Development of novel hybrid machine learning models for monthly thunderstorm frequency prediction over Bangladesh

Abstract

Accurate thunderstorm frequency (TSF) prediction is of great significance under climate extremes for reducing potential damages. However, TSF prediction has received little attention because a thunderstorm event is a combination of intricate and unique weather scenarios with high instability, making it difficult to predict. To close this gap, we proposed a novel hybrid machine learning model through hybridization of data pre-processing Ensemble Empirical Mode Decomposition (EEMD) with two state-of-arts models namely artificial neural network (EEMD-ANN), support vector machine (EEMD-SVM) for TSF prediction at three categories of yearly frequencies over Bangladesh. We were demarcated the yearly TSF datasets into three categories for the period 1981-2016 recorded at 28 sites; high (March-June), moderate (July-October), and low (November-February) TSF months. The performance of the proposed EEMD-ANN and EEMD-SVM hybrid models was compared 2 with classical ANN, SVM, Autoregressive Integrated Moving Average (ARIMA). EEMD-ANN and EEMD-SVM hybrid models showed 8.02%-22.48% higher performance precision in terms of root mean square error (RMSE) compared to other models at high, moderate and low-frequency categories. Eleven out of 21 input parameters were selected based on the Random Forest (RF) variable importance analysis. The sensitivity analysis results showed that each input parameter was positively contributed to building the best model of each category and thunderstorm days are the most contributing parameters influencing TSF prediction. The proposed hybrid models outperformed the conventional models where EEMD-ANN is the most skillful for high TSF prediction, and EEMD-SVM is for moderate and low TSF prediction. The findings indicate the potential of hybridization of EEMD with the conventional models for improving prediction precision. The hybrid model developed in this work can be adopted for TSF prediction in Bangladesh as well as different parts of the world.

A Survey of Deep Learning-Based Lightning Prediction

“…Azad M et al put forth a hybrid model aiming to predict the monthly frequency of lightning occurrences [17]. This model commences with a random forest to sieve out 11 impactful predictive features from a pool of 21 feature parameters.…”

A Survey of Deep Learning-Based Lightning Prediction

“…Azad et al put forth a hybrid model aiming to predict the monthly frequency of lightning occurrences [18]. This model commences with a random forest to sieve out 11 impactful predictive features from a pool of 21 feature parameters obtained from 28 observation stations of the Bangladesh Meteorological Department ranging from 1981 to 2016, including the convective rain rate, Earth skin temperature, monthly averaged precipitation, and so on.…”

“…EEMD + SVM/ANN [18] Observation meteorological parameters Gradient boosting machine learning [21] Binary meteosat satellite images and lightning detected data Undersampling + shallow neural network/DT [22] Observation meteorological parameters Back-propagation neural network [23] Observation meteorological parameters Undersampling + SVM/RF [24] Observation meteorological parameters…”

Thunderstorms Prediction Using Satellite Images

“…When BEADS is added, sample set coefficients are more than 99.8%, whereas no deciding coefficients fall below 94.12 percent before and after BEADS. Similarly [30], It is suggested to use ARIMA modeling using the Thunderstorm frequency (TSF) dataset. DP, RH, WS50, and Earth skin temperature (EST) are all single-point measurements of the dew/frost point, relative humidity, and wind speed range at 2 m. (ST) dataset.…”