Deception Island: the phoenix rises

The British base on Deception Island in 1967, with a fresh new building. Soon it was no more.

Volcanoes can hide themselves in clear sight. We may see a rugged hill or a lake, but may not recognize the lurking danger. A volcano that lacks a conical shape can hide its nature from us.

Volcanoes are deceptive by nature. That cone with the steam plume at the top may look friendly, but it has a dark secret. The name was Tambora. The rugged normal-looking hill may not show any indication of a volcanic heart, until it suddenly explodes. It was called Pinatubo. That beautiful circular lake is a popular place to spend the summer, away from the heat of nearby Rome. But how did it form? And that island with frequent small, eminently viewable (from a distance) eruptions suddenly disintegrates and sends a tsunami halfway across the world. No, appearances can deceive. We cannot always trust what our eyes tell us.

Do you believe what you see? The cubes below appear to be moving. They are not.

One volcano in particular is so deceptive that it is called Deception Island. It is near the Antarctic Peninsula, and not easy to reach. On approach it shows as a typical island. After a while a narrow channel appears giving access to the interior. Pass through the channel (beware of a submerged rock in the middle of the channel) and the island disappears, as in a mirage. A sea appears, almost completely surrounded by an irregular steep rim with black beaches. Chinstrap penguins meander on the black sands. The rim created the illusion of a solid island, while hiding the large hole in the centre. It is a very useful hole: the enclosed sea provided a safe harbour for the whalers of centuries past. Remains of their buildings can be seen. They were also attracted by the volcanic activity which warms the soil, very welcome so close to Antarctica. But this island harbour is not all it seems. The 10-km wide ring is the remnant of a massive volcanic eruption which wasn’t all that long ago. There is danger here.

The video below shows it well. It was provided by contributor Virtual, and dates from a 2012 visit.

Source: Virtual

With illusory islands and deceptive volcanoes, it seemed worth a try writing an illusory post. So I approached ChatGPT: the new chatbot which may put an end to essays as a form of assessment. The bot was set leading questions, in order to get a post on Deception Island. Here is the result. My questions are in italic. The order has been slightly changed.

ChatGPT on Deception

Me: How many active volcanoes are there?

ChatGPT: It is difficult to give an exact number of active volcanoes, as new ones can be discovered and the level of activity of existing ones can change. However, a commonly cited estimate is that there are around 1,500 potentially active volcanoes on Earth. Of these, approximately 50-60 are erupting at any given time.

Can we predict volcanic eruptions?

Volcanic eruptions can be predicted to some extent using various methods such as monitoring changes in seismic activity, ground deformation, gas emissions, and temperature changes. However, the accuracy and lead time of these predictions vary and there is still a significant level of uncertainty involved, especially for less predictable or less monitored volcanoes. It’s important to note that the science of volcano forecasting is still evolving, and the best way to stay safe during an eruption is to stay informed of current conditions and follow evacuation orders from local authorities.

When was Deception Island discovered?

Deception Island, located in the South Shetland Islands of Antarctica, was discovered in 1820 by a group of sealers led by American seal hunter Nathaniel Palmer. (Warning: error of fact.)

Tell me about the bases at Deception Island

Deception Island, located in the South Shetland Islands of Antarctica, was used as a base by various countries in the early 20th century, including Britain, Chile, and Argentina. The first permanent scientific base on the island, called Whalers Bay Base, was established by Britain in 1944. It was used for various scientific and meteorological purposes. However, the base was destroyed in 1967 following a volcanic eruption. Currently, the island is a popular tourist destination, with only a Chilean refuge station, which serves as a research facility, still operating on the island.

Wasn’t there an Argentinian base as well?

Yes, you are correct. There was also an Argentine base, called “Carlini Base”, located on Deception Island. The base was established in 1952 and was primarily used for scientific research and meteorological observations. It was one of several Argentine bases in Antarctica and served as an important hub for the country’s scientific community. (Warning: incomplete fact.)

What kind of science is done on the island?

Deception Island, located in the South Shetland Islands of Antarctica, is primarily used for earth and atmospheric sciences research. The following are some examples of scientific studies that have been conducted on the island:

  • Volcanology: Deception Island is an active volcanic caldera, making it an important site for the study of volcanic processes, including magma formation and eruption dynamics.
  • Geology: The island’s unique geological features, including its geysers, hot springs, and fumaroles, make it an important location for geological research.
  • Meteorology: The island’s location and weather conditions make it an ideal site for meteorological observations, including studies of the atmosphere, oceanography, and climate.
  • Biology: Deception Island is also a site for biological research, including studies of the local flora and fauna, as well as their interactions with the changing environment.

These are just a few examples of the scientific research that is conducted on Deception Island. The island remains an important hub for scientific investigation, as it provides a unique opportunity to study the Earth’s systems in a remote and challenging environment.

Do you have a reference for this information?

I’m sorry, but as a language model AI, I don’t have any specific references. However, you can find more information about scientific research on Deception Island through various sources such as scientific journals, research papers, and academic databases. Additionally, information about the history and current status of scientific research on Deception Island can be found on the websites of organizations such as the Antarctic Treaty System and the Council of Managers of National Antarctic Programs.

(So it did actually tell me where the information came from.)

How active is the Deception Island volcano?

Deception Island is a potentially active volcano located in the South Shetland Islands, Antarctica. It has a history of frequent eruptions, with the most recent one occurring in 1970. Since then, there have been numerous seismic events and fumarolic activity observed, indicating that the volcano is still active and capable of erupting again in the future.

The level of activity at Deception Island can vary and is monitored by scientific agencies to assess the risk of future eruptions. At present, the volcano is considered to be at a low level of activity. However, it’s important to note that this can change quickly and unexpectedly, so visitors to the island are advised to follow any safety recommendations from local authorities.

How did the 1970 volcanic eruption of Deception Island occur?

The 1970 eruption of Deception Island was a phreatic (steam-driven) eruption that occurred on the island in Antarctica. It was triggered by the interaction of magmatic heat with shallow water or sediment, causing a steam explosion.

The eruption caused significant damage to scientific stations and facilities on the island, but no human casualties were reported. Ash and pumice deposits were spread over a large area, and the shape of the island was altered by the formation of a new caldera (a large, bowl-shaped depression formed by the collapse of a volcanic cone).

After the 1970 eruption, the island has continued to show signs of volcanic activity, including steam emissions, earthquakes, and changes in sea level. These suggest that Deception Island remains a potentially active volcano, and scientists continue to monitor the island for signs of future eruptions.

How did the 1967 eruption happen?

The 1967 eruption of Deception Island, located in the South Shetland Islands of Antarctica, was caused by a volcanic eruption. The eruption occurred on the 12th of February, 1967 and was one of several eruptions that have taken place on the island throughout its history.

During the 1967 eruption, magma rose to the surface and broke through the caldera, which is a large crater formed by a previous volcanic eruption. The eruption produced ash, steam, and volcanic gases, and also caused significant damage to the British research station located on the island. The station was evacuated, and several buildings were destroyed or severely damaged.

The 1967 eruption was considered a moderate-sized eruption, with an estimated volcanic explosivity index (VEI) of 2. Despite the damage caused to the research station, no casualties were reported.

The Deception Island volcanic system is considered active, and ongoing monitoring is necessary to understand its behavior and potential for future eruptions. The island remains a popular site for scientific research due to its unique geological and biological features, and the lessons that can be learned from its volcanic history.

When did the caldera of deception island form?

The caldera of Deception Island formed during a volcanic eruption that occurred in the late Holocene epoch, around 7,000 years ago. The eruption was one of several large explosive eruptions that have occurred on the island in the last 10,000 years, and it caused the collapse of the central part of the volcanic cone, creating the large, circular depression that is now known as the caldera. (Warning: outdated fact.)

The caldera of Deception Island is now filled with seawater, forming a sheltered bay that is known as Port Foster. The caldera and its surrounding areas are a popular destination for tourists and scientific researchers, who come to study the island’s unique geology and wildlife, including penguins, seals, and whales.

How often has Deception Island erupted?

That model is currently overloaded with other requests.

How often has Deception Island erupted?

Deception Island is a potentially active volcano located in the South Shetland Islands, Antarctica. It has a history of frequent eruptions, with several known eruptions occurring in the past 10,000 years. The most recent eruption at Deception Island took place in 1970, when a phreatic (steam-driven) eruption caused significant damage to scientific stations and facilities on the island, but no human casualties were reported.

Since then, the island has shown signs of volcanic activity, including steam emissions, earthquakes, and changes in sea level, suggesting that it remains a potentially active volcano. The frequency of eruptions at Deception Island is difficult to predict, as it is influenced by a complex interplay of geological and environmental factors.

Scientific monitoring of Deception Island is ongoing, and scientists are using a variety of techniques, such as seismology, gas monitoring, and satellite imagery, to track changes in the level of activity and assess the risk of future eruptions.


I decided that ChatGPT writes well and gives relevant information but it has a tendency to digress, uses stock phrases, suffers from repetition and inaccuracies. The content is variable, sometimes quite good (as in the overview of science), sometimes more superficial and on a number of occasions wrong. Palmer did not discover Deception Island: he was the first to visit it. The British base was destroyed in 1969, not 1967. The Argentinian base it lists was on nearby King George island. Their base on Deception Island was a different one and was called Deception Station. (The bot didn’t actually say it was on the island!) The inaccuracies reflect where it gets its information from: as it told me, it is a language model, not a science database. You get what is available. It will produce mistakes if that is what it finds or if it doesn’t fully understand what is written. A similar experiment asking physics questions (that wasn’t me) gave very dubious results. I noticed it prioritized the British base over the Argentinian or Chilean one, suggesting the language model takes input mainly (or only) from english-language sites, and it preferred the American discovery of Deception Island over the earlier British one.

ChatGPT is probably best used as as a front-end to a search engine or to wikipedia. Rather than giving a list of web sites, it presents the relevant material in a clear way. The writing is very good but it is obvious there is no real understanding of the material behind it: the critical analysis is a task for the reader. In fact it told me so! It will need a fact checker attachment. The stock phrases give the impression of knowledge without understanding. In a student essay such phrases would be guaranteed to lead to questions about their meaning, in order to test the underlying understanding.

ChatGPT would be ideal for writing a strategy document: these typically consist of stock phrases, are repetitive and lack meaning. A basic popular website on volcanoes might also work but you won’t get more than what is commonly known. It is wisywig: what you see it what you get. Writing a post for VC will take more training for the bot. But I would not rule it out.

(I can see why google is worried. This bot could pull the rug from underneath their income stream. I would expect google to respond by inserting adverts into the information stream in such a way that the bot does not recognize them as such. Once that happens, ChatGPT could include answers such as: ‘ Excursions are very popular and can be booked at …’ . My prediction for the future of artificial intelligence is that there will be a battle between truth and adverts. VC favours the former.)

Good news! ChaGPT can do a lot of our work for us. Now we have even more time for meetings!

Deception Island

Let’s get back to the real world. Deception Island measures 14 by 13 km. It is the tip of a mountain which measures 25 kilometers across: it is a substantial volcano. The central bay which takes up the interior of the island is called Port Foster. The bay is 10 by 7 km wide; the entrance channel is only 500 meters across. The highest points on the island are on the east (Mount Pond) and southwest (Mount Kirkwood), at 550 and 450 meters. Glaciers have formed on these hills. Elsewhere the island is ice-free but often snow covered. Temperatures are cold but moderately so, a bit below freezing in winter, barely above in summer, with little change between day and night. Port Foster has a depth of 180 meter at the centre, but there is a shallower platform around the coast which is less than 50 meters deep.

Source: Wikipedia

Everything on the island is volcanic. The composition is basaltic-andesitic. Dikes (there are not many) are mainly basaltic. There are active fumaroles and hot ponds. There are also many maars, remnants of phreatic explosions, often at the edge of Port Foster.

There are ruins of Norwegian whaling stations on Deception Island; these were occupied intermittently from 1911 to 1929. They were abandoned when whaling no longer required shore facilities. The British scientific base was opened in 1944, the Argentinian one in 1948 and Chile followed in 1955. They were abandoned after the eruption in 1967.

Deception Island

Faults of deception

The tectonics here are complicated. Deception Island is located in between the Antarctic peninsula and the South Shetland Islands. The strait between them is called the Bransfield Strait. The Strait is around a million years old and formed as a back-arc basin. The arc is the volcanic arc of the South Shetland Islands, and the cause was the subduction of the Phoenix plate, a small plate in between the Antarctic plate and the Scota plate. This subduction pulled down the back-arc. But the subduction ceased some three million years ago when the Phoenix plate stopped spreading. The Phoenix is now dead. In response, a new spreading centre formed in the Bransfield Strait, perhaps because of the relaxation after the Phoenix died. The South Shetland Islands now lie on their own microplate. Deception Island lies exactly on the new spreading centre that separates this microplate from the Antarctic peninsula.

The region is fault ridden. A belt of faults runs southwest to northeast underneath the island, forming a half graben. The few dikes that have been found on Deception Island are mainly aligned with this SW-NE fault which appears an axis of extension. A significant fault (called the Maraconi fault) runs SSE-NNW along the side of the island, causing the straight cliff that forms the western coast of Deception Island.

The island was shaped by a caldera forming eruption. After this, Deception Island did not go quietly into the dark. It continued to be a very active volcano. The fumaroles and geysers have been present ever since the discovery and presumably much longer. An eruption was reported in 1842 from the slopes of Mount Kirkwood. This eruption was discredited by later reports, which argued there had been no other evidence of eruptions. However, debris from this eruption was later found in the glacier ice showing that the doubters were wrong. But this was only proven after the events of 1967.


Institute of Polar Studies, 1972

The island first proved its volcanic doubters wrong on 4 December, 1967. A pyroclastic eruption occurred in Telefon Bay, in 23-m deep water. After three days the eruption ceased: by that time the new island was 62 meters high, 1 kilometer long and 350 meters wide. There were three craters on the island, aligned northeast to southwest. This orientation suggests a dike was involved, as this is the axis of least resistance due to the graben. The new island quickly began to erode on the southeast side facing Port Foster, and the craters became water filled. The opposite side of the new island was better protected.

A second eruption occurred about 2 kilometer to the east. This happened on the coast of Port Foster where a new bay was cut in the coast here. There may also have been a submarine eruption in the same region. A damaging debris flood came downhill just north of the eruption. This may have been ice melting from a third eruption point.

The eruption lasted only three days. But a little over a year later, on 21 February 1969, strong tremors appeared. There were five people present on the island at the time. They were from the British Antarctic Survey and were staying at the British station at Whalers Bay on the east side of the island. The five men fled the station huts but while trying to reach an evacuation point, an eruption began at Pendulum Cove on the side of Mount Pond, near to where they were. Two eruption plumes were seen and rocks began to rain down. The men sheltered underneath corrugated iron sheets from the abandoned whaling huts. Carrying these sheets above their heads, they went back to the station for better shelter. There they discovered that a debris flood carrying large ice blocks had swept through the site in their absence. It was a lucky escape. Helicopters from a Chilean vessel rescued the men later that day. This was the same vessel that had evacuated the bases on 5 December 1967! This was the time the base was actually destroyed, not 1967. (ChatGPT, take note.)

The eruption had occurred along a 5-km fissure with 20 separate eruption vents. This had triggered the debris flood, which reached 15 meter high in places. Both the Chilean and British base were badly damaged.

The 12 August 1970 eruption happened in the same location as in 1967 but it was much larger. It was not directly observed: no one was present as it was still winter, a good time not to be there. There was an earthquake at around 5.40pm on that day which may have been the onset or the run-up of the eruption. The next morning, ash fell on nearby islands. It was later found that the eruption had produced 13 vents on land and in shallow water. Some of the vents coincided with the vents from 1967 and had enlarged those craters. The eruption plume was 10 kilometer high. The eruption likely reached VEI 3.

Some of the 1970 craters (Baker, 1971)

It is notable that all three eruptions came from linear fissures. Even though the eruptions were along the inner edge of the caldera, it does not appear that a ring fault was involved.

Other recent eruptions

The ice on the island contains a record of the recent eruptions: these produced layers of ash. Between 1780 and 1972, there are indications for 23 separate explosive eruptions. There may have been twice as many: in summer ash is blown around by the wind, and it may be hard to distinguish these from new eruptions. In winter the island is covered in snow and all ash is fresh. The oldest reported eruption was in 1842, when ‘a wall of fire’ was seen on the side of Mount Kirkwood. The ice shows that this may have been the largest eruption in 350 years. Ice deposits also show eruptions in 1912 and 1917 which were not recorded.

What will happen next? It is plausible that the next eruption will be in the northeast of Port Foster. The sea floor here is showing inflation, with a 5 meter rise between 1990 and 1999. We’ll see.

Caldera formation: Deception in the making

The faulting in the region has led to the suggestion that the caldera collapse was caused by the faults, and was largely a tectonic affair. The opposing view is that the crater formed in a large eruption driven from a shallow magma chamber.

The evidence points at the latter. The eruptive layers are exposed best in the coastal cliff but are also seen elsewhere. The bottom of the stratigraphy shows a basaltic shield. These were often strombolian eruptions which build up the large edifice. Above this is the so-called ‘Outer Coast Tuff Formation’ consisting of yellow tuff. It is present everywhere on the island with a very uniform thickness of around 45-50 meters on the coast and 90 meters at the centre. It shows individual layers of some 10-15 meters thick. Above that are the more recent ejecta. These are different in different parts of the island, as expected from small individual vents, but are typical of similar thickness to the Tuff layer.

The yellow tuff at the coast. Source: Origin and evolution of the Deception Island caldera (South Shetland Islands, Antarctica), Marti et al Bulletin of Volcanology 75, 732 (2013)

The yellow tuff clearly comes from a major explosive eruption, and it is considered as the origin of the caldera. It consists of ignimbrite and co-ignimbrite.

The internal strcuture of the caldera has been measured with seismic waves. This has shown a staggering of 1.2 km depth of infill by pyroclastic materials similar to (and probably identical with) the yellow tuff. Above that is up to 100 meters of post-caldera eruptions. The caldera once was much deeper than it is now.

The caldera cuts the yellow tuff. However, it also cuts the early post-caldera material. This suggests that the current caldera did not all form in the original eruption. Part of the caldera formed later, either as a true collapse or by erosion. The original crater was smaller than the current size.

One can estimate the original size by assuming that the later volcanic vents are located on the edge of the original crater, which is where the structural weakness is. This gives a size of 50km2, versus 82 km2 of the current caldera. It has an irregular shape. The edges of the original caldera seem to coincide with structures or faults that are still visible in the landscape. Thus, although the caldera formed in a large explosion, the shape of the hole was largely determined by pre-existing faults. There was no obvious ring fault. It is perhaps not surprising that a volcano located in such a faulty region will be affected by those faults.

How large was the eruption? The size of the hole may have been as much as 89km3. Of this 60km3 fell back into the crater, albeit as lower density material. The remainder was thrown out. So the eruption was at least 29km3 DRE. This makes it a high end VEI-6 at minimum.

What caused the eruption? The yellow tuff is of uniform composition, but also contains basaltic inclusions. This may suggest that the eruption was triggered by fresh basalt entering and destabilizing a more evolved magma chamber. If this is the case, then the eruption happened fairly quickly after the intrusion as there is no evidence for mixed magmas, only the two separate magmas. The composition suggests that the magma was stored at around 10 km deep, well below the current caldera. The magma chamber was not particularly shallow. The magma moved up very quickly from this depth.

Some of the yellow tuff shows effects from water while other doesn’t. This suggests that water may have been involved with part of the eruption. A natural suggestion is that the eruption started on dry land, but that sea water intruded once the vent had dropped below sea level. This could make the eruption similar to Krakatoa – or Hunga Tonga. It is quite speculative, but whenever a large eruption takes place on an oceanic island not far from sea level, the influence of sea water must be considered.

When did the eruption happen? This has only recently been discovered. It had not been conclusively identified with a dust layer in Antarctic ice cores. It could have been in the late Pleistocene (ice age) or the early Holocene. The co-ignimbrite shows that the eruption was above sea level. The nature of the eruption may suggest that the sea level was similar to current levels. However, we don’t know that for certain. But in 2018, three tephra layers were found in lakes on Livingstone island, about 40 km from Deception Island (Antoniades et al. Science Reports, 8: 17279). The tephra had composition similar to Deception Island, and the largest layer showed the presence of two separate magma types, as was seen in the yellow tuff. This layer was carbon dated to 3860-4110 BP. The other two tephra layers are younger, at 2370 ± 100 and 1890 ± 140 BP, and were much smaller eruptions.

Thus, the caldera-forming eruption appears to be only 4000 years old. ChatGPT thought it was 7000 years ago. It also suggested that later eruptions were also large. Both claims were inaccurate. The yellow tuff is the only major layer here. Later eruptions were much smaller whilst earlier eruptions were probably not explosive. (In fact, the description of the 1970 eruption by ChatGPT seems a bit dubious. It is a language machine, not a library.)

These new data provide an intriguing piece of information. They show that the tephra was dry: the isotopic ratios were not affected by sea water. Thus, the major eruption took place on land, or before sea water could interact with the magma. That means the caldera had not yet formed. This has similarity with Krakatoa where only the last of the four major explosions on the day of destruction produced wet ash: the first three were dry. This leaves the precise role of sea water unclear. The team finds indications for a large earthquake shortly after the deposition of the ash, and suggest that this was due to the collapse of the caldera. But if that was true, how did 2/3rd of the ejecta end up inside the caldera? One wonders whether the ‘earthquake’ was just the thick tephra blanket in Livingstone Island sliding into the lakes.


Deception Island is a unique place, an active caldera masquerading as a typical antarctic island. It is neither a typical fault-driven collapse nor a typical ring-fault caldera. It was a singular VEI-6 or 7 eruption which was shaped by pre-existing faults.

The volcano sits on top of a spreading rift which was caused by the cessation of the spreading of the neighbouring Phoenix plate. We can speculate that the local oceanic plate began to be pulled towards the stalled edge of the Phoenix and this triggered a new spreading centre to accommodate the pull. Deception Island formed at the end of this spreading centre, in a region of extension, where perhaps heat welled up past the subduction edge. It grew out of the Phoenix plate.

The phoenix is a well-known story which even played a role in Harry Potter. It dies in fire to be resurrected. But it is an illusion. The pPhoenix did not rise from the ashes. Instead, from the ashes of the Phoenix rose Deception Island.

Albert, February 2023


(Street art by Edward Mueller)

103 thoughts on “Deception Island: the phoenix rises

  1. Poor Albert, his otherwise very interesting article got upstaged by an earthquake.

    • They predict “potential for stronger seismic activity” all the time. Of course they’re going to get one right every now and then. Their “forecasts” are based on “planetary geometry”. Anyone who believes in that sort of stuff should go and have a look at this:

      The location, magnitude and timing of that tweet unfortunately seems very impressive. Note that he only states “sooner or later”. That’s a well known fact. It’s a bit like saying sooner or later Alaska will have an M7.5 earthquake. Point at a spot that has not ruptured in a long time and increase your odds of getting it right.

    • Dubious does not begin to describe it. ‘Unhelpful’ would be a start

    • “The earthquake in this region was predicted 3 days ago (~M 7.5):”

      No it wasn’t. You cannot predict earthquakes. Anyone who claims to do so is a charlatan or a crank or both.

  2. Another big one. Over M7.5. I feel sorry for the people in the area.

      • Just horrible. Waves from the second quake are visible on the icelandic drumplots now. Rescue work will be very problematic and dangerous since any new quake may destabilise already damaged buildings.

      • I must wonder how much additional strain this shift puts on the ‘North Anatolian’, whose release in the ‘locked’ region near Istanbul would dwarf the damage from current ghastly event…

        Note: I’ve seen some suggestions that the NA ‘gap’ is not locked solid, but creeping: Would mitigate the likely disaster to ‘merely apocalyptic’…

        • The North Anatolian fault is strongly segmented, and Istanbul is many segments away. There won’t be any change of stress there. It is still a region at risk (see our post on this fault) but it is not related to the current event. In the current region, earthquakes tend to migrate south and west over decades. But given the size of this quake, it may well have ruptured to the southwestern end of the fault.

      • The first one has been estimated to around 190km long. It was a shallow strike slip quake with northeast-southwest alignment, consistent with the East Anatolian Fault. The second was estimated 120km long, also shallow strike slip, but with N-S or possibly E-W alignment. N-S would indicate the Dead Sea Transform, right where it connects to the East Anatolian Fault.

        • Judging from the aftershock distribution it’s the E-W aligned plane that’s the correct one for the second quake.

        • for some reason the second large quake gave a much lower frequency s-wave in Iceland. Perhaps that quake ruptured in the direction away from Iceland. Assuming that the rupture is at 90% of the speed of sound, and the frequency was 50% lower, it was at an angle of very roughly 60 degrees with respect to the first quake, away from Iceland. It is a rather vague estimate though but would fit with a west-east progression

          • Just seen some videos from Elbistan near the epicentre of second major quake. Looks like virtually every building is destroyed or seriously damaged.

            Video at link

            Brian Krassenstein @krassenstein

            The destruction in Turkey is horrific as aftershocks continue to make the situation worse. Here is a video from Elbistan, which is a district in the Turkish Province of Kahramanmaraş.

            Americans stand with you all in Syria and Turkey.

          • I’m trying to understand the tectonic setting in the area. There is a triple junction where the Karasu Fault (KF) connects to the East Anatolia Fault (EAF). KF is a continuation of the Cyprus Arc that also links the EAF to the Dead Sea Fault.

            Tracing the aftershocks, it seems like the first quake struck along the KF all the way up to the triple junction. From the triple junction, aftershocks continue and trace the EAF to the east but not to the west.

            The second quake appears to have happened on a conjugate fault to EAF that I can’t find on any map. The whole mess looks like a chain reaction all around the triple junction.

          • It is compression zone – say crumple zone – where the plates converge somewhat. That makes it quite broken. The east-west fault is a short conjugate of the north anatolian fault: the first earthquake moved the right plate north and this pushed the left plate west (in addition to the transform motion). The second quake resolved some of the westward pressure, I expect.

          • Now seeing references to Cardak fault.


            An earthquake with a magnitude of 6.8 occurred in 1544 on Cardak Fault [21]. Nalbant et al. [22] studied the KM zone (the area between Kahramanmaras and Malatya), which has gathered significant amount of stress during the last 200 years; thus the magnitude of a possible earthquake along the segment ruptured by 1114 (Mw > 7.8) and 1513 (Mw > 7.4) earthquakes is expected to be larger than 7.3. Palutoglu and Sasmaz [18] pointed out that another destructive earthquake in the vicinity of study area took place in 1795 with a magnitude of 7.0 (Figure 2). Accordingly, Golbasi-Turkoglu Segment, the KFZ, the Engizek Fault, and the Cardak Fault come to the forefront. Therefore, Kahramanmaras and its vicinity area are defined as an area with a seismic gap, and large earthquakes are expected to occur in a near future.

          • Yes, that seems consistent both with the epicenter and the aftershock pattern.

  3. By the way things are going this looks like it could be the deadliest quake since 2011, especially if enough rescues are made.


    Gaziantep Castle was a castle first built by the Hittite Empire as an observation point on top of a hill at the center of Gaziantep, Turkey. It suffered damage during the 2023 Turkey–Syria earthquakes.

    It was later built into a main castle by the Roman Empire in 2nd and 3rd centuries AD.[1] It underwent further expansion and renovation under Emperor Justinian I between AD 527 and 565.[1] The circumference of the round shaped castle is 1,200 metres (3,900 ft). The walls are built of stone and the castle has 12 towers.



  5. Nice article .. Thank you Albert

    Im working on my own, as I took many extraodinary beautyful photos from Etnas summit craters, needs to put them as an article

  6. I don’t know what’s going on with phivolcs or the IGEPN but it’s almost 2 weeks since we’ve gotten a daily report on Taal as tremor increased last month and 8 months since the last monthly report on CCN.

    • It is either Chinese new year or Taal has erupted and wiped out IGEPN.

      • They’d better share whatever they’ve been smoking once everything’s all said in done.

  7. It looks like multiple faults are involved, notice the newer quake by Latakia

    • Could be like the 2016 Kaikōura, New Zealand, quake which involved a domino effect in nearby faults.

      • That happened in eastern California a while back, but the quakes were way out in the desert and nowhere near the size of these ones. Because this is multiple earthquakes on different faults, all along a plate boundary.

        I sent money to MSF. They are on the ground in northern Syria.

  8. Just two comments.

    1) Given the population density, the size of the quake (dimensionally & quantitatively) and the building construction methods (standard narrow reinforced concrete column) the fatalities were bound to be huge. To be honest including syria I cannot see the total being much less than 30k and I would be unsurprised if it were more. Note the original USGS red estimate band.

    2) I have a personal gripe with the use of ‘epicentre’ in these situations (that is any quake over 6.8 at) in that ‘epicentre’ is totally misleading. The first indication (for me) was Albert’s comment that the fracture zone was 400km long. What is essentially a line 400km long is badly and INACCURATELY describes as ‘epicentre’. Better a 7.8 earthquake 400km long northwest of Gaziantep. Not only does that show how HUGE it is in energy but how huge in size.

    • I gather (from a BBC tv report) that Turkey has decent building standards as it knows it in an earthquake zone. But that older buildings and cut corners obviously don’t follow those.

      I wondered whether the NS motion from the one fault and then the EW movement from the other fault would make buildings more vulnerable to damage/collapse even with good building regs.

      Anyone got any more info on that ?

      Also I gather getting aid into Turkey is easier diplomatically – and that getting aid into the north of Syria is particularly problematic (as it’s the part of Syria that is not under control of the Assad regime, and with only 1 narrow border post into northern Syria). The part under Assad regime control is getting support from Russia and China at least, but Assad might even obstruct assistance into the other region.

      • Don’t know if the direction of the motion would make any difference. It shouldn’t as the direction of the shock would not be known in advance; earthquakes can occur on any side of a building. Earthquake proofing is based on shock absorption and damage limitation if part of the building fails.

        Do we know yet how earthquake-proofed buildings fared compared to others?

        • no idea – I just imagined a brick wall and shook it left to right – and then front to back – and compared that imagined scenario to shaking both times in the same direction.

          in my imagination shaking both ways meant the wall was shaken lengthways and then side to side – so it fell either the first or second time

          shaking one way twice had a 50/50 of being lengthways both times = still standing
          or sideways both times = falls the first time
          which gives a 50% chance of it not falling (in the very simple mental model – as I have a very simple mind 🙂 )

          and obviously in the real world the building alignments won’t be like that – but that thought experiment suggested that multi directional shaking probably results in more building collapse than single directional shaking (possibly even for buildings with good earthquake-proofing)?

          • Brick walls are not particularly resistant to earthquakes. You need vertical supports

          • Bricks and earthquakes do not get along, not at all.
            Not used much at all in Japan or California.

            The 1989 Loma Prieto earthquake, which I experienced in San Francisco, collapsed every chimney in Santa Cruz as well as some older brick buildings downtown, including a coffee shop where multiple people were killed.

            I was living in a wooden Victorian and the only damage was to the electrical system and to our dishes, which all went flying out of the cabinets.

          • Where the walls / foundations were weakened in the first quake, large aftershocks would be more likely to bring the walls down.

      • These codes are fairly recent so many/most dwellings in the zone will be conventional construction. That’s even if the codes were being faithfully followed.

  9. I think this is the signal of the quakes in Turkey, recorded on the tiltmeter at Kilauea. It isnt a big signal but usually quakes big enough to see on the tilt are obvious on the map, not so today.

  10. If Mauna Loa keeps recovering at the current rate, then the summit will be back at is pre-eruption level by June

    • Did this after 1984 too, and after 1975. Seems it is a fairly typical response. My educated guess is that after eruptions the lack of pressure causes rapid resupply of magma from lower levels of storage, which reinflates the volcano. But the actual resupply of magma from the plume is usually low and now the entire volcano is lower pressure, so the real recharge to cause the next eruption takes a long time. When the supply is high like in the 1850s and 1860s (and to some extent all of 1850-1950) then eruptions are about an order of magnitude faster recurral time, although not really bigger in absolute scale which is interesting.
      1975 was not very big, about 100 million m3 lost from the chamber total (30 million erupted) so the volcano could erupt again within a decade but last years eruption was about 2.5-3x larger so chances are we have another long wait, although that is a potentially risky bet. At least, last years eruption was not as big as 1984 so it shouldnt be another 40 years 🙂

      Kilauea I dont think does this so much. The magma chamber at Mauna Loa is structurally the same as the large deep south caldera magma teservoir at Kilauea, which is probably why its eruptions are rarely long lived and relatively infrequent but often large in scale and very high in intensity. Kilaueas major chamber rarely erupts directly though, in recent decades perhaps only in 2018 (and that is only my speculation) and maybe 1959-1960, both LERZ eruptions. Kilauea has many smaller magma chambers in the upper 3 km of the volcano, in a way each is kind of like asmall volcano of its own. So generally because these are smaller the volume of magma and the pressure is lower. Just my observation though.

      This lack of a shallow system like that may be a sign of the age of Mauna Loa, it is slowly waning, and the volcano is not appreciably growing larger on average, Kilauea is overall the more dominant of the two at a longer timescale. Although it seems the change to erupting transitional alkaline basalt is pretty abrupt at Hualalai and Mauna Kea so that point is still some time off before Mauna Loa reaches its senior years, nothing important on our human timescale.

      • You might file this under ‘duh’, but I don’t Kilauea will grow appreciably taller until Loihi/Kamaʻehuakanaloa gets well above sea level. Those ERZ ‘hemorrhage’ eruptions keep knocking the summit down.

        • I think that the volcanoes probably reach that 4 km elevation only in their older years, when supply wanes a bit and most of the lava will erupt at the summit and upper rifts.

          I also expect that kilauea will grow south a lot in the near geological future, to be honest I cant see Kama’ehuakanaloa reaching sea level any time soon without Kilauea helping it out, if Kilauea grew south more in the past then perhaps it already would be subaerial. Kilauea is entering its golden age so to speak, Kama’ehuakanaloa still might have another 100k years before that, maybe by then Mauna Loa will be post shield.

          Kilauea probably will struggle to get really tall for a long time yes, shield eruptions tend to do that, they spread out very far and wide. But if it forms a proper ring faulted caldera then that could change the dynamics, it may not be only infrequent low altitude rift eruptions that are high intensity and large volume but summit eruptions too. Like a cross of Bardarbunga and Sierra Negra, but with 5x the magma supply, 🙂

  11. Indeed the gigantic icesheet on Antartica chills down the Sourthen hemisphere alot more than the Northen.

    This is South Georgia at same latitude as South UK, yet its pretty much stuck in the Ice Age, as Antartica cools down the south hemisphere alot more than the Northen. The Sourthen hemisphere is quite chilly.. for soure

    • It is interesting to compare this to Shackleton’s route across the island. The lake that he describes as ‘tarn’ is visible on the Sentinel image.


    • This is one of the worst climates in the world, an Subpolar Marine climate, overall mild, But extremely chilly and very wet. Its a wet bone chilling cold that goes into the nerves. Most of the year its cold rain and wet snow. Summer temperatures rarely climbs above 5 degrees C and winters sit little below freezing

      Its the cold wetness and high humidity that makes Oceanic Arctic climates misrable

    • Very nasty climate, wet and bone chilling sea spray .. only the most hardened beardy fishermen can enjoy this

      • I dont think anyone enjoys being there, just that there are very few other options… All the other places near Antarctica are just this but worse, and the other islands nearby are also active volcanoes and with no anchorpoints.

        You being from the great northern land that is Scandinavia are probably very aware of the tendency for desire to go south at any opportunity that presented itself up until the past century, it kind of defined a whole era of your history from the perspective of the rest of the world 🙂 Nowdays you can go Viking without being a pirate lol.

      • South Scandinavia is not very cold luckly, warmed by the Gulf Stream and Westerly winds, we have a climate similar to the coldest regions of South New Zeelands lowland interior, and we are similar to Germany as well in weather so warm temperate, some frosts in winter but rarely any snow that last long, and summer are warm and pleasant and and sometimes hot.

        Vancouver is a good climate analoge despite that we are as far up as Anchorange

        You woud not complain about the winter in South Sweden and Denmark because they rarely gets any. But its cold enough where example Carl lives to prevent growing of Subtropical plants that grow example in UK and Ireland

        • Hi Jasper
          In the 1980s I worked for the British Antarctic Survey (BAS) and visited South Georgia on our way south in 83 and again heading north in 86. It is a beautiful and astonishing place. Later in the 80s I toured Finland and Norway for a month on motorcycles during September and October and can confirm the climates are similar albeit at very different latitudes! The wildlife in the south is much larger in numbers and clearly not afraid of humans. There is a small island at the northern end called Bird Island (BAS used to have a small summer base there) that is almost literally covered in birds and seals. During a survey of the penguin numbers, a colleague of mine was ‘nipped’ by a fur seal (they guard their patches of beach ferociously) which almost took the muscle off the bone…he was lucky to get away without more serious injury.

          • Sounds like quite an adventure! Thanks for sharing, sorry about your colleague and glad to hear he was ultimately alright!

      • Norway and Sweden have mild winters similar to South Georgia but we have much warmer summers well into the upper 20 s

        South Georgia being a small landmass in a large very cold ocean very rarely reach above 10 C in summer

    • Northen Scandinavia where many of my relatives live is boreal and subarctic similar to Canada and Siberia in apparence. Long long winters, its even longer in examples in populated places in Lapland.
      Winters are milder than Canada and Siberia some coastal influense, but we are still talking about months months with temperatures below – 6 C. Often sit around – 12 C for most of the winter year. Dips to well below
      – 20 C is common. And rare cold spells can go to almost – 50 C , and its quite dry because of rainshadow from the Norway Mountains. Winters are snowy and reflective and helps alot to make the short days in Lapland longer.
      Summers are short and cool.. but long days but often pleasant figures like + 15 to 18 C are common, some days there are hot with +30 C possible.
      Winters are often clear and sunny, summers are quite dry but with rain showers and thunder possible and weak fronts.

      Sourthen Scandinavia is alot warmer thats for soure with coastal influense.
      Its similar to Vancouver and UK in apparence of biomes. Winters are mild in South Scandinavia, and parts like South Denmark and South Sweden rarely gets any snow at all, even If frosts happens. Its very rainy in winter there and humid and very windy. Winter temperatures are generaly sitting at around
      – 2 C to + 9 C in South Scandinavia with +2 C is common. Warm fronts in winter can bring very mild weather for these latitudes, winters are Icelandic there, althrough Iceland Maybe even milder still in winter. The high humidity and windy conditions makes winter in South Scandinavia feel very cold indeed, despite the very mild temperatures. Its very cloudy in South Sweden and that makes the winters feel very gloomy and dark without snow

      Summers are warm and pleasant in South Scandinavia, with temperatures well above +20 C possible in June to August +22 to +25 C is common, and some days are hot with +28 to 34 C is a possibilty. The high humidity in South Sweden makes 26 C feel extremely hot, so we kind of have muggy summers. Coasts near the cold Sea are sunny and have strong seabreezes in summer. Summer in South Scandinavia is warm and pleasant and with unstable weather, fronts and local thunderstorms bring alot of rain.

      While Sweden like rest of Nordic Countries are very good to live in like Cost Free Education and Healthcare, and it seems possible too without having taxes so high that pepole complain..

      But I finds Sweden generaly boring .. geologicaly dead, and many living areas are miles of grey apartment blocks looking like a ”resident evil game” rather than city planning, immensely depressing during a cloudy rainy winter day. But most of our man made structures are very beautyful and we have many old cities.

      No active volcanoes : ( so I think Iceland woud fit me better

      I been in Sweden too long ..
      But here is a full write – up of Swedens weather .. Big diffrence between South and North

  12. some more pictures of displacement from Turkey earthquake
    This article contains the first image (that I have seen), copied below, of apparent surface rupture during the M7.8 Kahramanmaraş earthquake. It appears to show about 3 meters of left lateral displacement. The report is from Prof. Dr. Hasan Sözbilir.

  13. Regarding the “earthquake prediction”, Boris Behncke has written some very wise words about it:

    One thing I’d like to add is that the tweet that supposedly predicted the quake was made as a general statement related to a smaller quake that had already happened. It was not given as part of one of the regular forecasts. As Boris explains, it had absolutely zero value as a warning.

  14. Kilauea has been erupting for over a month now and the dome fountain has been constant but there have been few overflows. That us because it isnt the lake in the webcam that is overflowing but the smaller one in the middle of the crater, the spot where this eruption began.

    Seems to be entering a phase of shield building, looks a lot like those geyser episodes at Fagradalsfjall only without a fountain. The main lake seems to be closing iff towards distinct vent areas too, maybe soon we will have a collection of overflowing shields.

      • That middle lake is actually going pretty crazy this past day, hopefully HVO will zoom the webcam out a bit to show this activity 🙂

        • Wow, great timing on the thermal cam’s hourly image to catch that dispersal pattern!

          You should be able to right-click the animated image and save it offline as a non-updating animated .gif if you want to keep a copy that shows this (long press and select ‘download image’ in Crome browser on an Android phone)

          • Actually why I didnt put it in before is because imgur is inconsistent in loading on my phone, why I dont know…

            But after that comment and still going as we speak the lake has overflowed again many times, maybe instead of breaking out of the edge of the crust all the pressure building decided to go up through the lake, which I can only presume isthe lowest of the active vents. I guess this might just continue until lava erupts from the edge of the crater and removes the pressure at the lakes. Or just completely exits the caldera altogether and heads to the southwest…

            Wherever the laser is pointed now is 20 meters higher than when the eruption began, and over 900 meters above sea level, it is only 15 meters or so lower than the lava lake was in 2011 which triggered dike formation on the ERZ. That is unlikely soon but even with the GPS saying the 2018 eruption is halfway recovered a big part of that was permanent collapse, the summit is likely pressurized at this point just not enough to intrude magma into the ERZ while an open path already exists.

  15. Has the lava lake drained out somewhere? There seem to be islands all of a sudden.

    • Deflation inflation event, normal but still not explained in a satisfactory way. Typically they are net no change, the lake will be back to normal in a day or two 🙂

      • And now the DI event has ended and the lava is back. Except instead of erupting in the lake basin it is erupting out of the small pond again, the glow from that is visible in the live but not the actual lava 🙁

        Hopefully HVO zooms out the live just a bit soon, to show all of the activity.

        The western lake also seems to be completely unaffected by the DI events too, which is interesting.

        • They just repositioned the camera to point at the active flow out of that central pond.

          • On the video feed it changed at 10/02/22 07.58

            The feed still feels a little too zoomed in. Is there a wider view anywhere?

  16. Before the next article is posted, I’d just like to take the opportunity to say that I really enjoyed this one. I like what you did here with ChatGPT. It really demonstrates both the power and the caveats with using these new AI tools. Also an interesting read about Deception Island. After the Hunga Tonga event these shallow submerged calderas seem a little more intriguing. Thanks Albert for a really nice piece, I always enjoy reading your articles!

    • The displacements I have seen are smaller than expected. For a quake this size, it could have been 10 meters. I expect that the photos are from less affected regions

  17. It looks like HVO has switched the V1 cam’s orientation?


  18. Fascinating volcano. You have to think Deception Island is transitioning from a volcanic back arc to mid ocean ridge style volcano. Pretty likely unique. Basalt is the current vibe!

    The whole area is really interesting. We could have a VEI 6 in the Sth Sandwich volcanic arc and no one would notice, the place is so remote.

    Thanks for another excellent article Albert! The to and fro with the chat bot is fun! And very impressive. The errors are small in the scheme of things, and the continuity of the conversation was quite interesting (until it crashed, whereupon the conversation looks like it reset.)

Comments are closed.