2023

Weather Data collected by CIMIS automatic weather stations. The data is available in CSV format. Station data include measured parameters such as solar radiation, air temperature, soil temperature, relative humidity, precipitation, wind speed and wind direction as well as derived parameters such as vapor pressure, dew point temperature, and grass reference evapotranspiration (ETo).

Bangladesh Weather Dataset
This dataset falls under the category Environmental Data Climate Data.
It contains the following data: This dataset contains the monthly average value of Bangladesh temperature and rain from 1901 to 2015
This dataset was scouted on 2022-03-01 as part of a data sourcing project conducted by TUMI. License information might be outdated: Check original source for current licensing. The data can be accessed using the following URL / API Endpoint: https://www.kaggle.com/yakinrubaiat/bangladesh-weather-dataset

Some say climate change is the biggest threat of our age while others say it’s a myth based on dodgy science. We are turning some of the data over to you so you can form your own view.

Even more than with other data sets that Kaggle has featured, there’s a huge amount of data cleaning and preparation that goes into putting together a long-time study of climate trends. Early data was collected by technicians using mercury thermometers, where any variation in the visit time impacted measurements. In the 1940s, the construction of airports caused many weather stations to be moved. In the 1980s, there was a move to electronic thermometers that are said to have a cooling bias.

Given this complexity, there are a range of organizations that collate climate trends data. The three most cited land and ocean temperature data sets are NOAA’s MLOST, NASA’s GISTEMP and the UK’s HadCrut.

We have repackaged the data from a newer compilation put together by the Berkeley Earth, which is affiliated with Lawrence Berkeley National Laboratory. The Berkeley Earth Surface Temperature Study combines 1.6 billion temperature reports from 16 pre-existing archives. It is nicely packaged and allows for slicing into interesting subsets (for example by country). They publish the source data and the code for the transformations they applied. They also use methods that allow weather observations from shorter time series to be included, meaning fewer observations need to be thrown away.

In this dataset, we have include several files:

Global Land and Ocean-and-Land Temperatures (GlobalTemperatures.csv):

• Date: starts in 1750 for average land temperature and 1850 for max and min land temperatures and global ocean and land temperatures
• LandAverageTemperature: global average land temperature in celsius
• LandAverageTemperatureUncertainty: the 95% confidence interval around the average
• LandMaxTemperature: global average maximum land temperature in celsius
• LandMaxTemperatureUncertainty: the 95% confidence interval around the maximum land temperature
• LandMinTemperature: global average minimum land temperature in celsius
• LandMinTemperatureUncertainty: the 95% confidence interval around the minimum land temperature
• LandAndOceanAverageTemperature: global average land and ocean temperature in celsius
• LandAndOceanAverageTemperatureUncertainty: the 95% confidence interval around the global average land and ocean temperature

Other files include:

• Global Average Land Temperature by Country (GlobalLandTemperaturesByCountry.csv)
• Global Average Land Temperature by State (GlobalLandTemperaturesByState.csv)
• Global Land Temperatures By Major City (GlobalLandTemperaturesByMajorCity.csv)
• Global Land Temperatures By City (GlobalLandTemperaturesByCity.csv)

The raw data comes from the Berkeley Earth data page.

This dataset contains Raleigh Durham International Airport weather data pulled from the NOAA web service described at Climate Data Online: Web Services Documentation. We have pulled this data and converted it to commonly used units. This dataset is an archive - it is not being updated.

dust

The Weather Generator Gridded Data consists of two products:

[1] statistically perturbed gridded 100-year historic daily weather data including precipitation [in mm], and detrended maximum and minimum temperature in degrees Celsius, and

[2] stochastically generated and statistically perturbed gridded 1000-year daily weather data including precipitation [in mm], maximum temperature [in degrees Celsius], and minimum temperature in degrees Celsius.

The base climate of this dataset is a combination of historically observed gridded data including Livneh Unsplit 1915-2018 (Pierce et. al. 2021), Livneh 1915-2015 (Livneh et. al. 2013) and PRISM 2016-2018 (PRISM Climate Group, 2014). Daily precipitation is from Livneh Unsplit 1915-2018, daily temperature is from Livneh 2013 spanning 1915-2015 and was extended to 2018 with daily 4km PRISM that was rescaled to the Livneh grid resolution (1/16 deg). The Livneh temperature was bias corrected by month to the corresponding monthly PRISM climate over the same period. Baseline temperature was then detrended by month over the entire time series based on the average monthly temperature from 1991-2020. Statistical perturbations and stochastic generation of the time series were performed by the Weather Generator (Najibi et al. 2024a and Najibi et al. 2024b).

The repository consists of 30 climate perturbation scenarios that range from -25 to +25 % change in mean precipitation, and from 0 to +5 degrees Celsius change in mean temperature. Changes in thermodynamics represent scaling of precipitation during extreme events by a scaling factor per degree Celsius increase in mean temperature and consists primarily of 7%/degree-Celsius with 14%/degree-Celsius as sensitivity perturbations. Further insight for thermodynamic scaling can be found in full report linked below or in Najibi et al. 2024a and Najibi et al. 2024b.

The data presented here was created by the Weather Generator which was developed by Dr. Scott Steinschneider and Dr. Nasser Najibi (Cornell University). If a separate weather generator product is desired apart from this gridded climate dataset, the weather generator code can be adopted to suit the specific needs of the user. The weather generator code and supporting information can be found here: https://github.com/nassernajibi/WGEN-v2.0/tree/main. The full report for the model and performance can be found here: https://water.ca.gov/-/media/DWR-Website/Web-Pages/Programs/All-Programs/Climate-Change-Program/Resources-for-Water-Managers/Files/WGENCalifornia_Final_Report_final_20230808.pdf

This map displays the Quantitative Precipitation Forecast (QPF) for the next 72 hours across the contiguous United States. Data are updated hourly from the National Digital Forecast Database produced by the National Weather Service.The dataset includes incremental and cumulative precipitation data in 6-hour intervals. In the ArcGIS Online map viewer you can enable the time animation feature and select either the "Amount by Time" (incremental) layer or the "Accumulation by Time" (cumulative) layer to view a 72-hour animation of forecast precipitation. All times are reported according to your local time zone.Where is the data coming from?The National Digital Forecast Database (NDFD) was designed to provide access to weather forecasts in digital form from a central location. The NDFD produces forecast data of sensible weather elements. NDFD contains a seamless mosaic of digital forecasts from National Weather Service (NWS) field offices working in collaboration with the National Centers for Environmental Prediction (NCEP). All of these organizations are under the administration of the National Oceanic and Atmospheric Administration (NOAA).Source: https://tgftp.nws.noaa.gov/SL.us008001/ST.opnl/DF.gr2/DC.ndfd/AR.conus/VP.001-003/ds.qpf.binWhere can I find other NDFD data?The Source data is downloaded and parsed using the Aggregated Live Feeds methodology to return information that can be served through ArcGIS Server as a map service or used to update Hosted Feature Services in Online or Enterprise.What can you do with this layer?This map service is suitable for data discovery and visualization. Identify features by clicking on the map to reveal the pre-configured pop-ups. View the time-enabled data using the time slider by Enabling Time Animation.This map is provided for informational purposes and is not monitored 24/7 for accuracy and currency.If you would like to be alerted to potential issues or simply see when this Service will update next, please visit our Live Feed Status Page!

Single Label Weather

## Overview

Single Label Weather is a dataset for classification tasks - it contains Weather annotations for 5,096 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [BY-NC-SA 4.0 license](https://creativecommons.org/licenses/BY-NC-SA 4.0).

[ NOTE – 2022/05/06: this dataset supersedes the earlier versions https://doi.org/10.15482/USDA.ADC/1482548 and https://doi.org/10.15482/USDA.ADC/1526329 ]. This dataset contains 15-minute mean weather data from the USDA-ARS Conservation and Production Laboratory (CPRL), Soil and Water Management Research Unit (SWMRU) research weather station, Bushland, Texas (Lat. 35.186714°, Long. -102.094189°, elevation 1170 m above MSL) for all days in each year. The data are from sensors placed at 2-m height over a level, grass surface mowed to not exceed 12 cm height and irrigated and fertilized to maintain reference conditions as promulgated by Allen et al. (2005, 1998). Irrigation was by surface flood in 1989 through 1994, and by subsurface drip irrigation after 1994. Sensors were replicated and intercompared between replicates and with data from nearby weather stations, which were sometimes used for gap filling. Quality control and assurance methods are described by Evett et al. (2018). Data from a duplicate sensor were used to fill gaps in data from the primary sensor using appropriate regression relationships. Gap filling was also accomplished using sensors deployed at one of the four large weighing lysimeters immediately west of the weather station, or using sensors at other nearby stations when reliable regression relationships could be developed. The primary paper describes details of the sensors used and methods of testing, calibration, inter-comparison, and use. The weather data include air temperature (C) and relative humidity (%), wind speed (m/s), solar irradiance (W m-2), barometric pressure (kPa), and precipitation (rain and snow in mm). Because the large (3 m by 3 m surface area) weighing lysimeters are better rain gages than are tipping bucket gages, the 15-minute precipitation data are derived for each lysimeter from changes in lysimeter mass. The land slope is

This dataset replaces the previous Time Bias Corrected Divisional Temperature-Precipitation Drought Index. The new divisional data set (NClimDiv) is based on the Global Historical Climatological Network-Daily (GHCN-D) and makes use of several improvements to the previous data set. For the input data, improvements include additional station networks, quality assurance reviews and temperature bias adjustments. Perhaps the most extensive improvement is to the computational approach, which now employs climatologically aided interpolation. This 5km grid based calculation nCLIMGRID helps to address topographic and network variability. This data set is primarily used by the National Oceanic and Atmospheric Administration (NOAA) National Climatic Data Center (NCDC) to issue State of the Climate Reports on a monthly basis. These reports summarize recent temperature and precipitation conditions and long-term trends at a variety of spatial scales, the smallest being the climate division level. Data at the climate division level are aggregated to compute statewide, regional and national snapshots of climate conditions. For CONUS, the period of record is from 1895-present. Derived quantities such as Standardized precipitation Index (SPI), Palmer Drought Indices (PDSI, PHDI, PMDI, and ZNDX) and degree days are also available for the CONUS sites. In March 2015, data for thirteen Alaskan climate divisions were added to the NClimDiv data set. Data for the new Alaskan climate divisions begin in 1925 through the present and are included in all monthly updates. Alaskan climate data include the following elements for divisional and statewide coverage: average temperature, maximum temperature (highs), minimum temperature (lows), and precipitation. The Alaska NClimDiv data were created and updated using similar methodology as that for the CONUS, but with a different approach to establishing the underlying climatology. The Alaska data are built upon the 1971-2000 PRISM averages whereas the CONUS values utilize a base climatology derived from the NClimGrid data set. As of November 2018, NClimDiv includes county data and additional inventory files.

Dataset

This dataset was created by Ioana Gheorghiu

Contents

Daily observation data for each station, for all elements (observation types)

The United States Department of Agriculture-Agricultural Research Service (USDA-ARS) North Central Soil Conservation Research Laboratory - Soil Management Unit established a weather data collection system at the Swan Lake Research Farm in 1997. Weather data collected include wind speed and direction, barometric pressure, relative humidity, air temperature, soil temperatures, soil heat flux, solar radiation, photosynthetic active radiation, and precipitation. In 2015 the site became part of the Long Term Agroecosystem Research (LTAR) project. The Swan Lake Research Farm is located in Stevens County Minnesota, in the Upper Mississippi River Basin (UMRB) watershed. Resources in this dataset:Resource Title: GeoData catalog record. File Name: Web Page, url: https://geodata.nal.usda.gov/geonetwork/srv/eng/catalog.search#/metadata/ad80c14b-f4a0-41b2-8592-3a5b6bbebcc7

The NOAA Weather and Climate Toolkit is an application that provides simple visualization and data export of weather and climatological data archived at NCDC. The Toolkit also provides access to weather and climate web services provided from NCDC and other organizations. The Viewer provides tools for displaying custom data overlay, Web Map Services (WMS), animations and basic filters. The export of images and movies is provided in multiple formats. The Data Exporter allows for data export in both vector point/line/polygon and raster grid formats. Current data types supported include: CF-compliant Fridded NetCDF; Generic CF-compliant Irregularly-Spaced/Curvilinear Gridded NetCDF/HDF; GRIB1, GRIB2, GINI, GEMPAK, HDF(CF-compliant) and more gridded formats; GPES Satellite AREA Files; NEXRAD Radar Data(Level-II and Level-III); U.S. Drought Monitor Service from the National Drought Mitigation Center (NDMC); OPeNDAP support for Gridded Datasets

📊 Dataset README (Updated with Temporal Coverage) 📈 Overview 🌐 This README document provides detailed information about a dataset that combines temperature 🌡️ and rainfall 🌧️ data. The temperature data is sourced from NASA's POWER Project, and the rainfall data is obtained from the Humanitarian Data Exchange (HDX) website, specifically focusing on Bangladesh rainfall data. Temperature Data Source 🔥 Source: NASA's POWER (Prediction of Worldwide Energy Resources) Data Access Viewer URL: NASA POWER Data Access Viewer Description: The POWER Project provides solar and meteorological data sets, primarily intended for renewable energy, sustainable buildings, agriculture, and other related applications. The temperature data from this source is a part of NASA's global meteorological data. Rainfall Data Source 🌧️ Source: Humanitarian Data Exchange (HDX) URL: Bangladesh Rainfall Data - HDX Description: HDX hosts various humanitarian data including climate and weather-related datasets. The rainfall data for Bangladesh is part of their collection, providing detailed subnational rainfall statistics. Dataset Description 📝 Composition 📊 The dataset is a combination of the temperature and rainfall data, aligned by date to facilitate joint analysis. The key components are: Temperature Data (tem): Represents the monthly average temperature, presumably in degrees Celsius. Rainfall Data (rain): Indicates monthly total rainfall, presumably measured in millimeters. Structure 🏗️ The dataset is structured into a CSV file with the following columns: tem: Average temperature for the month. Month: The month for the data point, ranging from 1 (January) to 12 (December). Year: The year of the data point. rain: Total rainfall for the month. Temporal Coverage 📆 Earliest Date: 1901 Latest Date: 2023 This dataset provides a historical perspective on climate trends from the earliest year of 1901 to the most recent data available up to 2023. Usage and Applications 🚀 This dataset is particularly useful for studying climatic patterns, seasonal changes, and long-term climate trends. Applications include but are not limited to: Climatological research and climate change studies. Agricultural planning and forecasting. Environmental and ecological studies. Resource management and planning in sectors sensitive to climatic variations. Limitations and Considerations 🚧 Geographical Specificity: The rainfall data is specific to Bangladesh and may not represent global patterns. Data Integration: The temperature and rainfall data come from two different sources; users should consider potential discrepancies in data collection methods and accuracy. Updates and Maintenance 🔄 Data Update Frequency: Check the source websites for the update frequency and availability of more recent data. Last Updated: Refer to the source websites for the last update date of the data. Licensing and Usage Rights ©️ Users should refer to the respective source websites for information on licensing and usage rights. It is important to adhere to the terms and conditions set by the data providers. Contact Information 📞 For specific queries related to the temperature or rainfall data, users should contact the respective data providers through their official communication channels provided on their websites.

This is an hourly future weather dataset for energy modeling applications. The dataset is primarily based on the output of a regional climate model (RCM), i.e., the Weather Research and Forecasting (WRF) model version 3.3.1. The WRF simulations are driven by the output of a general circulation model (GCM), i.e., the Community Climate System Model version 4 (CCSM4).

This dataset is in the EPW format, which can be read or translated by more than 25 building energy modeling programs (e.g., EnergyPlus, ESP-r, and IESVE), energy system modeling programs (e.g., System Advisor Model (SAM)), indoor air quality analysis programs (e.g., CONTAM), and hygrothermal analysis programs (e.g., WUFI). It contains 13 weather variables, which are the Dry-Bulb Temperature, Dew Point Temperature, Relative Humidity, Atmospheric Pressure, Horizontal Infrared Radiation Intensity from Sky, Global Horizontal Irradiation, Direct Normal Irradiation, Diffuse Horizontal Irradiation, Wind Speed, Wind Direction, Sky Cover, Albedo, and Liquid Precipitation Depth.

The weather data is created for two emissions scenarios: RCP4.5 and RCP8.5 and spans two 10-year time slices in the future: 2045 - 2054 and 2085 - 2094. It offers a spatial resolution of 12 km by 12 km with extensive coverage across most of North America. Due to the enormous size of the entire dataset, in the first stage of its distribution, we provide 20 years of future weather data for the centroid of each Public Use Microdata Area (PUMA), excluding Hawaii. PUMAs are non-overlapping, statistical geographic areas that partition each state or equivalent entity into geographic areas containing no fewer than 100,000 people each. The 2,378 PUMAs as a whole cover the entirety of the U.S. The weather data can be utilized alongside the large-scale energy analysis tools, ResStock and ComStock, developed by National Renewable Energy Laboratory, whose smallest resolution is at the PUMA scale.

The data for RCP4.5 is still being processed and will be published soon.

this work provides the Korean weather dataset

General weather forecast for the Netherlands, presented as text. Forecast is for the current and upcoming day. The data is published in two different formats: txt and xml.

Typical Downscaled Year (TDY), Extreme Cold Year and Extreme Warm Year based on the methodology of Nik (2016), is extracted for the location of Leuven City Centre (50°52'48"N 4°42'0" E) from the EC-Earth driven convection-permitting climate model COSMO-CLM for the Belgian domain extended with land-surface scheme TERRA_URB(v2.0) making use of the SURY (Semi-empirical URban canopY) parameterization ( Wouters et al. 2016). The integrations are identical to the ones which are described in Vanden Broucke et al. (2019). The climate model has a spatial resolution of 2.8 km and an hourly temporal resolution and is available for the recent past (1976-2004) and future (2070-2098, RCP 8.5 climate change scenario) as 30-year datasets. For this dataset, the TDY, ECY, and EWY are extracted for the future period. A bias correction is applied for the following variables: temperature (as described in Ramon et al. 2020), solar radiation and relative humidity as described in Ramon et al. (202X).