Deep BLSTM-GRU Model for Monthly Rainfall Prediction: A Case Study of Simtokha, Bhutan

Chhetri, Manoj; Kumar, Sudhanshu; Roy, Partha Pratim; Kim, Byung-Gyu

doi:10.3390/rs12193174

Cited by 81 publications

(38 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In an experimental study to address the erratic rainfall patterns being predicted for Himalayan mountainous areas, Wangdi et al, conducted 100% throughfall exclusion and ambient control plots experiments to study the drought stresses on the ecology [36]. Chhetri used linear regression, multi-layer perceptron (MLP), convolutional neural network (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional long short-term memory (BLSTM) to predict the monthly rainfall in Bhutan [37]. Using variable infiltration capacity (VIC) hydrological model, Sonessa et al found that the temperature variation greatly affects the runoff in northern part the country where elevation is more than 5000 m above sea level [38].…”

Section: Previous Studiesmentioning

confidence: 99%

A Critical Review of Water Resources and Their Management in Bhutan

2021

View full text Add to dashboard Cite

Bhutan is a small yet water-abundant country. The country suffers from frequent flooding and is lately experiencing a growing risk of localized droughts due to inappropriate water resource management and climate change. Such a situation calls for much more efficient use and management of water in Bhutan. This paper undertakes an extensive analysis of the country’s water resources for better planning and management of the available water resources. Bhutan can be divided into three zones, the Southern Foothills, the Central Inner Himalayas, and the Higher Himalayas. The top four leading industries of Bhutan are related to water, either directly or indirectly. The country at present is at a very early stage of development. The government has prioritized water resources management over recent years. Water for hydropower in Bhutan has been in focus as compared to that allocated for irrigation, industries, and environmental demand. The demand for water in Bhutan has also increased in the last decade due to population increase, changes in lifestyle, and economic advancements through tourism and hydropower projects. Climate variation, deteriorating water quality, frequent floods, and increasing urbanization threaten the sustainability of water resources. Water accessibility issues for settlements due to the country’s harsh geographical landscape is leading towards localized water scarcity. Serious attention to rainwater harvesting and groundwater recharge is required to address localized water scarcity issues.

show abstract

Section: Previous Studiesmentioning

confidence: 99%

A Critical Review of Water Resources and Their Management in Bhutan

2021

View full text Add to dashboard Cite

show abstract

“…When time scales on the order of months or longer are involved, datasets are typically much smaller than those involving shorter time scales. A broad range of ML methods are applied, from simple methods like multilinear regression (MLR) up to advanced neural networks models [13,[16][17][18]20,21,24,25,46,47,49,[59][60][61][62]. Because of the small data sets used, researchers often perform feature selection/reduction to avoid overfitting.…”

Section: Literature Review and Scope Of The Researchmentioning

confidence: 99%

“…Because of the small data sets used, researchers often perform feature selection/reduction to avoid overfitting. Most often, the selected features in the literature are combinations of features derived from previous time steps in the data, for example, a parameter at month n may be predicted based one or more parameter values taken from months previous to n [ [25][26][27]46,63].…”

Section: Literature Review and Scope Of The Researchmentioning

confidence: 99%

“…Another concern is that some common pre-processing practices produce data leakage, so that ML algorithm accuracies are over-reported. Some examples of such practices are: data shuffling, whereby researchers randomly shuffle the data [11,[16][17][18][19][20][21][22][23]; data imputation methods that use statistics (such as averaging) calculated on the entire data set, including both training and testing [24][25][26]; and data transformations such as de-seasonalization that also use statistics calculated on the whole dataset [27,28].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Basic Statistical Estimation Outperforms Machine Learning in Monthly Prediction of Seasonal Climatic Parameters

et al. 2021

View full text Add to dashboard Cite

Machine learning (ML) has been utilized to predict climatic parameters, and many successes have been reported in the literature. In this paper, we scrutinize the effectiveness of five widely used ML algorithms in the monthly prediction of seasonal climatic parameters using monthly image data. Specifically, we quantify the predictive performance of these algorithms applied to five climatic parameters using various combinations of features. We compare the predictive accuracy of the resulting trained ML models to that of basic statistical estimators that are computed directly from the training data. Our results show that ML never significantly outperforms the statistical baseline, and underperforms for most feature sets. Unlike previous similar studies, we provide error bars for the relative performance of different predictors based on jackknife estimates applied to differences in predictive error magnitudes. We also show that the practice of shuffling data sequences which was employed in some previous references leads to data leakage, resulting in over-estimated performance. Ultimately, the paper demonstrates the importance of using well-grounded statistical techniques when producing and analyzing the results of ML predictive models.

show abstract

“…Kumar et al [ 68 ] used LSTM for forecasting monthly rainfall by using long sequential raw data for time-series analysis. Chhetri et al [ 69 ] presented a GRU-based model for rainfall prediction using weather parameters (temperature, rainfall, relative humidity, sunshine hour, and wind speed). Although advanced GRUs exhibit advantages in developing forecasting models, they have seldom been used in rainfall forecasting using radar reflectivities.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Rainfall Forecasts Based on Radar Reflectivity during Typhoons: Case Study in Southeastern Taiwan

Wei

Hsu

2021

Sensors

View full text Add to dashboard Cite

This study developed a real-time rainfall forecasting system that can predict rainfall in a particular area a few hours before a typhoon’s arrival. The reflectivity of nine elevation angles obtained from the volume coverage pattern 21 Doppler radar scanning strategy and ground-weather data of a specific area were used for accurate rainfall prediction. During rainfall prediction and analysis, rainfall retrievals were first performed to select the optimal radar scanning elevation angle for rainfall prediction at the current time. Subsequently, forecasting models were established using a single reflectivity and all elevation angles (10 prediction submodels in total) to jointly predict real-time rainfall and determine the optimal predicted values. This study was conducted in southeastern Taiwan and included three onshore weather stations (Chenggong, Taitung, and Dawu) and one offshore weather station (Lanyu). Radar reflectivities were collected from Hualien weather surveillance radar. The data for a total of 14 typhoons that affected the study area in 2008–2017 were collected. The gated recurrent unit (GRU) neural network was used to establish the forecasting model, and extreme gradient boosting and multiple linear regression were used as the benchmarks. Typhoons Nepartak, Meranti, and Megi were selected for simulation. The results revealed that the input data set merged with weather-station data, and radar reflectivity at the optimal elevation angle yielded optimal results for short-term rainfall forecasting. Moreover, the GRU neural network can obtain accurate predictions 1, 3, and 6 h before typhoon occurrence.

show abstract

Deep BLSTM-GRU Model for Monthly Rainfall Prediction: A Case Study of Simtokha, Bhutan

Cited by 81 publications

References 34 publications

A Critical Review of Water Resources and Their Management in Bhutan

A Critical Review of Water Resources and Their Management in Bhutan

Basic Statistical Estimation Outperforms Machine Learning in Monthly Prediction of Seasonal Climatic Parameters

Real-Time Rainfall Forecasts Based on Radar Reflectivity during Typhoons: Case Study in Southeastern Taiwan

Contact Info

Product

Resources

About