Datasets
Standard Dataset
Dataset for 4G Signal Strength Prediction Based on Rain Attenuation and Winter Conditions(Nanjing，China，2023－2025)
- Citation Author(s):
- Submitted by:
- Beifen Zhou
- Last updated:
- Wed, 03/05/2025 - 02:38
- DOI:
- 10.21227/v1sa-6t94
- Data Format:
- License:
27 Views- Categories:
- Keywords:
Abstract
Solar-powered insecticidal lamps have been widely used in agricultural pest control systems, where stable 4G connectivity is critical for real-time transmission of multi-source field data (soil parameters, pest images, and environmental metrics). However, the lack of reliable 4G signal strength datasets in agricultural scenarios, especially under rainfall conditions that cause signal degradation, poses a great challenge to deployment planning and network reliability. This project fills this gap by constructing the first agricultural 4G signal strength dataset under different weather conditions. Using UAV-assisted surveys and manual collection of 4G signal strength data, we systematically collect 4G signal metrics (RSRP) synchronized with precise latitude and longitude coordinates and weather parameters. This dataset enables signal mapping and rain-induced attenuation modeling based on spatial interpolation.
The dataset covers three different agricultural scenarios for the winter months of 2023 to 2025 and contains a total of 65,676 valid data. The data fields specifically include: timestamp (time), user identification (username), 4G signal strength value (rsrp in dBm), latitude/longitude coordinates (longitude/latitude), weather type (type, with enumeration values of snow/rain), precipitation (precip in mm), temperature ( temperature, in °C) and humidity (humidity, in %). Among them, rsrp characterizes the 4G signal strength at a specific geographic location, and temperature and humidity correspond to real-time environmental parameters. To address the problem of missing values in the raw data, cleaning has been accomplished by deleting entries containing missing fields. The dataset aims to construct a 4G signal strength prediction model for 4G networks under rain and snow by correlating spatialized signal strength with meteorological parameters, which provides support for communication reliability analysis in agricultural scenarios.
