Region-Wise Rainfall Prediction Using MapReduce-Based Exponential Smoothing Techniques

Dhamodharavadhani, S.; Rathipriya, R.

doi:10.1007/978-981-13-1882-5_21

Cited by 14 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the proposed work, COVID-19 data has made for forecasting by using three separate training algorithms [ 54 – 57 ] as discussed below: LM training algorithm is commonly used for nonlinear data and optimization problems. It provides a nonlinear least-square minimization as a solution, which shows the minimization function defined in the following Eq.…”

Section: Proposed Schemementioning

confidence: 99%

Nonlinear Neural Network Based Forecasting Model for Predicting COVID-19 Cases

Namasudra

Dhamodharavadhani

Rathipriya

2021

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

The recent COVID-19 outbreak has severely affected people around the world. There is a need of an efficient decision making tool to improve awareness about the spread of COVID-19 infections among the common public. An accurate and reliable neural network based tool for predicting confirmed, recovered and death cases of COVID-19 can be very helpful to the health consultants for taking appropriate actions to control the outbreak. This paper proposes a novel Nonlinear Autoregressive (NAR) Neural Network Time Series (NAR-NNTS) model for forecasting COVID-19 cases. This NAR-NNTS model is trained with Scaled Conjugate Gradient (SCG), Levenberg Marquardt (LM) and Bayesian Regularization (BR) training algorithms. The performance of the proposed model has been compared by using Root Mean Square Error (RMSE), Mean Square Error (MSE) and correlation co-efficient i.e. R-value. The results show that NAR-NNTS model trained with LM training algorithm performs better than other models for COVID-19 epidemiological data prediction.

show abstract

Section: Proposed Schemementioning

confidence: 99%

Nonlinear Neural Network Based Forecasting Model for Predicting COVID-19 Cases

Namasudra

Dhamodharavadhani

Rathipriya

2021

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

show abstract

“…It works by breaking down every process into two stages. It consists of two phases, namely Map and Reduce [10,11].…”

Section: Mapreducementioning

confidence: 99%

“…It processed data block and generates the key-value pairs as intermediate outputs. The output of a Mapper is given as the input to the Reducer function [10,11].…”

Section: Mapreducementioning

confidence: 99%

See 1 more Smart Citation

Rainfall-Based Crop Selection Model Using MapReduce-Based Hybrid Holt Winters Algorithm

Kaleeswaran

Dhamodharavadhani

Rathipriya

2021

Artificial Intelligence and Technologies

Self Cite

View full text Add to dashboard Cite

Water is essential for all life processes, cannot be an alternative, and is used for transportation; it is a source of energy and serves many useful purposes like agriculture and industry-related activities. Rain is the major source of irrigation in the India, and it is directly connected with the crop production. Yields of crops, especially in rain-fed region, depend on rainfall patterns. Therefore, it is very important to predict rainfall quantity from historical rainfall data using statistical methods [1]. Another important factor is soil moisture that purely depends on the rainfall. It also play vital role in the crop production. Therefore, rainfall prediction is the most important area and needy tool. It has very good impact in determining the food production. The most popular and frequently used data mining algorithms are K-means, C4.5, SVM, EM, Apriori, AdaBoost, PageRank, Naive Bayes, KNN, and CART. The authors of [2] provided detailed explanations of each of these methods and discussed their impact on current and future research in these methods. The rainfall forecasting for boyolai, central java, Indonesia is made by using the Z-Score model and Winters triple exponential smoothing. The authors predicted the weather based on climate classification using the Oldman method [3]. The weather-based crop yield prediction model was proposed in [4] to forecast the yield of 12 major California crops. But very few crop yields were predicted with high accuracy, suggesting that crop yield variability should be captured for more accurate forecasting. The time series analysis using HW algorithm is used to identify level, trend, and seasonality in the rainfall dataset and forecast the districtwise rainfall in Tamilnadu, India, based on these information [5]. In this paper, forecasting the districtwise rainfall using hybridization of KNN with MapReduce-based HW. MapReduce framework is used here for the effective initialization process of HW algorithm iteratively. The experimental study is designed with different initializa-

show abstract

“…This information can be in the form of forecasts of rainfall both in the short term and in the long term. Forecasting the amount of rainfall is very important (Wichitarapongsakun et al 2016;Dhamodharavadhani and Rathipriya 2019;Noviandi and Ilham 2020) information because it can be used to plan several production sectors such as agricultural production (Hartomo, Subanar, and Winarko 2015), plantations (Zhu et al 2020), fisheries (Dunstan et al 2018), aviation (Chen and Wang 2019), public service (Golding et al 2019), and so on. In addition, this information is useful for early detection of disasters that may occur due to extreme rainfall (Zhu et al 2020).…”

Section: Introductionmentioning

confidence: 99%

Applied Exponential Smoothing Holt-Winter Method for Predict Rainfall in Mataram City

Pertiwi

2020

JICHI

View full text Add to dashboard Cite

Weather conditions in the city of Mataram tend to be erratic and difficult to predict, such as the condition of rainfall data in 2018 which changes over a certain period of time so that the weather is difficult to predict accurately. In this study, we propose the Exponential Smoothing Holt-Winter method to forecast rainfall in the city of Mataram, so that it can be a decision support for various interested sectors. This method has been tested using secondary data from the Mataram City Central Bureau of Statistics for the period January 2014 to 2018 and evaluated using Mean Absolute Deviation (MAD), Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). The results of this study indicate that using the Exponential Smoothing Holt-Winter method yields better results, each of which is MAPE 142.3, MAD 95.6 and MSD value 24988.7 and the data smoothing value is obtained for the smallest combination value of α 0.2, β 0.1, and γ 0.1. It can be concluded that the proposed method can provide better information and can be used to predict rainfall in Mataram City for the next 12 periods.

show abstract

Region-Wise Rainfall Prediction Using MapReduce-Based Exponential Smoothing Techniques

Cited by 14 publications

References 3 publications

Nonlinear Neural Network Based Forecasting Model for Predicting COVID-19 Cases

Nonlinear Neural Network Based Forecasting Model for Predicting COVID-19 Cases

Rainfall-Based Crop Selection Model Using MapReduce-Based Hybrid Holt Winters Algorithm

Applied Exponential Smoothing Holt-Winter Method for Predict Rainfall in Mataram City

Contact Info

Product

Resources

About