This is the third part of flight delay prediction i.e. for the month of March. To check the first and second parts i.e. for the month of January and February, please have a look at these datasets: January Flight Delay Prediction, February Flight Delay Prediction

This data is collected from the Bureau of Transportation Statistics, Govt. of the USA. This data is open-sourced under U.S. Govt. Works. This dataset contains all the flights in the month of March 2019 and March 2020. There are more than 400,000 flights in the month of March itself throughout the United States. The features were manually chosen to do a primary time series analysis. There are several other features available on their website.

This data could well be used to predict the flight delay at the destination airport particularly for the month of March in upcoming years as the data is for March only.

This is the second part of flight delay prediction i.e. for the month of February. To check the first part i.e. for the month of January, please have a look at this dataset: January Flight Delay Prediction

This data is collected from the Bureau of Transportation Statistics, Govt. of the USA. This data is open-sourced under U.S. Govt. Works. This dataset contains all the flights in the month of February 2019 and February 2020. There are more than 400,000 flights in the month of February itself throughout the United States. The features were manually chosen to do a primary time series analysis. There are several other features available on their website.

This data could well be used to predict the flight delay at the destination airport particularly for the month of February in upcoming years as the data is for February only.

Have you ever been stuck in an airport because your flight was delayed or cancelled and wondered if you could have predicted it if you'd had more data? This is your chance to find out.

The 2009 ASA Statistical Computing and Graphics Data Expo consisted of flight arrival and departure details for all commercial flights on major carriers within the USA, from October 1987 to April 2008. This is a large dataset containing nearly 120 million records in total.

The aim of the data expo is to provide a graphical summary of important features of the data set. This is intentionally vague in order to allow different entries to focus on different aspects of the data, but here are a few ideas to get you started: •When is the best time of day, day of the week, and time of year to fly to minimise delays? •Do older planes suffer more delays? •How well does weather predict plane delays? •How does the number of people flying between different locations change over time? •Can you detect cascading failures as delays in one airport create delays in others? Are there critical links in the system? •Use the available variables to construct a model that predicts delays.

The Reporting Carrier On-Time Performance Dataset contains information on approximately 200 million domestic US flights reported to the United States Bureau of Transportation Statistics. The dataset contains basic information about 2 million flights (such as date, time, departure airport, arrival airport) and, if applicable, the amount of time the flight was delayed and information about the reason for the delay. This dataset can be used to predict the likelihood of a flight arriving on time.

Dataset Glossary

Column description can be found here

Citation

This dataset was compiled from data available on the Bureau of Transportation Statistics website and is US Government work not subject to copyright.

Acknowledgement

Original Data

Foto von Ivan Shimko auf Unsplash

BACKGROUND The data contained in the compressed file has been extracted from the Marketing Carrier On-Time Performance (Beginning January 2018) data table of the "On-Time" database from the TranStats data library. The time period is indicated in the name of the compressed file; for example, XXX_XXXXX_2001_1 contains data of the first month of the year 2001.

RECORD LAYOUT Below are fields in the order that they appear on the records: Year Year Quarter Quarter (1-4) Month Month DayofMonth Day of Month DayOfWeek Day of Week FlightDate Flight Date (yyyymmdd) Marketing_Airline_Network Unique Marketing Carrier Code. When the same code has been used by multiple carriers, a numeric suffix is used for earlier users, for example, PA, PA(1), PA(2). Use this field for analysis across a range of years. Operated_or_Branded_Code_Share_Partners Reporting Carrier Operated or Branded Code Share Partners DOT_ID_Marketing_Airline An identification number assigned by US DOT to identify a unique airline (carrier). A unique airline (carrier) is defined as one holding and reporting under the same DOT certificate regardless of its Code, Name, or holding company/corporation. IATA_Code_Marketing_Airline Code assigned by IATA and commonly used to identify a carrier. As the same code may have been assigned to different carriers over time, the code is not always unique. For analysis, use the Unique Carrier Code. Flight_Number_Marketing_Airline Flight Number Originally_Scheduled_Code_Share_Airline Unique Scheduled Operating Carrier Code. When the same code has been used by multiple carriers, a numeric suffix is used for earlier users,for example, PA, PA(1), PA(2). Use this field for analysis across a range of years. DOT_ID_Originally_Scheduled_Code_Share_Airline An identification number assigned by US DOT to identify a unique airline (carrier). A unique airline (carrier) is defined as one holding and reporting under the same DOT certificate regardless of its Code, Name, or holding company/corporation. IATA_Code_Originally_Scheduled_Code_Share_Airline Code assigned by IATA and commonly used to identify a carrier. As the same code may have been assigned to different carriers over time, the code is not always unique. For analysis, use the Unique Carrier Code. Flight_Num_Originally_Scheduled_Code_Share_Airline Flight Number Operating_Airline Unique Carrier Code. When the same code has been used by multiple carriers, a numeric suffix is used for earlier users, for example, PA, PA(1), PA(2). Use this field for analysis across a range of years. DOT_ID_Operating_Airline An identification number assigned by US DOT to identify a unique airline (carrier). A unique airline (carrier) is defined as one holding and reporting under the same DOT certificate regardless of its Code, Name, or holding company/corporation. IATA_Code_Operating_Airline Code assigned by IATA and commonly used to identify a carrier. As the same code may have been assigned to different carriers over time, the code is not always unique. For analysis, use the Unique Carrier Code. Tail_Number Tail Number Flight_Number_Operating_Airline Flight Number OriginAirportID Origin Airport, Airport ID. An identification number assigned by US DOT to identify a unique airport. Use this field for airport analysis across a range of years because an airport can change its airport code and airport codes can be reused. OriginAirportSeqID Origin Airport, Airport Sequence ID. An identification number assigned by US DOT to identify a unique airport at a given point of time. Airport attributes, such as airport name or coordinates, may change over time. OriginCityMarketID Origin Airport, City Market ID. City Market ID is an identification number assigned by US DOT to identify a city market. Use this field to consolidate airports serving the same city market. Origin Origin Airport OriginCityName Origin Airport, City Name OriginState Origin Airport, State Code OriginStateFips Origin Airport, State Fips OriginStateName Origin Airport, State Name OriginWac Origin Airport, World Area Code DestAirportID Destination Airport, Airport ID. An identification number assigned by US DOT to identify a unique airport. Use this field for airport analysis across a range of years because an airport can change its airport code and airport codes can be reused. DestAirportSeqID Destination Airport, Airport Sequence ID. An identification number assigned by US DOT to identify a unique airport at a given point of time. Airport attributes, such as airport name or coordinates, may change over time. DestCityMarketID Destination Airport, City Market ID. City Market ID is an identification number assigned by US DOT to identify a city market. Use this field to consolidate airports serving the same city market. Dest Destination Airport DestCityName Destination Airport, City Name DestState Destination Airport, State Code DestStateFips De...

This dataset contains predictions of whether temperature inversions will occur at locations in Allegheny County.

This dataset is still under active development and should be considered to be in "beta".

Motivation

Temperature inversions occur when there is a warmer layer of air above the air at or near ground level. This represents a reversal of the normal flow of heat near the earth and results in the cooler air being trapped near the ground. Temperature inversions can lead to the formation of fog or dew. Pollution or smoke from fires, which would rise and dissipate in the atmosphere under normal conditions, become trapped near the ground in a temperature inversion, potentially leading to hazardous concentrations of pollutants in the air.

This dataset was extracted from NASA's Goddard Earth Observing System Forward-Processing (GEOS-FP) system as a collaboration between NASA's Goddard Space Flight Center and the Western Pennsylvania Regional Data Center, to provide access to 1-day, 3-day, and 5-day predictions of temperature inversions in Allegheny County.

Preprocessing/Formatting/Methodology

This dataset is generated using data-processing scripts written by partners at NASA Goddard Space Flight Center. The scripts extract from the GEOS-FP model the predicted air temperature as a function of latitude/longitude/date/height, and then, starting near surface level, search upward for the height of the local maximum in air temperature. This determines whether a temperature inversion is expected.

Each record is a prediction of whether there will be a temperature inversion, for a particular day at 12pm UTC (7am EST) within five days after the prediction, and for a particular cell in a coarse grid overlaying Allegheny County. If an inversion is predicted, the height of top of the inversion above the ground and the temperature difference between the ground and the top of the inversion are given, as well as an estimate of the inversion strength on a scale of 0 to 4 (where the strength of the inversion is calculated based on the value of the temperature difference). For some locations, we've also added the name of a place (e.g., "Pittsburgh" or "Monroeville") within that cell, to make look-ups easier.

Additionally, we've created forecast maps for the region and 5-day timeline forecasts (for particular locations) of both inversion strength and PM2.5 concentration.

Known Uses

If you are using this dataset, please write to the data steward (listed below) and let us know! Your stories support the development of future datasets like this.

Recommended Uses

This data could provide an early-warning system for certain kinds of unhealthy air-quality events, such as dangerously high PM_2.5 levels from wildfire-induced smog or pollution, trapped near the ground.

Known Limitations/Biases

The spatial resolution of the forecast is pretty coarse.

To validate the forecast, a comparison was made of its predictions with actual temperature-inversion measurements made by weather balloon (or sodar/RASS acoustic upper air profiler) by the Allegheny County Health Department Air Quality Office. The results are shown in this table, which is accompanied by some additional analysis. When the 1-day forecast predicted a strong or moderate inversion, there was about a 90% chance that it was historically correct, and when the 3-day or 5-day forecast confirmed this forecast for the same date, the accuracy increased, with more than 96% historical accuracy when confirmed by the 5-day forecast.

Also, sometimes the model results can not be computed on the expected schedule. (These delays are reported on the "geos5-fp-users" mailing list.) In these instances, the WPRDC's automated processes fall back to the previous day's forecasts; the forecast_version field provides the date and hour that the forecast simulation was started.

Related Datasets

The Allegheny County Health Department's measurement of pollutant concentrations (and other parameters) at several measurements stations are published in the Allegheny County Air Quality dataset.

We are also publishing a dataset that forecasts concentrations of three air quality parameters: carbon monoxide (CO), nitrogen dioxide (NO2), and fine particulate matter (PM2.5).

Credits

This work is the result of a collaboration between the WPRDC and NASA's Goddard Space Flight Center. This dataset would not have been possible without the efforts of NASA Goddard Space Flight Center personnel to apply NASA's atmospheric models and domain expertise to the problem of forecasting temperature inversions, yielding this prototype forecast, tailored to Allegheny County. Thanks also to Jason Maranche and Angela Wilson of the Allegheny County Health Department's Air Quality Program for providing us with, and helping us understand, their historical temperature-inversion measurement data (used to validate the predictions).

This dataset contains predictions of whether temperature inversions will occur at locations in Allegheny County.

This dataset is still under active development and should be considered to be in "beta".

Motivation

Temperature inversions occur when there is a warmer layer of air above the air at or near ground level. This represents a reversal of the normal flow of heat near the earth and results in the cooler air being trapped near the ground. Temperature inversions can lead to the formation of fog or dew. Pollution or smoke from fires, which would rise and dissipate in the atmosphere under normal conditions, become trapped near the ground in a temperature inversion, potentially leading to hazardous concentrations of pollutants in the air.

This dataset was extracted from NASA's Goddard Earth Observing System Forward-Processing (GEOS-FP) system as a collaboration between NASA's Goddard Space Flight Center and the Western Pennsylvania Regional Data Center, to provide access to 1-day, 3-day, and 5-day predictions of temperature inversions in Allegheny County.

Preprocessing/Formatting/Methodology

This dataset is generated using data-processing scripts written by partners at NASA Goddard Space Flight Center. The scripts extract from the GEOS-FP model the predicted air temperature as a function of latitude/longitude/date/height, and then, starting near surface level, search upward for the height of the local maximum in air temperature. This determines whether a temperature inversion is expected.

Each record is a prediction of whether there will be a temperature inversion, for a particular day at 12pm UTC (7am EST) within five days after the prediction, and for a particular cell in a coarse grid overlaying Allegheny County. If an inversion is predicted, the height of top of the inversion above the ground and the temperature difference between the ground and the top of the inversion are given, as well as an estimate of the inversion strength on a scale of 0 to 4 (where the strength of the inversion is calculated based on the value of the temperature difference). For some locations, we've also added the name of a place (e.g., "Pittsburgh" or "Monroeville") within that cell, to make look-ups easier.

Additionally, we've created forecast maps for the region and 5-day timeline forecasts (for particular locations) of both inversion strength and PM2.5 concentration.

Known Uses

If you are using this dataset, please write to the data steward (listed below) and let us know! Your stories support the development of future datasets like this.

Recommended Uses

This data could provide an early-warning system for certain kinds of unhealthy air-quality events, such as dangerously high PM_2.5 levels from wildfire-induced smog or pollution, trapped near the ground.

Known Limitations/Biases

The spatial resolution of the forecast is pretty coarse.

To validate the forecast, a comparison was made of its predictions with actual temperature-inversion measurements made by weather balloon (or sodar/RASS acoustic upper air profiler) by the Allegheny County Health Department Air Quality Office. The results are shown in this table, which is accompanied by some additional analysis. When the 1-day forecast predicted a strong or moderate inversion, there was about a 90% chance that it was historically correct, and when the 3-day or 5-day forecast confirmed this forecast for the same date, the accuracy increased, with more than 96% historical accuracy when confirmed by the 5-day forecast.

Also, sometimes the model results can not be computed on the expected schedule. (These delays are reported on the "geos5-fp-users" mailing list.) In these instances, the WPRDC's automated processes fall back to the previous day's forecasts; the forecast_version field provides the date and hour that the forecast simulation was started.

Related Datasets

The Allegheny County Health Department's measurement of pollutant concentrations (and other parameters) at several measurements stations are published in the Allegheny County Air Quality dataset.

We are also publishing a dataset that forecasts concentrations of three air quality parameters: carbon monoxide (CO), nitrogen dioxide (NO2), and fine particulate matter (PM2.5).

Credits

This work is the result of a collaboration between the WPRDC and NASA's Goddard Space Flight Center. This dataset would not have been possible without the efforts of NASA Goddard Space Flight Center personnel to apply NASA's atmospheric models and domain expertise to the problem of forecasting temperature inversions, yielding this prototype forecast, tailored to Allegheny County. Thanks also to Jason Maranche and Angela Wilson of the Allegheny County Health Department's Air Quality Program for providing us with, and helping us understand, their historical temperature-inversion measurement data (used to validate the predictions).

What is Data Expo 2009 - Airline on-time performance?

Have you ever been stuck in an airport because your flight was delayed or canceled and wondered if you could have predicted it if you'd had more data? This is your chance to find out.

.

How to use this dataset

We had a total of nine entries, and turn ou at the poster session at the JSM was great, with plenty of people stopping by to find out why their flights were delayed.

Acknowledgments

When we use this dataset in our research, we credit the authors.

• License : CC BY 4.0.

• This data set is taken from Harvard Dataset- Data Expo 2009: Airline on time data

The main idea for uploading this dataset is to practice data analysis with my students, as I am working in college and want my student to train our studying ideas in a big dataset, It may be not up to date and I mention the collecting years, but it is a good resource of data to practice

Context: This dataset contains flight fare data that was collected from the EaseMyTrip website using web scraping techniques. The data was collected with the goal of providing users with information that could help them make informed decisions about when and where to purchase flight tickets. By analyzing patterns in flight fares over time, users can identify the best times to book tickets and potentially save money.

Sources: 1. Data collected using Python script with Beautiful Soup and Selenium libraries. 2. Script collected data on various flight details such as Date of booking, Date of travel, Airline and class, Departure time and source, Arrival time and destination, Duration, Total stops, Price. 3. The scraping process was designed to collect data for flights departing from a specific set of airports (Top 7 busiest airports in India). Note that the Departure Time feature also includes the Source airport, and the Arrival Time feature also includes the Destination airport. Which is later extracted in Cleaned_dataset. Also both cleaned and scraped datasets have provided so that one can use dataset as per their requirement and convenience.

Inspiration: 1. Dataset created to provide users with valuable resource for analyzing flight fares in India. 2. Detailed information on flight fares over time can be used to develop more accurate pricing models and inform users about best times to book tickets. 3. Data can also be used to study trends and patterns in the travel industry through air can act as a valuable resource for researchers and analysts.

Limitations: 1. This dataset only covers flights departing from specific airports and limited to a certain time period. 2. To perform time series analysis one have gather data for at least top 10 busiest airports for 365 days. 3. This does not cover variations in aviation fuel prices as this is the one of influencing factor for deciding fare, hence the same dataset might not be useful for next year, but I will try to update it twice in an year. 4. Also demand and supply for the particular flight seat is not available in the dataset as this data is not publicly available on any flight booking web site.

Scope of Improvement: 1. The dataset could be enhanced by including additional features such as current aviation fuel prices and the distance between the source and destination in terms of longitude and latitude. 2. The data could also be expanded to include more airlines and more airports, providing a more comprehensive view of the flight market. 3. Additionally, it may be helpful to include data on flight cancellations, delays, and other factors that can impact the price and availability of flights. 4. Finally, while the current dataset provides information on flight prices, it does not include information on the quality of the flight experience, such as legroom, in-flight amenities, and customer reviews. Including this type of data could provide a more complete picture of the flight market and help travelers make more informed decisions.