Asian Soybean Rust Spores Data - Parana,Brazil

This dataset contains processed monitoring data of Phakopsora pachyrhizi (Asian soybean rust) collected through the IDR-Paraná Alerta Ferrugem network in the state of Paraná. The monitoring system consists of physical spore collectors distributed across soybean-producing regions, each recording the first detection date of detected spores along with its geographic coordinates. The original monitoring data were obtained from publicly available records provided by the Alerta Ferrugem program. The raw dataset is organized as one CSV file per crop season, covering the following soybean seasons: 2020–2021 2021–2022 2022–2023 Paraná is located in southern Brazil and borders the states of São Paulo, Santa Catarina, and Mato Grosso do Sul, as well as Paraguay and Argentina. The monitoring network provides standardized spatial coverage across the state's main soybean-producing regions. To ensure consistency and suitability for machine learning and epidemiological modeling, several preprocessing steps were applied, including: normalization of detection dates; spatial aggregation of nearby collectors into a regular geographic grid; removal of inconsistent or incomplete records; computation of temporal attributes derived from the crop season timeline. The processed dataset was used for both model training and evaluation in experiments on spatio-temporal prediction of Asian soybean rust spread. Dataset Fields The processed CSV files include the following main attributes: Field Description LatitudeDecimal Latitude of the monitoring collector in decimal degrees LongitudeDecimal Longitude of the monitoring collector in decimal degrees FirstSporeDate First date on which P. pachyrhizi spores were detected DetectionStatus Binary or categorical indication of spore detection SeasonStart Initial date of the soybean crop season DaysAfterSeasonStart Number of days elapsed since the start of the crop season The dataset is intended for research purposes involving epidemiological analysis, spatial modeling, graph-based learning, and forecasting of soybean rust dissemination.