Deep learning and regression modelling of cloudless downward longwave radiation

Obot, Nsikan I.; Humphrey, Ibifubara; Chendo, M.A.C.; Udo, Sunday O.

doi:10.1186/s43088-019-0018-8

Cited by 4 publications

(2 citation statements)

References 123 publications

(153 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several intelligent algorithms and optimization techniques [71][72][73][74][75][76][77][78][79][80][81][82][83][84][85] have been deployed to solve various boundary value problems in physical sciences. This section contains a brief explanation of machine learning methods implemented in estimating undersaturated oil viscosity.…”

Section: Methodsmentioning

confidence: 99%

An assessment of ensemble learning approaches and single-based machine learning algorithms for the characterization of undersaturated oil viscosity

Akano

James

2022

Beni-Suef Univ J Basic Appl Sci

View full text Add to dashboard Cite

Background Prediction of accurate crude oil viscosity when pressure volume temperature (PVT) experimental results are not readily available has been a major challenge to the petroleum industry. This is due to the substantial impact an inaccurate prediction will have on production planning, reservoir management, enhanced oil recovery processes and choice of design facilities such as tubing, pipeline and pump sizes. In a bid to attain improved accuracy in predictions, recent research has focused on applying various machine learning algorithms and intelligent mechanisms. In this work, an extensive comparative analysis between single-based machine learning techniques such as artificial neural network, support vector machine, decision tree and linear regression, and ensemble learning techniques such as bagging, boosting and voting was performed. The prediction performance of the models was assessed by using five evaluation measures, namely mean absolute error, relative squared error, mean squared error, root mean squared error and root mean squared log error. Results The ensemble methods offered generally higher prediction accuracies than single-based machine learning techniques. In addition, weak single-based learners of the dataset used in this study (for example, SVM) were transformed into strong ensemble learners with better prediction performance when used as based learners in the ensemble method, while other strong single-based learners were discovered to have had significantly improved prediction performance. Conclusion The ensemble methods have great prospects of enhancing the overall predictive accuracy of single-based learners in the domain of reservoir fluid PVT properties (such as undersaturated oil viscosity) prediction.

show abstract

Section: Methodsmentioning

confidence: 99%

An assessment of ensemble learning approaches and single-based machine learning algorithms for the characterization of undersaturated oil viscosity

Akano

James

2022

Beni-Suef Univ J Basic Appl Sci

View full text Add to dashboard Cite

show abstract

“…Evaluation of DSLF products is performed using ground stations provided by two separate databases: BSRN (Driemel et al, 2018) and FLUXNET2015 (Pastorello et al, 2020). BSRN data (https://bsrn.awi.de/; accessed on 22 January 2024) are often used for downward longwave radiation studies (e.g., Obot et al, 2019;Roesch et al, 2011;Wild et al, 2001;Zhang et al, 2015), serving as reference for radiation measurements over the last decades, given the high-quality standards for the measured data. In the present work, following the data preprocessing (described further on), measured data from 17 (out of 57 in total) operational BSRN ground stations (temporally aggregated to hourly and then to monthly values) is used to validate DSLF estimates produced Journal of Geophysical Research: Atmospheres 10.1029/2023JD040306 with the MARS algorithm considering a 19-year period (from 2004 to 2022).…”

Section: Observational Datamentioning

confidence: 99%

Evaluation of Downward Surface Longwave Flux Estimates Using Meteosat Cloud Observations

Lopes,

Dutra,

Trigo

et al. 2024

JGR Atmospheres

View full text Add to dashboard Cite

The downward surface longwave flux (DSLF) plays a relevant role in the Earth’s surface radiative budget, which is crucial to monitor, understand and model the impact of changes at local and global scales on surface temperature and surface conditions. This study focuses on the evaluation and intercomparison of four DSLF products: (a) a recently developed all‐weather DSLF product based on the multivariate adaptive regression splines (MARS) algorithm driven by satellite cloud information from the Meteosat Second Generation (MSG) and ERA5 reanalysis screen variables; (b) the Satellite Application Facility on Land Surface Analysis (LSA SAF); (c) CERES Synoptic top‐of‐atmosphere and surface fluxes and clouds (CERES‐SYN1deg) and (d) ERA5 reanalysis. The study covers the period 2005–2021 and the MSG region focusing on monthly means. The evaluation performed against 48 ground stations from the Baseline Surface Radiation Network (BSRN) and FLUXNET2015 networks showed that the MARS product outperforms the remaining products, particularly the LSA SAF, while ERA5 and CERES show similar performance metrics. The fours products are intercompared in terms of their mean spatial variability and temporal mean annual cycles and inter‐annual variability in four selected regions, showing a high level of agreement, particularly between MARS, ERA5 and CERES. Our results highlight the clear added value of MARS with respect to LSA SAF, while providing higher spatial resolution (0.05°), constrained by satellite cloud information, when compared with ERA5 (0.25°) or CERES (1°).

show abstract

Comparison of different techniques for estimation of incoming longwave radiation

Bilgiç

Mert

2020

Int. J. Environ. Sci. Technol.

View full text Add to dashboard Cite

Deep learning and regression modelling of cloudless downward longwave radiation

Cited by 4 publications

References 123 publications

An assessment of ensemble learning approaches and single-based machine learning algorithms for the characterization of undersaturated oil viscosity

An assessment of ensemble learning approaches and single-based machine learning algorithms for the characterization of undersaturated oil viscosity

Evaluation of Downward Surface Longwave Flux Estimates Using Meteosat Cloud Observations

Comparison of different techniques for estimation of incoming longwave radiation

Contact Info

Product

Resources

About