Date China takes major military action against Taiwan – By Dec 2036
Loading…
(a) at least 1,000 People's Liberation Army military personnel have been deployed to the main island of Taiwan for the purpose of establishing PRC sovereignty;
(b) the People's Republic of China has imposed a blockade that closes all major Taiwanese ports (Kaohsiung, Keelung, Taichung, and Taipei) for at least 10 consecutive days; or
(c) the People's Republic of China has launched kinetic strikes (missiles, airstrikes, or naval bombardment) against military or civilian infrastructure on the main island of Taiwan.
Exclusions: military exercises that do not actively intercept traffic or strike targets; cyber-only operations; actions limited to outlying islands (Kinmen, Matsu, Penghu) without action against the main island; economic sanctions or trade restrictions without physical military action.
Bars include events up to their close, 23:59:59 UTC: “By end of Apr 2026” includes everything up to 30 Apr 2026, 23:59:59 UTC.
Built from historical cases only. Old, high-stakes territorial claims rarely turn into war (about 0.6% a year), and China has not invaded, blockaded or struck Taiwan in 77 years. Past buildups that ended in action mostly did so within a decade; the PLA's last reorganisation is about that age, lifting the line to 14% by late 2033.
Reference classes
- High-salience territorial claims at least 15 years old: years in which a war over the claim began (ICOW, 1816-2001, Americas, Europe, Middle East): 6 of 1057
- The same claims in their first 15 years: 7 of 577
- Territorial disputes that stopped at a blockade or a deadly attack without becoming a war, per war (COW MID 5.0, 1816-2014): 14 per 54 wars (4 blockades, 10 attacks)
- Military buildups by a claimant power that ended in military action (corrected: Aegean dropped, India-Kashmir and Turkey-Cyprus coded to this question's event): 9 of 12
- Action within 10 years of a buildup starting (Kaplan-Meier): 67%
- Buildups still without action after year 14 (China-Taiwan, Korea, Essequibo): 0 actions in about 171 case-years
- China-Taiwan's own record: years since 1949 with an invasion, port-closing blockade or strike on the main island: 0 of 77
Method
Reference classes
We use three levels of evidence, from general to specific, combined with partial pooling to estimate a time-varying monthly hazard rate.
Level 1: General territorial dispute base rate
Among all major-power territorial disputes post-1945, roughly 1-2% per year escalate to significant military action. This comes from the Correlates of War MID dataset (~2,400 militarized interstate disputes 1816-2014, 85% of fatal conflicts involving territorial issues). This is the weakest prior — just a sanity floor.
Level 2: Major powers with active military buildup for a specific territorial goal
This is the core reference class. We identified 13 historical cases — 8 that resulted in military action, 5 where no action has been taken despite decades of tension.
Cases that resulted in military action:
Cases where no military action has been taken:
Kaplan-Meier survival analysis of these 13 cases gives roughly 54% probability of action within 10 years of active buildup starting, implying an average annual hazard of ~7.5%/year during the buildup phase. The median time to action among those that acted was ~6 years.
The cases where no action was taken are critical — they show that roughly 40% of these disputes simply never result in full military action, even over many decades. China-Taiwan itself is the longest-running such case at 77 years.
Level 3: China-Taiwan specific expert data
Current prediction markets and expert surveys (as of March 2026) provide the most directly relevant evidence:
- Metaculus: full-scale blockade by 2030 at 40%, by 2035 at 60%; full-scale invasion by 2028 at 10%, by 2030 at ~20%, by 2035 at ~33%
- CSIS 2024 survey: 52% of 64 China experts think force short of invasion “likely” within 10 years; only 27% of US experts and 17% of Taiwan experts believe China can currently execute an amphibious invasion
- Swift Centre: 9% blockade probability by mid-2027
- Pentagon 2025 report: PLA targeting capability to fight and win a Taiwan war by end of 2027; new bridge landing vessels and expanded amphibious training observed
These imply annualised hazard rates of ~12-16%/year near-term (peaking 2027-2028 around the PLA modernisation milestone), declining to ~7%/year long-term.
Multilevel model
The posterior annual hazard rate for each year is a weighted average of Level 2 and Level 3:
λ_pooled(year) = 0.80 × λ_specific(year) + 0.20 × λ_group
- 80% weight on Level 3 (specific): prediction markets aggregate hundreds of forecasters with diverse information — substantially more informative than the small historical sample.
- 20% weight on Level 2 (group): the reference class pull prevents overconfidence and anchors the long-run tail to historical base rates.
Level 1 is absorbed into Level 2 (the Kaplan-Meier already incorporates the non-action cases).
Time variation
The hazard rate is time-varying: it peaks in 2027 (the PLA's stated modernisation deadline, the consensus “window of maximum danger” identified by military analysts) then gradually declines as the specific risk window passes. It remains well above the general base rate throughout the forecast horizon due to the structural nature of the cross-strait dispute. Monthly values are smoothed via linear blending at year boundaries, then converted to a cumulative CDF via the survival function.
Hazard rates and cumulative probabilities by year
Resolution criteria
This market resolves to the earliest date at which any of the following conditions is reported by at least two of AP, Reuters, and AFP: (a) at least 1,000 People's Liberation Army military personnel have been deployed to the main island of Taiwan for the purpose of establishing PRC sovereignty; (b) the People's Republic of China has imposed a blockade that closes all major Taiwanese ports (Kaohsiung, Keelung, Taichung, and Taipei) for at least 10 consecutive days; or (c) the People's Republic of China has launched kinetic strikes (missiles, airstrikes, or naval bombardment) against military or civilian infrastructure on the main island of Taiwan. Exclusions: military exercises that do not actively intercept traffic or strike targets; cyber-only operations; actions limited to outlying islands (Kinmen, Matsu, Penghu) without action against the main island; economic sanctions or trade restrictions without physical military action.
Sources
- Metaculus Q#11480: Chinese invasion of Taiwan forecasts
- Metaculus Q#12309: China blockade of Taiwan forecasts
- Metaculus Q#5320: Chinese control of half of Taiwan by 2050
- Metaculus Q#11401: China controls Taiwan after invasion
- CSIS ChinaPower 2024: expert survey on China's approach to Taiwan
- CSIS ChinaPower 2022: earlier expert survey (64 China experts)
- Swift Centre: China-Taiwan and TSMC risks to 2027
- Pentagon 2025 Report: annual report on PRC military and security developments
- UI Sweden (2024): “Is a conflict over Taiwan drawing near?” — review of available forecasts
- EA Forum (2023): “An invasion of Taiwan is uncomfortably likely”
- Correlates of War: Militarized Interstate Disputes dataset (base rates)
Download the Python script used for this analysis
Refitted again on 17 November 2026 under the house rule that the line comes from reference classes only. v1's Level 3 (prediction markets and expert surveys, 80% of the weight) is removed, and so is the 2027 peak: no reference class was found linking a stated military deadline to when action came. Level 1 is now measured, not assumed: in the ICOW territorial claims data, high-salience claims at least 15 years old saw a war over the claim begin in 6 of 1057 claim-years (0.57% a year), against 7 of 577 in their first 15 years. This question also counts a 10-day closure of the main ports or strikes on the main island, so blockade-only and attack-only disputes are added from the COW MID data: 4 blockades and 10 attacks with over 25 deaths per 54 territorial wars, giving a background of 0.71% a year.
Level 2 is the corrected 12-case buildup set, coded to this question's event: Greece → Aegean dropped (it runs the other way), India → Kashmir coded as action in 1947 → 1948, and Turkey → Cyprus as action in 1964, when Turkish jets struck the island. No case acted after year 14, so the hazard is matched to the age of the buildup with a cure model (a share of buildups act after an exponential wait; the rest never do). Taiwan's age is dated two ways with equal weight: from 1949, as v1 and the other open cases are coded (age 77, extra risk near zero), and from the PLA's 2016 reorganisation into theatre commands, as the Crimea case is dated from Russia's 2008 military reform (age 11, about 4.8% in the next year, falling). The line is conditional on no qualifying action by 17 November 2026.
Level 2: Major powers with active military buildup for a specific territorial goal
| Case | Buildup start | Action year | Time to action |
|---|---|---|---|
| China → Tibet | 1949 | 1950 | 1 years |
| Indonesia → East Timor | 1974 | 1975 | 1 years |
| Iraq → Kuwait | 1988 | 1990 | 2 years |
| Argentina → Falklands | 1976 | 1982 | 6 years |
| Russia → Crimea | 2008 | 2014 | 6 years |
| Turkey → Cyprus | 1964 | 1974 | 10 years |
| India → Goa | 1947 | 1961 | 14 years |
| Russia → Ukraine (full) | 2014 | 2022 | 8 years |
Checked against sources, November 2026.
| Case | Buildup start | Duration so far |
|---|---|---|
| China → Taiwan | 1949 | 77+ years (ongoing) |
| N. Korea → S. Korea | 1953 | 73+ years (ongoing) |
| Venezuela → Essequibo | 1966 | 60+ years (ongoing) |
Checked against sources, November 2026. Removed as wrong: India → Pak Kashmir; Greece → Turkey Aegean.
Hazard rates and cumulative probabilities by year
| Year | Annual hazard (pooled) | Cumulative P(action by year-end) |
|---|---|---|
| 2026 | 7.9% | 7.0% |
| 2027 | 15.9% | 20.7% |
| 2028 | 14.3% | 32.1% |
| 2029 | 12.7% | 40.6% |
| 2030 | 10.3% | 46.8% |
| 2031 | 8.7% | 51.4% |
| 2032 | 7.1% | 55.0% |
| 2033 | 7.1% | 58.2% |
| 2034 | 7.1% | 61.1% |
| 2035 | 7.1% | 63.9% |
Sources
Liquidity over time
i Shows the market’s available liquidity over time. Liquidity can decay continuously and may change discretely if liquidity adjustments are applied.22 comments
Log in to comment.
Taiwan's Ministry of National Defense said on Oct 15 that it is watching for a large-scale PLA exercise around Taiwan during the PLA's usual November–December peak drill season. China has held at least one large encirclement exercise around Taiwan every year from 2022 to 2025, the latest being Justice Mission 2025 in late December; none has been held so far in 2026. Focus Taiwan, Oct 15: MND watching for large-scale drills
On Oct 18 Taiwan's coast guard reported 12 China Coast Guard and research ships plus four fishing boats operating at the same time off Taiwan's east, south and southwest coasts and around Pratas, some inside restricted waters, and called it "hybrid warfare" (Al Jazeera/AFP, Oct 18). The AEI/ISW Oct 20 update notes that simultaneous incursions at several locations have been rare outside blockade-simulating exercises such as the Joint Sword series, and assesses that Beijing is likely testing vessel types for a blockade or other contingency (AEI/ISW China & Taiwan Update, Oct 20). Taiwan holds local elections on Nov 28.
On October 28, NSC Secretary-General Joseph Wu posted a map of 53 Chinese ships, 34 of them warships, operating from southern Japan to off the Philippines, with the Liaoning carrier group east of the Philippines. China calls the Liaoning's activity routine training. Taipei Times
On November 3 Taiwan's MND logged 49 PLA aircraft sorties in 24 hours—its highest daily count of 2026, with 31 crossing the median line—as over 100 Chinese naval and coast guard ships operated across the Western Pacific (Taipei Times). Geospatial tracking also identified four Chinese research vessels (Xiangyang Hong 22, Tongji, Jia Geng, Mushanzi) loitering over Taiwan's undersea cables (Taiwan News).
Defence Minister Wellington Koo said on November 10: "China has indeed conducted area denial drills in the Western Pacific with the Liaoning carrier group and other naval training formations." China has declared no exercise. Trump and Xi are due to meet at APEC in Shenzhen next week. Reuters via Yahoo
At their November 19 Shenzhen bilateral, Xi urged Washington to "keep doing the right thing" on Taiwan, China's readout quoted Trump reiterating opposition to "Taiwan Independence," and no new Taiwan agreement was announced. PRC MFA · AP
AEI/ISW (November 6) assess this may be a major unannounced exercise simulating Taiwan's isolation, larger than Justice Mission 2025: surface groups from the Eastern, Northern and Southern Theater Commands, the Liaoning group, and the Fujian seen leaving Sanya on November 2. AEI/ISW
MND reported no PLA aircraft in each of the three daily windows ending October 22–24, after 29 sorties on October 21. The latest window had one PLAN ship and five official ships. MND daily reports
Reuters reported on October 1 that U.S. officials increasingly see a Chinese invasion of Taiwan before 2028 as unlikely, despite Xi Jinping's instruction for the PLA to be ready by 2027. The report cites two current U.S. officials, one former official and one person familiar with the matter, all anonymous. Their reasons: the anti-corruption purge has hurt readiness and left two active members on the seven-seat Central Military Commission; they described last year's exercises as smaller and less threatening; and Beijing wants to see the result of Taiwan's January 2028 election. One official said a fourth straight DPP win would change that: “If that happens, I think 2028 becomes pretty sporty.” The sources discussed invasion only; the report does not assess blockade or strike options. The Pentagon declined to comment. Reuters via Internazionale: U.S. officials see invasion unlikely before 2028
China's fifth plenum communique on October 29 expelled a record 33 Central Committee members, including 16 military officers (among them generals Zhang Youxia and Liu Zhenli), leaving the seven-seat Central Military Commission with just Xi Jinping and Zhang Shengmin (BBC).
China's revised National Defense Mobilization Law takes effect today, October 1. The NPC Standing Committee adopted it on August 28. Article 2 defines national defense mobilization as state action to meet threats to sovereignty, unity, territorial integrity, security and development interests by converting economic and social capacity into defense capacity, with rapid shifts between peacetime and wartime. Article 25 requires county-level and higher governments to build mobilization preparation into economic and social development plans, and military authorities to fold implementation plans into combat-readiness planning. Xinhua: full revised law text (Chinese); State Council/Xinhua: NPC Standing Committee adoption, August 28.
Taiwan’s Ministry of National Defense budget proposal sets out a six-year NT$27.59 billion (US$868.16 million) program to raise combat-ammunition stocks from 30 days to 120 days, to sustain operations during a blockade. The ministry allocated NT$7.3 billion after the Executive Yuan approved the program on September 3. A defense-planning director said the program needs to be accelerated because more frequent exercises and drills have depleted ammunition. Taipei Times, September 29
Taiwan’s defense minister Wellington Koo said on September 29 that Taipei had received no notice of a change to existing U.S. arms sales or cooperation. A separate $14 billion package remains stalled after the May Trump–Xi summit; Koo said 66 F-16V jets have reached the production stage for delivery. Associated Press, September 29
Defense Priorities’ September 10 report recommends ending U.S. mutual-defense treaties with Japan, South Korea, the Philippines and Australia and adopting a non-intervention policy for a Taiwan conflict. It proposes moving most U.S. forces from the first island chain toward Guam, Palau and other second-chain locations, with changes completed by 2035. Stars and Stripes reports about 80,000 U.S. troops are currently stationed in Japan and South Korea. This remains a think-tank proposal; the 2026 National Defense Strategy calls for a denial defense along the first island chain. Defense Priorities report · Stars and Stripes, September 23
From June 6–10, China’s Ministry of Transport said maritime authorities inspected 198 vessels east of Taiwan. The Diplomat reports that Chinese Coast Guard ships radioed all transiting commercial vessels for origin and destination details, including ships from Singapore, Benin and Liberia. The Diplomat: China is moving toward a new form of coercion at sea.
Kyodo: Beijing threatens to cancel the September 24 summit if Washington approves new Taiwan arms sales.
President promulgates KMT-backed drone bill — NT$240bn over six years in principle; annual appropriations still matter.
China deploys record number of ships around Taiwan as pressure grows — AFP. July’s 244 excludes warships.
Taiwan says ‘unpredictable’ China strengthens air and sea control nearby — Reuters.
I don't think the PLA purges mean much of anything. The PLA has a longstanding modernization program dedicated to producing an army that can take Taiwan if the political leadership decides it needs to. A few sackings/eliminations, even of elite generals, are not going to change the PLA's trajectory nor IMO do they tell us much about how the political leadership perceives PLA readiness: there are a LOT of plausible reasons to purge someone, ranging from genuine corruption and incompetence to political disloyalty to simply wanting/needing to flex party control over the army (something that has not typically been entirely guaranteed in modern China).
More significant IMO are the 2028 Taiwan elections. If the KMT wins and manages to put together enough internal coherence that it is perceived as a credible negotiating partner in Beijing, this IMO lowers the risk of invasion very substantially out to at least 2032. The CCP leadership is relatively risk averse and I think would prefer to settle the Taiwan question through political means rather than war. I think everyone in the West thinks this is impossible (especially after Hong Kong) and maybe it is, but
a) the CCP may well not agree
b) although Hong Kong is perhaps something of a failure as far as the "one China, a few different systems" model goes, Macao is still right there!
The KMT is a broad coalition with pro-US and more open-to-Beijing factions, and has historically struggled to stick to a coherent unified party platform enforced by the party leadership: everything is worked out by negotiation between factions instead. That said, the pro-Beijing faction seems to be in the ascendancy, winning the party chairmanship via Cheng Li-wun, who is currently visiting China and is expected to meet Xi (this is the first trip to China by a senior KMT figure in at least 10 years). The governing DPP is unpopular and widely perceived to be dubiously competent, and only won the last election due to vote-splitting between the KMT and TPP. I do expect the DPP to lose power in 2028, and so most of my risk is concentrated in the period after 2032: if there is no move towards a more pro-China politics on Taiwan by then, and no progress at all towards reunification talks, then invasion risk rises considerably.
Very unlikely in the next couple of years given the extensive purges in the PLA.
Also very unlikely to happen outside of March–May and September–October.
Worth watching this video of their amphibious vehicle to realise how bad rough seas will be.