Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360764524> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4360764524 abstract "Temperature prediction is critical for many industrial and everyday applications. Numerical Weather Prediction (NWP) models using high-performance computing is the most sought technique to forecast weather, including temperature. However, NWP is complex in nature and computationally expensive. In this paper, the temperature is forecast using data-driven Machine Learning techniques, which are not computationally intensive and are further accelerated using GPUs. Two deep learning models: A stacked Long Short-Term Memory (LSTM) and Random Forest Regressor (RFR), are developed and validated using the standard ERA5 data (at 850hPa, above the atmospheric boundary layer). In addition, the models are tested against the ground-level observations (inside the atmospheric boundary layer) for twenty different locations in India. The performance of univariate and multivariate models is also analyzed for the real-time dataset. Root Mean Square Error (RMSE) obtained by the LSTM and RFR are 0.47 and 0.23, respectively, for ERA5 data. When compared to the numerical weather prediction model - operational IFS, the RMSE using LSTM and RFR is smaller by 65% and 83%, respectively. The LSTM and RFR models forecast temperature with an average RMSE of 0.7 for the real-time data at twenty locations. The GPU-enabled LSTM model performed 64 times faster than the CPU-enabled model. The developed RNN models are made publicly available at https://github.com/arasuadrian/RNN-Models." @default.
- W4360764524 created "2023-03-25" @default.
- W4360764524 creator A5013004524 @default.
- W4360764524 creator A5064632576 @default.
- W4360764524 creator A5090492507 @default.
- W4360764524 date "2022-12-01" @default.
- W4360764524 modified "2023-10-16" @default.
- W4360764524 title "Application of Machine Learning Techniques in Temperature Forecast" @default.
- W4360764524 cites W2023645751 @default.
- W4360764524 cites W2064675550 @default.
- W4360764524 cites W2100798126 @default.
- W4360764524 cites W2903132559 @default.
- W4360764524 cites W2954192867 @default.
- W4360764524 cites W2980189150 @default.
- W4360764524 cites W3011075401 @default.
- W4360764524 cites W3080366021 @default.
- W4360764524 cites W3080707674 @default.
- W4360764524 cites W3096902305 @default.
- W4360764524 cites W3132280960 @default.
- W4360764524 doi "https://doi.org/10.1109/icmla55696.2022.00083" @default.
- W4360764524 hasPublicationYear "2022" @default.
- W4360764524 type Work @default.
- W4360764524 citedByCount "0" @default.
- W4360764524 crossrefType "proceedings-article" @default.
- W4360764524 hasAuthorship W4360764524A5013004524 @default.
- W4360764524 hasAuthorship W4360764524A5064632576 @default.
- W4360764524 hasAuthorship W4360764524A5090492507 @default.
- W4360764524 hasConcept C105795698 @default.
- W4360764524 hasConcept C108583219 @default.
- W4360764524 hasConcept C119857082 @default.
- W4360764524 hasConcept C121332964 @default.
- W4360764524 hasConcept C139945424 @default.
- W4360764524 hasConcept C147947694 @default.
- W4360764524 hasConcept C153294291 @default.
- W4360764524 hasConcept C154945302 @default.
- W4360764524 hasConcept C161584116 @default.
- W4360764524 hasConcept C169258074 @default.
- W4360764524 hasConcept C199163554 @default.
- W4360764524 hasConcept C21001229 @default.
- W4360764524 hasConcept C33923547 @default.
- W4360764524 hasConcept C41008148 @default.
- W4360764524 hasConceptScore W4360764524C105795698 @default.
- W4360764524 hasConceptScore W4360764524C108583219 @default.
- W4360764524 hasConceptScore W4360764524C119857082 @default.
- W4360764524 hasConceptScore W4360764524C121332964 @default.
- W4360764524 hasConceptScore W4360764524C139945424 @default.
- W4360764524 hasConceptScore W4360764524C147947694 @default.
- W4360764524 hasConceptScore W4360764524C153294291 @default.
- W4360764524 hasConceptScore W4360764524C154945302 @default.
- W4360764524 hasConceptScore W4360764524C161584116 @default.
- W4360764524 hasConceptScore W4360764524C169258074 @default.
- W4360764524 hasConceptScore W4360764524C199163554 @default.
- W4360764524 hasConceptScore W4360764524C21001229 @default.
- W4360764524 hasConceptScore W4360764524C33923547 @default.
- W4360764524 hasConceptScore W4360764524C41008148 @default.
- W4360764524 hasLocation W43607645241 @default.
- W4360764524 hasOpenAccess W4360764524 @default.
- W4360764524 hasPrimaryLocation W43607645241 @default.
- W4360764524 hasRelatedWork W2950495821 @default.
- W4360764524 hasRelatedWork W2968586400 @default.
- W4360764524 hasRelatedWork W2995227436 @default.
- W4360764524 hasRelatedWork W3211546796 @default.
- W4360764524 hasRelatedWork W4223564025 @default.
- W4360764524 hasRelatedWork W4226246648 @default.
- W4360764524 hasRelatedWork W4281616679 @default.
- W4360764524 hasRelatedWork W4281986673 @default.
- W4360764524 hasRelatedWork W4311106074 @default.
- W4360764524 hasRelatedWork W4322727400 @default.
- W4360764524 isParatext "false" @default.
- W4360764524 isRetracted "false" @default.
- W4360764524 workType "article" @default.