An Approach for Rainfall Prediction Using Long Short Term Memory Neural Network

Samad, Anjali; Bhagyanidhi,; Gautam, Vaibhav; Jain, Piyush; Sangeeta, .; Sarkar, Kanishka

doi:10.1109/iccca49541.2020.9250809

Cited by 19 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other LSTM studies, while Samad et al (2020) and forecasted precipitation using LSTMs for Australia and Bangladesh, respectively, Oswalt Manoj and Ananth (2020) utilized convolutional LSTMs for India. In a comparative study for Thimphu, Bhutan, Chhetri et al (2020) trained ANNs, LSTMs, BiLSTMs, and GRUs, as well as a BiLSTM-GRU combination.…”

Section: D Rainfall Forecastingmentioning

confidence: 99%

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

Sit¹,

Demiray²,

Demir³

2022

Preprint

View full text Add to dashboard Cite

With technological enhancements, the volume, velocity, and variety (3Vs) of the raw digital Earth data have increased in recent years. Due to the increased availability of computer resources and the growing popularity of deep learning applications, this data has been a crucial source for data-driven studies that have transformed the fields of climate and earth science. One of the critical data sources is precipitation supporting climate and earth science studies on modeling, forecasting, and preparedness for extreme events (i.e., floods, droughts, pollution transport). In this study, we worked on an extensive review of manuscripts focusing on use of deep learning methods to tackle challenges either to improve the quality or extrapolate (forecast) rainfall datasets. The purpose of this study is to summarize the most recent developments in deep learning approaches for forecasting rainfall or improving rainfall datasets, as well as highlighting issues, shortcomings, and open questions with insightful recommendations for future directions.

show abstract

Section: D Rainfall Forecastingmentioning

confidence: 99%

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

Sit¹,

Demiray²,

Demir³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The most effective optimizer and hyperparameters as identified from the experiments are selected to predict precipitation using the RNN variant model. Also, the results of the proposed RNN variants and ensemble models are compared in terms of error metrics, with those from publications by S. Aswin et al [26], Haq et al [27], Ouma et al [29], Samad A, et al [30], Dada et al [21], and Saha et al [31]. The comparative analysis demonstrates that the proposed model outperforms all other models and techniques under comparison.…”

Section: Introductionmentioning

confidence: 97%

“…Both models performed well and predicted the precipitation with R2 values of 0.8610 and 0.7825 respectively. Samad et al [30] built a model for rainfall prediction based on an Australian dataset for the regions of Albany, Walpole, and Witchcliffe. The LSTM network outperformed the ANN after comparison using different performance measures including MSE, RMSE and MAE.…”

Section: Introductionmentioning

confidence: 99%

“…Time-series data-based precipitation forecast can aid in the decision-making processes associated with flood and disaster to manage, flood, control floods and plan safety preparations [31,32]. Also, based on a survey of related work [21,[25][26][27][28][29][30][31], it has been determined that articles for predicting precipitation use DL neural network models such as LSTM, ANN, GRU, FFNN, RNN, ENN, and CFNN. Also, measures such as RMSE and MAE are used to assess the expected precipitation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Precipitation forecast using RNN variants by analyzing Optimizers and Hyperparameters for Time-series based Climatological Data

Subha,

Saudia

2024

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Flood is a significant problem in many regions of the world for the catastrophic damage it causes to both property and human lives; excessive precipitation being the major cause. The AI technologies, Deep Learning Neural Networks and Machine Learning algorithms attempt realistic solutions to numerous disaster management challenges. This paper works on RNN- based rainfall/ precipitation forecasting models by investigating the performances of various Recurrent Neural Network (RNN) architectures, Bidirectional RNN (BRNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and ensemble models such as BRNN-GRU, BRNN-LSTM, LSTM-GRU, BRNN-LSTM-GRU using NASAPOWER datasets of Andhra Pradesh (AP) and Tamil Nadu (TN) in India. The different stages in the workflow of the methodology are Data collection, Data pre-processing, Data splitting, Defining hyperparameters, Model building and Performance evaluation. Experiments for identifying improved optimizers and hyperparameters for the time-series climatological data are investigated for accurate precipitation forecast. The metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE) and Root Mean Squared Logarithmic Error (RMSLE) values are used to compare the precipitation predictions of different models. The RNN variants and ensemble models, BRNN, LSTM, GRU, BRNN-GRU, BRNN-LSTM, LSTM-GRU, BRNN-LSTM-GRU produce predictions with RMSLE values of 2.448, 0.555, 0.255, 1.305, 1.383, 0.364, 1.740 for AP and 1.735, 0.663, 0.152, 0.889, 1.118, 0.379, 1.328 for TN respectively. The best performing RNN model, GRU when ensembled with the existing statistical model SARIMA produces an RMSLE value of 0.754 and 1.677 respectively for AP and TN.

show abstract

“…Advance prediction of rainfall by this model also gives enough time to makes adequate arrangements for saving lives, transportation, procurement and supply of food and medicines. Data mining is a set of techniques used to extract unknown pieces of information from the large database repository [7][8][9]. There are various data mining techniques available to extract valuable and useful information from spatial, temporal, sequencing and time series data.…”

Section: Introductionmentioning

confidence: 99%

Modelling an automated rainfall forecasting system using an optimized intelligent agent

Nnenna¹,

Eke²,

Edith³

2023

Global J. Eng. Technol. Adv.

View full text Add to dashboard Cite

Weather forecasting information is very crucial in decision making process regarding to activities and works, such as in the field of agriculture to determine initial growing season. Recently, climate change causes trouble in weather forecasting. Time series data analysis for forecasting, is one of the most important aspects of the practical usage. Time Series data is large in volume, highly dimensional and continuous updating. Accurate rainfall forecasting with the help of time series data analysis had helped in the field of agriculture, in evaluating drought and flooding situations in advance. The data used within this paper is taken from Automatic Digital Meteorological Station (NECOP Station) in National Space Research and Development Agency (NASRDA-Centre for Basic Space Science, Nsukka, Enugu State Nigeria). Those data include ambient temperature, air pressure, solar radiation, relative humidity, and wind speed etc. In this paper, rainfall forecasting models were developed for Artificial Neural Network (ANN) based on Levenberg-Marquardt training function and Multiple linear regression (MLR) and was used for the prediction. Based on experimental result, it was concluded that prediction using ANN model for NASRDA-CBSS weather data produced prediction with more than 90% accuracy while MLR prediction gives 70%.

show abstract

An Approach for Rainfall Prediction Using Long Short Term Memory Neural Network

Cited by 19 publications

References 17 publications

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

A Systematic Review of Deep Learning Applications in Interpolation and Extrapolation of Precipitation Data

Precipitation forecast using RNN variants by analyzing Optimizers and Hyperparameters for Time-series based Climatological Data

Modelling an automated rainfall forecasting system using an optimized intelligent agent

Contact Info

Product

Resources

About