Forecasting the Daily Maximal and Minimal Temperatures from Radiosonde Measurements Using Neural Networks
In one sentence. Dense neural networks predict daily max and min 2 m temperatures from radiosonde profiles up to 500 days ahead, beating persistence but not climatology beyond day 2-3.
Abstract
This study investigates the potential of direct prediction of daily extremes of temperature at 2 m from a vertical profile measurement using neural networks (NNs). The analysis is based on 3800 daily profiles measured in the period 2004–2019. Various setups of dense sequential NNs are trained to predict the daily extremes at different lead times ranging from 0 to 500 days into the future. The short- to medium-range forecasts rely mainly on the profile data from the lowest layer—mostly on the temperature in the lowest 1 km. For the long-range forecasts (e.g., 100 days), the NN relies on the data from the whole troposphere. The error increases with forecast lead time, but at the same time, it exhibits periodic behavior for long lead times. The NN forecast beats the persistence forecast but becomes worse than the climatological forecast on day two or three. The forecast slightly improves when the previous-day measurements of temperature extremes are added as a predictor. The best forecast is obtained when the climatological value is added as well, with the biggest improvement in the long-term range where the error is constrained to the climatological forecast error.
Labels
- Topic
- Local & station forecasting, Sub-seasonal to seasonal
- Type
- New model or method
- Method
- Classical ML (trees, GP, linear, kernels)
- Time scale
- 3–15 days, 2 weeks–2 months, Seasonal to annual
- Domain
- Local / station
- Data
- Station / in-situ
- Status
- Research
- Identifiers
- DOI:10.3390/app112210852 OpenAlex:W3214317286
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.