Machine learning for total cloud cover prediction
- URL: http://arxiv.org/abs/2001.05948v1
- Date: Thu, 16 Jan 2020 17:13:37 GMT
- Title: Machine learning for total cloud cover prediction
- Authors: \'Agnes Baran, Sebastian Lerch, Mehrez El Ayari and S\'andor Baran
- Abstract summary: We investigate the performance of post-processing using multilayer perceptron (MLP) neural networks, gradient boosting machines (GBM) and random forest (RF) methods.
Compared to the raw ensemble, all calibration methods result in a significant improvement in forecast skill.
RF models provide the smallest increase in predictive performance, while POLR and GBM approaches perform best.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Accurate and reliable forecasting of total cloud cover (TCC) is vital for
many areas such as astronomy, energy demand and production, or agriculture.
Most meteorological centres issue ensemble forecasts of TCC, however, these
forecasts are often uncalibrated and exhibit worse forecast skill than ensemble
forecasts of other weather variables. Hence, some form of post-processing is
strongly required to improve predictive performance. As TCC observations are
usually reported on a discrete scale taking just nine different values called
oktas, statistical calibration of TCC ensemble forecasts can be considered a
classification problem with outputs given by the probabilities of the oktas.
This is a classical area where machine learning methods are applied. We
investigate the performance of post-processing using multilayer perceptron
(MLP) neural networks, gradient boosting machines (GBM) and random forest (RF)
methods. Based on the European Centre for Medium-Range Weather Forecasts global
TCC ensemble forecasts for 2002-2014 we compare these approaches with the
proportional odds logistic regression (POLR) and multiclass logistic regression
(MLR) models, as well as the raw TCC ensemble forecasts. We further assess
whether improvements in forecast skill can be obtained by incorporating
ensemble forecasts of precipitation as additional predictor. Compared to the
raw ensemble, all calibration methods result in a significant improvement in
forecast skill. RF models provide the smallest increase in predictive
performance, while MLP, POLR and GBM approaches perform best. The use of
precipitation forecast data leads to further improvements in forecast skill and
except for very short lead times the extended MLP model shows the best overall
performance.
Related papers
- FuXi Weather: A data-to-forecast machine learning system for global weather [13.052716094161886]
FuXi Weather is a machine learning weather forecasting system that assimilates data from multiple satellites.
FuXi Weather consistently outperforms ECMWF HRES in observation-sparse regions, such as central Africa.
arXiv Detail & Related papers (2024-08-10T07:42:01Z) - Enhancing multivariate post-processed visibility predictions utilizing CAMS forecasts [0.0]
Weather forecasts increasingly incorporate ensemble predictions of visibility.
Post-processing is recommended to enhance the reliability and accuracy of predictions.
Our study confirms that post-processed forecasts are substantially superior to raw and climatological predictions.
arXiv Detail & Related papers (2024-06-20T09:57:49Z) - Aardvark weather: end-to-end data-driven weather forecasting [30.219727555662267]
Aardvark Weather is an end-to-end data-driven weather prediction system.
It ingests raw observations and outputs global gridded forecasts and local station forecasts.
It can be optimised end-to-end to maximise performance over quantities of interest.
arXiv Detail & Related papers (2024-03-30T16:41:24Z) - ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast.
We also introduce ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples.
Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
arXiv Detail & Related papers (2024-02-02T10:34:13Z) - FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather
Forecasting [56.73502043159699]
This work presents FengWu-GHR, the first data-driven global weather forecasting model running at the 0.09$circ$ horizontal resolution.
It introduces a novel approach that opens the door for operating ML-based high-resolution forecasts by inheriting prior knowledge from a low-resolution model.
The hindcast of weather prediction in 2022 indicates that FengWu-GHR is superior to the IFS-HRES.
arXiv Detail & Related papers (2024-01-28T13:23:25Z) - When Rigidity Hurts: Soft Consistency Regularization for Probabilistic
Hierarchical Time Series Forecasting [69.30930115236228]
Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting.
Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions.
We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
arXiv Detail & Related papers (2023-10-17T20:30:16Z) - Generative ensemble deep learning severe weather prediction from a
deterministic convection-allowing model [0.0]
Method combines conditional generative adversarial networks (CGANs) with a convolutional neural network (CNN) to post-process convection-allowing model (CAM) forecasts.
The CGANs are designed to create synthetic ensemble members from deterministic CAM forecasts.
The method produced skillful predictions with up to 20% Brier Skill Score (BSS) increases compared to other neural-network-based reference methods.
arXiv Detail & Related papers (2023-10-09T18:02:11Z) - Statistical post-processing of visibility ensemble forecasts [0.0]
We investigate the predictive performance of locally, semi-locally and regionally trained proportional odds logistic regression (POLR) and multilayer perceptron (MLP) neural network classifiers.
We show that while climatological forecasts outperform the raw ensemble by a wide margin, post-processing results in further substantial improvement in forecast skill.
arXiv Detail & Related papers (2023-05-24T16:41:36Z) - Forecast reconciliation for vaccine supply chain optimization [61.13962963550403]
Vaccine supply chain optimization can benefit from hierarchical time series forecasting.
Forecasts of different hierarchy levels become incoherent when higher levels do not match the sum of the lower levels forecasts.
We tackle the vaccine sale forecasting problem by modeling sales data from GSK between 2010 and 2021 as a hierarchical time series.
arXiv Detail & Related papers (2023-05-02T14:34:34Z) - Beyond S-curves: Recurrent Neural Networks for Technology Forecasting [60.82125150951035]
We develop an autencoder approach that employs recent advances in machine learning and time series forecasting.
S-curves forecasts largely exhibit a mean average percentage error (MAPE) comparable to a simple ARIMA baseline.
Our autoencoder approach improves the MAPE by 13.5% on average over the second-best result.
arXiv Detail & Related papers (2022-11-28T14:16:22Z) - When Rigidity Hurts: Soft Consistency Regularization for Probabilistic
Hierarchical Time Series Forecasting [69.30930115236228]
Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting.
Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions.
We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
arXiv Detail & Related papers (2022-06-16T06:13:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.