Hourly Rainfall Forecast Model Using Supervised Learning Algorithm

Zhao, Qingzhi; Liu, Yang; Yao, Wanqiang; Yao, Yibin

doi:10.1109/tgrs.2021.3054582

Cited by 46 publications

(28 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researchers have used parameters derived from the GNSS and radar for analysis [18], classification [8], and nowcasting [6] of the rainfall, storms, thunderstorms. The parameters derived from GNSS include zenith tropospheric delay (ZTD) [8], [17], precipitable water vapor [11], [19], [20], IWV [21], and IWV with vertical profiles of wet refractivity [6], to name a few. Most of these are related to multiclass classification and utilize several different features for this purpose.…”

Section: Introductionmentioning

confidence: 99%

Binary classification of rainfall time-series using machine learning algorithms

Hudnurkar¹,

Rayavarapu²

2022

IJECE

View full text Add to dashboard Cite

Summer monsoon rainfall contributes more than 75% of the annual rainfall in India. For the state of Maharashtra, India, this is more than 80% for almost all regions of the state. The high variability of rainfall during this period necessitates the classification of rainy and non-rainy days. While there are various approaches to rainfall classification, this paper proposes rainfall classification based on weather variables. This paper explores the use of support vector machine (SVM) and artificial neural network (ANN) algorithms for the binary classification of summer monsoon rainfall using common weather variables such as relative humidity, temperature, pressure. The daily data, for the summer monsoon months, for nineteen years, was collected for the Shivajinagar station of Pune in the state of Maharashtra, India. Classification accuracy of 82.1 and 82.8%, respectively, was achieved with SVM and ANN algorithms, for an imbalanced dataset. While performance parameters such as misclassification rate, F1 score indicate that better results were achieved with ANN, model parameter selection for SVM was less involved than ANN. Domain adaptation technique was used for rainfall classification at the other two stations of Maharashtra with the network trained for the Shivajinagar station. Satisfactory results for these two stations were obtained only after changing the training method for SVM and ANN.

show abstract

Section: Introductionmentioning

confidence: 99%

Binary classification of rainfall time-series using machine learning algorithms

Hudnurkar¹,

Rayavarapu²

2022

IJECE

View full text Add to dashboard Cite

show abstract

“…Therefore, the water content in the atmosphere is taken into account in global and regional meteorological models [16][17][18]. In practice, PW is used to increase the accuracy of weather forecasts [19][20][21][22][23][24][25][26] and explains the course and occurrence of extreme weather events, such as heavy precipitation, violent storms, super-cell thunderstorms and others [27][28][29][30][31][32][33]. Analyzing PW trends is also crucial because of the observed climate change [16,18,32,34].…”

Section: Introductionmentioning

confidence: 99%

Precipitable Water Content Climatology over Poland

2022

View full text Add to dashboard Cite

In this work, the high-resolution spatial and temporal variability of precipitable water (PW) over Poland is presented. PW is one of the key parameters of the atmosphere taken into account in thermodynamic and radiation models. The daily PW values from years 2001–2010, calculated with the use of the WRF model, were compared with PW from soundings. The WRF modeled PW is in close agreement with measurements for the whole column of the troposphere and for individual levels: below 1.5 km, 1.5–3 km, 3–6 km and 6–10 km. The best agreement is observed in the lower part of the troposphere, especially for winter months. At the levels of 1.5 km to 10 km, the WRF model overestimates the PW values throughout the year, whereas up to 1.5 km PW is underestimated. The study shows an increasing trend of PW annual values between 1983 and 2010, but the trend is statistically insignificant. A significant positive trend with a high Sen’s slope is observed for the summer season up to 3 km in the troposphere, along with a significant negative tendency for spring. The trends in PW over Poland and Central Europe identified in this study contribute to the ongoing discussion on the observed climate changes.

show abstract

“…To determine long-term hydrological system trends, Lin et al [ 11 ] proposed a hybrid grey model for forecasting annual maximum daily rainfall. Zhao et al [ 12 ] proposed an hourly rainfall forecast model based on a supervised learning algorithm to predict rainfall with high accuracy and high time resolution. For mathematical prediction models, grey system theory focuses mainly on issues, such as partial information unknowns [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

Causal Analysis and Prevention Measures for Extreme Heavy Rainstorms in Zhengzhou to Protect Human Health

Liu

2022

Behavioral Sciences

View full text Add to dashboard Cite

This study focused on the extreme heavy rainstorm that occurred in Zhengzhou in July 2021; approximately 380 people were killed or missing as a result of this storm. To investigate the evolution behaviors of this rainstorm and take corresponding prevention measures, several methods and models were adopted, including cloud modeling, preliminary hazard analysis (PHA), fault tree analysis (FTA), bow-tie modeling, and chaos theory. The main reasons for this rainstorm can be divided into the following three aspects: force majeure, such as terrain and extreme weather conditions, issues with city construction, and insufficient emergency rescue. The secondary disasters caused by this rainstorm mainly include urban water logging, river flooding, and mountain torrents and landslides. The main causes of the subway line-5 accident that occurred can be described as follows: the location of the stabling yard was low, the relevant rules and regulations of the subway were not ideal, insufficient attention was given to the early warning information, and the emergency response mechanism was not ideal. Rainstorms result from the cross-coupling of faults in humans, objects, the environment, and management subsystems, and the evolution process shows an obvious butterfly effect. To prevent disasters caused by rainstorms, the following suggestions should be adopted: vigorously improve the risk awareness and emergency response capabilities of leading cadres, improve the overall level of urban disaster prevention and mitigation, reinforce the existing reservoirs in the city, strengthen the construction of sponge cities, and improve the capacity of urban disaster emergency rescue.

show abstract

Hourly Rainfall Forecast Model Using Supervised Learning Algorithm

Cited by 46 publications

References 36 publications

Binary classification of rainfall time-series using machine learning algorithms

Binary classification of rainfall time-series using machine learning algorithms

Precipitable Water Content Climatology over Poland

Causal Analysis and Prevention Measures for Extreme Heavy Rainstorms in Zhengzhou to Protect Human Health

Contact Info

Product

Resources

About