How many state-based conflict deaths in Sudan will be reported by ACLED in 2025?
Phillip Godzin’s pgodzinai predicts today:
Less than 1,000: 1%
Between 1,000 and ,3000: 1%
Between 3,000 and 5,000: 1%
Between 5,000 and 8,000: 3%
Between 8,000 and 12,000: 9%
More than 12,000: 85%
13–16 minutes read (This is a condensed version of pgodzinai’s results. Full rationale here —>)
Perplexity response:
To effectively forecast state-based conflict deaths in Sudan for 2025, I need to analyze current conflict intensity, recent escalation patterns, casualty trends, international involvement, seasonal factors, and historical ACLED data for comparison. The key information required includes current death tolls, major battle locations, weapon flows, humanitarian access, and expert assessments of conflict trajectory.
## Recent Citation Analysis
Based on the available search results, here are the key sources with relevant information:
** Critical Threats Project – August 28, 2025**
This source documents recent RSF advances and civilian casualties in Sudan’s ongoing civil war. The RSF killed at least 89 civilians in el Fasher and Abu Shouk between August 11-20, with 16 civilians summarily executed. The report highlights systematic targeting of refugee camps and ethnically motivated violence against the Zaghawa ethnic group, indicating sustained high-intensity conflict with deliberate civilian targeting.
** Sea Guardian Assessment – August 27, 2025**
This assessment reports accusations against Sudan’s army and security forces of torture and operating “execution sites” as of August 17. This indicates that both sides of the conflict are engaged in systematic violence against civilians, suggesting elevated casualty rates beyond direct combat deaths.
**ADF Magazine – August 26, 2025**
*”Experts Warn of ‘Jihadist PMCs’ Fanning Flames of Conflict”*
This source provides broader context, noting that terrorists killed 150,000 people across Africa in the past decade. While not Sudan-specific, this indicates the severe scale of violence across the continent and suggests Sudan’s conflict fits within a pattern of highly lethal conflicts in the region.
**The Defense Post – August 26, 2025**
*”African Militaries Eye Lighter, Cheaper Drones”*
This report mentions that handheld drones supplied by China and Russia have “further upended fighting” in Sudan since the civil war began. The introduction of new weapons technology suggests potential for increased lethality and escalation in the conflict.
## Current Conflict Dynamics
The Sudan civil war shows **sustained high intensity** as of late August 2025. The RSF continues major offensive operations, particularly around el Fasher, while systematically targeting civilian populations. The conflict has evolved to include **deliberate ethnic targeting**, with the RSF specifically executing members of the Zaghawa ethnic group. Both sides are accused of systematic human rights violations, with Sudan’s army operating alleged execution sites.
## Escalation Factors
Several factors indicate **potential for increased casualties** in the remainder of 2025. The introduction of **advanced drone technology** from Chinese and Russian suppliers has intensified fighting capabilities. The RSF’s strategy of targeting refugee camps as staging grounds demonstrates a shift toward more lethal tactics that maximize civilian casualtie. The systematic nature of attacks on humanitarian infrastructure suggests **deliberate efforts to increase mortality** through indirect means like famine conditions.
Grok response:
**Title:** Sudan’s Rapid Support Forces Shell a Besieged Darfur City
**Description:** News article from The Independent on recent military actions in Sudan.
**Date:** August 28, 2025.
**Summary:** The article reports at least 24 deaths from a single RSF shelling in Darfur, contributing to ACLED’s 2025 tally of ongoing state-based fatalities. It describes the broader conflict as intensifying, with estimates of thousands more deaths in recent months. Sources like ACLED provide context on the escalating humanitarian crisis.
Expert opinions from ACLED analysts emphasize that peace initiatives by the US, Saudi Arabia, and the African Union have yielded little progress, with risks of ethnic cleansing and famine driving higher death tolls. While posts on X reflect public sentiment estimating totals around 150,000 (treated as inconclusive), they underscore growing concern over the crisis.
Extracted resolution criteria links:
[‘https://acleddata.com/conflict-watchlist-2025/sudan/‘, ‘https://acleddata.com/africa/horn-of-africa/sudan/‘]
Claude Vision analysis response:
Based on the image, here is the relevant data for predicting state-based conflict deaths in Sudan for 2025:
**Recent Death Toll Data:**
– **2023**: Approximately 15,000 state-based conflict deaths reported by ACLED
– **2024 (through late year)**: The graph shows approximately 16,000-17,000 state-based conflict deaths
**Key Trend Analysis:**
The bar chart shows a dramatic escalation in state-based conflict deaths:
– Pre-2023: Deaths remained relatively low (under 2,000 annually)
– 2023: Massive spike to around 15,000 deaths (representing the outbreak of conflict between SAF and RSF in April 2023)
– 2024: Continued high levels, slightly exceeding 2023 totals
**Current Conflict Dynamics:**
The text indicates that Sudan’s conflict involves:
– Fighting between the Sudanese Armed Forces (SAF) and Rapid Support Forces (RSF)
– The conflict began in April 2023
– It has become “one of the world’s most severe humanitarian crises”
Gemini Multiple Choice response:
My forecast for state-based conflict deaths in Sudan in 2025, as reported by ACLED, leans heavily towards the “More than 12000” category. This assessment is primarily driven by the consistent and high casualty rates observed in Sudan’s conflict throughout 2023 and 2024, coupled with current reporting that indicates no significant de-escalation.
The most critical data point for this forecast comes from the visual analysis of ACLED’s historical data for Sudan. This data clearly shows approximately 15,000 state-based conflict deaths reported for 2023 and an estimated 16,000-17,000 deaths for 2024 (projected through late year on the graph). These figures firmly place the conflict’s intensity in the “More than 12000” range for consecutive years. The monthly averages during 2024 have fluctuated but generally remained between 1,000 and 3,000 deaths, with peaks reaching 3,500-4,000 in certain months.
Current intelligence as of August 2025 further reinforces this trend. Reports highlight ongoing advances by the Rapid Support Forces (RSF), systematic targeting of civilians, and accusations of human rights abuses by both the RSF and the Sudanese Armed Forces (SAF). The introduction of new weapon technologies, such as drones supplied by China and Russia, suggests a potential for continued, or even increased, lethality in the conflict. Moreover, the social media research indicates “thousands of deaths in the first half of 2025 alone,” which, when annualized, points towards a total well above 12,000.
Given that it is already late August 2025, a substantial portion of the year has passed. For the total annual deaths to fall below 12,000, a dramatic and sustained de-escalation would need to occur immediately and persist through the end of the year. Such an abrupt cessation of large-scale hostilities is not supported by any current conflict reporting or analysis. Peace initiatives have largely stalled, and the conflict continues to be described as one of the world’s most severe humanitarian crises.
Anthropic response:
## Current Situation Analysis
The ACLED visual data shows a dramatic escalation since April 2023, with approximately 15,000 deaths in 2023 and 16,000-17,000 deaths in 2024. As of August 29, 2025, we’re about 8 months into the year with 4 months remaining. The research indicates that ACLED has already recorded substantial fatalities in 2025, with reports suggesting “thousands of deaths in the first half of 2025” and ongoing high-intensity conflict continuing through August.
The most recent evidence shows no signs of de-escalation. The RSF killed at least 89 civilians in just 10 days (August 11-20) in el Fasher alone, representing a sustained high casualty rate. The August 28 shelling in Darfur added at least 24 more deaths. These are just documented civilian deaths in specific locations and don’t include combat deaths or casualties from other regions.
## Statistical Analysis
Based on the monthly patterns from 2024 showing 1,000-3,000 deaths per month with an average around 1,500-2,000, and assuming 8 months have already passed in 2025:
– Conservative estimate for first 8 months: 8 × 1,000 = 8,000 deaths
– Moderate estimate: 8 × 1,500 = 12,000 deaths
– High estimate: 8 × 2,000 = 16,000 deaths
Adding 4 remaining months at similar rates would push totals well above 12,000 in most scenarios.
## Final Assessment
Given the sustained high intensity of conflict matching or exceeding 2024 levels, the lack of any peace progress, ongoing escalation factors, and the fact that we’re already 8 months into 2025 with continued high casualty reports, the probability strongly favors the highest bracket. The conflict shows no signs of the dramatic de-escalation that would be needed to keep 2025 deaths below 12,000.
Model’s Answer:
Summary of evidence and baseline: ACLED’s published data and visualizations show a very large spike in state-based conflict deaths in Sudan beginning in 2023, with 2023 and 2024 each in the many‑thousands range (ACLED’s own monthly tallies and the conflict-watchlist materials imply annual totals on the order of tens of thousands when the high monthly rates are annualized). Recent reporting through August 2025 documents repeated high‑fatality episodes (large mass-casualty attacks, continuing heavy urban and Darfur fighting, use of drones and heavy indirect fire, and deliberate targeting of civilians). The most straightforward baseline—extrapolating recent monthly averages observed in 2024–mid‑2025—points to an annual 2025 total comfortably above the highest threshold in the question (12,000).
How I turned that baseline into a probability distribution: Because the ACLED baseline is strongly tilted to a high annual total, the modal outcome is “More than 12000.” But I tempered that with uncertainty about: (a) conflict de‑escalation or ceasefires that could materially reduce 2025 fatalities, (b) changes in ACLED’s data coverage or coding (upward or downward revisions), and (c) the chance of a rapid, large external intervention or partitioning that either reduces localized fighting or causes a temporary spike and subsequent reporting oddities. I assigned non‑zero probability mass to lower bins to reflect the real (if small) chances of these scenarios, and to avoid overconfidence given the adjudication risk that ACLED revisions or methodology changes could alter the reported counts.
Quantitative anchors and arithmetic intuition: ACLED’s monthly counts in recent high‑intensity months ranged in the low thousands to multiple thousands. If the conflict averaged even ~1,000 state‑based deaths/month across 2025 that would produce 12,000/year; given observed spikes well above that in 2023–2024, sustaining the >12,000 outcome is the default. For 2025 to fall into 8–12k, average monthly deaths would need to fall to roughly 700–1,000/month—feasible only with significant de‑escalation. Falling to the 5–8k or lower brackets would require major negotiated cessation and sustained calm, which looks unlikely given the conflict dynamics as of late August 2025.
Key assumptions whose failure would most affect the forecast
1) Continued intensity/stability of reporting: I assume the SAF–RSF war remains active at roughly current intensity (no comprehensive and lasting ceasefire). Probability this assumption fails (i.e., a durable de‑escalation occurs in enough places to lower annual deaths materially): ~15%. If this fails, the probability mass shifts toward 8–12k and below.
2) ACLED methodology and coverage remain consistent: I assume no major downward data revision or abrupt change in what ACLED classifies as “state‑based conflict deaths.” Probability this assumption fails: ~7%. If it fails via major downward revisions, reported totals could be lower than current event counts suggest.
3) No massive one‑off shock that drastically increases deaths (e.g., a sudden nationwide offensive, foreign intervention or intensified aerial campaign causing a single catastrophic spike): probability of such a shock materially increasing the total above trend: ~10%. If fulfilled, this would increase probability of the top bin.
How those assumptions were folded into probabilities: I started with a strong prior for >12k (based on extrapolation of monthly rates). I then discounted that prior modestly to account for the (non‑negligible) chance of durable de‑escalation or reporting changes, and allocated small but meaningful probability to the 8–12k bucket and very small probabilities to lower buckets to reflect tail risks (large negotiated ceasefire, mass reporting revisions, or unusual data anomalies).
Conservative calibration and scoring considerations: Because the question will be scored with a proper scoring rule (Brier score), I avoided extremely narrow allocations and left some mass in adjacent categories to reflect model and information uncertainty. The distribution therefore places most weight on the >12k bin but preserves modest probabilities for plausible, though less likely, lower outcomes.
Final probabilities
Less than 1,000: 1%
Between 1,000 and ,3000: 1%
Between 3,000 and 5,000: 1%
Between 5,000 and 8,000: 3%
Between 8,000 and 12,000: 9%
More than 12,000: 85%
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 with VIEWS.
Source: Thomas van Linge, Institute of War, 1 May 2025, as reported by the BBC, https://www.bbc.com/news/articles/cjel2nn22z9o
