This statistic shows cities in the United States with the highest average annual temperatures. Data is based on recordings from 1981 to 2010. In San Antonio, Texas the average temperature is 80.7 degrees Fahrenheit. Some cities that have the hottest maximum summer temperatures will not be included in this list due to their extreme temperature variance.

The monthly mean temperature data presented in this dataset was obtained from the Climate Prediction Center (CPC) Global Land Surface Air Temperature Analysis, which was loaded into Python using xarray. The data was then filtered to include only the latitude and longitude coordinates corresponding to each city in the dataset. In order to select the nearest location to each city, the 'select' method with the nearest point was used, resulting in temperature data that may not be exactly at the city location. The data is presented on a 0.5x0.5 degree grid across the globe.

The temperature data provides a valuable resource for time series analysis, and if you are interested in obtaining temperature data for additional cities, please let me know. I will also be sharing the source code on GitHub for anyone who would like to reproduce the data or analysis.

Historical changes of annual temperature and precipitation indices at selected 210 U.S. cities

This dataset provide:

Annual average temperature, total precipitation, and temperature and precipitation extremes calculations for 210 U.S. cities.

Historical rates of changes in annual temperature, precipitation, and the selected temperature and precipitation extreme indices in the 210 U.S. cities.

Estimated thresholds (reference levels) for the calculations of annual extreme indices including warm and cold days, warm and cold nights, and precipitation amount from very wet days in the 210 cities.

Annual average of daily mean temperature, Tmax, and Tmin are included for annual average temperature calculations. Calculations were based on the compiled daily temperature and precipitation records at individual cities.

Temperature and precipitation extreme indices include: warmest daily Tmax and Tmin, coldest daily Tmax and Tmin , warm days and nights, cold days and nights, maximum 1-day precipitation, maximum consecutive 5-day precipitation, precipitation amounts from very wet days.

Number of missing daily Tmax, Tmin, and precipitation values are included for each city.

Rates of change were calculated using linear regression, with some climate indices applied with the Box-Cox transformation prior to the linear regression.

The historical observations from ACIS belong to Global Historical Climatological Network - daily (GHCN-D) datasets. The included stations were based on NRCC’s “ThreadEx” project, which combined daily temperature and precipitation extremes at 255 NOAA Local Climatological Locations, representing all large and medium size cities in U.S. (See Owen et al. (2006) Accessing NOAA Daily Temperature and Precipitation Extremes Based on Combined/Threaded Station Records).

Resources:

See included README file for more information.

Additional technical details and analyses can be found in: Lai, Y., & Dzombak, D. A. (2019). Use of historical data to assess regional climate change. Journal of climate, 32(14), 4299-4320. https://doi.org/10.1175/JCLI-D-18-0630.1

Other datasets from the same project can be accessed at: https://kilthub.cmu.edu/projects/Use_of_historical_data_to_assess_regional_climate_change/61538

ACIS database for historical observations: http://scacis.rcc-acis.org/

GHCN-D datasets can also be accessed at: https://www.ncei.noaa.gov/data/global-historical-climatology-network-daily/

Station information for each city can be accessed at: http://threadex.rcc-acis.org/

• 2024 August updated -

  Annual calculations for 2022 and 2023 were added.

  Linear regression results and thresholds for extremes were updated because of the addition of 2022 and 2023 data.

  Note that future updates may be infrequent.

• 2022 January updated -

  Annual calculations for 2021 were added.

  Linear regression results and thresholds for extremes were updated because of the addition of 2021 data.

• 2021 January updated -

  Annual calculations for 2020 were added.

  Linear regression results and thresholds for extremes were updated because of the addition of 2020 data.

• 2020 January updated -

  Annual calculations for 2019 were added.

  Linear regression results and thresholds for extremes were updated because of the addition of 2019 data.

  Thresholds for all 210 cities were combined into one single file – Thresholds.csv.

• 2019 June updated -

  Baltimore was updated with the 2018 data (previously version shows NA for 2018) and new ID to reflect the GCHN ID of Baltimore-Washington International AP. city_info file was updated accordingly.

  README file was updated to reflect the use of "wet days" index in this study. The 95% thresholds for calculation of wet days utilized all daily precipitation data from the reference period and can be different from the same index from some other studies, where only days with at least 1 mm of precipitation were utilized to calculate the thresholds. Thus the thresholds in this study can be lower than the ones that would've be calculated from the 95% percentiles from wet days (i.e., with at least 1 mm of precipitation).

The monthly average temperature in the United States between 2020 and 2025 shows distinct seasonal variation, following similar patterns. For instance, in August 2025, the average temperature across the North American country stood at 22.98 degrees Celsius. Rising temperatures Globally, 2016, 2019, 2021 and 2024 were some of the warmest years ever recorded since 1880. Overall, there has been a dramatic increase in the annual temperature since 1895. Within the U.S. annual temperatures show a great deal of variation depending on region. For instance, Florida tends to record the highest maximum temperatures across the North American country, while Wyoming recorded the lowest minimum average temperature in recent years. Carbon dioxide emissions Carbon dioxide is a known driver of climate change, which impacts average temperatures. Global historical carbon dioxide emissions from fossil fuels have been on the rise since the industrial revolution. In recent years, carbon dioxide emissions from fossil fuel combustion and industrial processes reached over 37 billion metric tons. Among all countries globally, China was the largest emitter of carbon dioxide in 2023.

Record High Temperatures for US Cities

Clearly Defined Monthly Data

By Gary Hoover [source]

About this dataset

This dataset contains all the record-breaking temperatures for your favorite US cities in 2015. With this information, you can prepare for any unexpected weather that may come your way in the future, or just revel in the beauty of these high heat spells from days past! With record highs spanning from January to December, stay warm (or cool) with these handy historical temperature data points

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset contains the record high temperatures for various US cities during the year of 2015. The dataset includes columns for each individual month, along with column for the records highs over the entire year. This data is sourced from www.weatherbase.com and can be used to analyze which cities experienced hot summers, or compare temperature variations between different regions.

Here are some useful tips on how to work with this dataset: - Analyze individual monthly temperatures - this dataset allows you to compare high temperatures across months and locations in order to identify which areas experienced particularly hot summers or colder winters.
- Compare annual versus monthly data - use this data to compare average annual highs against monthly highs in order to understand temperature trends at a given location throughout all four seasons of a single year, or explore how different regions vary based on yearly weather patterns as well as across given months within any one year; - Heatmap analysis - use this data plot temperature information in an interactive heatmap format in order to pinpoint particular regions that experience unique weather conditions or higher-than-average levels of warmth compared against cooler pockets of similar size geographic areas; - Statistically model the relationships between independent variables (temperature variations by month, region/city and more!) and dependent variables (e.g., tourism volumes). Use regression techniques such as linear models (OLS), ARIMA models/nonlinear transformations and other methods through statistical software such as STATA or R programming language;
- Look into climate trends over longer periods - adjust time frames included in analyses beyond 2018 when possible by expanding upon the monthly station observations already present within the study timeframe utilized here; take advantage of digitally available historical temperature readings rather than relying only upon printed reports

With these helpful tips, you can get started analyzing record high temperatures for US cities during 2015 using our 'Record High Temperatures for US Cities' dataset!

Research Ideas

• Create a heat map chart of US cities representing the highest temperature on record for each city from 2015.
• Analyze trends in monthly high temperatures in order to predict future climate shifts and weather patterns across different US cities.
• Track and compare monthly high temperature records for all US cities to identify regional hot spots with higher than average records and potential implications for agriculture and resource management planning

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

Unknown License - Please check the dataset description for more information.

Columns

File: Highest temperature on record through 2015 by US City.csv | Column name | Description | |:--------------|:--------------------------------------------------------------| | CITY | Name of the city. (String) | | JAN | Record high temperature for the month of January. (Integer) | | FEB | Record high temperature for the month of February. (Integer) | | MAR | Record high temperature for the month of March. (Integer) | | APR | Record high temperature for the month of April. (Integer) | | MAY | Record high temperature for the month of May. (Integer) | | JUN | Record high temperature for the month of June. (Integer) | | JUL | Record high temperature for the month of July. (Integer) | | AUG | Record high temperature for the month of August. (Integer) | | SEP | Record high temperature for the month of September. (Integer) | | OCT | Record high temperature for the month of October. (Integer) | | ...

Where should we live in the next 10 years? Where should we settle down without relying on public transport? Which city should we move to without fearing losing our homes?

As weather patterns become more unpredictable with aggressive changes in temperatures, I collected some data below to see if there would be a city that could help assess our answers to the prior questions. I am curious to see if cities that typically have great infrastructure for walking, biking or public transit will be better prepared than those that are more typically car centric. Whichever you prefer, we can have a sense on where you might be migrating, and to which areas.

Here's how the data was collected:

1. Rhodium & ProPublica's combined work on counties risk factors against climate change across continental US (excludes Hawaii, Alaska, Puerto Rico and Guam. Washington D.C, is excluded as it does not have a county.)
2. The available Walk Score of major cities that have a population above 100,000 represented. Cities like Delaware's Wilmington or Maine's Portland are not considered as it falls under a small-city definition
3. Maximum temperatures (for select cities): This dataset is collected from the UC Davis Department of Agricultural and Resource by Prof. Aaron Smith. I selected a monthly temporal unit and county spatial unit ranging from 2019 - 2024 July. This dataset is extracted based on the average of highest temperatures in each selected counties. I did not use the overall daily average as it can easily shadow the extremities of temperature fluctuations.

The columns have different rating systems. The counties have all major climate risks expected in the future, while corresponding cities in each county have walking, transit and biking scores to assess livability without cars.

Understanding County Climate Risks The counties were were represented on a 1- 10 scale, based on RCP 8.5 levels. Here are the following explanations (0 = lowest, 10 = highest)

1) Heat: Heat is one of the largest drivers changing the niche of human habitability. Rhodium Group researchers estimate that, between 2040 and 2060 extreme temperatures, many counties will face extremely high temperatures for half a year. The measure shows how many weeks per year will we anticipate temperatures to soar above 95 degrees. (0 = 0 weeks, 10 = 26 weeks).

2) Wet Bulb: Wet bulb temperatures occur when heat meets excessive humidity. This is commonplace across cities that have a urban island heat effects (dense concentration of pavements, less nature, higher chances of absorbing heat). That combination creates wet bulb temperatures, where 82 degrees can feel like southern Alabama on its hottest day, making it dangerous to work outdoors and for children to play school sports. As wet bulb temperatures increase even higher, so will the risk of heat stroke — and even death. The measure shows how many days will a county experience high wet bulb temperatures yearly, from 2040 to 2060. (0 = 0 days, 10 = 70 days)

3) Farm Crop Yield: With rising temperatures, it will become more difficult to grow food. Corn and soy are the most prevalent crops in the U.S. and the basis for livestock feed and other staple foods, and they have critical economic significance. Because of their broad regional spread, they offer the best proxy for predicting how farming will be affected by rising temperatures and changing water supplies. As corn and soy production gets more sensitive to heat than drought, the US will see a huge continental divide between cooler counties now having more ability to produce, while current warmer counties loosing all abilities to produce basic crops. The expected measure shows the percent decline yields from 2040 to 2060 (0 = -20.5% decline, 10 = 92% decline).

4) Sea Level Rise: As sea levels rise, the share of property submerged by high tides increases dramatically, affecting a small sliver of the nation's land but a disproportionate share of its population. The rating measures how much of property in the county will go below high tide from 2040 to 2060 (0 = 0%, 10 = 25%).

5) Very Large Fires: With heat and evermore prevalent drought, the likelihood that very large wildfires (ones that burn over 12,000 acres) will affect U.S. regions increases substantially, particularly in the West, Northwest and the Rocky Mountains. The rating calculates how many average number of large fires will we expect to see per year (0 = N/A, 10 = 2.45) from 2040 to 2071.

6) Economic Damages: Rising energy costs, lower labor productivity, poor crop yields and increasing cr...

It is expected that the highest temperature in Summer on average will be approximately *** degrees Fahrenheit hotter in New York City by 2050 compared to the year 2000. The Winter lowest temperature will be *** degrees hotter by 2050. The city of Chicago, Illinois expects an even higher increase of *** degrees Fahrenheit in Summer's highest temperature and an increase of *** degrees in Winter.

Extreme heat in the U.S. – additional information

Projected changes in global average temperature are associated with widespread changes in weather patterns. Scientific studies indicate that extreme weather events, such as heat waves, are likely to become more frequent or more intense within the next few years. These changes may lead to an increase in heat-related deaths in the United States. Outdoor temperatures can affect daily life in many ways. Extreme heat and the combination of high heat and humidity can pose a serious risk for human health. Exposure to extreme heat can lead to heat stroke and dehydration, as well as cardiovascular, respiratory and cerebrovascular disease. When the weather becomes excessively hot, it can be deadly. According to the National Weather Service, heat waves caused ** fatalities in the United States in 2015.

The average temperatures in the U.S. have risen significantly since 1895. Long-term changes in climate can directly or indirectly affect many aspects of a person’s life. For example, warmer days could increase air conditioning or water supply costs. One way to measure the influence of temperature change on energy demand is by using heating and cooling degree days. Cooling degree days measure the difference between outdoor temperature and a temperature that people generally find comfortable indoors. Cooling degree days have not increased significantly over the past decades. However, a slight increase is evident for this period. In 2014, there were around ***** cooling degree days in the U.S., compared to ***** in 2009. More cooling degree days indicate an increase in temperature, leading to a greater likeliness of using air conditioning.

US Average, Maximum, and Minimum Temperatures

Analyzing Daily Temperatures Across the USA

By Matthew Winter [source]

About this dataset

This dataset features the daily temperature summaries from various weather stations across the United States. It includes information such as location, average temperature, maximum temperature, minimum temperature, state name, state code, and zip code. All the data contained in this dataset has been filtered so that any values equaling -999 were removed. With this powerful set of data you to explore how climate conditions changed throughout the year and how they varied across different regions of the country. Dive into your own research today to uncover fascinating climate trends or use it to further narrow your studies specific to a region or city

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset offers a detailed look at daily average, minimum, and maximum temperatures across the United States. It contains information from 1120 weather stations throughout the year to provide a comprehensive look at temperature trends for the year.

The data contains a variety of columns including station, station name, location (latitude and longitude), state name zip code and date. The primary focus of this dataset is on the AvgTemp, MaxTemp and MinTemp columns which provide daily average, maximum and minimum temperature records respectively in degrees Fahrenheit.

To use this dataset effectively it is useful to consider multiple views before undertaking any analysis or making conclusions:
- Plot each individual record versus time by creating a line graph with stations as labels on different lines indicating changes over time. Doing so can help identify outliers that may need further examination; much like viewing data on a scatterplot looking for confidence bands or examining variance between points that are otherwise hard to see when all points are plotted on one graph only.
- A comparison of states can be made through creating grouped bar charts where states are grouped together with Avg/Max/Min temperatures included within each chart - thereby showing any variance that may exist between states during a specific period about which it's possible to make observations about themselves (rather than comparing them). For example - you could observe if there was an abnormally high temperature increase in California during July compared with other US states since all measurements would be represented visually providing opportunity for insights quickly compared with having to manually calculate figures from raw data sets only.

With these two initial approaches there will also be further visualizations possible regarding correlations between particular geographical areas versus different climatic conditions or through population analysis such as correlating areas warmer/colder than median observances verses relative population densities etc.. providing additional opportunities for investigation particularly when combined with key metrics collected over multiple years versus one single year's results exclusively allowing wider inferences to be made depending upon what is being requested in terms of outcomes desired from those who may explore this data set further down the line beyond its original compilation starter point here today!

Research Ideas

• Using the Latitude and Longitude values, this dataset can be used to create a map of average temperatures across the USA. This would be useful for seeing which areas were consistently hotter or colder than others throughout the year.
• Using the AvgTemp and StateName columns, predictors could use regression modeling to predict what temperature an area will have in a given month based on it's average temperature.
• By using the Date column and plotting it alongside MaxTemp or MinTemp values, visualization methods such as timelines could be utilized to show how temperatures changed during different times of year across various states in the US

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

Unknown License - Please check the dataset description for more information.

Columns

File: 2015 USA Weather Data FINAL.csv

Acknowledgements

If you use this dataset in your research, please credit the original authors. If you use this dataset in your research, please credit Matthew Winter.

US Weather History

Actual and Average Temperatures and Precipitation

By FiveThirtyEight [source]

About this dataset

This dataset contains a collection of weather data from twelve major cities across the United States, including Los Angeles (KCTQ), Charlotte (KCLT), Houston (KHOU), Indianapolis (KIND), Jacksonville (KJAX), Chicago (KMDW), New York City (KNYC), Philadelphia(KPHL ), Phoenix( KPHX) and Seattle( KSEA). These datasets offer an exciting insight into the changing temperatures and climate in these key locations over a period of 12 months. Whether you are an experienced researcher in climate science or just interested in understanding more about world weather trends, this dataset provides an invaluable source.

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset contains 12 weather records from various cities across the US, from Los Angeles to New York City. Each record includes information about average and actual temperatures, as well as precipitation and related records.

Research Ideas

• Using the data to map out a timeline of high temperature records throughout the US and compare it to predictions of climate scientists on how climate change will affect regional temperatures in a given area.
• Tracking average and actual precipitation levels over the course of an entire year in various cities around the US in order to develop city-specific estimates for water resource availability in future years.
• Comparing record temperatures across cities in different regions, determining if there are any correlations between geographical location and temperature extremes, and then extrapolating these findings to better understand local weather patterns on both short-term or long-term scales

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

License: CC0 1.0 Universal (CC0 1.0) - Public Domain Dedication No Copyright - You can copy, modify, distribute and perform the work, even for commercial purposes, all without asking permission. See Other Information.

Columns

File: KPHL.csv | Column name | Description | |:--------------------------|:--------------------------------------------------------------------| | date | The date of the weather record. (Date) | | actual_mean_temp | The actual mean temperature for the day. (Float) | | actual_min_temp | The actual minimum temperature for the day. (Float) | | actual_max_temp | The actual maximum temperature for the day. (Float) | | average_min_temp | The average minimum temperature for the day. (Float) | | average_max_temp | The average maximum temperature for the day. (Float) | | record_min_temp | The record minimum temperature for the day. (Float) | | record_max_temp | The record maximum temperature for the day. (Float) | | record_min_temp_year | The year in which the record minimum temperature was set. (Integer) | | record_max_temp_year | The year in which the record maximum temperature was set. (Integer) | | actual_precipitation | The actual precipitation for the day. (Float) | | average_precipitation | The average precipitation for the day. (Float) | | record_precipitation | The record precipitation for the day. (Float) |

File: KPHX.csv | Column name | Description | |:--------------------------|:--------------------------------------------------------------------| | date | The date of the weather record. (Date) | | actual_mean_temp | The actual mean temperature for the day. (Float) | | actual_min_temp | The actual minimum temperature for the day. (Float) | | actual_max_temp | The actual maximum temperature for the day. (Float) | | average_min_temp | The average minimum temperature for the day. (Float) | | average_max_temp | The average maximum temperature for the day. (Float) | | **record_min_...

Temperature and precipitation projections for NYC reported by the New York City Panel on Climate Change (NPCC). The New York City Panel on Climate Change (NPCC) started in 2009 and was codified in Local Law 42 of 2012 with a mandate to provide an authoritative and actionable source of scientific information on future climate change and its potential impacts. The Intergovernmental Panel on Climate Change (IPCC) is the United Nations body for assessing the science related to climate change.

These maps show changes in the number of heat waves per year (frequency); the average length of heat waves in days (duration); the number of days between the first and last heat wave of the year (season length); and how hot the heat waves were, compared with the local temperature threshold for defining a heat wave (intensity). These data were analyzed from 1961 to 2021 for 50 large metropolitan areas. The size of each circle indicates the rate of change per decade. Solid-color circles represent cities where the trend was statistically significant. For more information: www.epa.gov/climate-indicators

The coldest temperature anomaly for 2019 was seen in Bozeman, Montana, which was on average *** degrees Celsius below the normal between 1981 and 2010. Lower than average temperatures were seen in the northern plains and north Midwest.

Monthly U.S. reported precipitation amounts in hundredths of inches (ex 100 is 1.00 inches) generated from the GTS metar(hourly) and synoptic(6-hourly)observations for selected cities based on the Weekly Weather and Crop Bulletin station list

Lowest Recorded Temps by City

Climate Data Over Time

By Gary Hoover [source]

About this dataset

This dataset includes information about the lowest recorded temperatures from 2015 for various US cities. It's a chilling reminder of just how cold winter can be - and that each city has its own unique climate! From scorching summer days to frigid winter ones, this dataset gives insight into the temperatures extremes experienced across the country. Whether you live in a balmy beach town or an icy mountain village, you can explore your city's yearly temperature range and prepare accordingly for whatever Mother Nature throws your way!

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

Research Ideas

• Analyzing the melting of snow and ice based on temperatures in US cities to observe shifts in global climate change.
• Comparing and plotting city temperature trends over 2015, to develop targeted energy efficiency programs for colder climates or regions
• Estimating extreme weather events for 2016 by extrapolating from 2015 data - understanding low temperatures helps predict when local authorities need to be prepared and take safety measures during extreme cold spells

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

Unknown License - Please check the dataset description for more information.

Columns

File: Lowest Temperature on Record through 2015 by US City.csv | Column name | Description | |:--------------|:--------------------------------------------------------| | CITY | The name of the city. (String) | | JAN | The lowest recorded temperature in January. (Float) | | FEB | The lowest recorded temperature in February. (Float) | | MAR | The lowest recorded temperature in March. (Float) | | APR | The lowest recorded temperature in April. (Float) | | MAY | The lowest recorded temperature in May. (Float) | | JUN | The lowest recorded temperature in June. (Float) | | JUL | The lowest recorded temperature in July. (Float) | | AUG | The lowest recorded temperature in August. (Float) | | SEP | The lowest recorded temperature in September. (Float) | | OCT | The lowest recorded temperature in October. (Float) | | NOV | The lowest recorded temperature in November. (Float) | | DEC | The lowest recorded temperature in December. (Float) | | ANN | The average annual lowest recorded temperature. (Float) |

Acknowledgements

If you use this dataset in your research, please credit the original authors. If you use this dataset in your research, please credit Gary Hoover.

Climate data and weather trends for New York City, United States. View temperature patterns, precipitation data, and historical climate analysis.

This dataset displays the locations of 248 cities in which long-term climate data has been recorded by the National Oceanic and Atmospheric Administration. From the year 2000.

Open the Data Resource: https://arcg.is/15jrWO1 Federal statistics over a 30-year period show extreme heat is the leading cause of weather-related deaths in the United States. Extreme heat exacerbated by urban heat islands can lead to increased respiratory difficulties, heat exhaustion and heat stroke. Urban Heat Island Severity for U.S. Cities contains the relative heat severity for every pixel for every city in the United States, including Alaska, Hawai'i and Puerto Rico. The purpose of this map is to show where certain areas of cities are hotter than the average temperature for that same city as a whole. Severity is measured on a scale of 1 to 5, with 1 being a relatively mild heat area (slightly above the mean for the city), and 5 being a severe heat area (significantly above the mean for the city). The absolute heat above mean values are classified into these 5 classes using the Jenks Natural Breaks classification method, which seeks to reduce the variance within classes and maximize the variance between classes. Knowing where areas of high heat are located can help a city government plan for mitigation strategies.

The majority of the wettest cities in the United States are located in the Southeast. The major city with the most precipitation is New Orleans, Louisiana, which receives an average of 1592 millimeters (62.7 inches) of precipitation every year, based on an average between 1981 and 2010.

Context

Who among us doesn't talk a little about the weather now and then? Will it rain tomorrow and get so cold to shake your chin or will it make that cracking sun? Does global warming exist?

With this dataset, you can apply machine learning tools to predict the average temperature of Detroit city based on historical data collected over 5 years.

Content

The given data set was produced from the Historical Hourly Weather Data [https://www.kaggle.com/selfishgene/historical-hourly-weather-data], which consists of about 5 years of hourly measurements of various weather attributes (eg. temperature, humidity, air pressure) from 30 US and Canadian cities.

From this rich database, a cutout was made by selecting only the city of Detroit (USA), highlighting only the temperature, converting it to Celsius degrees and keeping only one value for each date (corresponding to the average daytime temperature - from 9am to 5pm).

In addition, temperature values ​​were artificially and gradually increased by a few Celsius degrees over the available period. This will simulate a small global warming (or is it local?)...

In summary, the available dataset contains the average daily temperatures (collected during the day), artificially increased by a certain value, for the city of Detroit from October 2012 to November 2017.

The purpose of this dataset is to apply forecasting models in order to predict the value of the artificially warmed average daily temperature of Detroit.

See graph in the following image: black dots refer to the actual data and the blue line represents the predictive model (including a confidence area).

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F3089313%2Faf9614514242dfb6164a08c013bf6e35%2Fplot-ts2.png?generation=1567827710930876&alt=media" alt="">

Acknowledgements

This dataset wouldn't be possible without the previous work in Historical Hourly Weather Data.

Inspiration

What are the best forecasting models to address this particular problem? TBATS, ARIMA, Prophet? You tell me!

As global emissions and temperatures continue to rise, global climate models offer projections as to how the climate will change in years to come. These model projections can be used for a variety of end-uses to better understand how current systems will be affected by the changing climate. While climate models predict every individual year, using a single year may not be representative as there may be outlier years. It can also be useful to represent a multi-year period with a single year of data. Both items are currently addressed when working with past weather data by a using Typical Meteorological Year (TMY) methodology. This methodology works by statistically selecting representative months from a number of years and appending these months to achieve a single representative year for a given period. In this analysis, the TMY methodology is used to develop Future Typical Meteorological Year (fTMY) using climate model projections. The resulting set of fTMY data is then formatted into EnergyPlus weather (epw) files that can be used for building simulation to estimate the impact of climate scenarios on the built environment.

This dataset contains fTMY files for 18 cities in the continental United States. The locations are representative cities for each climate zone. The data for each city is derived from six different global climate models (GCMs) from the 6th Phase of Coupled Models Intercomparison Project CMIP6- ACCESS-CM2, BCC-CSM2-MR, CNRM-ESM2-1, MPI-ESM1-2-HR, MRI-ESM2-0, NorESM2-MM. The six climate models were statistically downscaled for 1980–2014 in the historical period and 2015–2059 in the future period under the SSP585 scenario using the methodology described in Rastogi et al. (2022). Additionally, hourly data was derived from the daily downscaled output using the Mountain Microclimate Simulation Model (MTCLIM; Thornton and Running, 1999). The shared socioeconomic pathway (SSP) used for this analysis was SSP 5 and the representative concentration pathway (RCP) used was RCP 8.5. More information about SSP and RCP can be referred to O’Neill et al. (2020).

More information about the six selected CMIP6 GCMs:

ACCESS-CM2 - http://dx.doi.org/10.1071/ES19040

BCC-CSM2-MR - https://doi.org/10.5194/gmd-14-2977-2021

CNRM-ESM2-1- https://doi.org/10.1029/2019MS001791

MPI-ESM1-2-HR - https://doi.org/10.5194/gmd-12-3241-2019

MRI-ESM2-0 - https://doi.org/10.2151/jmsj.2019-051

NorESM2-MM - https://doi.org/10.5194/gmd-13-6165-2020

Additional references:

O’Neill, B. C., Carter, T. R., Ebi, K. et al. (2020). Achievements and Needs for the Climate Change Scenario Framework. Nat. Clim. Chang. 10, 1074–1084 (2020). https://doi.org/10.1038/s41558-020-00952-0

Rastogi, D., Kao, S.-C., and Ashfaq, M. (2022). How May the Choice of Downscaling Techniques and Meteorological Reference Observations Affect Future Hydroclimate Projections? Earth's Future, 10, e2022EF002734. https://doi.org/10.1029/2022EF002734

Thornton, P. E. and Running, S. W. (1999). An Improved Algorithm for Estimating Incident Daily Solar Radiation from Measurements of Temperature, Humidity and Precipitation, Agricultural and Forest Meteorology, 93, 211-228.

Shovan Chowdhury, Fengqi Li, Avery Stubbings, Joshua R. New, Deeksha Rastogi, and Shih-Chieh Kao (2023). "Future Typical Meteorological Year (fTMY) US Weather Files for Building Simulation for every US County (West and Midwest)." ORNL internal Scientific and Technical Information (STI) report, doi:10.5281/zenodo.8338549, Sept 2023. [Data]

Shovan Chowdhury, Fengqi Li, Avery Stubbings, Joshua R. New, Deeksha Rastogi, and Shih-Chieh Kao (2023). "Future Typical Meteorological Year (fTMY) US Weather Files for Building Simulation for every US County (East and South)." ORNL internal Scientific and Technical Information (STI) report, doi:10.5281/zenodo.8335815, Sept 2023. [Data]

Bass, Brett, New, Joshua R., Rastogi, Deeksha and Kao, Shih-Chieh (2022). "Future Typical Meteorological Year (fTMY) US Weather Files for Building Simulation (1.0) [Data set]." Zenodo, doi.org/10.5281/zenodo.6939750, Aug. 2022. [Data]