scholarly journals Error Correction of Meteorological Data Obtained with Mini-AWSs Based on Machine Learning

2018 ◽  
Vol 2018 ◽  
pp. 1-8 ◽  
Author(s):  
Ji-Hun Ha ◽  
Yong-Hyuk Kim ◽  
Hyo-Hyuc Im ◽  
Na-Young Kim ◽  
Sangjin Sim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Error Correction ◽  
Atmospheric Pressure ◽  
Observation Interval ◽  
Meteorological Data ◽  
Weather Prediction ◽  
Observation Data ◽  
Pressure Data ◽  
Weather Forecasts ◽  
Weather Events

Severe weather events occur more frequently due to climate change; therefore, accurate weather forecasts are necessary, in addition to the development of numerical weather prediction (NWP) of the past several decades. A method to improve the accuracy of weather forecasts based on NWP is the collection of more meteorological data by reducing the observation interval. However, in many areas, it is economically and locally difficult to collect observation data by installing automatic weather stations (AWSs). We developed a Mini-AWS, much smaller than AWSs, to complement the shortcomings of AWSs. The installation and maintenance costs of Mini-AWSs are lower than those of AWSs; Mini-AWSs have fewer spatial constraints with respect to the installation than AWSs. However, it is necessary to correct the data collected with Mini-AWSs because they might be affected by the external environment depending on the installation area. In this paper, we propose a novel error correction of atmospheric pressure data observed with a Mini-AWS based on machine learning. Using the proposed method, we obtained corrected atmospheric pressure data, reaching the standard of the World Meteorological Organization (WMO; ±0.1 hPa), and confirmed the potential of corrected atmospheric pressure data as an auxiliary resource for AWSs.

scholarly journals Automatic Regional Interpretation and Forecasting System Supported by Machine Learning

Atmosphere ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 793
Author(s):  
Chao Yan ◽  
Jing Feng ◽  
Kaiwen Xia ◽  
Chaofan Duan
Keyword(s):  
Machine Learning ◽  
Meteorological Data ◽  
Weather Prediction ◽  
Weather Forecast ◽  
Forecast Model ◽  
Support Vector ◽  
Observation Data ◽  
Forecasting System ◽  
Weather Changes ◽  
Model Output Statistics

The Model Output Statistics (MOS) model is a dynamic statistical weather forecast model based on multiple linear regression technology. It is greatly affected by the selection of parameters and predictors, especially when the weather changes drastically, or extreme weather occurs. We improved the traditional MOS model with the machine learning method to enhance the capabilities of self-learning and generalization. Simultaneously, multi-source meteorological data were used as the input to the model to improve the data quality. In the experiment, we selected the four areas of Nanjing, Beijing, Chengdu, and Guangzhou for verification, with the numerical weather prediction (NWP) products and observation data from automatic weather stations (AWSs) used to predict the temperature and wind speed in the next 24 h. From the experiment, it can be seen that the accuracy of the prediction values and speed of the method were improved by the ML-MOS. Finally, we compared the ML-MOS model with neural networks and support vector machine (SVM), the results show that the prediction result of the ML-MOS model is better than that of the above two models.

Using neural networks for postprocessing of numerical weather predictions in complex terrain

2020 ◽  
Author(s):  
Jonas Bhend ◽  
Christoph Spirig ◽  
Max Hürlimann ◽  
Lionel Moret ◽  
Mark Liniger
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Complex Terrain ◽  
Weather Prediction ◽  
Lessons Learned ◽  
Swiss Alps ◽  
Local Effects ◽  
Weather Forecasts ◽  
Numerical Weather ◽  
Available Information

<p>Weather forecasts have been steadily improving in quality over the last decades. These ongoing improvements are due to advances in numerical weather prediction (NWP) and the advent of ever more powerful supercomputers that allow simulating future weather and its uncertainty with increasing resolution and using ensemble approaches. Such physics-based computer models, however, are not free of systematic errors. Statistical postprocessing can be used to calibrate NWP forecasts to further improve forecast quality and better exploit the available information. Here we present results from several explorative deep learning studies using artificial neural networks (ANN) to calibrate high resolution forecasts of temperature, precipitation, wind, and cloud cover in Switzerland. These first attempts at ANN-based postprocessing help us to understand the strengths and weaknesses of machine learning and are the basis to build more complex and comprehensive statistical models accounting for local effects in complex terrain such as the Swiss Alps. In all cases, ANN leads to significant improvements over the direct NWP output. While the improvement is comparable in magnitude with improvements achieved with conventional postprocessing approaches, ANN-based postprocessing is easier to generalize in space for a calibration of forecasts also at unobserved sites. In addition to the results of the postprocessing, we will also discuss the lessons learned so far in using machine learning for this particular problem.</p>

scholarly journals A Fingerprinting Technique for Major Weather Events

2007 ◽  
Vol 46 (7) ◽  
pp. 1053-1066 ◽  
Author(s):  
Benjamin Root ◽  
Paul Knight ◽  
George Young ◽  
Steven Greybush ◽  
Richard Grumm ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Numerical Weather Prediction ◽  
Clustering Algorithm ◽  
Weather Prediction ◽  
Weather Forecasts ◽  
Numerical Weather ◽  
Middle Atlantic ◽  
Weather Events ◽  
Operational Forecasting ◽  
Multimodel Ensembles

Abstract Advances in numerical weather prediction have occurred on numerous fronts, from sophisticated physics packages in the latest mesoscale models to multimodel ensembles of medium-range predictions. Thus, the skill of numerical weather forecasts continues to increase. Statistical techniques have further increased the utility of these predictions. The availability of large atmospheric datasets and faster computers has made pattern recognition of major weather events a feasible means of statistically enhancing the value of numerical forecasts. This paper examines the utility of pattern recognition in assisting the prediction of severe and major weather in the Middle Atlantic region. An important innovation in this work is that the analog technique is applied to NWP forecast maps as a pattern-recognition tool rather than to analysis maps as a forecast tool. A technique is described that employs a new clustering algorithm to objectively identify the anomaly patterns or “fingerprints” associated with past events. The potential refinement and applicability of this method as an operational forecasting tool employed by comparing numerical weather prediction forecasts with fingerprints already identified for major weather events are also discussed.

scholarly journals A Machine-Learning Approach Combining Wavelet Packet Denoising with Catboost for Weather Forecasting

Atmosphere ◽  
2021 ◽  
Vol 12 (12) ◽  
pp. 1618
Author(s):  
Dan Niu ◽  
Li Diao ◽  
Zengliang Zang ◽  
Hongshu Che ◽  
Tianbao Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Weather Forecasting ◽  
Human Life ◽  
Wavelet Packet ◽  
Weather Prediction ◽  
Convergence Time ◽  
Observation Data ◽  
Initial State ◽  
Historical Observation ◽  
Meteorological Elements

Accurate forecasting of future meteorological elements is critical and has profoundly affected human life in many aspects from rainstorm warning to flight safety. The conventional numerical weather prediction (NWP) sometimes leads to unsatisfactory performance due to inappropriate initial state settings. In this paper, a short-term weather forecasting model based on wavelet packet denoising and Catboost is proposed, which takes advantage of the fusion information combining the historical observation data with the prior knowledge from NWP. The feature selection and spatiotemporal feather addition are also explored to further improve performance. The proposed method is evaluated on the datasets provided by Beijing weather stations. Experimental results demonstrate that compared with many deep-learning or machine-learning methods such as LSTM, Seq2Seq, and random forest, the proposed Catboost model incorporated with wavelet packet denoising can achieve shorter convergence time and higher prediction accuracy.

Analysis of Gust Characteristics and Forecast Correction for the 2022 Olympic and Paralympic Winter Games in Zhangjiakou

2020 ◽  
Author(s):  
Jiarui Li ◽  
Quan Dong ◽  
Rong Li
Keyword(s):  
Wind Speed ◽  
Weather Prediction ◽  
Numerical Weather Prediction Model ◽  
Original Model ◽  
Observation Data ◽  
Systematic Bias ◽  
High Demand ◽  
Scaling Method ◽  
Weather Forecasts ◽  
The Relationship

<p>In order to meet the high demand for advanced weather forecasts in the 2022 Olympic and Paralympic Winter Games, hourly wind observation data of some venues in Zhangjiakou City  is analyzed. Based on the specific gust characteristics in these venues, deviation of numerical weather prediction model is initially calculated to demonstrate the systematic bias of instantaneous wind speed forecasts derived from ECMWF. Additionally, a statistical down scaling method is further used by establishing the relationship between model forecasts and observation. Then independent samples are imported to the established equations to generate revised outputs. Tests show that the established equations have a better effect on forecasting the instantaneous wind speed than original model outputs and the corrected outputs have significantly better accuracy in predicting the instantaneous wind speed in the studied area.</p>

scholarly journals Can deep learning beat numerical weather prediction?

2021 ◽  
Vol 379 (2194) ◽  
pp. 20200097
Author(s):  
M. G. Schultz ◽  
C. Betancourt ◽  
B. Gong ◽  
F. Kleinert ◽  
M. Langguth ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Weather Prediction ◽  
Weather Data ◽  
Climate Modelling ◽  
Weather Forecasts ◽  
Numerical Weather ◽  
Numerical Weather Models ◽  
Weather And Climate ◽  
Weather Models

The recent hype about artificial intelligence has sparked renewed interest in applying the successful deep learning (DL) methods for image recognition, speech recognition, robotics, strategic games and other application areas to the field of meteorology. There is some evidence that better weather forecasts can be produced by introducing big data mining and neural networks into the weather prediction workflow. Here, we discuss the question of whether it is possible to completely replace the current numerical weather models and data assimilation systems with DL approaches. This discussion entails a review of state-of-the-art machine learning concepts and their applicability to weather data with its pertinent statistical properties. We think that it is not inconceivable that numerical weather models may one day become obsolete, but a number of fundamental breakthroughs are needed before this goal comes into reach. This article is part of the theme issue ‘Machine learning for weather and climate modelling’.

scholarly journals Using 3D-Var Data Assimilation for Improving the Accuracy of Initial Condition of Weather Research and Forecasting (WRF) Model in Java Region (Case Study : 23 January 2015)

2016 ◽  
Vol 30 (2) ◽  
pp. 112
Author(s):  
Novvria Sagita ◽  
Rini Hidayati ◽  
Rahmat Hidayat ◽  
Indra Gustari ◽  
Fatkhuroyan Fatkhuroyan
Keyword(s):  
Data Assimilation ◽  
Meteorological Data ◽  
Weather Prediction ◽  
Dew Point ◽  
Radiosonde Data ◽  
Weather Research And Forecasting ◽  
Observation Data ◽  
Initial Condition ◽  
Condition Model ◽  
Weather Research

Weather Research and Forecasting (WRF) is a numerical weather prediction model developed by various parties due to its open source, but the WRF has the disadvantage of low accuracy in weather prediction. One reason of low accuracy  of model is inaccuracy initial condition model to the actual atmospheric conditions. Techniques to improve the initial condition model is the observation data assimilation. In this study, we used three-dimensional variational (3D-Var) to perform data assimilation of some observation data. Observational data used in data assimilation are observation data from basic stations, non-basic stations, radiosonde data, and The Binary Universal Form for the Representation of meteorological data (BUFR) data from the National Centers for Environmental Prediction (NCEP) , and aggregate observation data from all stations. The aim of this study compares the effect of data assimilation with different data observation on January 23, 2015 at 00.00 UTC for Java island region. The results showed that changes root mean square error (RMSE) of surface temperature from 2° C to 1.7° C - 2.4° C, dew point from 2.1o C to 1.9o  C - 1.4o C, relative humidity from 16.1% to 3.5% - 14.5% after the data assimilation.

scholarly journals Improved Correction of Atmospheric Pressure Data Obtained by Smartphones through Machine Learning

2016 ◽  
Vol 2016 ◽  
pp. 1-12 ◽  
Author(s):  
Yong-Hyuk Kim ◽  
Ji-Hun Ha ◽  
Yourim Yoon ◽  
Na-Young Kim ◽  
Hyo-Hyuc Im ◽  
...  
Keyword(s):  
Machine Learning ◽  
Regression Analysis ◽  
Atmospheric Pressure ◽  
Absolute Error ◽  
Time Of Day ◽  
Support Vector ◽  
Pressure Data ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Em Clustering

A correction method using machine learning aims to improve the conventional linear regression (LR) based method for correction of atmospheric pressure data obtained by smartphones. The method proposed in this study conducts clustering and regression analysis with time domain classification. Data obtained in Gyeonggi-do, one of the most populous provinces in South Korea surrounding Seoul with the size of 10,000 km2, from July 2014 through December 2014, using smartphones were classified with respect to time of day (daytime or nighttime) as well as day of the week (weekday or weekend) and the user’s mobility, prior to the expectation-maximization (EM) clustering. Subsequently, the results were analyzed for comparison by applying machine learning methods such as multilayer perceptron (MLP) and support vector regression (SVR). The results showed a mean absolute error (MAE) 26% lower on average when regression analysis was performed through EM clustering compared to that obtained without EM clustering. For machine learning methods, the MAE for SVR was around 31% lower for LR and about 19% lower for MLP. It is concluded that pressure data from smartphones are as good as the ones from national automatic weather station (AWS) network.

scholarly journals Data assimilation of stratospheric constituents: a review

2007 ◽  
Vol 7 (22) ◽  
pp. 5745-5773 ◽  
Author(s):  
W. A. Lahoz ◽  
Q. Errera ◽  
R. Swinbank ◽  
D. Fonteyn
Keyword(s):  
Data Assimilation ◽  
Numerical Weather Prediction ◽  
Chemical Constituents ◽  
Meteorological Data ◽  
Weather Prediction ◽  
Chemical Model ◽  
Weather Forecasts ◽  
Numerical Weather ◽  
State Of Affairs ◽  
Prediction Approach

Abstract. The data assimilation of stratospheric constituents is reviewed. Several data assimilation methods are introduced, with particular consideration to their application to stratospheric constituent measurements. Differences from meteorological data assimilation are outlined. Historically, two approaches have been used to carry out constituent assimilation. One approach has carried constituent assimilation out as part of a Numerical Weather Prediction system; the other has carried it out in a standalone chemical model, often with a more sophisticated representation of chemical processes. Whereas the aim of the Numerical Weather Prediction approach has been to improve weather forecasts, the aims of the chemical model approach have included providing chemical forecasts and analyses of chemical constituents. A range of constituent assimilation systems developed in these two areas is presented and strengths and weaknesses discussed. The use of stratospheric constituent data assimilation to evaluate models, observations and analyses, and to provide analyses of constituents, monitor ozone, and make ozone forecasts is discussed. Finally, the current state of affairs is assessed, future directions are discussed, and potential key drivers identified.

scholarly journals Machine Learning-Based Turbulence-Risk Prediction Method for the Safe Operation of Aircrafts

2021 ◽  
Author(s):  
Shinya Mizuno ◽  
Haruka Ohba ◽  
Koji Ito
Keyword(s):  
Machine Learning ◽  
Human Resources ◽  
Meteorological Data ◽  
Prediction Method ◽  
Principal Component ◽  
Training Data ◽  
Support Vector ◽  
Observation Data ◽  
Safe Operation ◽  
Effective Use

Abstract Customer comfort is an important requirement for airlines, and avoiding and mitigating aircraft shaking have always been crucial in this regard. In particular, managing aircraft operations during turbulence is a major issue for airlines. We propose a method for predicting the occurrence of turbulence to support the safe and comfortable operation of aircrafts. Our method integrates meteorological data from Japan and turbulence information provided by Fuji Dream Airlines. Because turbulence occurs rarely, we define a risk cluster that includes turbulence observation data and use it as turbulence training data. Hence, we first estimated the risk cluster, then performed a principal component analysis (PCA) on meteorological data to obtain a projection matrix \(W\) for reducing data dimensions. Using the turbulence-occurrence indicator and the meteorological data coordinates linear transformed by \(W\), we calculated the risk cluster using the k-means method which, in turn, was used in conjunction with support vector classification (SVC) to predict the turbulence-risk dates based on meteorological data from 2019. The results revealed that the days with turbulence risks were accurately identified from the meteorological data; thus, we believe that this method can help support the safe operation of aircrafts. Furthermore, we believe this study will lead to the development of human resources by providing a guide for making safety decisions through the effective use of aviation data.

Sign in / Sign up

Export Citation Format

Share Document