Bibliographic Details
| Title: |
IRF-LSTM: enhanced regularization function in LSTM to predict the rainfall. |
| Authors: |
Bhimavarapu, Usharani1 (AUTHOR) ushareddy@kluniversity.in |
| Superior Title: |
Neural Computing & Applications. Nov2022, Vol. 34 Issue 22, p20165-20177. 13p. |
| Subject Terms: |
*RAINFALL, *EARTH temperature, *OCEAN temperature, *ATMOSPHERE, *SEAWATER |
| Abstract: |
Sea surface temperature modifies the air in the earth's atmosphere. EINi η ~ o signs in the sea surface temperature spread the warm water in the ocean and take the rain. Several existing models forecast rainfall using statistical analysis, machine learning, and deep learning. Neural Networks are powerful models that are extensively used for solving problems in many areas but still suffer from significant weaknesses. The presence of nonlinear hidden layers makes the deep networks prone to severe overfitting. This research used a rainfall dataset and reduced the issue of overfitting by using the improved regularized function. The main contribution of this research is proposing the enhanced regularized function to predict rainfall to reduce the bias. To evaluate the performance of the proposed Improved Regularization Function Long Short-Term Memory (IRF-LSTM) to forecast rainfall are RMSE, MAE, NSE, r. The output performance of the proposed IRF-LSTM is surpassed other state-of-the-art methods and is verified as by far the best implementation. [ABSTRACT FROM AUTHOR] |
|
Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Academic Search Premier |
|
Full text is not displayed to guests. |
Login for full access.
|