but requires verification through original estimates.
– **Importance**: Critical, as it addresses the total mortality impact of the conflict.
– **Relevance**: True; indirect deaths are relevant to comprehensive mortality figures.
4. **Fact**: The conflict started in April 2023 as a struggle between the Sudanese Armed Forces and the Rapid Support Forces.
– **Correctness**: Likely true based on context, but sourcing would confirm.
– **Importance**: Lesser, as it only provides background.
– **Relevance**: True; relevant for context, less for numerical prediction.
5. **Fact**: The conflict displaced over 14 million people.
– **Correctness**: This would need to be confirmed against UNHCR or other agencies.
– **Importance**: Important for understanding humanitarian impacts.
– **Relevance**: True; contextual relevance, not numerical prediction.
6. **Fact**: The LSHTM study used capture-recapture analysis to estimate unrecorded deaths.
– **Correctness**: Likely true given typical methodologies for such studies.
– **Importance**: Important, as the methodology affects confidence in estimates.
– **Relevance**: True; relevant for understanding data reliability.
7. **Fact**: A UN Security Council resolution was recently vetoed by Russia.
– **Correctness**: Requires external verification regarding the specific resolution.
– **Importance**: Unimportant, for the purpose of numerical predictions.
– **Relevance**: False; not relevant for estimating conflict deaths.

The summary provides insights into mortality estimates, existing data inconsistencies, and humanitarian impacts, but detail verification from original sources is needed for accurate future analysis and projections.

Fact-checked summary:
The London School of Hygiene and Tropical Medicine (LSHTM) reported over 61,000 deaths from all causes in Khartoum between April 2023 and June 2024, with 26,000 attributed to violence. This provides an important baseline for the scale of conflict-related deaths. It’s critical for future projections to consider indirect deaths due to preventable disease and starvation, estimated to surpass 62,000, addressing the total mortality impact of the conflict. ACLED reported 20,178 intentional-injury deaths for the entire country during the same period, highlighting discrepancies in reported figures that are important to assess. The LSHTM study, which used capture-recapture analysis, provides important insights into estimating unrecorded deaths and understanding data reliability. These facts are crucial for comprehensively understanding mortality figures and potential future projections.

OpenAI gives a base rate of rate (Carolyn‘s note: OpenAI failed to return a value.)
The question difficulty is rated 7 (0 to 10)
Historical weighted factors include:
Conflict-related deaths in Khartoum from April 2023 to June 2024, 0.4
Indirect deaths from preventable diseases and starvation, 0.4
Data discrepancies in reported figures from different sources, 0.2
A Bayesian calculation could be performed as follows:
Using the base rate of 0.6 from conflict-related direct deaths and accounting for indirect deaths and data discrepancies, we adjust for data reliability. Prior: 0.6 (conflict deaths) * Likelihood of reliable indirect death data capturing (~0.9) * Likelihood of continued conflict (~0.7) = 0.378.
Bayesian base rate: 37.8%. (Error! This calculation failed to specify the number of deaths associated with this percentage.)
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: 396 (Carolyn’s note Error! the Multi-AI Oracle has trouble counting. The correct number of days remaining in 2025 is 215, not counting today.)

The following were considered in order to produce this base rate:
The base rate is derived primarily from the recent data on conflict-related deaths in Khartoum over a 14-month period, with adjustments made for indirect deaths and potential underreporting. LSHTM data (26,000 violent deaths) and ACLED data discrepancies were particularly instrumental in establishing this base rate.

Ideally, the news feed would contain the following sorts of information for a better forecast:
Additional data would be beneficial, particularly any updates regarding de-escalation of ongoing conflicts or shifts in geopolitical dynamics by key players and humanitarian aid organizations’ reports on ground conditions.

Some potential divergent considerations that might affect the base rate:
If peace negotiations were to succeed or if there were significant international interventions, it could greatly reduce the expected death toll. Additionally, macroeconomic improvements or unforeseen humanitarian aid could decrease indirect death rates.

The following chain of events are necessary for the question to resolve positively:
– Continued conflict in Khartoum or similar regions causing direct violence-related deaths. Moderate
– Significant indirect deaths from preventable diseases and starvation due to ongoing conflict. High
– Data reliability continues to improve or remain consistent with capture-recapture methods. High

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”: 0.35, “More than 12000”: 0.19] – confidence: 4)

Querying Mistral (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.14, “Between 5000 and 8000”: 0.25, “Between 8000 and 12000”: 0.3, “More than 12000”: 0.25] – confidence: 6)

Querying OpenAI (AI predicts: [“Less than 1000”: 0.01, “Between 1000 and 3000”: 0.05, “Between 3000 and 5000”: 0.1, “Between 5000 and 8000”: 0.14, “Between 8000 and 12000”: 0.2, “More than 12000”: 0.5] – confidence: 6)

Question Type: Multiple Choice
Confidence: 6
MAPD: Avg: 0.068888888888889, 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: 14%
* Between 5000 and 8000: 25%
* Between 8000 and 12000: 30%
* More than 12000: 25%

The predictions regarding violent deaths in Khartoum for 2025 are based on historical data and ongoing conflict dynamics, with predictions drawing from the London School of Hygiene and Tropical Medicine (LSHTM) and ACLED data sources. LSHTM reported 26,000 violent deaths in Khartoum over a 14-month period, while ACLED reported about 20,178 for the entire country, indicating discrepancies likely due to differing data collection methodologies. The overall trend from these datasets suggests severe and persistent conflict in Sudan, with a high likelihood of continued mortality, exacerbated by indirect deaths from diseases and starvation. However, the estimations for 2025 could be significantly reduced if peace negotiations, international interventions, or humanitarian aid occur. The uncertainties and discrepancies in data highlight the challenge of providing accurate mortality figures due to underreporting and the fluid nature of the conflict, emphasizing that future projections are
contingent on dynamic and unpredictable conflict dynamics.

Runtime: 171 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 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.