Hybrid deep learning framework for weather forecast with rainfall prediction using weather bigdata analytics

Lalitha, C.; Ravindran, D.

doi:10.1007/s11042-023-17801-9

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ensemble methods, exemplified by EK-stars, leverage the strengths of individual classifiers, leading to enhanced predictions. Additionally, a hybrid DL framework for weather forecasting, specifically targeting rainfall prediction, was developed, integrating a modified planet optimization (MPO) algorithm for data preprocessing [6]. This step aimed to remove unwanted artifacts and improve input data quality.…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison of Various Machine Learning Models for Rainfall Prediction Using Wind Information

Jain

2024

IJSREM

View full text Add to dashboard Cite

Forecasting rainfall, crucial for agriculture, water management, and disaster preparedness, presents significant challenges due to intricate relationships often missed by conventional statistical methods. Hence, machine learning (ML) models offer promising alternatives, enhancing the precision and dependability of rainfall predictions. This paper presents a comprehensive comparison of various ML models with diverse model structures and regularization strategies for rainfall prediction in urban metropolitan cities. The results show that the random forest model, and gradient boosting model outperform the other models such as logistic regression, support vector machine (SVM), decision tree, K-nearest neighbor (KNN), Naive Bayes, linear SVM, and neural network in terms of accuracy. Validation accuracies of 75%, 77%, 68%, 78%, 76%, 78%, 74%, 75% and 76% were achieved for logistic regression, SVM, decision tree, random forest model, KNN, gradient boosting model, Naive Bayes, linear SVM, and neural network, respectively. The choice of ML models for rainfall prediction should consider the characteristics of the data, e.g. a lag feature for 20 days was employed that uses previous time steps to predict the next time step. The paper concludes that ML models, especially the random forest and gradient boosting models are powerful and robust tools for rainfall prediction in urban metropolitan cities. Key Words: rainfall prediction, wind information, machine learning, gradient boosting, random forest

show abstract

Section: Introductionmentioning

confidence: 99%

Performance Comparison of Various Machine Learning Models for Rainfall Prediction Using Wind Information

Jain

2024

IJSREM

View full text Add to dashboard Cite

show abstract

Method of Calculating Outdoor PM2.5 Concentration in Fresh Air Systems Based on Population Density Distribution Regions

Tang,

Guo,

Zhao

et al. 2024

Buildings

View full text Add to dashboard Cite

With the gradual increase in population density, population migration poses unprecedented challenges to urban environments and their capacity. The fresh air system effectively ensures fresh air in indoor environments. An important parameter affecting the selection of a fresh air filtration system is calculating particulate matter at a concentration of less than 2.5 μm (PM2.5). The PM2.5 concentration values of 31 cities in China from 2017 to 2020 were selected for analysis in this study. Based on mathematical induction and population density zoning, a new method that combines population density zoning is proposed, and the recommended constant K values for different regions are analyzed. The definition of K refers to the ratio of the outdoor design concentration value of PM2.5 to the annual average at different guarantee rates. The air filters for fresh air systems in five typical cities (Harbin, Beijing, Urumqi, Xi’an, Guangzhou) are also used as examples. The K values and selection differences under different recommendation methods are compared and analyzed. Under population migration and urbanization scenarios, the results indicate that the recommended K of the seven major regions method was optimal. Under these conditions, the recommended K values for five typical cities under strict and normal conditions differ from their average K values by 0.07 and 0.04, respectively. This method can accurately select fresh air filtration systems under different population densities; however, population density is related to factors such as policies and the economy and must be updated and revised regularly. On the whole, it provides reference values for the selection of PM2.5 design concentrations in fresh air systems under population distribution differentiation.

show abstract

Hybrid deep learning framework for weather forecast with rainfall prediction using weather bigdata analytics

Cited by 2 publications

References 18 publications

Performance Comparison of Various Machine Learning Models for Rainfall Prediction Using Wind Information

Performance Comparison of Various Machine Learning Models for Rainfall Prediction Using Wind Information

Method of Calculating Outdoor PM2.5 Concentration in Fresh Air Systems Based on Population Density Distribution Regions

Contact Info

Product

Resources

About