A weather features dataset for prediction of short-term rainfall quantities in Uganda

Andrew Gahwera Tumusiime; Odongo Steven Eyobu; Isaac Mugume; Tonny J Oyana

doi:10.1016/j.dib.2023.109613

A weather features dataset for prediction of short-term rainfall quantities in Uganda

Data Brief. 2023 Sep 25:50:109613. doi: 10.1016/j.dib.2023.109613. eCollection 2023 Oct.

Authors

Andrew Gahwera Tumusiime¹, Odongo Steven Eyobu¹, Isaac Mugume², Tonny J Oyana¹

Affiliations

¹ College of Computing and IS, Makerere University, P.O Box, 7062, Kampala, Uganda.
² College of Agricultural and Environmental Sciences, Makerere University, P.O Box, 7062, Kampala, Uganda.

Abstract

Weather data is of great importance to the development of weather prediction models. However, the availability and quality of this data remains a significant challenge for most researchers around the world. In Uganda, obtaining observational weather data is very challenging due to the sparse distribution of weather stations and inconsistent data records. This has created critical gaps in data availability to run and develop efficient weather prediction models. To bridge this gap, we obtained country-specific time series hourly observational weather data. The data period is from 2020 to 2022 of 11 weather stations distributed in the four regions of Uganda. The data was accessed from the Ogimet data repository using the "climate" R-package. The automated procedures in the R-programming language environment allowed us to download user-defined data at a time resolution from an hourly to an annual basis. However, the raw data acquired cannot be used to learn rainfall patterns because it includes duplicates and non-uniform data. Therefore, this article presents a prepared and cleaned dataset that can be used for the prediction of short-term rainfall quantities in Uganda.

Keywords: Climate R-package; Dataset; Deep learning; Meteorology; Python; Short-term rainfall prediction.