Jump to content
  • Member Statistics

    17,597
    Total Members
    7,904
    Most Online
    DAinDC
    Newest Member
    DAinDC
    Joined

What to expect in future MA winters (don't read this if you love snow)


Terpeast
 Share

Recommended Posts

Okay, you’ve been warned.

This is a long post, so get comfortable. 

Several months ago, I decided to undertake some research and statistical analyses to tease out what we can expect in future winters in the mid-Atlantic with a warmer background state. Thanks @psuhoffman for the inspiration.

The conclusion is… sobering. 

Short answer? 

We will still get snow, just less than we used to… not surprisingly. 

The real question is “Just how MUCH less?”

Here’s how I did my analysis.

 

DATA PREP

I downloaded all daily temperature, precipitation, and snowfall data at KIAD from NWS’s NOWData. 

I chose KIAD even though it only goes back to 1962 because DCA is a poorly sited measuring location, even with a longer record. I could have chosen KBWI for a longer record, but I’m not sure how relevant weather records before 1960 would be due to those earlier years being in a vastly different climate state. 

1962 through 2023 is 60 years worth of data, which may not seem like much, but found it sufficient for this purpose.

After downloading, I put it together as an entire series in one Excel tab. There were something like 22k+ rows of data.

 

TRENDS IN TEMPERATURE AND PRECIPITATION

Next, I analyzed a linear trend in temperature and precipitation to get their slopes. 

At KIAD, we have warmed by 3.9 degrees F between 1962 and 2023 - from 52.9 to 56.8 F.

At the same time, we have had a 16% increase in precipitation from 3.23”/month to 3.74”/month.

Warmer and wetter.

So, using the slopes of these trends, I applied a reverse delta-T and reverse delta-P to adjust the entire time series warmer and wetter to match today’s climate. But not all days or years are adjusted the same way… the earlier in the time series, the bigger the adjustment. The most recent years prior to 2023 only had negligible adjustments just because they are closer to today in time.

The “adjusted” time series would have no trend (flat trendline), and are thus used in methods 1 and 2 to derive “new” snowfall totals for every winter “event”.

I’ll explain each method…

 

METHOD 1: SNOWFALL ADJUSTED BY TEMPERATURE

First, I studied the daily average and minimum temperatures for each snow event (using the original dataset).

At first, I tried using daily average temperatures, but the data was too noisy. There were snow events even with daily averages between 35 and 40 degrees F. And it was hard for me to tell what daily average temperature do snow totals begin to decrease. 

wg5wo_GL00K8yJuVcep50Jk1PVC_y0uf7HUkW4jofSqcch7gFo97ePU4IBJaYJlZZ_E3LibdLn54dy2X8EMQaXwQr0LGeu8ZR4BhFHxfT080-JXjDk8BMPO6Q3ZfcLgpWuS3X_n-wERZjUKGfFbdIFQ

So I switched to daily minimum temperatures. 

Now the picture becomes clearer:

0gBDPZB3sTl5yCJW_1-E4L_uY0SKnM24PAHlO5-7sXayM9uUDytr-0zg5eq1DIh1RC2ZRc2O3FNJm_aZ5WPvLrYwayb6mQEZgcfJl8pZP81VQtaQ5zUX9yjv7w1k5-vyW9IkEjxR61dGwSqci7tL1w0

From visualizing this graph, I can make assumptions:

1) For the biggest events, snowfall increases 50% every 4 degrees until around 25 degrees (due to higher moisture content and better dendritic growth). Then snowfall levels off from 25 degrees and up, and then decreases past 30 F.

2) If MIN temps increase from 25 to 30, there is not much difference in snowfall. But we get a 30-50% decrease from 30 to 32 degrees.

  • Minor snowfall events (5" or less) get cut in half when MIN temps go from 32 to 33 
  • Major snowfall events (>5") become minor (<5") when MIN temps go from 32 to 33
  • Minor snowfall events become rain when MIN temps go from 33 to 34 (important!)

So when I apply these assumptions to the “warmer” time series, I adjust past snowfall events to new snowfall totals as if they happened today.

 

METHOD 1 RESULTS:

From Jan 1962 through April 2023, a cumulative total of 1325 inches had fallen at KIAD.

With adjusted snowfall using method 1, the cumulative total becomes 1142 inches. 

This is a 14% decrease in snowfall at KIAD. So if KIAD averaged 22”, then our new average in TODAY’s climate is now 18.9”.

I can hear you saying now:

"Oh, that's not so bad, we'll still average almost 19" of snow even in a warmed world!"

Ah... not so fast... remember we are not accounting for FUTURE warming - more on this later.

Back to the analysis.

I also cataloged changes to each winter “event” as to whether their snowfall decreased, increased, or stayed the same (within 10% of the original snowfall). If my adjusted snowfall for an “event” became zero (i.e. all rain), I log it as an “Event Lost”.

Here’s how all of our past snow events would have changed if they happened in TODAY’s climate:

  • Increased Snowfall: 17.1%
  • No Change: 35.4%
  • Decreased Snowfall: 32.6%
  • Event Lost: 15.0%

Note: I only consider any snow day with 0.5” or more of snow an “event”. I omitted the rest.

In other words, one-third of past snow events wouldn’t have happened much differently today. Another one-third would have resulted in less snow, but still a snow event nonetheless (perhaps with more mixing if the conditions are right). 

More notably, 17% of past events would have resulted in increased snowfall, while 15% of them would have been all rain today. Here are some examples:

Of those 17%, I can highlight a few examples of very cold storms where a few degrees increase wouldn't flip it to rain, but would actually juice up the storm:

  • Feb 1979 (PD1) would have dropped 22" if it happened today rather than 16" at IAD\
  • Feb 1983 would have dropped 30" today instead of just 23" (!!)
  • Jan 1996 would also have dumped 30" instead of 24"

Then as we get into more recent storms like 2010 and 2016, the effect would be minimal because the temperature difference would be minimal. Interestingly, in the first 2010 storm, day 1 yielded 4" less, but day 2 yielded 2" more, so the result was 30". The actual was 32.4", so the loss was minimal, but more on the front end of that storm when the BL temps were still warm-ish and lots of snowfall was lost to melting.

The 2016 storm had almost no change (obviously).

Now, on the flip side... how many major storms did we lose?

1) We lost a footer in Feb 1987... assuming my method is correct (more or less), that storm would be the perfect track rainstorm. Total shutout. 

Sobering fact: This is the most notable example of losing a great snowstorm to a perfect-track rainstorm as the climate warms. We already have examples of this like 1998 (which was a preview into the future during that super El Nino) and more recently in 2013, 2018, etc. with more of these “lost events” yet to come.

And here’s yet another kick in the gut:

2) There were four 8" storms throughout the 1960s... and we lost them all! Four 1960’s era 8-inchers all zeroed out. 

(Though there were other 3-4 storms in the 60s that made up for those losses by adding more snowfall... one 10" storm would produce 15" today, for example).

Pretty sobering, eh?

Now, we haven’t looked at changes in precipitation and SWE due to CC, so let’s try another method…

 

METHOD 2: SNOW WATER EQUIVALENT ADJUSTED BY TEMPERATURE AND PRECIPITATION 

This time I used average (adjusted) daily temperatures to apply treatment to SWE values based on adjusted precipitation/QPF to derive new daily snowfall values. 

I made this treatment only to a small window of temperatures, though. If the adjusted average daily temp was 25 degrees or colder, I leave it unchanged and only adjust snowfall based on precipitation. 

But when the temp is between 26 and 32, I apply the decreasing slope on this graph to SWE and derive snowfall from both that and precipitation.

Here’s where it gets tricky, though. If an event had an average temperature of 24 degrees, and the adjusted temperature is now 28 degrees, I don’t apply the full adjustment to SWE. I only use the portion from 26 to 28 degrees, so in such case, only one-half of the full adjustment is applied. 

5a6R1whjFTALH5jJ8iTgxvzc0okM9MvziRFX8qdvI8jaXH31dys3Woti2Mmam7nm7dKW5Dc3yh2yyxaNkxS2UslH9kkUyXLg2H-8i1tLDbIkQkw8S9eSDhCq_qzdXPxS1YBQnlZRZY9BaNVFYJUMGXQ

I also made other adjustments for when the average temp is pushed above freezing (e.g. a 31 F event now becomes 35 F):

  • SWE falls by 30% when AVG temps go from 32 to 34
  • SWE falls to below 5 when AVG temps go from 35 to 36
  • SWE falls to zero when AVG temps go from 36 to 37

Note on potential mixed/icing events: 

A) SWE of between 3 and 7 with AVG temps of 32 or less may be mixed events (partially filtered out by only considering days with >1" snowfall). 

B) SWE <3 with AVG temps of 32 or less may be sleet or ice events (filtered out by only considering days with >1" snowfall).

 

METHOD 2 RESULTS:

Remarkably similar to method 1. Total cumulative snowfall is now 1144 inches, again a 14% decrease in snowfall. 

Here’s how the “events” shake out:

  • Increased Snowfall: 9.5%
  • No Change: 40.8%
  • Decreased Snowfall: 30.7%
  • Event Lost: 18.9%

The main difference is that method 2 is less generous towards top-end snowstorms in terms of increased totals. Instead, most of these events don’t change much. Also worth noting that we lost almost 19% of past events with this method.

 

ChatGPT’s Take: What AI Has to Say About This…

I input all this data into GPT’s code interpreter to do some analyses and fill in any gaps I might have missed.

I started with something super basic. 

I asked it to create histograms of average daily temps between two time periods: 1962-1990 and 1991-2023:

eoMI76F9YLo1b76F7MmCya7f9RxznCPsFGeBUwtC9_LvbgqkZVjT5CYwhgWd1M9iE2Wc_4Vrb4pe1ruPCad6k7SK7b4aMGl9wlWrpy8Pl4V4L3PQffRXVGghdb8W0AjHjt7-lvXGfCs6tiripxe_BKs

cnomtY40ZVOpRGzIK9QT9uvaQeGvEt-FUBn8lbAPCefTHm_l_w1pWHN20ccU_xcbxraSfhKy_N71eFv2KISopfwJnhpU74u4E89yf7uXNS_AdxXbEqPNh90C__UoEnRRSmHk-v9ge2wTrOpAjGHFU0Q

You can notice a shift towards the right with daily average temperatures. So now we know that GPT can see the warming trend.

Then I asked if our hypothesis of increased snowfall in discrete events within a warming world is valid:

The response:

Yes, that's a scientifically valid hypothesis. While a warmer climate can lead to overall reduced snowfall, it can also result in more intense, albeit less frequent, snowstorms. Here's why:

1. Increased Moisture Content: Warmer air can hold more moisture. For every 1°F increase in temperature, the atmosphere's capacity to hold moisture increases by approximately 4%. When conditions are cold enough for snow, this additional moisture can fall as more significant snow accumulations.

2. Oceanic Effects: Warmer temperatures can lead to less sea ice and warmer ocean waters. Open and warmer waters, particularly in the early winter, can be a source of added moisture to the atmosphere. Coastal areas, or regions downwind of large bodies of water, can experience heavy snowfalls when cold air passes over these warmer waters, picking up moisture and subsequently dropping it as heavy snow over land.

3. Storm Patterns: Climate change can influence atmospheric circulation patterns, potentially leading to changes in the frequency, intensity, and tracks of snowstorms. Some research suggests that certain regions could see more frequent and intense snowstorms, even if the total number of snowy days decreases.

4. Temperature Fluctuations: Even in a generally warmer world, there will still be periods of cold temperatures. If these cold periods coincide with moist conditions (as might be more common due to the reasons above), the result could be significant snowstorms.

5. Changing Landscapes: As the climate warms, the line between rain and snow can shift. This means that regions previously receiving rain might start receiving snow if the conditions are right, leading to unexpected snow events.

However, while these factors can contribute to larger snow accumulations in specific storms, they don't necessarily contradict the potential for reduced overall snowfall. It's a matter of frequency versus intensity. There might be fewer snow events, but when they occur, they could be more intense.


Cool, nice response. Very plausible. Now let’s try to validate it using the KIAD data series:


To better understand the trend in the intensity of snowfall events, we'll proceed with the next step:

Check for Extreme Snowfall Events: We'll identify and count the number of days with snowfall amounts exceeding a certain threshold over the years. Specifically, we'll consider days in the top 5% of all recorded snowfall amounts and see if there's an upward trend in their frequency.

fV7_Ve5RO1lvDRgIq_AgCKyUO-jXzJ37XOfucayqua9-C_U99Zk-9VccgOMjxYjwsfnHL7m1fVzpDrk5NaN9owUsGS7D2ZNMFd7SndssP6AS3gU8LDwRUN0mTqBpvI9HKGX3KIwZogbtlalYgHSzMhE

The plot illustrates the number of extreme snowfall days (days exceeding the 95th percentile of snowfall amounts) for each year from 1962 to 2022.

From the plot, we observe some fluctuations in the frequency of extreme snowfall days over the years. There are periods with a higher number of extreme snowfall days, but there isn't a clear, consistent upward trend throughout the dataset.

To further explore, let's look at the next approach:

Yearly Maximum Snowfall: Analyzing the maximum daily snowfall for each year can provide insights into whether peak snowfall events are becoming more intense.

YaMR4qF77SUGfsOa0oo8D_WypeKYUCsQCuVv8tfGzAfKdUTCOnWD588Vfe4g6xsb2E4D2hx0vD1PUfhfIcMvJUtQuKmlZ2b2cB7b3TapWBmsnUK5f6psNar_kpG4buypoHbjHcxNQStMMOjZ-QWzIQQ

The plot showcases the maximum daily snowfall for each year from 1962 to 2022. A few observations:

1) Fluctuating Intensity: The intensity of the maximum daily snowfall fluctuates from year to year without a definitive upward or downward trend.

2) No Clear Increase in Intensity: There doesn't seem to be a clear increase in the intensity of peak snowfall events over the dataset's span. While there are some years with notably high maximum snowfall amounts, they are interspersed throughout the dataset without a consistent pattern.

While the dataset does indicate the occurrence of significant snowfall events, it doesn't conclusively support the idea that the intensity of individual snowstorms is increasing over time. 

However, it's essential to note that more comprehensive datasets, encompassing larger geographical regions or longer periods, might yield different insights. Additionally, factors like localized climate influences, geographical variations, and data collection methodologies can also play a role in these observations.


So, not much of a trend in either graph. Maybe it’s due to my prompting skills, or maybe we’re looking for a trend that isn’t really there.

Next, I asked it to project our future annual average snowfall assuming the world warms a further 1 degree F over the next 20 years (I’m being conservative here):

It first produced a graph like this:

bYP5IOJRIZDww67oN3I3x2oY_XOticgRuTJyC6QTrBDUaBMHqPpkx_-2jAddhQ2TR2uLsCCfpGNHdSUqKlArHdLwxiA-vHDhLnxYCs1PDfoJ67Ad_1MZ6BevsaNZq_LU4-W70BYE94XdI4RRnxrwASk

Then it said:

jaWERvRD4pnnjyELqZLh2maM0hPdUKhjgVnaJebkQP9T2mIkRE7DdPpndyolPsXEwkCYYhKvzpakyZHd_orPw8Dka07QD5XfrEpwdEmNin3PD80m7kzQc0EfL_0t2QTnak8ayXN0q0prOmK7PF44PXc

10.91” annual average snowfall?

Ouch…

And that’s the average over the next 20 years… meaning that by 2043, single-digit averages with a ratter every other year will become the norm. 

And that’s assuming we warm only a conservative 1 degree F over the next 20 years, while a ton of evidence points to a faster or accelerated rate of warming.

How’s that for a real kick in the balls?

Now, if you want to poke holes in my study or tear it apart, allow me to do it for you:

 

WEAKNESSES and/or BIASES

Many studies have limitations or biases, and this is no exception. Here are the weaknesses:

  • We are using a point snapshot of sensible weather in one location. 
  • We do not consider any spatial alterations in weather patterns over time.
  • We do not consider changes in storm tracks, jet stream placement or strength, or the placement or strength of H5 anomalies
  • We do not consider the state of ENSO, PDO, AO/NAO, etc.
  • We do not consider mixed events (if SWE is less than 5 or 6 while the average daily temperature is colder than 29 degrees, it is likely a mixed event)
  • This is only a statistical analysis that relies on hypothetical changes in snowfall based on a warmer climate
  • This does not take into account non-linear changes imposed by a warming climate, which needs to be modeled and validated
  • This study uses ChatGPT's code interpreter to draw certain conclusions, which may or may not contain bias or imperfections
  • In my use of ChatGPT, my prompting may or may not have introduced bias

The “gold standard” would be to run op models with ensembles starting in 1962 (or whatever past date you prefer) using an adjusted initialization state with parameters that factor in today’s warmer climate, without allowing the models to revert to the previous/colder base state. 

Then repeat for every 6-hour intervals all the way through today’s date. That would be the proper way to do such research, but I (and most people on here) don’t have the resources to do that.

And finally, this assumes warming will continue into the future. There’s an outside chance that I could be totally wrong, but it’s hard to argue against the trend.

 

CONCLUSION

Although this probably won’t pass the muster of an academic peer review, I’m glad I did this exercise to satisfy my curiosity and reset my own expectations of our winters to come.

On a positive note, due to increased QPF and moisture with warmer SSTs, we may experience at least one, maybe two more record-breaking snowstorms in the next 10-15 years…

One of them could be an extreme and biblical 1 in a 10,000-year event.

And then, sadly, as the world warms even further and maybe faster than expected… it’s lights out.

Meanwhile, let’s enjoy what we get… and we will get quite a few memorable storms - hopefully this coming winter.

 

  • Like 23
  • Thanks 6
Link to comment
Share on other sites

I didn't even have to read or attempt to understand all this. The basic eye test says it's snowing less, and being too warm more often. The last 8 years have been sobering enough! Like you said...we need to just enjoy what we get, and do NOT dream of more--it will only depress you, lol If what you said is gonna be an increasing reality in the future, think it will get a little easier to take the as time goes along, as we'll start to get used to the new normal, and be basically an extension of the southeast forum! Where they know they'll be warm, probably not snow except by fluke, and have far fewer posters. People kinda ribbed me for calling it that, but I mean...look where we are, folks! 

Now for @psuhoffman to write his own one post-due-for all "it's not snowing as much" post to refer all future 2023-24 arguments to :lol:

  • Like 1
Link to comment
Share on other sites

https://journals.ametsoc.org/view/journals/clim/34/6/JCLI-D-20-0197.1.xml

5. Summary and discussion

This study investigates effects of global warming on extreme snowstorms along the NEUS coast by conducting and comparing dynamical-downscaling WRF simulations driven with and without the mean climate change signal extracted from HiRAM historical and future simulations. The 93 observed snowstorms in 1980–2015 documented in G. Chen et al. (2019) were adopted as surrogates for studying the potential effects. Results show that the number of events with moderate and heavy daily snowfall (SWE greater than 10 mm day−1) at Boston, New York City, Philadelphia, and Washington, D.C. is decreased from 60, 54, 43, and 30 to 32, 29, 30, and 20, respectively (Fig. 7). In addition, although the rainfall increases in all four cities, total precipitation increases in the south (especially along the coast), where the rainfall is increased due to the warming-caused increase of water vapor content and upward vertical motion, but decreases in the north (especially along the coast), where the rainfall increase is overwhelmed by the snow decrease (Figs. 57). As a result, the precipitation distribution exhibits a southwestward shift. Another notable effect is that the frequency of mixed rain and snow and freezing precipitation events is increased in the north of NEUS (Figs. 8 and 9), attributed to the northward retreat of the 0°C zone and the expansion of the zone with temperature near 0°C.

 

 

  • Like 2
  • Thanks 1
Link to comment
Share on other sites

https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2023JD038804

 

Plain Language Summary

Snowstorms affect the highly populated regions of the northeastern United States and southeastern Canada every winter, disrupting ground and air travel and resulting in substantial socioeconomic impacts. Understanding how climate change may impact snowstorms is necessary for this region to prepare for the future. We explore how snowstorms in these regions may change in a future, warmer world using two sets of climate model simulations. We find that yearly total snowfall is likely to decrease over most of this region, with the largest declines to the south and smaller declines farther north. Despite these decreases, we find that the snowfall amounts that currently occur during the largest snowstorms are still likely to occur even in a much warmer future climate. Finally, we examine snowstorms that produce a large percentage of the annual snowfall during a single event. We find that the region where these big snowstorms relative to the yearly snowfall occur most often will shift northward in the future. In summary, while yearly snowfall is likely to decrease nearly everywhere in eastern North America, significant snowstorms will continue to occur, and some regions will see more of their yearly snowfall during a few large events.

  • Like 3
  • Thanks 1
Link to comment
Share on other sites

5 minutes ago, MN Transplant said:

https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2023JD038804

 

Plain Language Summary

Snowstorms affect the highly populated regions of the northeastern United States and southeastern Canada every winter, disrupting ground and air travel and resulting in substantial socioeconomic impacts. Understanding how climate change may impact snowstorms is necessary for this region to prepare for the future. We explore how snowstorms in these regions may change in a future, warmer world using two sets of climate model simulations. We find that yearly total snowfall is likely to decrease over most of this region, with the largest declines to the south and smaller declines farther north. Despite these decreases, we find that the snowfall amounts that currently occur during the largest snowstorms are still likely to occur even in a much warmer future climate. Finally, we examine snowstorms that produce a large percentage of the annual snowfall during a single event. We find that the region where these big snowstorms relative to the yearly snowfall occur most often will shift northward in the future. In summary, while yearly snowfall is likely to decrease nearly everywhere in eastern North America, significant snowstorms will continue to occur, and some regions will see more of their yearly snowfall during a few large events.

Looks like my analysis supports this. 

  • Thanks 1
Link to comment
Share on other sites

1 minute ago, Terpeast said:

Looks like my analysis supports this. 

Yeah.  This is a brutal image.  The +2 period is basically ending in 2040, +3 in 2060, and +4 in 2080.

 

jgrd58792-fig-0006-m.jpg

Projected changes to mean annual snowfall (%) at Toronto, Ontario (a); Montréal, Québec (b); Halifax, Nova Scotia (c); Boston, Massachusetts (d); New York City, New York (e); and Washington, D.C. (f) for the three global warming levels. Relative changes with respect to the 1980–2009 mean are plotted for each CRCM5 simulation (symbols indicated in the legend). A kernel density estimation of the distribution of projected changes among the CRCM5-ClimEx simulations is shaded in the gray violin plots generated using the Seaborn package (Waskom, 2021). Within each violin plot, a smaller box plot is included indicating the median (white dot), 25th–75th percentile (dark gray box) and complete range of the CRCM5-ClimEx data (dark gray vertical lines). Values calculated from the pooled data for all 50 ClimEx members are indicated by the purple circles. Signal-to-noise ratio (S/N) calculated from the ClimEx data is indicated under each violin plot.

  • Like 2
  • Thanks 2
Link to comment
Share on other sites

From what I can glean from these studies with my limited knowledge, they appear to be based on correlations of precipitation with predicted atmospheric warming. However, if the ocean currents change (gulf stream, etc.), wouldn’t that result in substantially altered storm tracks? I’m sure that there must be studies on this (not that I could understand them!).

Link to comment
Share on other sites

5 minutes ago, uncletim said:

From what I can glean from these studies with my limited knowledge, they appear to be based on correlations of precipitation with predicted atmospheric warming. However, if the ocean currents change (gulf stream, etc.), wouldn’t that result in substantially altered storm tracks? I’m sure that there must be studies on this (not that I could understand them!).

My guess would be that storm tracks would be shifted north. But I have no way, or resources, of proving this hypothesis.

Link to comment
Share on other sites

13 minutes ago, uncletim said:

Ahh, more good news! :axe:

Yeah, I don’t think I’m making a lot of friends here haha but I rather be honest and call it for what it is.

Positive thing to draw from this is that CC makes extreme events more likely. So if it’s going to snow, it may be extreme. 

  • Like 4
Link to comment
Share on other sites

11 hours ago, Terpeast said:

My guess would be that storm tracks would be shifted north. But I have no way, or resources, of proving this hypothesis.

This was one of the best posts ever on here. Thank you!  Truly epic. 
 

I was thinking this same thing with regards to how the statistical analysis could be conservative on the results because the whole storm track is likely also shifting north with increased ridging. Think back to all the times we popped a huge SER despite a stout NAO block. Such a shift could accelerate the negative impacts for snow, especially at our latitude!  

  • Like 2
  • Haha 1
  • Weenie 2
Link to comment
Share on other sites

9 hours ago, psuhoffman said:

This was one of the best posts ever on here. Thank you!  Truly epic. 
 

I was thinking this same thing with regards to how the statistical analysis could be conservative on the results because the whole storm track is likely also shifting north with increased ridging. Think back to all the times we popped a huge SER despite a stout NAO block. Such a shift could accelerate the negative impacts for snow, especially at our latitude!  

Thanks. sometimes I do wonder if the “tipping point” had already happened after the last super nino, or if we’re just in a down cycle. 

I still think it’s the latter, but this coming winter should be a good test if the nino plays out as most think it will. 

But even if we’re in a down cycle now, these kinds of winters will become the norm anyway. Any double digit winter will be a win for this forum. 

Link to comment
Share on other sites

1 hour ago, Terpeast said:

Thanks. sometimes I do wonder if the “tipping point” had already happened after the last super nino, or if we’re just in a down cycle. 

I still think it’s the latter, but this coming winter should be a good test if the nino plays out as most think it will. 

But even if we’re in a down cycle now, these kinds of winters will become the norm anyway. Any double digit winter will be a win for this forum. 

it’s probably a down cycle with some CC sprinkled in there

Link to comment
Share on other sites

This is a fantastic contribution to this forum!!  My hat is off to Terpeast!

I agree completely that this coming winter will be an excellent test. My research into my point specific home base Enso winter influence during the past 43 years reveals that average 1.45+ Nino winters give above normal snowfall west of the BR 88% of the time.  The CPC and other venues project an approximation of this anomaly for the coming winter.  This is a base of support for my winter 23-24 prediction.

According to NASSA'S GISS the earth has warmed 1.9 F. since 1880 and the warming has increased since 1980.                                                                 https://earthobservatory.nasa.gov/world-of-change/global-temperatures

Ironically, the 30 year period from 1945 to 1975 was slightly cooler than normal. Scientists believe that atmospheric aerosols from anthropogenic burning of fossils fuels resulted in this cooler period. Yes, from 1945-1975 we actually had anthropogenic global cooling.  Passage of clean air acts in 1970 from countries around the world brought this AGC to a halt.     https://skepticalscience.com/global-cooling-mid-20th-century-advanced.htm

Predicting future climate cannot be more than speculation because climate models have often been incorrect with details.

I thoroughly enjoyed digesting this excellent study. My personal take away is that from 1962 - 2015, maximum daily snow per year was largely static. The past 8 years  have witnessed a steady decline of annual snowfall at this snapshot one location. My personal one location has been static with one above normal year.

I firmly believe that future winters will be variable because of many short range factors not possible to fathom more than a week or two in advance. I agree with Bob Chill along these lines.

 I also believe that if the current warming continues, marginal locations and certainly D.C. is included will ultimately see more very low snowfall winters. West of the BR, not so much during the lifetime of anyone reading this.

 

 

 

Link to comment
Share on other sites

Well, at least we have the Earth's tilt still in our favor.

Snowfall decreasing is the most logical outcome, but this is the first year where I'm actually concerned about precipitation decreasing.  If we have a jet stream that is farther north throughout the year, then just like what's been occurring throughout this summer, we may be too far from where the storm tracks are....or at least too far from minimizing the effects of downsloping.  I hope I'm wrong about that one, but when you look at the geography here, I can see how we may get skimped going forward on winter clippers as well as summer MCS's due to the mountains robbing our moisture with more of those systems being north of the average path they take now.  Obviously, I don't want us to lose our winters, but droughts and wildfires are more concerning imo.

Link to comment
Share on other sites

I would actually bet a ton that we end up above normal this year. With the base state we live in Nino's are probably our best shot. Bombs are probably the best way to score going forward. And we all know that nino's give us bombs. Could be wrong. Wouldnt be the first time. But that is where I am at right now. And if we cant score in a nino than we are probably done for good. Because the base state here is a clown show. 

Link to comment
Share on other sites

From about 20-50N, this is what I've found in terms of snow, when mapping out several hundred locations by their annual temperature v snow. In colder areas in the tropics (high mountains) it still doesn't snow as there is too little variation from Summer to Winter temps.

<45F:  Heavy snow is possible most of the year. Sites average 40"-750" (Bismarck, Caribou)

45-50F Heavy snow is is common in Fall-Spring. Sites average 30"-175"  (Denver, Flagstaff, Buffalo)

50-55F: Snow is common, and frequently heavy in winter. Sites average 10"-60" (Boston, Santa Fe)

55-60F: Snow is common in winter. Sites average 3"-30"  (Albuquerque, Philadelphia, Parral)

60-65F: Snow is uncommon, but not unheard of. Sites average 1-10" (Atlanta, Birmingham, Chihuahua city, Durango city)

>65F:  Snow is rare, sites average 0-3" (Houston, Miami)

I've not really found exceptions at 60-year time scales for annual temps v. the snow ranges I'm listing above. Generally, the more arid spots are on the lower end of the scale, while sites adjacent to large bodies of water or on mountain tops are at the high end.

Parts of the Northeast / Mid Atlantic (NJ / PA / MD / DE / VA) should be moving into the 60-65F zone pretty soon, if they aren't there already. It's still pretty common to get snow 3-7 winters a decade in those zones. Even down to old MX, Chihuahua (mean temps are typically w/in 2F of 65F) still gets ~3" on average with snow in ~half of winters. Albuquerque has had snow every cold season on record, at an average temperature of about 59F annually, but some of those years are under 1.0" and sites just 20 miles to the south or 300-600 feet lower in elevation go 1-3 years with no snow.

The white xs in Mexico are examples of cooler towns that still semi-regularly see snow. The point is to show how it's tied to temps and not latitude. The green zone sees snow in ~nearly all or all winters. The yellow zone is where you can go years without meaningful snow. You guys are on the border of the yellow / green zone now, with the yellow advancing north.

What I've found near the transition from the 55-60F zone to the 60-65F zone is that big March storms tend to start happening more frequently in mid-late February, with March starting to behave more like a full-on Spring month.

2023-09-04-0wg-Kleki

  • Like 1
Link to comment
Share on other sites

20 minutes ago, raindancewx said:

From about 20-50N, this is what I've found in terms of snow, when mapping out several hundred locations by their annual temperature. In colder areas in the tropics (high mountains) it still doesn't snow as there is too little variation from Summer to Winter temps.

<45F:  Heavy snow is possible most of the year. Sites average 40"-750" (Bismarck, Caribou)

45-50F Heavy snow is is common in Fall-Spring. Sites average 30"-175"  (Denver, Flagstaff, Buffalo)

50-55F: Snow is common, and frequently heavy in winter. Sites average 10"-60" (Boston, Santa Fe)

55-60F: Snow is common in winter. Sites average 3"-30"  (Albuquerque, Philadelphia, Parral)

60-65F: Snow is uncommon, but not unheard of. Sites average 1-10" (Atlanta, Birmingham, Chihuahua city, Durango city)

>65F:  Snow is rare, sites average 0-3" (Houston, Miami)

I've not really found exceptions at 60-year time scales for annual temps v. the snow ranges I'm listing below. Generally, the more arid spots are on the lower end of the scale, while sites adjacent to large bodies of water or on mountain tops are at the high end.

Parts of the Northeast / Mid Atlantic (NJ / PA / MD / DE / VA) should be moving into the 60-65F zone pretty soon, if they aren't there already. It's pretty common to get snow 3-7 winters a decade in those zones. Even down to old MX, Chihuahua (mean temps are typically w/in 2F of 65F) still gets ~3" on average with snow in ~half of winters. Albuquerque has had snow every cold season on record, at an average temperature of about 59F annually, but some of those years are under 1.0" and sites just to 20 miles the south or 300-600 feet lower in elevation go 1-3 years with no snow.

The white xs in Mexico are examples of cooler towns that still semi-regularly see snow. The point is to show how it's tied to temps and not latitude. The green zone sees snow in ~nearly all or all winters. The yellow zone is where you can go years without meaningful snow. You guys are on the border of the yellow / green zone now, with the yellow advancing north.

What I've found near the transition from the 55-60F zone to the 60-65F zone is that big March storms tend to start happening more frequently in mid-late February, with March starting to behave more like a full-on Spring month.

2023-09-04-0wg-Kleki

We’re most definitely not in the yellow yet. 

Our recent 15-year average temp is 56.6, and even the last 7 years averages out to 57.3. Still solidly green. 

Maybe well SE of DCA towards the bay is where you’ll see the green/yellow line creeping up, but it will be a long time before I-95 and west becomes yellow.

  • Like 2
Link to comment
Share on other sites

I think the 60F annual temperature threshold is probably somewhere near Richmond in real time tbh.

Screenshot-2023-09-04-8-27-39-PM

Just to be clear - the map I made is 7.25C to 18.25C in increments of 2.75C. So it's not exactly 5F, but very close. 

Part of the issue you guys have is that it's rarely cold enough for good snow outside of core winter, like 12/15-3/15 roughly. Here in the desert, it's certainly warming at night. But it still gets really fucking cold sometimes in Oct-Nov, and Apr-May. So we get fairly regular fluky snow in those months. You guys don't really have that to fall back on once the core season starts to warm/shrink. In the past five years alone I've had lows in the 30s every month from September-May. 

My point is the increase in moisture is more meaningful when its spread out over a longer zone of opportunity for snow. But you guys have a tight window for snow. Not like here when we've had snow over a foot of snow in Oct-Nov, Mar-Apr just in the past five years.

  • Like 1
Link to comment
Share on other sites

1 hour ago, Terpeast said:

We’re most definitely not in the yellow yet. 

Our recent 15-year average temp is 56.6, and even the last 7 years averages out to 57.3. Still solidly green. 

Maybe well SE of DCA towards the bay is where you’ll see the green/yellow line creeping up, but it will be a long time before I-95 and west becomes yellow.

the 1991-2020 normals have DCA at 59.3F (https://en.wikipedia.org/wiki/Washington,_D.C.#Climate)

Link to comment
Share on other sites

8 hours ago, pazzo83 said:

Looks like the 2012-2022 period at DCA is already in the 60-65 range (barely):
image.thumb.png.0747fcd81230343f7c50096af108c320.png

I’d compare DCA to BWI, SBY, and EZF though. The lows at DCA are often warmer than all three. 

BWI is closer to DCA at 59 for the same reason, while SBY and EZF are both in the 56-57 range.

Like raindance says, the 60F line is probably down closer to richmond. It’ll take a while for it to creep up, even if locally it gets there first at the river and bay areas. 
 

  • Like 1
Link to comment
Share on other sites

I hate this thread.  It is a great thread and lots of information.  Confirms my suspicions on trends for marginal events.  Its not just always my elevation thats to blame.  Temps really have affected things.

 

But I hate this thread.  I knew what it would be before reading and this was my first thought

fudge-oh.gif

 

 

Link to comment
Share on other sites

2 minutes ago, H2O said:

I hate this thread.  It is a great thread and lots of information.  Confirms my suspicions on trends for marginal events.  Its not just always my elevation thats to blame.  Temps really have affected things.

 

But I hate this thread.  I knew what it would be before reading and this was my first thought

fudge-oh.gif

 

 

Hence the warning ^_^

Link to comment
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
 Share

  • Recently Browsing   0 members

    • No registered users viewing this page.
×
×
  • Create New...