Displacement prediction of landslide based on generalized regression neural networks with K-fold cross-validation

Jiang, Ping; Chen, Jie‐Jie

doi:10.1016/j.neucom.2015.08.118

Cited by 138 publications

(47 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Model tuning. For all ML algorithms, k-fold cross-validation method is performed to determine the optimal model settings and evaluating the generalized model performance to an independent data set 47,48 . The k-fold cross validation also helps to avoid overfitting.…”

Section: Ensemble Learningmentioning

confidence: 99%

Long-lead Prediction of ENSO Modoki Index using Machine Learning algorithms

Pal

Maity

Ratnam

et al. 2020

Sci Rep

View full text Add to dashboard Cite

The focus of this study is to evaluate the efficacy of Machine Learning (ML) algorithms in the long-lead prediction of El Niño (La Niña) Modoki (ENSO Modoki) index (EMI). We evaluated two widely used nonlinear ML algorithms namely Support Vector Regression (SVR) and Random Forest (RF) to forecast the EMI at various lead times, viz. 6, 12, 18 and 24 months. The predictors for the EMI are identified using Kendall's tau correlation coefficient between the monthly EMI index and the monthly anomalies of the slowly varying climate variables such as sea surface temperature (SST), sea surface height (SSH) and soil moisture content (SMC). The importance of each of the predictors is evaluated using the Supervised Principal Component Analysis (SPCA). The results indicate both SVR and RF to be capable of forecasting the phase of the EMI realistically at both 6-months and 12-months lead times though the amplitude of the eMi is underestimated for the strong events. the analysis also indicates the SVR to perform better than the Rf method in forecasting the eMi. The El Niño (La Niña) Modoki (ENSO Modoki, hereafter EM) 1 is a newly acknowledged phenomenon characterized by warm (cool) central Pacific sea surface temperature (SST) flanked by cool (warm) eastern and western Pacific SSTs. The EM events affect the global climate at various time scales. The EM affects the equatorial or near equatorial countries by the modified Walker circulation with rising (sinking) motion in the central equatorial Pacific and sinking (rising) motion over the west and east Pacific during EM warm (cold) events and other parts of the globe are affected by the atmospheric teleconnections due to the distribution of heating associated with the equatorial SST anomalies during the EM events 2-8. Although impacts of EM events have been well established, the EM is apparently not so well predicted at long lead times by current operational climate forecast models 2,9-14. The Bureau of Meteorology Predictive Ocean Atmosphere Model for Australia (POAMA) coupled seasonal forecast model showed a partial success in predicting differences between Modoki and canonical El Niños one season ahead with correlation coefficient more than 0.6 15,16. APEC Climate Center (APCC) Multi-Model Ensemble (MME) seasonal forecast system shows the ability to predict the patterns of tropical Pacific SST anomaly (SSTA) of the Modoki events four months ahead with a high correlation coefficient i.e. 0.8 17. However, the predictability of anomalous SST patterns in the APCC MME is seasonally dependent. The IAP-DecPreS near-term climate prediction system, though could predict the EMI with a good skill (correlations coefficient of 0.62 and 0.53) at 4 and 7 months lead, has limited skill (correlation coefficient 0.43) at a lead time of 10 months and beyond 18. All the above models have difficulties in forecasting the amplitude of the EMI events though they forecast the phase of the EMI realistically. The limited skill in predicting the ENSO Modoki index (EMI) in terms of long lead times by the c...

show abstract

Section: Ensemble Learningmentioning

confidence: 99%

Long-lead Prediction of ENSO Modoki Index using Machine Learning algorithms

Pal

Maity

Ratnam

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…This process is repeated K times, and each K subsample is used exactly once as the validation data. The K results from the folds can then be averaged (or otherwise combined) to produce a single estimation (Jiang & Chen, 2016). This strategy was used for SVM validation using K = 10 and the mean accuracy was considered as the final accuracy for SVM.…”

Section: Methodsmentioning

confidence: 99%

Performance comparison of machine learning techniques in sleep scoring based on wavelet features and neighboring component analysis

Savareh

Bashiri

Behmanesh

et al. 2018

PeerJ

View full text Add to dashboard Cite

IntroductionSleep scoring is an important step in the treatment of sleep disorders. Manual annotation of sleep stages is time-consuming and experience-relevant and, therefore, needs to be done using machine learning techniques.MethodsSleep-EDF polysomnography was used in this study as a dataset. Support vector machines and artificial neural network performance were compared in sleep scoring using wavelet tree features and neighborhood component analysis.ResultsNeighboring component analysis as a combination of linear and non-linear feature selection method had a substantial role in feature dimension reduction. Artificial neural network and support vector machine achieved 90.30% and 89.93% accuracy, respectively.Discussion and ConclusionSimilar to the state of the art performance, the introduced method in the present study achieved an acceptable performance in sleep scoring. Furthermore, its performance can be enhanced using a technique combined with other techniques in feature generation and dimension reduction. It is hoped that, in the future, intelligent techniques can be used in the process of diagnosing and treating sleep disorders.

show abstract

“…A small number of hidden nodes may cause under-fitting, while larger numbers favor increasing accuracy but with a larger risk of over-fitting. Instead of a trial and error approach to optimize this tradeoff, the k-fold cross-validation (CV) is pursued here for selecting an optimal number of neurons [107,108]. The CV approach sequentially partitions the…”

Section: Fundingmentioning

confidence: 99%

Enhancing Precipitation Estimates Through the Fusion of Weather Radar, Satellite Retrievals, and Surface Parameters

2020

View full text Add to dashboard Cite

Accurate and timely monitoring of precipitation remains a challenge, particularly in hyper-arid regions such as the United Arab Emirates (UAE). The aim of this study is to improve the accuracy of the Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM) mission’s latest product release (IMERG V06B) locally over the UAE. Two distinct approaches, namely, geographically weighted regression (GWR), and artificial neural networks (ANNs) are tested. Daily soil moisture retrievals from the Soil Moisture Active Passive (SMAP) mission (9 km), terrain elevations from the Advanced Spaceborne Thermal Emission and Reflection digital elevation model (ASTER DEM, 30 m) and precipitation estimates (0.5 km) from a weather radar network are incorporated as explanatory variables in the proposed GWR and ANN model frameworks. First, the performances of the daily GPM and weather radar estimates are assessed using a network of 65 rain gauges from 1 January 2015 to 31 December 2018. Next, the GWR and ANN models are developed with 52 gauges used for training and 13 gauges reserved for model testing and seasonal inter-comparisons. GPM estimates record higher Pearson correlation coefficients (PCC) at rain gauges with increasing elevation (z) and higher rainfall amounts (PCC = 0.29 z0.12), while weather radar estimates perform better for lower elevations and light rain conditions (PCC = 0.81 z−0.18). Taylor diagrams indicate that both the GWR- and the ANN-adjusted precipitation products outperform the original GPM and radar estimates, with the poorest correction obtained by GWR during the summer period. The incorporation of soil moisture resulted in improved corrections by the ANN model compared to the GWR, with relative increases in Nash–Sutcliffe efficiency (NSE) coefficients of 56% (and 25%) for GPM estimates, and 34% (and 53%) for radar estimates during summer (and winter) periods. The ANN-derived precipitation estimates can be used to force hydrological models over ungauged areas across the UAE. The methodology is expandable to other arid and hyper-arid regions requiring improved precipitation monitoring.

show abstract

Displacement prediction of landslide based on generalized regression neural networks with K-fold cross-validation

Cited by 138 publications

References 27 publications

Long-lead Prediction of ENSO Modoki Index using Machine Learning algorithms

Long-lead Prediction of ENSO Modoki Index using Machine Learning algorithms

Performance comparison of machine learning techniques in sleep scoring based on wavelet features and neighboring component analysis

Enhancing Precipitation Estimates Through the Fusion of Weather Radar, Satellite Retrievals, and Surface Parameters

Contact Info

Product

Resources

About