Visibility Analysis and Time Series Forecasting
In one sentence. XGBoost, ARIMA and LSTM models forecast atmospheric visibility from station time series, with outputs reported as close to observed values.
Abstract
Visibility prediction and time series forecasting are two important fields in the domain of data analysis and machine learning. Visibility prediction deals with the estimation of atmospheric visibility or the distance over which objects can be clearly seen in a particular location, while time series forecasting involves predicting future values based on historical data. Both these fields have a wide range of applications, including transportation safety, air quality monitoring, and renewable energy management. However, the current prediction of visibility is mostly based on the numerical prediction method similar to the weather prediction [1]. In the present study the authors proposed a method using XGBoost(Extreme Gradient Boosting) and Unsupervised Models(ARIMA, ARMA, LSTM) models to build a weather visibility prediction system. The results obtained were very close to actual dataset.
Labels
- Topic
- Local & station forecasting
- Type
- New model or method
- Method
- Classical ML (trees, GP, linear, kernels), RNN / LSTM / ConvLSTM
- Time scale
- 6 h–3 days
- Domain
- Local / station
- Data
- Station / in-situ
- Status
- Research
- Identifiers
- DOI:10.32628/cseit2390321 OpenAlex:W4381052206
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.