☆ 4.6 Article

Sequential Data Processing for IMERG Satellite Rainfall Comparison and Improvement Using LSTM and ADAM Optimizer

APPLIED SCIENCES-BASEL (2023)

Related references

Note: Only part of the references are listed.

Article Environmental Sciences

Multiple Spatial and Temporal Scales Evaluation of Eight Satellite Precipitation Products in a Mountainous Catchment of South China

Binbin Guo et al.

Summary: Satellite precipitation products (SPPs) are important for improving catchment water resource management and hydrologic modeling, especially in data-sparse regions. A systematic evaluation of eight popular SPPs was conducted, and the results show that GSMaP and MSWEP are the best-performing SPPs, while CHIRPS and SM2RAIN perform poorly. GSMaP provides the closest agreement with observations and is superior in depicting the rainfall-runoff relationship compared to other SPPs.

REMOTE SENSING (2023)

Add to Collection

Article Ecology

Comparative evaluation of LSTM, CNN, and ConvLSTM for hourly short-term streamflow forecasting using deep learning approaches

Adnan Dehghani et al.

Summary: This study investigates the effectiveness of three deep learning methods, Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Convolutional Long Short-Term Memory (ConvLSTM), in short-term streamflow forecasting in the Kelantan and Muda River basins in Malaysia. The results showed that all three deep learning methods performed with high accuracy in predicting streamflow. The study highlights the importance of accurate short-term streamflow forecasting and emphasizes the potential of using deep learning algorithms to achieve this goal.

ECOLOGICAL INFORMATICS (2023)

Add to Collection

Article Meteorology & Atmospheric Sciences

Near real-time hurricane rainfall forecasting using convolutional neural network models with Integrated Multi-satellitE Retrievals for GPM (IMERG) product

Taereem Kim et al.

Summary: This study applies CNN models to predict rainfall observation imagery for hurricane predictions. The results show satisfactory performance of the CNN models, but with limitations in underestimating larger rainfall rates.

ATMOSPHERIC RESEARCH (2022)

Add to Collection

Article Engineering, Civil

Correcting the bias of daily satellite precipitation estimates in tropical regions using deep neural network

Xiaoying Yang et al.

Summary: This study aims to establish a bidirectional long short-term memory recurrent network (Bi-LSTM) framework for the bias correction of satellite precipitation products (SPPs) in tropical regions. After optimization and statistical comparison, Bi-LSTM with the covariates of daily maximum and minimum temperature (Bi-LSTM-T) was determined to be the best model for bias correction. Bi-LSTM-T significantly outperformed two benchmark methods, ratio bias correction (RBC) and cumulative distribution function (CDF) matching, in correcting the bias of SPPs in tropical regions.

JOURNAL OF HYDROLOGY (2022)

Add to Collection

Article Engineering, Multidisciplinary

Evaluation of spatial interpolation methods and spatiotemporal modeling of rainfall distribution in Peninsular Malaysia

Kit Fai Fung et al.

Summary: This study evaluated spatial interpolation methods for rainfall pattern changes in the Peninsular Malaysia, with results indicating that Multi-scale Geographical Weighted Regression (MGWR) was the best performing model. The research showed that the rainfall intensity in Peninsular Malaysia is gradually increasing due to climate change and is vulnerable to El Nino/La Nina events.

AIN SHAMS ENGINEERING JOURNAL (2022)

Add to Collection

Article Meteorology & Atmospheric Sciences

Sub-hourly resolution quality control of rain-gauge data significantly improves regional sub-daily return level estimates

Roberto Villalobos-Herrera et al.

Summary: This research demonstrates the significant impact of using high-resolution rain-gauge data for quality control on extreme rainfall estimates. A new open QC algorithm is developed using sub-hourly rain-gauge data from official networks in Great Britain. The algorithm effectively removes spurious large values and improves extreme rainfall estimates, particularly for short-duration rainfall.

QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY (2022)

Add to Collection

Article Engineering, Environmental

Hybrids of machine learning techniques and wavelet regression for estimation of daily solar radiation

Sahar Mohsenzadeh Karimi et al.

Summary: Solar radiation simulations are crucial for hydrological, climatological, and agricultural studies. This study compares the performance of various machine learning models for solar radiation simulation in Illinois, USA. The LSTM model outperforms other models, and the SCN_4 dataset, which includes variables such as solar radiation, maximum and minimum air temperature, and Day of Year, performs the best. Overall, machine learning-based models show acceptable performance for estimating solar radiation, with the LSTM model being the most recommended.

STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT (2022)

Add to Collection

Article Engineering, Multidisciplinary

Predicting crop yields using a new robust Bayesian averaging model based on multiple hybrid ANFIS and MLP models

Ommolbanin Bazrafshan et al.

Summary: Predicting crop yield is important for farmers and decision-makers. This study used a new Bayesian model averaging (BMA) to predict tomato yield in Iran, and the results showed that using multiple MLP and ANFIS models in BMA was effective in predicting tomato yield.

AIN SHAMS ENGINEERING JOURNAL (2022)

Add to Collection

Article Water Resources

Rainfall in the Greater and Lesser Antilles: Performance of five gridded datasets on a daily timescale

Ralph Bathelemy et al.

Summary: This study evaluates the performance of several rainfall datasets and recommends their usage in different hydro-meteorological research fields. MSWEP is the preferred choice for most studies, CHIRPS and PERSIANN-CDR are suitable for water resources management research, and ERA-5 and GPM IMERG are applicable in climatic and atmospheric science research. However, bias reduction methods are needed for ERA-5 and GPM IMERG.

JOURNAL OF HYDROLOGY-REGIONAL STUDIES (2022)

Add to Collection

Article Environmental Sciences

Validation of CHIRPS Precipitation Estimates over Taiwan at Multiple Timescales

Jie Hsu et al.

Summary: The study compared the performance of CHIRPS and IMERG in depicting multiple timescale precipitation variation over Taiwan and found that while IMERG is slightly better overall, CHIRPS performs better in certain aspects. Specifically, CHIRPS excels in representing the magnitude of annual precipitation climatology, spatial distribution of seasonal mean precipitation, quantitative estimation of interannual variation in winter precipitation, and occurrence frequency of non-rainy grids in winter.

REMOTE SENSING (2021)

Add to Collection

Article Environmental Sciences

Assessment of Near-Real-Time Satellite Precipitation Products from GSMaP in Monitoring Rainfall Variations over Taiwan

Wan-Ru Huang et al.

Summary: This study evaluated the performance of four satellite precipitation products in representing daily and monthly rainfall variations over Taiwan. The gauge-adjusted products had higher errors in underestimating rainfall compared to non-adjusted products, particularly during the warm season.

REMOTE SENSING (2021)

Add to Collection

Article Meteorology & Atmospheric Sciences

Comprehensive validation of the latest IMERG V06 precipitation estimates over a basin coupled with coastal locations, tropical climate and hill-karst combined landform

Fuwan Gan et al.

Summary: The study evaluated different versions of the Global Precipitation Measurement (IMERG) products using various performance metrics. It found that IMERG V06 has advantages in rainfall detection, but still needs improvement in rainfall overestimation and underestimation.

ATMOSPHERIC RESEARCH (2021)

Add to Collection

Article Meteorology & Atmospheric Sciences

Spatial evaluation of satellite-retrieved extreme rainfall rates in the Upper Awash River Basin, Ethiopia

Kirubel Mekonnen et al.

Summary: This study evaluated the performance of satellite-retrieved extreme rainfall rates in the highland and lowland regions of the Upper Awash Basin in Ethiopia, finding that TAMSATv3 performed best in detecting and estimating low rainfall, while IMERG-v06B, TRMM 3B42v7, and TRMM 3B42RT were relatively better for high rainfall. Microwave-based SREs showed the highest results in capturing high rainfall in both regions, while infrared-based SREs had a better performance for low rainfall.

ATMOSPHERIC RESEARCH (2021)

Add to Collection

Article Meteorology & Atmospheric Sciences

Evaluation of GPM-IMERG and TRMM-3B42 precipitation products over Pakistan

Muhammad Arshad et al.

Summary: The study evaluated Global Precipitation Measurements and Tropical Rainfall Measuring Mission precipitation products over Pakistan, finding that satellite precipitation products performed well in central and southern regions, but were influenced by topography and precipitation intensity. The products were able to capture extreme precipitation events, with the IMERG final run showing the best performance in terms of performance metrics.

ATMOSPHERIC RESEARCH (2021)

Add to Collection

Article Meteorology & Atmospheric Sciences

Performance evaluation and correction of precipitation data using the 20-year IMERG and TMPA precipitation products in diverse subregions of China

Qian Ma et al.

Summary: The study evaluated the accuracy of multi-satellite precipitation products in China over the past two decades, showing that IMERG outperformed TMPA at various time scales and in most regions, making it suitable for large-scale precipitation investigations in China.

ATMOSPHERIC RESEARCH (2021)

Add to Collection

Article Engineering, Civil

Blending multi-satellite, atmospheric reanalysis and gauge precipitation products to facilitate hydrological modelling

Jiabo Yin et al.

Summary: A three-stage blending approach was developed to correct biases in precipitation data, integrating multiple datasets and observational data. The dynamic weights produced through this approach outperformed traditional blending methods, leading to improved hydrological modeling efficiency.

JOURNAL OF HYDROLOGY (2021)

Add to Collection

Article Engineering, Civil

Merging multiple satellite-based precipitation products and gauge observations using a novel double machine learning approach

Ling Zhang et al.

Summary: This study proposed a novel double machine learning approach to merge multiple satellite-based precipitation products and gauge observations, with results showing that the DML algorithms outperform other merging methods and original data in precipitation estimation over the Chinese mainland.

JOURNAL OF HYDROLOGY (2021)

Add to Collection

Article Engineering, Civil

A comprehensive evaluation of GPM-IMERG V06 and MRMS with hourly ground-based precipitation observations across Canada

S. Moazami et al.

Summary: This study evaluates the performance of multiple high-resolution remotely sensed precipitation estimates over Canada, with PrecipitationCal performing best in the Prairies but still having room for improvement in intense precipitation events.

JOURNAL OF HYDROLOGY (2021)

Add to Collection

Article Environmental Sciences

Assessing Near Real-Time Satellite Precipitation Products for Flood Simulations at Sub-Daily Scales in a Sparsely Gauged Watershed in Peruvian Andes

Harold Llauca et al.

Summary: This study investigates the applicability of Satellite Precipitation Products in near real-time for sub-daily runoff simulation in the Vilcanota River basin, finding that the IMERG-E product generally presents higher quality and has the potential for real-time flood monitoring. The results are helpful for implementing flood early warning systems and the monitoring and short-term hydrological forecasting of floods by the Peruvian National Weather and Hydrological Service.

REMOTE SENSING (2021)

Add to Collection

Article Environmental Sciences

Assessment of GPM-Era Satellite Products' (IMERG and GSMaP) Ability to Detect Precipitation Extremes over Mountainous Country Nepal

Bikash Nepal et al.

Summary: This study evaluated two recent satellite precipitation products in the southern slope of the central Himalaya, Nepal, showing that IMERG product performs better in capturing daily precipitation extremes while GSMaP product tends to be more consistent in capturing duration-based extremes.

ATMOSPHERE (2021)

Add to Collection

Article Green & Sustainable Science & Technology

A Novel Stacked Long Short-Term Memory Approach of Deep Learning for Streamflow Simulation

Majid Mirzaei et al.

Summary: This study introduces a novel SLSTM model for daily rainfall-runoff simulation, which outperforms physically-based models like SWAT when not considering data spatial distribution, making it suitable for studying specific phenomena.

SUSTAINABILITY (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A Survey on Data Collection for Machine Learning: A Big Data-AI Integration Perspective

Yuji Roh et al.

Summary: Data collection is a major bottleneck in machine learning due to the lack of labeled data in new applications and the feature generation process in deep learning requiring more labeled data. Research in data collection comes from machine learning, natural language, and computer vision communities, as well as data management due to the importance of handling large amounts of data. The integration of machine learning and data management opens many opportunities for new research in the context of Big Data and Artificial Intelligence (AI) integration.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2021)

Add to Collection

Article Computer Science, Information Systems

Analysis of Gradient Vanishing of RNNs and Performance Comparison

Seol-Hyun Noh

Summary: The study analyzed the problem of gradient vanishing in standard RNN, LSTM, and GRU, showing that LSTM and GRU have higher learning ability and better performance in long-range input data learning, leading to higher validation accuracy and prediction accuracy compared to standard RNN.

INFORMATION (2021)

Add to Collection

Article Environmental Sciences

A Novel Modeling Strategy of Weighted Mean Temperature in China Using RNN and LSTM

Wenliang Gao et al.

Summary: In this study, a high-precision weighted mean temperature model for China was built using deep learning algorithms, which showed good accuracy and generalization in prediction. The recurrent neural network (RNN) and long short-term memory neural network (LSTM) models demonstrated strong performance in predicting weighted mean temperature.

REMOTE SENSING (2021)

Add to Collection

Review Computer Science, Theory & Methods

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Laith Alzubaidi et al.

Summary: Deep learning has become the gold standard in the machine learning community, widely used in various domains and capable of learning massive data. Through a comprehensive survey, a better understanding of the most important aspects of deep learning is provided.

JOURNAL OF BIG DATA (2021)

Add to Collection

Article Geosciences, Multidisciplinary

A two-stage blending approach for merging multiple satellite precipitation estimates and rain gauge observations: an experiment in the northeastern Tibetan Plateau

Yingzhao Ma et al.

Summary: A two-stage blending approach was proposed to improve gridded precipitation estimates by correcting systematic errors in satellite precipitation estimates and merging them with a Bayesian weighting model. This method can extract benefits from bias-corrected estimates and mitigate negative impacts from lower quality data. The study demonstrated significant improvements in blended estimates compared to original estimates, even in heavy rainfall events.

HYDROLOGY AND EARTH SYSTEM SCIENCES (2021)

Add to Collection

Article Geochemistry & Geophysics

A Machine Learning System for Precipitation Estimation Using Satellite and Ground Radar Network Observations

Haonan Chen et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2020)

Add to Collection

Article Mathematics, Applied

Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network

Alex Sherstinsky

PHYSICA D-NONLINEAR PHENOMENA (2020)

Add to Collection

Article Engineering, Civil

A spatiotemporal deep fusion model for merging satellite and gauge precipitation in China

Hongcai Wu et al.

JOURNAL OF HYDROLOGY (2020)

Add to Collection

Article Engineering, Civil

Improving satellite rainfall estimation from MSG data in Northern Algeria by using a multi-classifier model based on machine learning

Mourad Lazri et al.

JOURNAL OF HYDROLOGY (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Transductive LSTM for time-series prediction: An application to weather forecasting

Zahra Karevan et al.

NEURAL NETWORKS (2020)

Add to Collection

Article Mathematics, Applied

Forecasting of extreme flood events using different satellite precipitation products and wavelet-based machine learning methods

Pavan Kumar Yeditha et al.

CHAOS (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Improving near real-time precipitation estimation using a U-Net convolutional neural network and geographical information

Mojtaba Sadeghi et al.

ENVIRONMENTAL MODELLING & SOFTWARE (2020)

Add to Collection

Review Engineering, Electrical & Electronic

Google Earth Engine Cloud Computing Platform for Remote Sensing Big Data Applications: A Comprehensive Review

Meisam Amani et al.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2020)

Add to Collection

Article Multidisciplinary Sciences

Machine Learning-Based Error Modeling to Improve GPM IMERG Precipitation Product over the Brahmaputra River Basin

Md Abul Ehsan Bhuiyan et al.

FORECASTING (2020)

Add to Collection

Article Meteorology & Atmospheric Sciences

Assessment of satellite precipitation product estimates over Bali Island

Chian-Yi Liu et al.

ATMOSPHERIC RESEARCH (2020)

Add to Collection

Article Water Resources

Evaluation of satellite precipitation products for extreme flood events: case study in Peninsular Malaysia

Eugene Zhen Xiang Soo et al.

JOURNAL OF WATER AND CLIMATE CHANGE (2019)

Add to Collection

Article Environmental Sciences

Improving Monsoon Precipitation Prediction Using Combined Convolutional and Long Short Term Memory Neural Network

Qinghua Miao et al.

WATER (2019)

Add to Collection

Article Environmental Sciences

Estimating High Spatio-Temporal Resolution Rainfall from MSG1 and GPM IMERG Based on Machine Learning: Case Study of Iran

Nazli Turini et al.

REMOTE SENSING (2019)

Add to Collection

Article Energy & Fuels

A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data

Shikhar Srivastava et al.

SOLAR ENERGY (2018)

Add to Collection

Article Environmental Sciences

Adjustment of global precipitation data for enhanced hydrologic modeling of tropical Andean watersheds

Michael Strauch et al.

CLIMATIC CHANGE (2017)

Add to Collection

Article Water Resources

Enhanced identification of a hydrologic model using streamflow and satellite water storage data: A multicriteria sensitivity analysis and optimization approach

Fuad Yassin et al.

HYDROLOGICAL PROCESSES (2017)

Add to Collection

Article Meteorology & Atmospheric Sciences

Extreme Rainstorms that Caused Devastating Flooding across the East Coast of Peninsular Malaysia during November and December 2014

Ooi See Hai et al.

WEATHER AND FORECASTING (2017)

Add to Collection

Article Meteorology & Atmospheric Sciences

Climate Engine: Cloud Computing and Visualization of Climate and Remote Sensing Data for Advanced Natural Resource Monitoring and Process Understanding

Justin L. Huntington et al.

BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY (2017)

Add to Collection

Article Meteorology & Atmospheric Sciences

SO, HOW MUCH OF THE EARTH'S SURFACE IS COVERED BY RAIN GAUGES?

Chris Kidd et al.

BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY (2017)

Add to Collection

Article Meteorology & Atmospheric Sciences

Comparison of four machine learning algorithms for their applicability in satellite-based optical rainfall retrievals

Hanna Meyer et al.

ATMOSPHERIC RESEARCH (2016)

Add to Collection

Article Engineering, Civil

Random walk method for modeling water exchange: An application to coastal zone environmental management

Xiangcui Lv et al.

JOURNAL OF HYDRO-ENVIRONMENT RESEARCH (2016)

Add to Collection

Article Physics, Multidisciplinary

Method for Measuring the Information Content of Terrain from Digital Elevation Models

Lujin Hu et al.

ENTROPY (2015)

Add to Collection

Article Geosciences, Multidisciplinary

Trends in rainfall and rainfall-related extremes in the east coast of peninsular Malaysia

OLANIYA OLUSEGUN MAYOWA et al.

Journal of Earth System Science (2015)

Add to Collection

Article Computer Science, Information Systems

Data Series Management: The Road to Big Sequence Analytics

Themis Palpanas

SIGMOD RECORD (2015)

Add to Collection

Article Multidisciplinary Sciences

The climate hazards infrared precipitation with stations-a new environmental record for monitoring extremes

Chris Funk et al.

SCIENTIFIC DATA (2015)

Add to Collection

Article Environmental Sciences

Improving the accuracy of rainfall rates from optical satellite sensors with machine learning - A random forests-based approach applied to MSG SEVIRI

Meike Kuehnlein et al.

REMOTE SENSING OF ENVIRONMENT (2014)

Add to Collection

Article Engineering, Civil

Merging gauge and satellite rainfall with specification of associated uncertainty across Australia

Fitsum M. Woldemeskel et al.

JOURNAL OF HYDROLOGY (2013)

Add to Collection

Article Engineering, Civil

Comprehensive evaluation of multi-satellite precipitation products with a dense rain gauge network and optimally merging their simulated hydrological flows using the Bayesian model averaging method

Shanhu Jiang et al.

JOURNAL OF HYDROLOGY (2012)

Add to Collection

Article Engineering, Civil

Runoff conditions in the upper Danube basin under an ensemble of climate change scenarios

Harald Kling et al.

JOURNAL OF HYDROLOGY (2012)

Add to Collection

Article Engineering, Civil

Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling

Hoshin V. Gupta et al.

JOURNAL OF HYDROLOGY (2009)

Add to Collection

Article Environmental Sciences

Components of information for multiple resolution comparison between maps that share a real variable

Robert Gilmore Pontius et al.

ENVIRONMENTAL AND ECOLOGICAL STATISTICS (2008)

Add to Collection

Article Meteorology & Atmospheric Sciences

Numerical case study of an extreme rainfall event during 9-11 December 2004 over the east coast of Peninsular Malaysia

L. Juneng et al.

METEOROLOGY AND ATMOSPHERIC PHYSICS (2007)

Add to Collection

Article Geochemistry & Geophysics

Global precipitation map using satellite-borne microwave radiometers by the GSMaP project: Production and validation

Takuji Kubota et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2007)

Add to Collection

Article Meteorology & Atmospheric Sciences

The TRMM multisatellite precipitation analysis (TMPA): Quasi-global, multiyear, combined-sensor precipitation estimates at fine scales

George J. Huffman et al.

JOURNAL OF HYDROMETEOROLOGY (2007)

Add to Collection

Article Computer Science, Information Systems

On the use of dimensioned measures of error to evaluate the performance of spatial interpolators

CJ Willmott et al.

INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE (2006)

Add to Collection

Article Economics

Another look at measures of forecast accuracy

Rob J. Hyndman et al.

INTERNATIONAL JOURNAL OF FORECASTING (2006)

Add to Collection

© Peeref 2019-2024. All rights reserved.