An Improved Cluster‐Wise Typhoon Rainfall Forecasting Model Based on Machine Learning and Deep Learning Models Over the Northwestern Pacific Ocean. Issue 14 (12th July 2022)

• Record Type: Journal Article
• Authors: Uddin, Md. Jalal; Li, Yubin; Sattar, Md. Abdus; Liu, Mingyang; Yang, Nan
• Is Part Of: Journal of geophysical research. Volume 127:Issue 14(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-07-12
• Subjects: typhoon rainfall forecasting -- machine learning -- deep learning -- northwestern Pacific Ocean -- clustering typhoon track; Atmospheric physics -- Periodicals; Geophysics -- Periodicals; 551.5
• DOI: 10.1029/2022JD036603
• Languages: English
• ISSNs: 2169-897X

Abstract

Abstract: Though large amounts of work with artificial intelligence are used in typhoon rainfall forecasting, the predictive skills of existing models are unsatisfactory. To address this problem, this study aims to propose an improved cluster‐wise typhoon rainfall forecasting model that integrates the grid‐search cross‐validation method with machine learning and deep learning (DL) models including support vector machine (SVM), random forest (RF), adaptive boosting (AdaBoost), convolutional neural network (CNN), and long short‐term memory (LSTM). Grid‐search cross‐validation is a modified parameterization technique that helps to find the best parameters for machine/DL models. In the first stage, a second‐order polynomial regression model was used to cluster the typhoon track; and in the second stage, cluster‐wise typhoon rainfall was recognized within a 500 km radius from each typhoon center. After that, a modified cluster‐wise typhoon rainfall forecasting model was proposed using cluster‐wise antecedent hourly typhoon rainfall within this distance for 1–6 hr lead time. Results show that the proposed model based on the SVM, RF, AdaBoost, CNN, and LSTM is capable of providing more accurate forecasts (the efficiency of the forecast is increased by 45%–90%) than the existing typhoon rainfall forecasting models that are based on SVM with a genetic algorithm, RF, artificial neural network, multilayer perceptron network, and deep neural network. Therefore, the current study recommends using cluster‐wise typhoon rainfall forecasting model with a grid‐search cross‐validation method for disaster prevention and mitigation. Plain Language Summary: There have been a large number of works with artificial intelligence used in typhoon rainfall forecasting. However, the predictive skills of existing models—which are based on the support vector machine (SVM) with a genetic algorithm, random forest (RF), artificial neural network (ANN), multilayer perceptron network, and deep neural network (DNN)—were unsatisfactory. To address this problem, this study proposes a cluster‐wise typhoon rainfall forecasting model that integrates the grid‐search cross‐validation method with machine learning and deep learning (DL) models such as SVM, RF, adaptive boosting (AdaBoost), convolutional neural network, and long short‐term memory. Grid‐search cross‐validation is a modified parameterization technique, which helps to find the best parameters for machine/DL models. And based on this technique, this study increases the efficiency of the forecast by 45%–90% compared to previous studies. Key Points: A cluster‐wise typhoon rainfall forecasting model based on machine learning and deep learning models is proposed Support Vector Machine with a grid‐search algorithm shows the best performance to forecast hourly typhoon rainfall The proposed model increases the efficiency of the forecast by 45%–90% compared to previous studies