Multi-model ensemble predictions of precipitation and temperature using machine learning algorithms

Atmospheric Research, Journal Year: 2019, Volume and Issue: 236, P. 104806 - 104806

Published: Dec. 20, 2019

Language: Английский

---

Selection of multi-model ensemble of general circulation models for the simulation of precipitation and maximum and minimum temperature based on spatial assessment metrics

Hydrology and earth system sciences, Journal Year: 2019, Volume and Issue: 23(11), P. 4803 - 4824

Published: Nov. 25, 2019

Abstract. The climate modelling community has trialled a large number of metrics for evaluating the temporal performance general circulation models (GCMs), while very little attention been given to assessment their spatial performance, which is equally important. This study evaluated 36 Coupled Model Intercomparison Project 5 (CMIP5) GCMs in relation skills simulating mean annual, monsoon, winter, pre-monsoon, and post-monsoon precipitation maximum minimum temperature over Pakistan using state-of-the-art metrics, SPAtial EFficiency, fractions skill score, Goodman–Kruskal's lambda, Cramer's V, Mapcurves, Kling–Gupta efficiency, period 1961–2005. multi-model ensemble (MME) data were generated through intelligent merging simulated selected employing random forest (RF) regression simple (SM) techniques. results indicated some differences ranks different metrics. overall NorESM1-M, MIROC5, BCC-CSM1-1, ACCESS1-3 as best patterns Pakistan. MME based on best-performing showed more similarities with observed compared by individual GCMs. MMEs developed RF displayed better than SM. Multiple have used first time selecting capability mimic annual seasonal temperature. approach proposed present can be extended any variables applicable region suitable selection an reduce uncertainties projections.

Language: Английский

---

Selection of climate models for projection of spatiotemporal changes in temperature of Iraq with uncertainties

Atmospheric Research, Journal Year: 2018, Volume and Issue: 213, P. 509 - 522

Published: July 7, 2018

Language: Английский

---

Evaluation of CMIP6 GCM rainfall in mainland Southeast Asia

Atmospheric Research, Journal Year: 2021, Volume and Issue: 254, P. 105525 - 105525

Published: Feb. 17, 2021

Language: Английский

---

Precipitation projection using a CMIP5 GCM ensemble model: a regional investigation of Syria

Engineering Applications of Computational Fluid Mechanics, Journal Year: 2019, Volume and Issue: 14(1), P. 90 - 106

Published: Nov. 7, 2019

The possible changes in precipitation of Syrian due to climate change are projected this study. symmetrical uncertainty (SU) and multi-criteria decision-analysis (MCDA) methods used identify the best general circulation models (GCMs) for projections. effectiveness four bias correction methods, linear scaling (LS), power transformation (PT), quantile mapping (GEQM), gamma (GAQM) is assessed downscaling GCM simulated precipitation. A random forest (RF) model performed generate multi ensemble (MME) projections representative concentration pathways (RCPs) 2.6, 4.5, 6.0, 8.5. results showed that suited GCMs projection Syria HadGEM2-AO, CSIRO-Mk3-6-0, NorESM1-M, CESM1-CAM5. LS demonstrated highest capability downscaling. Annual decrease by −30 −85.2% RCPs 8.5, while < 0.0 −30% RCP 2.6. entire country increase some parts other during wet season. dry season −12 −93%, which indicated a drier future.

Language: Английский

---

Evaluation and projection of precipitation in Pakistan using the Coupled Model Intercomparison Project Phase 6 model simulations

International Journal of Climatology, Journal Year: 2022, Volume and Issue: 42(13), P. 6665 - 6684

Published: March 6, 2022

Abstract This study aimed to evaluate the performance of global climate models (GCMs) from family Coupled Model Intercomparison Project Phase 6 (CMIP6) in historical simulation precipitation and select best performing GCMs for future projection Pakistan under multiple shared socioeconomic pathways (SSPs). The spatiotemporal was evaluated against Climate Research Unit (CRU) data simulating annual during 1951–2014, using Taylor diagram interannual variability skill (IVS). Moreover, modified Mann–Kendall (mMK) Sen's slope estimator (SSE) tests were employed estimate significant trends period 2015–2100. Based on comprehensive ranking index (CRI), HadGEM3‐GC31‐MM model has highest distributions followed by EC‐Earth3‐Veg‐LR, CNRM‐ESM2‐1, MPI‐ESM1‐2‐HR, CNRM‐CM6‐1, MRI‐ESM2‐0, CNRM‐CM6‐1‐HR, EC‐Earth3‐Veg, MCM‐UA‐1‐0, INM‐CM5‐0, KACE‐1‐0‐G, CAMS‐CSM1‐0, HadGEM3‐GC31‐LL models. Furthermore, projections ensemble mean (BMEM) showed that region will experience a substantial increase SSP3‐7.0 SSP5‐8.5 but an indolent rise SSP1‐2.6 SSP2‐4.5 scenarios. summer precipitations exhibit statistically increasing trend relative winter season most magnitude monotonic seasonal progresses low forcing scenario (SSP1‐2.6) high (SSP5‐8.5). findings could provide benchmark selecting appropriate over scare region, like Pakistan. projected are crucial devising adaption mitigation actions towards sustainable planning water resource management, food security, disaster risk management.

Language: Английский

---

Performance Assessment of General Circulation Model in Simulating Daily Precipitation and Temperature Using Multiple Gridded Datasets

Water, Journal Year: 2018, Volume and Issue: 10(12), P. 1793 - 1793

Published: Dec. 6, 2018

The performance of general circulation models (GCMs) in a region are generally assessed according to their capability simulate historical temperature and precipitation the region. 31 GCMs Coupled Model Intercomparison Project Phase 5 (CMIP5) is evaluated this study identify suitable ensemble for daily maximum, minimum Pakistan using multiple sets gridded data, namely: Asian Precipitation–Highly-Resolved Observational Data Integration Towards Evaluation (APHRODITE), Berkeley Earth Surface Temperature (BEST), Princeton Global Meteorological Forcing (PGF) Climate Prediction Centre (CPC) data. An entropy-based robust feature selection approach known as symmetrical uncertainty (SU) used ranking GCM. It from results that spatial distribution best-ranked varies different also found vary both temperatures precipitation. Commonwealth Scientific Industrial Research Organization, Australia (CSIRO)-Mk3-6-0 Max Planck Institute (MPI)-ESM-LR perform well while EC-Earth MIROC5 A trade-off formulated select common climatic variables data sets, which six GCMs, ACCESS1-3, CESM1-BGC, CMCC-CM, HadGEM2-CC, HadGEM2-ES reliable projection Pakistan.

Language: Английский

---

Changing characteristics of meteorological droughts in Nigeria during 1901–2010

Atmospheric Research, Journal Year: 2019, Volume and Issue: 223, P. 60 - 73

Published: March 5, 2019

Language: Английский

---

Projection of meteorological droughts in Nigeria during growing seasons under climate change scenarios

Scientific Reports, Journal Year: 2020, Volume and Issue: 10(1)

Published: June 22, 2020

Abstract Like many other African countries, incidence of drought is increasing in Nigeria. In this work, spatiotemporal changes droughts under different representative concentration pathway (RCP) scenarios were assessed; considering their greatest impacts on life and livelihoods Nigeria, especially when coincide with the growing seasons. Three entropy-based methods, namely symmetrical uncertainty, gain ratio, entropy used a multi-criteria decision-making framework to select best performing General Circulation Models (GCMs) for projection rainfall temperature. Performance four widely bias correction methods was compared identify suitable method correcting GCM projections period 2010–2099. A machine learning technique then generate multi-model ensemble (MME) bias-corrected RCP scenarios. The standardized precipitation evapotranspiration index (SPEI) subsequently computed estimate from MME mean projected temperature predict possible meteorological droughts. Finally, trends SPEI, rainfall, return seasons estimated using 50-year moving window, 10-year interval, understand driving factors accountable future analysis revealed that MRI-CGCM3, HadGEM2-ES, CSIRO-Mk3-6-0, CESM1-CAM5 are most appropriate GCMs projecting temperature, linear scaling (SCL) bias. an increase south-south, southwest, parts northwest whilst decrease southeast, northeast, central contrast, rise entire country during cropping projected. results further indicated would SPEI across which will make more frequent all RCPs. However, frequency be less higher RCPs due rainfall.

Language: Английский

---

Modeling and Uncertainty Analysis of Groundwater Level Using Six Evolutionary Optimization Algorithms Hybridized with ANFIS, SVM, and ANN

Sustainability, Journal Year: 2020, Volume and Issue: 12(10), P. 4023 - 4023

Published: May 14, 2020

In the present study, six meta-heuristic schemes are hybridized with artificial neural network (ANN), adaptive neuro-fuzzy interface system (ANFIS), and support vector machine (SVM), to predict monthly groundwater level (GWL), evaluate uncertainty analysis of predictions spatial variation analysis. The schemes, including grasshopper optimization algorithm (GOA), cat swarm (CSO), weed (WA), genetic (GA), krill (KA), particle (PSO), were used hybridize for improving performance ANN, SVM, ANFIS models. Groundwater (GWL) data Ardebil plain (Iran) a period 144 months selected hybrid pre-processing technique principal component (PCA) was applied reduce input combinations from time series up 12-month prediction intervals. results showed that ANFIS-GOA superior other models predicting GWL in first piezometer (RMSE:1.21, MAE:0.878, NSE:0.93, PBIAS:0.15, R2:0.93), second (RMSE:1.22, MAE:0.881, NSE:0.92, PBIAS:0.17, R2:0.94), third (RMSE:1.23, MAE:0.911, NSE:0.91, PBIAS:0.19, R2:0.94) testing stage. algorithms far better than classical ANFIS, SVM without hybridization. percent improvements versus standalone 10 14.4%, 3%, 17.8%, 181% RMSE, MAE, NSE, PBIAS training stage 40.7%, 55%, 25%, 132% stage, respectively. 6 train step 15%, 4%, 13%, 208% test 33%, 44.6%, 16.3%, 173%, respectively, clearly confirm superiority developed hybridization modelling. Uncertainty had, best worst performances among general, GOA enhanced accuracy

Language: Английский

---