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 September, 2025?
Phil’s pgodzinai predicts today:
Less than 500: 1%
Between 500 and 1,000: 4%
Between 1,000 and 1,500: 14%
Between 1,500 and 2,000: 45%
Greater than 2,000: 35%
13–17 minutes read (Full version of this report here —>)
Perplexity response:
## Key Citations and Summaries
**1. ACLED Europe and Central Asia Overview: August 2025**
*Date: August 13, 2025*
*Source: ACLED*
This report provides the most recent ACLED data available, covering July 2025. Russia’s offensive in eastern Ukraine reached record intensity with over 2,600 battles recorded – the highest number since the war began in early 2022. Russian forces made significant advances toward Pokrovsk, Kostiantynivka, and Kupiansk while creating additional pressure points across multiple regions. The civilian death toll reached 250 in July, marking the highest monthly total since September 2022, driven by nearly 458 remote attacks on civilians – an all-time high representing a 25% increase from the previous month.
**2. ACAPS Ukraine Crisis Update**
*Date: August 19, 2025*
*Source: ACAPS*
Between August 10-14, 2025, Russian sabotage groups advanced 10-12km past frontlines east of Dobropillia, forcing new mandatory evacuations affecting 3,000 children in affected areas. The increasing use of first-person-view drones by Russian forces significantly complicates evacuation efforts and poses heightened risks to both civilians and humanitarian workers. The pressure on transit centers has intensified, with older people and those with disabilities facing particular vulnerability in frontline areas where essential services have deteriorated.
Claude Vision analysis response:
Looking at this ACLED Ukraine Conflict Monitor page, I can extract the following relevant data for predicting state-based conflict deaths in September 2025:
## Current Death Toll Data (as of the page date):
– **Total reported fatalities since February 24, 2022**: 61,800+
– This includes both civilian and combatant deaths from both sides
## Recent Monthly Trends:
From the fatalities graph shown:
– Recent months appear to show approximately **1,500-2,500 deaths per month**
– The trend line shows some fluctuation but has remained relatively steady in recent periods
– There doesn’t appear to be a clear increasing or decreasing trend in monthly fatalities
## Most Recent Monthly Range:
Based on the visible graph, the most recent months shown appear to have fatality counts in the **1,500-2,500 range per month**, with some months potentially exceeding 2,000 deaths.
Gemini Multiple Choice response:
1. **Historical Base Rate from ACLED:** The ACLED Ukraine Conflict Monitor page explicitly states that “Recent months appear to show approximately 1,500-2,500 deaths per month” and notes that “some months potentially exceeding 2,000 deaths.” This establishes the primary base rate for monthly fatalities. [Vision Analysis]
2. **Recent Conflict Intensity:** The ACLED Europe and Central Asia Overview from August 2025 (covering July data) indicates a significant escalation in conflict intensity. July 2025 saw over 2,600 battles, the highest number since the war began in early 2022. Civilian deaths in July also reached 250, the highest monthly total since September 2022, primarily due to a record 458 remote attacks on civilians. This suggests that overall state-based conflict deaths, which include combatants, were likely very high in July.
3. **Continued Offensive Operations:** The ACAPS Ukraine Crisis Update from August 19, 2025, further corroborates sustained high-intensity conflict, reporting Russian forces advancing 10-12km past frontlines in mid-August and an increased use of first-person-view drones. This indicates that the high tempo of fighting observed in July continued into August.
4. **Lack of De-escalation Signals:** There is no information suggesting any significant de-escalation, ceasefire, or major shift in the conflict that would lead to a drastic reduction in casualties for September. The trend points towards continued, or even increased, combat operations.
GPT Multiple Choice JSON response:
Summary baseline: ACLED’s most recent public reporting (July 2025) shows exceptionally high battle counts and elevated civilian deaths, and August reporting/analysis indicates continued Russian offensives and localized breakthroughs. Visual inspection of ACLED’s monthly fatalities graph (and the textual summaries you provided) show recent months clustering in roughly the 1,500–2,500 fatalities per month range. Using that as the baseline — and given the August tactical advances and use of new ISR/attack methods (FPV drones, intensified remote strikes) that tend to increase both combatant and civilian fatalities — the base-case expectation for September 2025 is that total state-based conflict deaths will be in the mid-to-high thousands rather than the low hundreds.
Why I favor the 1,500–2,000 bucket most strongly: ACLED’s recent months do not show a low-intensity lull; instead they show sustained high-intensity combat across several regions (Donetsk, Kharkiv, Zaporizhia, around Kupiansk/Pokrovsk). Operational tempo has increased, but not necessarily by an order of magnitude in a single month. That makes the middle-high bucket (1,500–2,000) the modal outcome: it’s the most likely continuation of current intensity without a major new strategic shock. I also give substantial probability to the >2,000 bucket because recorded battle counts and the August tactical gains imply risk of an above-2,000 month if either side launches concentrated offensives, or if strikes on population centers spike.
Why I give non-zero probability to lower buckets: Data, reporting, and month-to-month variability matter. ACLED’s totals are aggregated from many sources and can vary with reporting delays, localized evacuations reducing exposure, or temporary operational pauses (weather, logistics) that could reduce monthly counts. Those mechanisms make very low monthly totals (<500 or 500–1,000) plausible but highly unlikely given current trajectory.
Anthropic response:
The most authoritative source is the ACLED Ukraine Conflict Monitor screenshot, which shows recent monthly fatality counts in the 1,500-2,500 range, with the graph suggesting most recent months cluster around 1,800-2,200 deaths. This represents total state-based conflict deaths including both civilian and combatant casualties from both sides. The visual analysis indicates the conflict has maintained this elevated intensity level without clear trends toward escalation or de-escalation in recent months.
The textual ACLED report from August 2025 provides critical context about July 2025 specifically, reporting over 2,600 battles (highest since the war began), 250 civilian deaths (highest since September 2022), and 458 remote attacks on civilians (all-time high). While this doesn’t give us total death figures for July, it strongly suggests July 2025 saw exceptionally high conflict intensity. The ACAPS report from August 19, 2025, confirms continued offensive operations with Russian forces advancing 10-12km beyond frontlines in mid-August, indicating sustained high-intensity combat continuing into late August.
The base rate from the visual analysis strongly anchors expectations around 1,800-2,200 deaths. The July 2025 intensity surge suggests we might be at the higher end of this range or slightly above. However, extreme outcomes (under 1,000 or over 3,000) appear unlikely given the sustained but relatively stable intensity pattern visible in the historical data. The “Greater than 2000” category deserves significant probability given July’s record intensity and the visual data showing several recent months at or above this threshold.
GPT Multiple Choice JSON response:
ACLED’s most recent complete-month reporting (July 2025) shows a marked increase in conflict intensity: unusually high battle counts (2,600+ in July) and elevated civilian deaths (≈250 in July), with ACLED’s visual monthly-fatalities series for recent months appearing to cluster around roughly 1,500–2,500 deaths per month. Independent reporting from August 2025 (open-source situational reporting and ACAPS summaries) documents Russian tactical advances in parts of Donetsk/adjacent sectors and heavier use of long-range and FPV-drone attacks that elevate both combatant and civilian risk. Taken together, the best baseline forecast is that September 2025 will be in line with the recent high-intensity months rather than a sharp drop to low levels.
Why I weight the mid–high bins most heavily
– Base case (no major new political settlement or radical change in operational tempo) implies monthly totals similar to recent months: most likely range is 1,500–2,000 or >2,000 rather than <1,500. Contemporary operational reports show active offensives and greater area of contact, which pushes the tail probability up for >2,000 but not so high that >2,000 is the single most probable bucket.
– The month is already underway (today 2 Sep) and major structural changes (a formal ceasefire or a dramatic single-month spike from a battle of unprecedented scale) have lower short-term probability. That reduces the chance of very-low or very-high outliers, but it does not eliminate the chance of >2,000 given the current high-intensity trend.
– ACLED’s methodology and reporting scope are stable and broadly consistent over time; changes to reporting practice are possible but unlikely to move a month’s total by an order of magnitude.
Calibration and final judgment
– Given the strong recent signal of high-intensity fighting, I place most probability in the two higher middle bins (1,500–2,000 and >2,000) while keeping a meaningful probability on the 1,000–1,500 bin to reflect plausible but less-likely moderation. The two lowest buckets (<500 and 500–1,000) are extremely unlikely given two-plus years of sustained fighting and the current uptick in activity.
Model’s Answer:
Summary and reasoning
ACLED’s most recent complete-month reporting (July 2025) shows a marked increase in conflict intensity: unusually high battle counts (2,600+ in July) and elevated civilian deaths (≈250 in July), with ACLED’s visual monthly-fatalities series for recent months appearing to cluster around roughly 1,500–2,500 deaths per month. Independent reporting from August 2025 (open-source situational reporting and ACAPS summaries) documents Russian tactical advances in parts of Donetsk/adjacent sectors and heavier use of long-range and FPV-drone attacks that elevate both combatant and civilian risk. Taken together, the best baseline forecast is that September 2025 will be in line with the recent high-intensity months rather than a sharp drop to low levels.
Why I weight the mid–high bins most heavily
– Base case (no major new political settlement or radical change in operational tempo) implies monthly totals similar to recent months: most likely range is 1,500–2,000 or >2,000 rather than <1,500. Contemporary operational reports show active offensives and greater area of contact, which pushes the tail probability up for >2,000 but not so high that >2,000 is the single most probable bucket.
– The month is already underway (today 2 Sep) and major structural changes (a formal ceasefire or a dramatic single-month spike from a battle of unprecedented scale) have lower short-term probability. That reduces the chance of very-low or very-high outliers, but it does not eliminate the chance of >2,000 given the current high-intensity trend.
– ACLED’s methodology and reporting scope are stable and broadly consistent over time; changes to reporting practice are possible but unlikely to move a month’s total by an order of magnitude.
Key drivers and uncertainty
– Drivers that raise fatalities: Russian localized offensives that create breakthrough-and-pursuit phases, heavy long-range strikes on populated areas, or very intense set-piece battles over urbanized frontline localities. The August field reporting of 10–12 km local advances and intensified strike campaigns point in this direction.
– Drivers that lower fatalities: rapid local de-escalations, successful defensive repulses that reduce battle duration and exposure, or a negotiated (even temporary) reduction in strikes and deep fires. These are possible but less supported by recent empirical trends.
– ACLED reporting caveats: ACLED collects from many sources and sometimes updates or revises counts; however, broad month-to-month patterns are generally reliable and consistent.
Most critical assumptions and probabilities they fail (and how failures would change the forecast)
1) Assumption: Operational intensity remains at or near the high July/August 2025 levels through September. Probability this assumption fails: 25%. If it fails via substantial de-escalation or a stabilization that lowers battlefield contacts, probabilities would shift downward (raising the 1000–1500 and 500–1000 bins). If it fails via an even larger escalation, the >2000 bin would rise.
2) Assumption: ACLED’s coverage and counting definitions remain consistent for September. Probability this assumption fails: 5%. If ACLED materially changes methodology or source coverage, the reported month total could move, but the chance is low and is treated as a small source of uncertainty.
3) Assumption: No single outlier battle (or very large strike with mass casualties) occurs in September that dramatically changes the monthly total. Probability this assumption fails: 20%. If such an outlier occurs, it would push probability toward >2000, potentially substantially.
Calibration and final judgment
– Given the strong recent signal of high-intensity fighting, I place most probability in the two higher middle bins (1,500–2,000 and >2,000) while keeping a meaningful probability on the 1,000–1,500 bin to reflect plausible but less-likely moderation. The two lowest buckets (<500 and 500–1,000) are extremely unlikely given two-plus years of sustained fighting and the current uptick in activity.
Final probabilities
Less than 500: 1%
Between 500 and 1,000: 4%
Between 1,000 and 1,500: 14%
Between 1,500 and 2,000: 45%
Greater than 2,000: 35%
Past forecasts by Phil’s and Jeremy ’s bots —>
Phil’s Ukraine forecasts are a side experiment with the VIEWS competition. Its Ukraine dashboard below.
Source: The VIEWS machine forecasting competition https://data.viewsforecasting.org
Source: https://www.understandingwar.org/backgrounder/russian-offensive-campaign-assessment-august-25-2025
