Several people have emailed me an article from the Australian Broadcasting Corporation, with claims that some startups can provided more accurate rainfall forecasts than the Bureau – using artificial intelligence (AI). The Bureau’s counter claim, repeated in the same article, is but, AI is not good for long-term forecasts.
It is not news that the Australian Bureau of Meteorology is not very good at seasonal weather forecasting.
They mostly keep forecasting below average rainfall, or drought, and then we get another flood. That is what happened last summer, for northeastern Australia – and it happens over and over with their forecasts for the Murray Darling Basin.
As I have written over and over, the Bureau don’t bother to benchmark how bad they are – though I have. In a series of technical papers published in international climate science journals with John Abbot, beginning in 2012 and ending for me in 2017, we documented an alternative and better technique using artificial intelligence (AI). In the first of these papers* we compared output from the Bureau’s simulation model with our AI-based statistical model for 17 locations in Queensland.
It was no small task getting the Bureau to provide the data allowing the comparison to be made – that was achieved in August 2011. In the same meeting at the Bureau’s headquarters in Melbourne, I outlined to the then head of their long-range weather forecasting unit the possible benefits of work with Abbot and I, to further develop the technique.
We were the first to demonstrate the value of AI for rainfall forecasting in Australia.
I hope that the start-ups that are now focused on short term forecasts have more commercial success than we did. AI has so much application for weather forecasting – short, medium term, seasonal and long range.
There is something about the history of my work with Abbot in the most recent issue of the IPA Review, CLICK HERE. This article includes comment by me:
Locations along the east coast of Australia, including Cairns and Lismore, are very affected by changing sea surface temperatures and pressures across the South Pacific that have been measured since the late 1800s.
The official temperature database for Australia, known as The Australian Climate Observations Reference Network – Surface Air Temperature (ACORN-SAT) is used to generate an average Australian temperature, and this database only begins in 1910.
This record only begins in 1910 because many weather stations did not record temperature in what is known as a Stevenson screen (basically a white louvred box) until about 1910. Before 1910 the mercury thermometers used to measure maximum temperatures were not necessarily kept in a standard housing, and this could result in higher temperatures for the same weather.
A Stevenson screen did not become the official housing for the thermometers at the Bureau’s official weather station in Sydney until 1910. In Melbourne a Stevenson screen was not installed until 1908, and in Brisbane a Stevenson screen was installed earlier in 1896.
Darwin has the longest record, with an official temperature record from a mercury thermometer in a Stevenson screen starting in March 1894. This is all documented in the online archive for Darwin at the Bureau’s website, and I have found photographs of different shelters and other instruments in the Darwin public library including a photograph taken in January 1890 of a Stevenson screen in the post office’s yard.
Charles Todd is the person to thank for Darwin’s exceptionally long, continuous, and reliable early temperature record. He was an avid meteorologist, astronomer, and electrical engineer who oversaw the construction of the Overland Telegraph line connecting Darwin with Adelaide that was completed in 1870. That was the same year Todd became Australia’s first Postmaster-General.
After the completion of the Overland Telegraph, telegraphic officers in South Australia and the Northern Territory were required to report temperatures, barometric pressure, and rainfall on a daily basis to his West Terrace Observatory in Adelaide.
Perhaps as unexpected as the exceptionally long continuous and reliable temperature record for Darwin, Darwin also has the earliest reliable atmospheric pressure measurements. So, the Southern Oscillation Index (SOI) is still measured as the pressure gradient difference—not between Brisbane and Tahiti or Sydney and Tahiti—but between Darwin and Tahiti. These SOI values (expressed as an index) are still derived from the 1887–1989 base period, with the first 10 years of measurements part of the network established by Charles Todd, and still, to this day, updated daily by the BoM.
Changing daily patterns in the SOI were incorporated into the statistical models that John Abbot and I used to forecast monthly rainfall for locations on Australia’s east coast.
There will obviously be problems if rainfall has not been accurately recorded for the location of interest—if the historical record has been corrupted—because the AI will be considering the rainfall total, relative to pressure and temperature gradients and pressures across the Pacific, including at Tahiti.
AI is only as good as the data inputted; AI forecasts are only as good as the data provided for model building, and then for training the model that will be used to make the forecast. Training essentially involves running segments of data to give the model some idea of what to expect. In this regard, AI is like human intelligence: it can get better at anticipating what will happen next, if it is given some practice and good data (reliable information).
ADDITIONAL INFORMATION
*Abbot J., & J. Marohasy, 2012. Application of artificial neural networks to rainfall forecasting in Queensland, Australia. Advances in Atmospheric Sciences, Volume 29, Number 4, Pages 717-730. doi: 10.1007/s00376-012-1259-9
The feature photograph (top of this post) was taken on 22nd August 2014, for a front-page (if I remember correctly) article in The Australian newspaper by Graham Lloyd detailing our technique using AI for forecasting monthly rainfall up to 18 months in advance.
Jennifer Marohasy BSc PhD is a critical thinker with expertise in the scientific method.
In the late 60’s I worked in data processing. The boss had a favourite saying…”Garbage in equals garbage out”. You write that “AI is only as good as the data inputted” Both mean the exact same thing and the BOM has been “adjusting” their data and delivering crook results for years as you know better than anybody. Reading between the lines of the ABC article, it appears that ABC and BOM are circling the wagons?
This was written:
AI is only as good as the data inputted; AI forecasts are only as good as the data provided for model building, and then for training the model that will be used to make the forecast. Training essentially involves running segments of data to give the model some idea of what to expect. In this regard, AI is like human intelligence: it can get better at anticipating what will happen next, if it is given some practice and good data (reliable information).
Now that millions of acres have been changed from past vegetation, natural and cultivated, to urban areas and or Wind Farms and/or Solar Farms with much more concrete and steel and roads and heat island influence,
There are millions of acres where storm patterns and flood runoff are altered. This will, already has, causes issues for AI, and also for human intelligence.
Reliable information about what happened in the past is of much less use when the land use has changed a huge amount. My advice, if live on low land where wind and solar farms have been built on higher ground, you should move to higher ground, not in a path of runoff from the new developments.
To know what will happen in the future, you must know and understand what happened in the past. What happened in the past did happen when we can determine many of the natural conditions at that time, but not all of everything, not even enough of many factors. Now, we can measure and determine many more factors, but many of the things we measure and determine are different from past conditions and neither AI or human intelligence can accurately forecast all of the future consequences. Yes, water retention on many high places has been destroyed replacing trees and other vegetation with roads and wind and solar farms and there will be much worse flooding downhill from much of that.
Yes, we have destroyed reliable 24/7/365 adequate power generation, we have destroyed our mining and manufacturing industry and damaged our farming ability. But, the climate will self-correct, it always has, even though our western countries will be destroyed, in China, India, Russia, Africa, some others, life will get better and better. I am not sure about Africa, even though Russia and China are helping Africa develop, I am not sure how much is help for Africa Vs exploitation.
Jennifer I am absolutely certain that your machine learning neural networks method would be better than “AI”. Perhaps it would even be superior to the “start ups”. The difference being that you would supervise the data and not let the the AI gather its own from misinformed sources. I have seen you use then compare several sources and eventually after checking accept that the BoM had it wrong. Darwin could well be an example of this. I found some of the ancient Stevenson screen to Glaisher stand comparison data for Darwin. There were long running comparisons in many places. For the sample I had in front of me, the BoM had used the hotter of the two. This potentially causes a bigger problem than just at Darwin because if that was the Stevenson screen data then their assumption based on Adelaide that Glaisher data from the past was consistently too hot could well be wrong.
Lance Pidgeon
Timely return to BoM recordings and forecasting. It seems that personnel at the coal face are replaced by computer nerds who couldn’t tell you which way a anti cyclone rotates.
The Axial Spin of the Earth is from West to East.
The path of High and Low Pressure Systems is therefore from West to East and towards the Poles,(depending on the Hemisphere.)
Cairns and Lismore are directly in the path of Volcanic Aerosol Fallout from the constant volcanism source of the Indonesian Archipelago. The fact that the Great Dividing Range stands in the way of this Heat-source/Volcanism means there is propensity for ‘excessive’ rainfall events to precipitate on the Eastern side of the Range – indeed, to sometimes ‘link up’ with the East Coast Lows that occur further South.
Cyclones and Anti-cyclones rotate on their own axes. They are in fact ‘travelling vortices’.
If anyone can point out to me, evidence of a ‘Pacific Decadal Oscillation’ please do so.
ENSO is,(and always has been) a myth.
I thought Jen deleted repetitive posts. Why does Don Gaddes get a pass?
I’m sure Jennifer is capable of adjudicating her own blog. If she thinks my contributions are in any way counterproductive, I would expect her to say so. Until I receive such an admonishment, I shall continue to offer opinion – backed up with Observation.
(e.g. The King’s birthday is NOT the King’s birthday.)
There are 360 Day/Night Intervals per Earth/Solar Year,(One 360 degree orbit of the Earth around the Sun.) This may be divided into 12 Earth/Solar Months, (or 4 Seasons of 3 months each.)Thus, there are 30 Day/Night Intervals per Month – no 7 day weeks, or ‘leap years’ – no 31st day of any month.
The current Judeo-Christian/Catholic (Gregorian) Calendar(1582) is the continuation of a fabrication produced and perpetuated by Christian/Catholic Priests, (stemming from the Council of Nicaea, held under the auspices of the Pagan King Constantine, at the Imperial Palace in 325 AD.)
The almost ‘universal’ adoption of this Gregorian Calendar among nations, renders all religious denominations (by association,)inexplicable and untenable.
The excising of Religion from this Planet will be difficult – but will happen one way or the other, (bloodshed, or intellect, or both.)
For better or worse, Humankind is the arbiter of the stewardship of this Planet.
Unfortunately, Humankind does NOT have any God/Deity on its side.
Don, I encourage you to listen to Jordan Pederson on the proposition:
Jordan Peterson on the Christian Origins of Science [Logos & Literacy]
https://www.youtube.com/watch?v=VuwfO5Rv3JY
And a great mathematician’s analysis – https://www.youtube.com/watch?v=CWnv8f-3u-4
I’m not sure what ‘proposition’ you refer to Hamish.
Universities evolved from all manner of faith-based sources – and are still ‘corrupted’ by these sources, to the point that any science seen as not complying with an ‘imposed’ religious doctrine, is still seen as ‘heresy’ by Universities (and education in general,) if only because non-compliance would affect their academic status, offend their bona-fides and financiers – and ultimately the financial bottom line.
I do not know if you have read the work below, defining an exact frequency and duration of orbiting Dry Cycles – but the fact that these observed and documented Cycles exist as a Repeating Solar-induced Function, favours no part of the planet over any other part – (according to the the particular Cycle timeframes.) These Dry Cycles operate under the auspices of the Earth/Solar Orbital Calendar, not the Judeo- Christian (Gregorian) Calendar, (though the two may be superimposed.)
You may note, I do not maintain there is no ‘Creation Identity’. Science is fundamentally Agnostic – and must remain so. This means such a concept as ‘Creation’ cannot be ruled out. This Identity has ( however,) nothing to do with Religion, or its superstitions – and the continuing deluded fabrications of its priests.
I wonder what the outcome would be if Galileo was ‘re-tried’ today.
I suspect the Jordan Petersons of this world would be thrust forward, front and centre, by the Religious ‘Right’ of all denominations. (‘Right’, as in Right and Wrong.)
https://drive.google.com/file/d/1TFFDXyhe5b0ZfLCiFt23W4PbubQaQfQo/view?usp=sharing
A further proposition for Jordan Peterson and cohorts;
If it is proven that Religion has never had ‘God on its side’;
Wouldn’t this render the Churches and their attendant, subservient European Monarchies – still liable for the Genocide, War, Slavery, Rape, Piracy, Corruption and forced Evangelism – performed by their proxies throughout History, in ‘the name of God’?
Note;
It took the Catholic Church until 1992 to ‘forgive’ Galileo for being correct.