Rainfall Prediction Model Research Articles

A rainfall prediction model based on ERA5 and Elman neural network

The heightened frequency and intensity of heavy rainfall, brought about by global climate warming, significantly affect various regions. Rainfall prediction plays a pivotal role in ensuring societal security and fostering development. There has been limited exploration of the impact of input parameters on the accuracy of rainfall predictions. Despite the advantages of Elman neural network models in handling non-linear relationships and spatiotemporal data, their application in weather forecasting is restricted. This paper assesses the accuracy of the European Centre for Medium-Range Weather Forecasts Reanalysis v5 (ERA5) with a dataset from meteorological stations. It introduces a novel rainfall forecasting model based on the Elman neural network and ERA5 reanalysis data. The study also identifies optimal input parameters through factor correlation analysis. Experimental results showcase the precision and stability of ERA5 across various rainfall conditions. Meteorological parameters, such as Precipitable Water Vapor (PWV), exhibit noticeable correlations with temporal variables and precipitation volume. The seven-factor model, including PWV, Zenith Tropospheric Delay, temperature, relative humidity, day-of-year, and hour of day, outperforms in precision evaluation. It achieves a mean critical success index of 57.06 %, a correct forecast rate of 91.39 %, and a false alarm rate of 39.48 %. This rainfall forecasting model introduces a novel approach and empirical research to enhance predictive accuracy, holding significant implications for the amelioration of meteorological alert systems, risk mitigation, and the safeguarding of life and property.

Bias correction and ensemble techniques in statistical downscaling model for rainfall prediction using Tweedie-LASSO in West Java, Indonesia

Rainfall is a climate element with high variations in space and time scales, so it is not easy to predict. One way to predict rainfall is statistical downscaling (SD). SD can predict local rainfall based on Global Circulation Model (GCM) data. The Decadal Climate Prediction Project (DCPP), one of the GCMs, originates from adjacent grids and experiences multicollinearity problems. Rainfall as a response variable is Tweedie Compound Poisson Gamma (TCPG) distribution data because it has a discrete component (rainfall events) and a continuous component (rainfall intensity), so SD modelling will be carried out using Tweedie-LASSO. This research aims to compare the performance of bias correction and ensemble methods in SD in predicting rainfall in West Java, Indonesia. Bias correction uses Empirical Quantile Mapping (EQM) with CHIRPS data, and the ensemble method uses a stacking technique with Random Forest (Stacking-RF) due to the varied characteristics of DCPP model sources. Evaluation results using Root Mean Square Error Prediction (RMSEP) and correlation coefficient show that bias correction improves single-model performance but not ensemble models. Besides that, ensemble models outperform single models both before and after bias correction. The combination of bias correction and ensemble modelling can be recommended when conducting SD to enhance the prediction capability of rainfall at stations and other areas.

Comparative analysis of machine learning models for rainfall prediction

Predicting rainfall is essential for many applications, including agriculture, hydrology, and disaster management. In this work, we undertake a comparison examination of various machine learning models to forecast rainfall based on meteorological data. The target variable in this study is rainfall, and the dataset used includes characteristics like temperature, relative humidity, wind speed, and wind direction. The following seven machine learning models were assessed: Support Vector Regression (SVR), Multivariate adaptive regression splines (MARS), Random Forest Regression, and Deep Neural Network with Historical Data (DWFH), Haar Wavelet Function, Decision Tree and Discrete wavelet Transform (DWT). Data preprocessing, which includes standardisation and lagging to capture temporal dependencies, comes first in the analysis phase. A wavelet transformation is also used to capture complex patterns in the data. Each model is tested on a different test set after being trained on a subset of the dataset. The results are assessed using the Root Mean Squared Error (RMSE) and Mean Squared Error (MSE), focusing on the RMSE and MSE values for better comparison across models. Our findings reveal that the DWFH model achieved an RMSE of 0.0138807 mm and MSE of 0.000193 mm2, demonstrating their effectiveness in predicting rainfall. The Random Forest and SVR models also provided competitive results. This study highlights the importance of selecting an appropriate machine learning model for rainfall prediction and the significance of preprocessing techniques in improving model performance. These insights can aid decision-makers in choosing the most suitable model for their specific application, contributing to more accurate rainfall predictions and enhanced decision support systems.

Optimizing Rain Prediction Model Using Random Forest and Grid Search Cross-Validation for Agriculture Sector

Agriculture, as a sector that is highly influenced by weather conditions, faces challenges due to increasingly unpredictable changes in weather patterns. The aim of this research is to create an optimal rainfall prediction model to help farmers create irrigation schedules, use fertilizer, and planting schedules, and protect plants from extreme weather events. The method used in this research to obtain the best rain prediction model is to use the random forest algorithm and the grid search cross-validation algorithm. Random Forest, known for its robustness and accuracy, emerged as a suitable algorithm for predicting rain. utilizing a substantial dataset from the West Nusa Tenggara Meteorology, Climatology, and Geophysics Agency covering the period 2000 to 2023. The data is then processed first to ensure its readiness for use. This process involves removing outlier data points, empty data entries, and unused features. After the preprocessing stage, the data underwent training using the Random Forest algorithm, resulting in an R-squared value of 0.1334. To obtain the optimal model, Grid Search Cross Validation is used. The results of this research obtained the best rain prediction model with an R-squared value of 0.0268. This model will be used to predict rain in the agricultural sector. This research concludes that we can get the best rain prediction model by combining Random Forest and Gird Search Cross-Validation. For further research, we can compare other rain prediction methods, add features, and combine datasets from a wider area.

A novel optimization rainfall coupling model based on stepwise decomposition technique

Traditional decomposition integration models decompose the original sequence into subsequences, which are then proportionally divided into training and testing periods for modeling. Decomposition may cause data aliasing, then the decomposed training period may contain part of the test period data. A more effective method of sample construction is sought in order to accurately validate the model prediction accuracy. Semi-stepwise decomposition (SSD), full stepwise decomposition (FSD), single model semi-stepwise decomposition (SMSSD), and single model full stepwise decomposition (SMFSD) techniques were used to create the samples. This study integrates Variational Mode Decomposition (VMD), African Vulture Optimization Algorithm (AVOA), and Least Squares Support Vector Machine (LSSVM) to construct a coupled rainfall prediction model. The influence of different VMD parameters α is examined, and the most suitable stepwise decomposition machine learning coupled model algorithm for various stations in the North China Plain is selected. The results reveal that SMFSD is relatively the most suitable tool for monthly precipitation forecasting in the North China Plain. Among the predictions for the five stations, the best overall performance is observed at Huairou Station (RMSE of 18.37 mm, NSE of 0.86, MRE of 107.2%) and Jingxian Station (RMSE of 24.74 mm, NSE of 0.86, MRE of 51.71%), while Hekou Station exhibits the poorest performance (RMSE of 25.11 mm, NSE of 0.75, MRE of 173.75%).

Rainfall Prediction Model Based on CEEMDAN-VMD-BiLSTM Network

Rainfall Prediction Model Based on CEEMDAN-VMD-BiLSTM Network

Assimilating the Subic radar data in the WRF model for tropical cyclone-enhanced heavy monsoon rainfall prediction in Metro Manila

Assimilating the Subic radar data in the WRF model for tropical cyclone-enhanced heavy monsoon rainfall prediction in Metro Manila

Short-Term and Imminent Rainfall Prediction Model Based on ConvLSTM and SmaAT-UNet.

Short-term precipitation forecasting methods are mainly divided into statistical forecasting, numerical model-based forecasting, and radar image extrapolation techniques. The two methods based on statistical prediction and numerical model have the disadvantages of being unstable and generating large errors. Therefore, this study proposes the use of deep learning for radar image extrapolation for precipitation forecasting, in particular by developing algorithms for ConvLSTM and SmaAT-UNet. The ConvLSTM model is a fusion of a CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory network), which solves the challenge of processing spatial sequence data, which is a task that traditional LSTM models cannot accomplish. At the same time, SmaAT-UNet enhances the traditional UNet structure by incorporating the CBAM (Convolutional Block Attention Module) attention mechanism and replacing the standard convolutional layer with depthwise separable convolution. This innovative approach aims to improve the efficiency and accuracy of short-term precipitation forecasting by improving feature extraction and data processing techniques. Evaluation and analysis of experimental data show that both models exhibit good predictive ability, with the SmaAT-UNet model outperforming ConvLSTM in terms of accuracy. The results show that the performance indicators of precipitation prediction, especially detection probability (POD) and the Critical Success index (CSI), show a downward trend with the extension of the prediction time. This trend highlights the inherent challenges of maintaining predictive accuracy over longer periods of time and highlights the superior performance and resilience of the SmaAT-UNet model under these conditions. Compared with the statistical forecasting method and numerical model forecasting method, its accuracy in short-term rainfall forecasting is improved.

A novel coupled rainfall prediction model based on stepwise decomposition technique

The traditional decomposed ensemble prediction model decomposes the entire rainfall sequence into several sub-sequences, dividing them into training and testing periods for modeling. During sample construction, future information is erroneously mixed into the training data, making it challenging to apply in practical rainfall forecasting. This paper proposes a novel stepwise decomposed ensemble coupling model, realized through variational mode decomposition (VMD) and bidirectional long short-term memory neural network (BiLSTM) models. Model parameters are optimized using an improved particle swarm optimization (IPSO). The performance of the model was evaluated using rainfall data from the Southern Four Lakes basin. The results indicate that: (1) Compared to the PSO algorithm, the IPSO algorithm-coupled model shows a minimum decrease of 2.70% in MAE and at least 2.62% in RMSE across the four cities in the Southern Four Lakes basin; the IPSO algorithm results in a minimum decrease of 25.58% in MAE and at least 28.19% in RMSE for the VMD-BiLSTM model. (2) When compared to IPSO-BiLSTM, the VMD-IPSO-BiLSTM based on the stepwise decomposition technique exhibits a minimum decrease of 26.54% in MAE and at least 34.16% in RMSE. (3) The NSE for the testing period of the VMD-IPSO-BiLSTM model in each city surpasses 0.88, indicating higher prediction accuracy and providing new insights for optimizing rainfall forecasting.

A Hybrid Feature Selection Gradient Recurrent Neural Network (HFSGRNN) Model for Rainfall Prediction in India Regions

A Hybrid Feature Selection Gradient Recurrent Neural Network (HFSGRNN) Model for Rainfall Prediction in India Regions

Research on a Rainfall Prediction Model in Guizhou Based on Raindrop Spectra

Research on a Rainfall Prediction Model in Guizhou Based on Raindrop Spectra

Comparative analysis of different rainfall prediction models: A case study of Aligarh City, India

This research paper delves into creating and comparing rainfall prediction models, employing diverse machine learning algorithms, including Logistic Regression, Decision Tree Classifier, Multi-Layer Perceptron classifier (neural network), and Random Forest. The study aims not only to predict rainfall patterns but also to evaluate the performance of each model through metrics such as Accuracy, Cohen's kappa coefficient, and Receiver Operating Characteristic (ROC) curve analysis. Additionally, the relevance of the predictors employed in each model is thoroughly assessed. The results of extensive experimentation and analysis reveal that the Logistic Regression (Accuracy = 82.80 %, ROC = 82.45 %, Cohen's Kappa = 65.05 %) and Neural Network model (Accuracy = 82.59 %, ROC = 81.94 %, Cohen's Kappa = 64.40 %) has emerged as the most promising approach, achieving the highest percentage of accuracy, ROC and Cohen's Kappa metrics; among the models considered. This outcome underscores the effectiveness of Logistic Regression and Neural Network architectures in capturing intricate patterns and relationships within rainfall data.

Times series data analysis: The Holt-Winters model for rainfall prediction In West Java

Time series data analysis is used to analyze data that considers time and data characteristics to predict future events. One of the time series data is rainfall data. Rainfall data has a seasonal pattern because there is a pattern that repeats itself over a certain period. Data analysis that considers the characteristics of seasonal patterns is the Holt-Winters method. The Holt-Winters model is divided into two, namely additive and multiplicative models. This research aims to compare the Holt-Winters additive and multiplicative methods to see the accuracy in predicting rainfall data in West Java. The additive model has level parameter α=0,435, trend parameter β=0, seasonal parameter γ=1, and RMSE value 140,174. The multiplicative model has level parameter α=0,936, trend parameter β=0, seasonal parameter γ=0,247, and RMSE value 150,020. The additive model has a smaller RMSE value so it can predict future rainfall with greater accuracy.

Developing an innovative machine learning model for rainfall prediction in a semi-arid region

ABSTRACT Due to global climate change, managing water resources is one of the most critical challenges for most countries in the world, especially in the Middle East. In the Kurdistan Region of Iraq (KRI), there is a good amount of precipitation, surface water, and groundwater, but the main issue is mismanagement of those sources. Rainfall is one of the major sources of water resources in KRI. In order to manage the available water resources and prevent natural disasters such as floods and droughts, there is a need for reliable models for forecasting rainfall. The current study focuses on developing a hybrid model, namely seasonal autoregressive integrated moving average combined with an artificial neural network (SARIMA-ANN) for forecasting monthly rainfall at Sulaymaniyah City for the duration of 1938–2012. For comparison purposes, a conventional machine learning model, namely artificial neural networks (ANN) has been applied on the same data. Two different statistical measurements, namely, root mean square error (RMSE) and coefficient of determination (R2), have been used to check the accuracy of the proposed models. According to the findings, SARIMA-ANN outperformed ANN with RMSE = 11.5, RMSE = 51.002, R2 = 0.98, R2 = 0.43, respectively. The findings of the current study could contribute to Sustainable Development Goal (SDG) 6.

How accurate are the machine learning models in improving monthly rainfall prediction in hyper arid environment?

Arid regions like the United Arab Emirates (UAE) face a dire challenge of scarce water resources and unpredictable climate patterns. This study investigates the efficacy of advanced Machine Learning (ML) techniques in enhancing rainfall prediction within hyper-arid environments. Leveraging an extensive 30-year dataset from 1991 to 2020, this study harnessed the power of XGBoost, LSTM, Random Forest (RF), Gradient Boost (GB), Support Vector Machine (SVM), Multilayer Perceptron (MLP), Linear Regression (LR), and ensemble methods to significantly enhance the prediction accuracy of monthly rainfall over UAE. In the initial univariate analysis, focused solely on rainfall as the predictor, the ML models displayed encouraging performance during the training phase, achieving an impressive correlation coefficient (CC) of 0.88 for both XGBoost and the ensemble models. However, their predictive efficacy witnessed a decline during the testing phase, where the maximum CC reached 0.45. In contrast, traditional models like Linear Regression and SVM, yielded subpar results in both training and testing, exhibiting correlation values lower than 0.3. To address these limitations, a multivariate analysis is conducted by incorporating additional meteorological parameters, including wind speed, temperature, humidity, and evapotranspiration. This augmentation proved highly beneficial as it substantially enhanced the models' predictive capacities during the testing period. The XGB achieves a CC of 0.76, LSTM improves from 0.21 to 0.71, and stacked models exhibit promising behavior jumping from an average of 0.44 to 0.82 during the testing periods. Additionally, we performed a sensitivity analysis utilizing LASSO regression, which revealed that wind speed and minimum temperature emerged as the most influential parameters for monthly rainfall prediction in the arid context. These two meteorological factors exerted a substantial impact on the accuracy of our predictive models, underscoring their significance in understanding and forecasting rainfall patterns in hyper-arid regions, such as the United Arab Emirates. The identification of these key drivers further strengthens the foundation for effective water resource management and climate adaptation strategies in such challenging environments. This study provides valuable insights for water resource planning, agriculture, and climate resilience strategies in hyper-arid regions. Further research can build upon these results to enhance rainfall prediction models and support sustainable development in arid regions.

Hybrid model for rainfall prediction with statistical and technical indicator feature set

As excessive rain may cause numerous disasters, rainfall prediction is very crucial and the prediction should be realistic since it encourages individuals to take preventative steps. This work proposes a new rainfall prediction model by following three major phases: Preprocessing, Extraction of Features and Prediction. The Improved Data Normalization technique is carried out for preprocessing the data. Then, it extracts the technical Indicator features like Average Directional Movement (ADX), Moving Average Convergence Divergence (MACD), RSI, Welles Wilder's Smoothing Average (WWS), statistical & higher order statistical features. According to these features, prediction takes place by a hybrid model that includes the Improved DBN & LSTM methods. By fine-tuning the best weights, the training will be carried out optimally to increase the prediction model's efficacy. For this, the Brownian Motion-based Pelican Optimization Algorithm (BMPOA) is implemented. Finally, the proposed technique has contrasted over existing models concerning different metrics.

Machine learning based forecasting model for rainfall prediction

Weather forecasts can be performed by collecting large amount of data about the present condition of the environment. The state of atmosphere or environment can be the temperature, humidity and wind. The future can be determined by the atmosphere evolution and this evolution can be done through meteorology with understanding of atmospherically processes. The foundation stone of Indian economy is the agriculture, which depends on the rain. Hence, early prediction of rain is highly necessary in India for agriculture. In worldwide, rainfall prediction is one among the challenging issues. Here, varied and most popular machine learning models are utilized for forecasting the rainfall. The outcome from the model gives the centre of the weather forecasts for predicting that whether tomorrow will rain or not. The experimental results will compare and show that good level of accuracy with the help of machine learning algorithms.

Gaussian mutation–orca predation algorithm–deep residual shrinkage network (DRSN)–temporal convolutional network (TCN)–random forest model: an advanced machine learning model for predicting monthly rainfall and filtering irrelevant data

Monitoring water resources requires accurate predictions of rainfall data. Our study introduces a novel deep learning model named the deep residual shrinkage network (DRSN)—temporal convolutional network (TCN) to remove redundant features and extract temporal features from rainfall data. The TCN model extracts temporal features, and the DRSN enhances the quality of the extracted features. Then, the DRSN–TCN is coupled with a random forest (RF) model to model rainfall data. Since the RF model may be unable to classify and predict complex patterns and data, our study develops the RF model to model outputs with high accuracy. Since the DRSN–TCN model uses advanced operators to extract temporal features and remove irrelevant features, it can improve the performance of the RF model for predicting rainfall. We use a new optimizer named the Gaussian mutation (GM)–orca predation algorithm (OPA) to set the DRSN–TCN–RF (DTR) parameters and determine the best input scenario. This paper introduces a new machine learning model for rainfall prediction, improves the accuracy of the original TCN, and develops a new optimization method for input selection. The models used the lagged rainfall data to predict monthly data. GM–OPA improved the accuracy of the orca predation algorithm (OPA) for feature selection. The GM–OPA reduced the root mean square error (RMSE) values of OPA and particle swarm optimization (PSO) by 1.4%–3.4% and 6.14–9.54%, respectively. The GM–OPA can simplify the modeling process because it can determine the most important input parameters. Moreover, the GM–OPA can automatically determine the optimal input scenario. The DTR reduced the testing mean absolute error values of the TCN–RAF, DRSN–TCN, TCN, and RAF models by 5.3%, 21%, 40%, and 46%, respectively. Our study indicates that the proposed model is a reliable model for rainfall prediction.

Short-term rainfall prédiction using prédictive analytics: A case study in Telangana

Rainfall forecasting is critical because heavy rains can bring a full of tragedies. This prediction aids people in requiring preventive steps, and it should be correct. There are two types of rainfall forecasting: short-term forecasting and long-term forecasting. Predictions are typically correct for short-term, but creating a model for future rainfall prediction is the most difficult task. Because it is strongly tied to economy and human lives, heavy precipitation forecast could be a severe disadvantage for natural science departments. It’s the cause of natural disasters like floods and droughts that affect people all around the world every year. For countries like India, where agriculture is the primary source of income, the accuracy of rainfall estimates is critical. Regression may be used in the prediction of precipitation utilizing machine learning approaches. The goal of this work is to provide non-experts with easy access to the techniques and approaches used in the field of precipitation prediction, as well as a comparison of the various machine learning algorithms.

Rainfall modeling using two different neural networks improved by metaheuristic algorithms

Rainfall is crucial for the development and management of water resources. Six hybrid soft computing models, including multilayer perceptron (MLP)–Henry gas solubility optimization (HGSO), MLP–bat algorithm (MLP–BA), MLP–particle swarm optimization (MLP–PSO), radial basis neural network function (RBFNN)–HGSO, RBFNN–PSO, and RBFGNN–BA, were used in this study to forecast monthly rainfall at two stations in Malaysia (Sara and Banding). Different statistical measures (mean absolute error (MAE) and Nash–Sutcliffe efficiency (NSE) and percentage of BIAS (PBIAS)) and a Taylor diagram were used to assess the models’ performance. The results indicated that the MLP–HGSO performed better than the other models in forecasting rainfall at both stations. In addition, transition matrices were computed for each station and year based on the conditional probability of rainfall or absence of rainfall on a given month. The values of MAE for testing processes for the MLP–HGSO, MLP–PSO, MLP–BA, RBFNN–HGSO, RBFNN–BA, and RBFNN–PSO at the first station were 0.712, 0.755, 0.765, 0.717, 0.865, and 0.891, while the corresponding NSE and PBIAS values were 0.90–0.23, 0.83–0.29, 0.85–0.25, 0.87–0.27, 0.81–0.31, and 0.80–0.35, respectively. For the second station, the values of MAE were found 0.711, 0.743, 0.742, 0.719, 0.863 and 0.890 for the MLP–HGSO, MLP–PSO, MLP–BA, RBFNN–HGSO, RBFNN–BA, and RBFNN–PSO during testing processes and the corresponding NSE–PBIAS values were 0.92–0.22, 0.85–0.28, 0.89–0.26, 0.91–0.25, 0.83–0.31, 0.82–0.32, respectively. Based on the outputs of the MLP–HGSO, the highest rainfall was recorded in 2012 with a probability of 0.72, while the lowest rainfall was recorded in 2006 with a probability of 0.52 at the Sara Station. In addition, the results indicated that the MLP–HGSO performed better than the other models within the Banding Station. According to the findings, the hybrid MLP–HGSO was selected as an effective rainfall prediction model.