What's new
  • Happy Birthday ICMag! Been 20 years since Gypsy Nirvana created the forum! We are celebrating with a 4/20 Giveaway and by launching a new Patreon tier called "420club". You can read more here.
  • Important notice: ICMag's T.O.U. has been updated. Please review it here. For your convenience, it is also available in the main forum menu, under 'Quick Links"!

Have you looked at the North Pole lately?

trichrider

trichrider

Kiss My Ring
Veteran
might be time for the 'scientist' porky to tell everyone how global temperature is measured everywhere at once and consolidated into an average????
his koolaid cannot convince skeptics who rely on personal observations bolstered by peer reviewed studies.

tell me oh porked one why high and low pressure systems move and are of different temperatures. be specific

what causes the polar vortex?

how did the temperature you claim to be hottest in recorded history get that way?

c'mon man...
 
trichrider

trichrider

Kiss My Ring
Veteran

Development of wavelet-based machine learning models for predicting long-term rainfall from sunspots and ENSO​




Download PDF

You have full access to this open access article

Applied Water Science Aims and scope Submit manuscript

Development of wavelet-based machine learning models for predicting long-term rainfall from sunspots and ENSO

Download PDF



Abstract​

The variations in rainfall and its spatial and temporal distribution in wet and dry seasons have increased substantially globally owing to the effect of climate change. These disparities can lead to droughts and severe water shortages, as exemplified by the unprecedented drought in Taiwan in 2021, which is considered the worst in 50 years. From a broader perspective, the overall climate and water resources on Earth are influenced by factors, such as the El Niño phenomenon and solar activity. Accordingly, this study examines the relationship between rainfall and planetary- or large-scale influencing factors, such as sunspots and the El Niño-Southern Oscillation. Additionally, rainfall patterns under various conditions are predicted using machine learning models combined with wavelet analysis. These models use 60-years historical data to build models, and the Bayesian network model exhibited the best overall prediction accuracy (85.7%), with sunspots emerging as the most influential factor. The novel findings of this study strongly confirmed that the relationship between sunspot and local rainfall patterns can serve as a valuable reference for water resources management and planning by relevant organizations.

Introduction​

In recent years, the impact of climate change and the natural terrain characteristics of high mountains and rapid water in several areas globally have resulted in the uneven rainfall distribution (in time and space), and the agricultural, industrial, and economic developments with the growing population density globally have resulted in the unfavorable utilization of water resources and groundwater (Allan et al. 2013; Misra 2014; Ritzema and Van Loon-Steensma 2018; Varis and Vakkilainen 2001). Moreover, changes in the spatial and temporal characteristics of rainfall have resulted in several extreme hydrological events and environmental problems. Although the annual average rainfall of Taiwan is approximately 2500 mm, which is 2.6 times higher than the average annual rainfall of the world, Taiwan is still regarded as a water-poor region (Narvaez et al. 2022; Shiau and Hsiao 2012). The main rainfall seasons in Taiwan are concentrated in the Meiyu season, from May to June, and the typhoon season, from July to September, (Chen and Chen 2003; Yim et al. 2015). Particularly, there is a significant difference in the rainfall behavior in the wet and dry seasons. Therefore, slight changes in the rainfall during the rainy season will directly or indirectly affect the risk of drought and flood disasters in Taiwan (Chen et al. 2009; De Silva and Kawasaki 2018).
In meteorology, the scale refers to the size and duration of the weather system. Generally, the more commonly used scale is the scale of the atmospheric weather system defined by Orlanski (1975), and it can be divided into small scales with a horizontal range of less than 2 km, mesoscale ranging from 2 to 2000 km, and large scale above 2000 km. The large scale can be further subdivided into the comprehensive scale of more than 2000 km with a life span of approximately 2–10 days (e.g., frigid cyclones, extratropical cyclones, and jet streams) and planetary-scale weather systems with a horizontal scale of more than 10,000 km and a life span of more than 10 days.
It is essential to scale up the discussion of the changing characteristics of climate and water resources to a relatively macroscopic spatio–temporal scale, and the scale corresponding to meteorological data can be at the mesoscopic scale or above the planetary scale (Barthel and Banzhaf 2016). Existing studies have demonstrated that the climate phenomenon of earth may be affected by the outer space of the earth and solar activity (Marsh and Svensmark 2003).
Sunspots are temporary phenomena on the photosphere of the sun, typically representing the strength of the solar activity, and they appear darker than the surrounding areas under visible light. The strong magnetic field activity of the sun suppresses convection, resulting in a relatively low surface temperature (approximately 3000–4500 K), and the darker areas are important indicators of solar activity. When sunspots are active, they affect the magnetic field of the Earth, resulting in bad weather and may even damage electronic products and electrical appliances (Cowling 1933). Another important large-scale climate factor is the El Niño-Southern Oscillation (ENSO), and when it occurs, it causes climate anomalies globally, such as a sharp drop in rainfall, severe drought, and forest fires (e.g., the forest fires in Indonesia, India, and Australia during the El Niño year). In contrast, ENSO may also cause an increase in rainfall (e.g., the increase in rainfall in the eastern Pacific during the El Niño year) and mild winter conditions (e.g., Canada experienced mild winter conditions during the El Niño year) (Yeh et al. 2009), and these factors may influence macroscopic spatio–temporal scale hydrological characteristics.
Currently, it is well known that the spatial and temporal characteristics of rainfall varies significantly in many areas (Cristiano et al. 2017; Kao et al. 2013). In recent years, several studies have analyzed factors that potentially affect rainfall to explore the relationship between long-term rainfall characteristics and potential macroscopic influencing factors, such as sunspots (Ananthakrishnan and Parthasarathy 1984; Bhattacharyya and Narasimha 2005; Seleshi et al. 1994). For example, by analyzing the time–frequency correlation between sunspots and annual rainfall through cross wavelet transform (XWT), studies have reported a significant correlation between sunspots and regional rainfall phenomena at a frequency cycle of 8–12 years (Nazari-Sharabian and Karakouzian 2020; Thomas and Abraham 2022). However, only few studies have attempted to construct prediction models to correlate this relationship. In addition, some studies have employed the commonly used indexes of ENSO, such as southern oscillation index (SOI) and Multivariate ENSO Index to determine the relationship between ENSO and the average rainfall of an area (Indeje et al. 2000; Kuo et al. 2010; Vladimiro and Guido 2018). For example, studies have reported that the average annual rainfall in Australia increases with an increase in the intensity of the anti-El Nino phenomenon, and vice versa (García‐García and Ummenhofer 2015). In recent years, some large-scale studies have been conducted on the impact of the El Nino phenomenon on the climate and water resources of Taiwan (Jiang et al. 2003; Lee et al. 2020). For example, some studies have discussed the varying characteristics of different seasonal rainfall or spring rainfall, or the characteristics of typhoon intensity in the Northwest Pacific (Chu 2004; Wang et al. 2020), and some studies have explored the long-term changes in the rainfall characteristics of Taiwan through sediment core drilling (Chen et al. 2019). These studies demonstrated that factors on macroscopic space and time scales may affect the characteristics of large-scale or periodic regional water resources and the overall medium-term and long-term trends, including possible seasonal or interannual changes in abundance and drought and the impact on drought and flood disasters.
Therefore, using actual ground weather observation data in Taiwan combined with remote sensing data at planetary scales, this study extracted features and investigated the relationship between rainfall in Taiwan and the factors that may induce changes in hydrological and water resources (e.g., sunspot and ENSO) using wavelet signal analysis method. In addition, machine learning methods were employed to predict and classify rainfall amount, and a set of rainfall–water resources warning system was established. We believe that the findings of this study will provide a better understanding of the rainfall mechanism in Taiwan and provide relevant government agencies with a more accurate grasp of large-scale rainfall fluctuation trends, and serve as a reference for water resources management policy in Taiwan.

Conclusion​

This study employed a novel data-driven approach to investigate the time–frequency relationships between sunspot and long-term local rainfall amount, and constructed machine learning prediction models to confirm the effect of solar activity on long-term local rainfall patterns. The results demonstrated that improved prediction results were achieved in relatively rainy areas. This could be attributed to the possible influence of extreme weather events, such as typhoons, on rainfall in other areas, and the inability to directly incorporate specific rainfall patterns associated with typhoons into this model to establish a connection with sunspot activity and the ENSO effect. In addition, the results revealed that the relationship between sunspots and local rainfall in Taiwan is increasing yearly, regardless of space or time; particularly, this was more notable in 1990, which was set as the boundary.
These results indicated that rainfall behavior (except extreme rainfall caused by typhoon) can be described using sunspots and ENSO effect, and this will be beneficial for providing water resource management. Although the impact of direct sunspots on rainfall may not be significant, the wavelet extraction indicated that it is one of the most influential features, and its impact exceeded that of humidity, which is typically believed to exert the greatest impact on rainfall. Therefore, we recommend that indicators of planetary-scale solar activity, such as sunspots, should be incorporated in future long-term water resource management or predictions, as it has been confirmed in this study as an important factor influencing regional rainfall on larger timescales, and is even more significant than the El Niño phenomenon and humidity.

link.springer.com

Development of wavelet-based machine learning models for predicting long-term rainfall from sunspots and ENSO - Applied Water Science

The variations in rainfall and its spatial and temporal distribution in wet and dry seasons have increased substantially globally owing to the effect of climate change. These disparities can lead to droughts and severe water shortages, as exemplified by the unprecedented drought in Taiwan in...
link.springer.com link.springer.com

incidentally 'long term rainfall' refers to climate for the scholarly inept. wink wink oink oink
 
I

igrowone

Well-known member
Veteran
arsekick said:
Has anyone noticed any "man made" climate change anywhere in their lifetime ?

Serious question believers/deniers
Click to expand...
I can see it right now, the lakes in my area would have been frozen solid when I was a kid by this time
now? they're not even started
and it's become a 50/50 shot in any given year if they will freeze completely
you're not seeing much change in the tropics? you may not for quite a while
the change is happening at the northerly latitudes, that's the start, not the end
and this has been discussed ad nauseum, if you don't want to listen that's on you
 
Old Piney

Old Piney

Well-known member
arsekick said:
Has anyone noticed any "man made" climate change anywhere in their lifetime ?

Serious question believers/deniers
Click to expand...
That is the big question.the Earth's climate is and has always been changing. Right now there's no doubt we are in a warming trend , is this one man-made? Is it possible that it's a little of both a natural warming with our influence adding to it a bit ? who knows .We all should strive to be good stewards of our planet. But we must be realistic. It doesn't help ( with CO2 ) to drive a electric if the power comes a plant the burns fossil fuels, or stop domestic fuel production only to buy it from foreign producers.
 
I

igrowone

Well-known member
Veteran
and the NOAA 2023 temperature report is available
as most have already heard, it is a record
big record

The year 2023 was the warmest year since global records began in 1850 at 1.18°C (2.12°F) above the 20th century average of 13.9°C (57.0°F). This value is 0.15°C (0.27°F) more than the previous record set in 2016. The 10 warmest years in the 174-year record have all occurred during the last decade (2014–2023). Of note, the year 2005, which was the first year to set a new global temperature record in the 21st century, is now the 12th-warmest year on record. The year 2010, which had surpassed 2005 at the time, now ranks as the 11th-warmest year on record.

1705093392375.png
 
A

arsekick

Active member
Well its the middle of summer here and we got a lovely 17.8c atm @ 12.30 pm

Its been the shittiest/wettest/coldest summer I've ever seen in almost 60 years, and we're supposed to be having the hottest driest summer EVER.

Things don't improve soon it will be a bloody disaster for me cannabis growing season, and I'll be as broke as a unemployed homeless bum :ROFLMAO:
 
A

arsekick

Active member
Not sure why it wont post ?
chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://www.sec.gov/comments/s7-10-22/s71022-20132171-302668.pdf

The PDF link works tho
 

Attachments

  • s71022-20132171-302668.pdf
    1.4 MB · Views: 24
Last edited:
A

arsekick

Active member
igrowone said:
and the NOAA 2023 temperature report is available
as most have already heard, it is a record
big record

The year 2023 was the warmest year since global records began in 1850 at 1.18°C (2.12°F) above the 20th century average of 13.9°C (57.0°F). This value is 0.15°C (0.27°F) more than the previous record set in 2016. The 10 warmest years in the 174-year record have all occurred during the last decade (2014–2023). Of note, the year 2005, which was the first year to set a new global temperature record in the 21st century, is now the 12th-warmest year on record. The year 2010, which had surpassed 2005 at the time, now ranks as the 11th-warmest year on record.

View attachment 18945284
Click to expand...
GBc6T8ta4AA2KUg.png

How would they know ?
 
You must log in or register to reply here.

Latest posts

Latest posts

Top