How many state-based conflict deaths (total of all civilian and combat deaths, including both Ukrainian and Russian combatants) will be reported by ACLED in Ukraine in May, 2025?
Here’s what Phil’s pgodzinai predicts today:
* Less than 500: 1%
^ Between 500 and 1000: 3%
* Between 1000 and 1500: 7%:
* Between 1500 and 2000: 14%
* Greater than 2000: 75%
Perplexity response:
{think}
Okay, let’s tackle this question about the number of state-based conflict deaths in Ukraine in May 2025 as reported by ACLED. The user wants a detailed rundown of the most relevant news sources to inform their superforecaster’s analysis.
First, I need to focus on the latest data from ACLED since they’re the specified source. The user provided several search results, but I should check each one for relevance and recency. Let’s go through each result:
1. The first result from ACLED’s Conflict Monitor (updated January 2025) gives weekly updates and key trends up to January 18-24, 2025. It mentions Russian advances and civilian deaths, with 24 civilians killed in one week and intercepted strikes. Notably, it’s dated April 30, 2025, which is recent. However, the data inside is from January, so it’s a bit older but still relevant for understanding ACLED’s methodology.
2. The second link from ReliefWeb (May 1, 2025) discusses the period April 12-18, 2025, and reports 71 civilian deaths from Russian shelling and attacks. This is more recent, just a couple of weeks before May, so this could indicate trends leading into May.
3. The third result from TVP World (May 6, 2025) mentions Ukraine as the second-deadliest conflict globally in 2025, after Gaza. This is the most recent, dated today (May 6, 2025). It says Ukraine ranks second in deaths, which suggests high ongoing casualties.
4. The fourth link from THE BUZZ (May 1, 2025) states over 40,000 civilian casualties, 4 million displaced, and 6.8 million refugees. While these are cumulative numbers, the page was updated May 1, so it’s recent but doesn’t specify May 2025 deaths.
5. The fifth result from Sharing4good (May 3, 2025) talks about global conflicts doubling, with 233,000 deaths estimated in the past year. It mentions Ukraine as the deadliest conflict, but the numbers here are global and not specific to May 2025.
The user’s query is about May 2025, so I need to focus on the most recent data leading up to that month. The ReliefWeb update (April 12-18) shows 71 civilian deaths in one week, and the TVP World article (today) ranks Ukraine as second-deadliest, which might imply continued high casualty rates.
ACLED’s Conflict Monitor is updated weekly, but the latest available in the search results is from April 30, which includes data up to January. However, ReliefWeb’s info for mid-April is more recent. Without explicit May data, we have to infer from recent trends.
The April data (71 civilian deaths in a week) and the TVP World note that Ukraine remains one of the deadliest conflicts suggest that the monthly death toll in May could be high. However, ACLED’s state-based conflict deaths include both combatants and civilians. The April data mentions 4 civilian deaths from Ukrainian actions and 24 from Russian actions, plus intercepted strikes that might have prevented more deaths.
But the user is asking for the total state-based deaths, including combatants. The available sources don’t explicitly break this down, so we need to consider that civilian deaths are a subset. If April saw 71 civilian deaths in a week, extrapolating that (assuming similar rates) would be around 284 civilian deaths in a month, but combatant deaths are typically higher.
However, the TVP World article states that Ukraine is the second-deadliest conflict, which might indicate higher overall numbers. Given that the user’s options start at ‘Less than 500’, up to ‘Greater than 2000’, we need to assess whether the monthly total would be in any of these brackets.
Considering that in April, a single week had 71 civilian deaths, and including combatants, the total could be significantly higher. For example, if combatant deaths are 3-4 times civilian deaths (common in conflicts), 71 civilians would mean around 250-300 combatants, totaling 320-400 state-based deaths in a week. Over a month, that’s around 1,280-1,600, which would fall into the ‘Between 1000 and 1500’ or ‘Between 1500 and 2000’ brackets.
But this is speculative. The sources don’t provide exact numbers for May, so we have to rely on recent trends. The most recent data point (April 12-18) shows high civilian casualties, and the TVP World article reinforces that Ukraine is among the deadliest conflicts, suggesting sustained high death rates.
Given that, the answer should present the available data, highlight the lack of May-specific numbers, and use recent trends to infer possible ranges. The superforecaster will need to consider that without explicit May data, the projection is based on recent weeks’ trends, possibly indicating a higher death toll, but uncertainty remains.
**Relevant Sources for Ukraine Conflict Death Projections (May 2025)**
### 1. **ACLED Ukraine Conflict Monitor (Updated April 30, 2025)**
– **Date**: April 30, 2025
– **Key Details**: Provides weekly updates on Russian advances, civilian casualties, and intercepted strikes. For January 18–24, 2025, ACLED recorded **24 civilian deaths** from Russian actions and **4 from Ukrainian actions**, alongside **18 long-range missile/drone strikes** intercepted in western regions[1].
– **Trend**: Highlights sustained violence, including settlement captures near Pokrovsk and Kupiansk, indicating continued front-line clashes.
### 2. **ReliefWeb Ukraine War Situation Update (April 12–18, 2025)**
– **Date**: May 1, 2025
– **Key Details**: Reports **71 civilian deaths** in Russian attacks across six regions (Dnipropetrovsk, Donetsk, Kharkiv, Kherson, Sumy, Zaporizhia). No combatant deaths explicitly mentioned[2].
– **Trend**: Marks a sharp escalation in civilian fatalities compared to earlier weeks, suggesting heightened military strikes in April.
### 3. **TVP World Peace Report (May 6, 2025)**
– **Date**: May 6, 2025
– **Key Details**: Ranks Ukraine as the **second-deadliest conflict globally** in 2025, after Gaza, with ongoing high-intensity clashes[3].
– **Context**: Reinforces Ukraine’s status as a major conflict hotspot, implying sustained or rising death tolls.
### 4. **THE BUZZ Russia-Ukraine War Updates (May 1, 2025)**
– **Date**: May 1, 2025
– **Key Details**: Notes **over 40,000 civilian casualties** and **4 million displaced** since 2022. Cumulative refugee figure cited as **6.8 million**[4].
– **Limitation**: Aggregate figures lack granularity for May-specific combatant or state-based deaths.
### 5. **Sharing4good Global Conflict Summary (May 3, 2025)**
– **Date**: May 3, 2025
– **Key Details**: Estimates **233,000 conflict-related deaths globally** in the past year, with Ukraine among the deadliest[5].
– **Insight**: Contextualizes Ukraine’s conflict within global trends, suggesting severe violence persistence.
—
### **Analysis for May 2025 Projections**
1. **Recent Trends**:
– **April 2025**: ReliefWeb reports **71 civilian deaths** in one week (April 12–18), indicating elevated Russian shelling and missile strikes[2].
– **Comparative Context**: TVP World’s ranking of Ukraine as the **second-deadliest conflict** (after Gaza) signals high combat intensity[3].
2. **Combatant vs. Civilian Deaths**:
– **Civilian Deaths**: April saw ~71 civilian fatalities in a week; extrapolating to a month (~280 civilian deaths), but actual totals likely higher due to underreporting.
– **Combatant Deaths**: Often 3–4x civilian deaths in state-based conflicts. If April’s civilian deaths were ~280/month, combatants could add **840–1,120**, totaling **~1,120–1,400** state-based deaths monthly.
3. **ACLED Methodology**:
– ACLED tracks **state-based conflict deaths** (including both sides’ combatants) but does not publish cumulative monthly totals. Weekly reports highlight key incidents, not aggregate figures[1].
4. **Options Consideration**:
– **Less than 500**: Unlikely given April’s ~280 civilian deaths alone and combatant inclusion.
– **Between 500–1,000**: Possible if combatant deaths are moderate, but recent escalation suggests higher.
– **Between 1,000–1,500**: Most plausible range, aligning with April’s trend and conflict intensity.
– **Between 1,500–2,000 / Greater than 2,000**: Less likely without evidence of extreme escalation.
—
**Conclusion**: Based on April’s civilian death rates and combat intensity, the most probable range for May 2025 is **Between 1,000 and 1,500 state-based conflict deaths**. However, ACLED’s lack of explicit monthly totals introduces uncertainty. Superforecasters should monitor ACLED’s weekly updates for fresh data.
(Carolyn’s note: Full report on how pgodzinai’s calculated its results here —>)
Model’s Answer:
# Analysis of State-Based Conflict Deaths in Ukraine (May 2025)
## Assessment of Information Sources
The research assistants have provided valuable information, but with varying degrees of specificity and relevance. Let me first evaluate the quality and relevance of each source:
1. **First research assistant**: Provides recent data from ACLED and other sources up to early May 2025, showing 71 civilian deaths in one week in April 2025. This source is directly relevant as it mentions ACLED’s methodology and recent reporting patterns.
2. **Second research assistant**: Reports high daily casualty rates (1,200/day for Russian forces) in April 2025, with extrapolations suggesting very high potential death counts. Their analysis includes ACLED-specific considerations and historical reporting patterns.
3. **Third research assistant**: Provides additional context on civilian and military casualties from various sources, noting 848 civilians killed or injured in the first 24 days of April 2025, and references to high Russian and Ukrainian military losses.
The second research assistant’s information appears most detailed regarding actual casualty rates, though their extrapolations may need careful scrutiny as they could overestimate ACLED’s official counts.
## ACLED’s Methodology and Historical Reporting
ACLED specifically tracks state-based conflict deaths, including both military and civilian casualties. A critical consideration is that ACLED’s methodology often results in lower counts than those claimed by either side due to their verification requirements. This creates a discrepancy between raw casualty reports and what ACLED ultimately publishes.
According to the research, in late 2024, ACLED reported approximately 19,600 conflict deaths per month. This provides an important baseline for our projection.
## Recent Conflict Intensity (April-May 2025)
Multiple sources confirm the conflict remains highly active with:
1. **Civilian casualties**: 71 deaths in a single week in April; 848 civilians killed or injured in the first 24 days of April.
2. **Military losses**: Russian forces reportedly suffering ~1,200 daily casualties (killed and wounded combined), with Ukrainian forces experiencing significant losses as well.
3. **Combat operations**: Continued fighting reported around Kupiansk, Chasiv Yar, and other areas, with no signs of de-escalation in early May 2025.
4. **Trend analysis**: British intelligence suggesting 2025 may surpass previous years in terms of Russian casualties, with no significant slowdown observed in early May.
## Extrapolating to May 2025
To forecast ACLED-reported deaths in May 2025, I need to consider:
1. **April 2025 intensity**: Multiple sources confirm high casualty rates in April, with civilian deaths at approximately 71 in a single week.
2. **Early May indicators**: As of May 6, 2025, there are no signs of de-escalation, with continued reports of casualties.
3. **ACLED’s reporting lag**: ACLED typically reports lower numbers than those claimed by either side due to their verification requirements.
4. **Historical context**: ACLED reported ~19,600 conflict deaths monthly in late 2024, providing a baseline.
The second research assistant suggests May 2025 could see >11,000 total deaths based on current casualty rates, but this likely overestimates what ACLED will ultimately report. ACLED’s verification process and more conservative methodology typically result in lower official counts.
## Calculation Approach
If we use the most recent ACLED baseline (~19,600 monthly deaths in late 2024) and consider the reported continued high intensity without major escalation or de-escalation, we can reasonably expect May 2025 to show similar or slightly higher figures.
Civilian deaths appear to be running at ~280-300 per month based on the April data. Military deaths would comprise the majority of ACLED’s count, likely in the multiple thousands given the reported intensity.
## Uncertainty Factors
Several factors introduce uncertainty:
1. **Reporting delays**: ACLED may not have complete May data by the June 15 resolution date.
2. **Verification challenges**: Not all reported deaths will be verified by ACLED.
3. **Potential for escalation/de-escalation**: While current evidence shows sustained high-intensity conflict, significant changes could occur during May.
4. **Data transparency**: Both sides may be incentivized to misrepresent casualty figures.
## Final Assessment
Based on all available evidence, ACLED’s historical reporting patterns, and the consistent reports of high-intensity conflict continuing into early May 2025:
1. **Less than 500**: Extremely unlikely given the confirmed civilian deaths alone approach this number monthly, and military deaths would push the total far higher.
2. **Between 500 and 1000**: Highly unlikely given the conflict intensity and historical ACLED reporting patterns.
3. **Between 1000 and 1500**: Possible but unlikely – would require a significant, unreported de-escalation from historical patterns.
4. **Between 1500 and 2000**: Possible but still below historical patterns – would require some de-escalation from previously reported levels.
5. **Greater than 2000**: Most likely outcome based on ACLED’s historical reporting of ~19,600 monthly deaths in late 2024 and no evidence of significant de-escalation.
Given that ACLED reported ~19,600 monthly deaths in late 2024 and all evidence points to continued high-intensity conflict, “Greater than 2000” appears to be the most probable outcome by a significant margin.
Model value:
* Less than 500: 1%
* Between 500 and 1000: 3%
* Between 1000 and 1500: 7%:
* Between 1500 and 2000: 14%
* Greater than 2000: 75%
Past forecasts by Phil’s and Jeremy ’s bots —>
Phil’s Ukraine forecasts are a side experiment with the VIEWS competition. Its Ukraine dashboard is below.
