Evaluation of IMERG and ERA5 precipitation products over the Mongolian Plateau

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Dec. 16, 2022

Abstract Precipitation is an important component of the hydrological cycle and has significant impact on ecological environment social development, especially in arid areas where water resources are scarce. As a typical semi-arid region, Mongolian Plateau ecologically fragile highly sensitive to climate change. Reliable global precipitation data urgently needed for sustainable development over this gauge-deficient region. With high-quality estimates, fine spatiotemporal resolutions, wide coverage, state-of-the-art Integrated Multi-satellite Retrievals Global Measurement (IMERG) European Center Medium-range Weather Forecasts Reanalysis 5 (ERA5) have great potential regional climatic, hydrological, applications. However, how they perform not been well investigated Plateau. Therefore, study evaluated performance three IMERG V06 datasets (ER, LR FR), two ERA5 products (ERA5-HRES ERA5-Land), their predecessors (TMPA-3B42 ERA-Interim) region across 2001–2018. The results showed that all broadly characterized seasonal cycles spatial patterns, but only reanalysis products, FR TMPA-3B42 could capture interannual decadal variability. When describing daily precipitation, dataset performances ranked ERA5-Land > ERA5-HRES ERA-Interim ER TMPA-3B42. All deficiencies overestimating weak underestimating high-intensity precipitation. Besides, performed best agricultural lands forests along northern south-eastern edges, followed by urban grasslands closer center, worst sparse vegetation bare south-west. Due negative effect topographic complexity, poor detection capabilities forests. Accordingly, research currently supports applicability arid, topographically complex Plateau, which can inform applications with different requirements.

Language: Английский

---

A two-step merging strategy for incorporating multi-source precipitation products and gauge observations using machine learning classification and regression over China

Hydrology and earth system sciences, Journal Year: 2022, Volume and Issue: 26(11), P. 2969 - 2995

Published: June 15, 2022

Abstract. Although many multi-source precipitation products (MSPs) with high spatiotemporal resolution have been extensively used in water cycle research, they are still subject to various biases, including false alarm and missed bias. Precipitation merging technology is an effective means alleviate this uncertainty. However, how efficiently improve detection efficiency intensity simultaneously a problem worth exploring. This study presents two-step strategy based on machine learning (ML) algorithms, gradient boosting decision tree (GBDT), extreme (XGBoost), random forest (RF). It incorporates six state-of-the-art MSPs (GSMaP, IMERG, PERSIANN-CDR, CMORPH, CHIRPS, ERA5-Land) rain gauges the accuracy of identification estimation from 2000 2017 over China. Multiple environment variables spatial autocorrelation combined process. The first employs classification models identify wet dry days then combines regression predict amounts classified days. merged results compared traditional methods, multiple linear (MLR), ML models, gauge-based Kriging interpolation. A total 1680 (70 %) randomly chosen for model training 692 (30 performance evaluation. show that (1) (MSMPs) outperformed all original terms statistical categorical metrics, which substantially alleviates temporal biases. modified Kling–Gupta (KGE), critical success index (CSI), Heidke Skill Score (HSS) improved by 15 %–85 %, 17 %–155 21 %–166 respectively. (2) plays significant role merging, considerably improves accuracy. (3) MSMPs obtained proposed method superior MLR, interpolation, models. XGBoost algorithm recommended more large-scale data owing its computational efficiency. (4) performs better when higher-density training. it has strong robustness can also obtain than even gauge number reduced 10 % (237). provides accurate reliable under complex climatic topographic conditions. could be applied other areas well if available.

Language: Английский

---

Fusion of gauge-based, reanalysis, and satellite precipitation products using Bayesian model averaging approach: Determination of the influence of different input sources

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 618, P. 129234 - 129234

Published: Feb. 7, 2023

Language: Английский

---

Improving Solar PV Prediction Performance with RF-CatBoost Ensemble: A Robust and Complementary Approach

Renewable energy focus, Journal Year: 2023, Volume and Issue: 46, P. 207 - 221

Published: June 28, 2023

Language: Английский

---

Improving rainfall-runoff modeling in the Mekong river basin using bias-corrected satellite precipitation products by convolutional neural networks

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 630, P. 130762 - 130762

Published: Jan. 24, 2024

Accurate rainfall-runoff (RR) modeling is crucial for effective Mekong River Basin (MRB) water resource management. Satellite precipitation products (SPPs) can offer valuable data such modeling; however, these often exhibit biases that may adversely affect hydrological simulations. This study aimed to improve RR using bias-corrected SPPs and the Soil Water Assessment Tool (SWAT) model MRB. A convolutional neural network-based deep learning framework was employed correct in four (TRMM, PERSIANN-CDR, CHIRPS, CMORPH), resulting respective (ADJ_TRMM, ADJ_CDR, ADJ_CHIR, ADJ_CMOR). The were compared against a gauge-based dataset terms of rainfall analysis, their performance within SWAT assessed over calibration (2004-2013) validation (2014-2015). Bias-corrected demonstrated superior with ADJ_TRMM outperforming other products. results showed satisfactory across all stations, Nash-Sutcliffe Efficiency (NSE) ranging from [0.76-0.87]. Integrating into significantly increased simulations MRB, indicated by higher NSE values [0.72-0.85] uncorrected [-0.37 0.85] at Kratie station. Besides, inconsistent between analysis observed, ADJ_CDR model. These highlight significance applications, especially areas limited ground-based data, need further research refine bias correction methods address limitations

Language: Английский

---

Spatiotemporal dependence of soil moisture and precipitation over India

Journal of Hydrology, Journal Year: 2022, Volume and Issue: 610, P. 127898 - 127898

Published: May 10, 2022

Language: Английский

---

Reference evapotranspiration estimation in hyper-arid regions via D-vine copula based-quantile regression and comparison with empirical approaches and machine learning models

Journal of Hydrology Regional Studies, Journal Year: 2022, Volume and Issue: 44, P. 101259 - 101259

Published: Nov. 5, 2022

Two hyper-arid regions (Atbara and Kassala stations) in Sudan. The study aims to evaluate the potential of D-vine Copula-based quantile regression (DVQR) model for estimating daily ETo during 2000–2015 based on various input structures. Further, DVQR was compared with Multivariate Linear (MLQR), Bayesians Model Averaging (BMAQR), Empirical Models (EMMs), Classical Machine Learning (CML). Besides, CML models including Random Forest (RF), Support Vector (SVM), Extreme (ELM), Gradient Boosting (XGBoost), M5 Tree (M5Tree) were employed. original EMMs showed poor performance, which improved after calibration techniques. DVQR, MLQR, BMAQR better performance than calibrated EMMs. However, exhibited highest accuracy MLQR over two sites. M5Tree, SVM, XGBoost perfumed ELM RF at both equivalent (R2, NSE, WIA > 0.99, MAE, RMSE < 0.2) M5Tree SVM models, but they had significantly more EMMs, BMAQR, ELM, regions. Overall, high dimensional is recommended as a promising alternative technique climate conditions around world.

Language: Английский

---

Precipitation data merging via machine learning: Revisiting conceptual and technical aspects

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 637, P. 131424 - 131424

Published: May 25, 2024

The development of accurate precipitation products with wide spatio-temporal coverage is crucial for a range applications. In this context, data merging (PDM) that entails the blending satellite-based estimates ground-based measurements holds prominent position, while currently there an increasing trend in deployment machine learning (ML) algorithms such endeavors. light recent advances field, work discusses key aspects PDM problem associated with: a) conceptual formulation problem, closely related to training ML models and their predictive capacity, b) selection fused, latency final product operational applicability method, c) efficiency single-step two-step approaches, former one treating via only regression latter combined use classification algorithms. By formulating as prediction we define assess two different strategies models, termed full per time step strategy, which entail building single or several respectively. Furthermore, performance allows predictions both spatial temporal dimensions, assessed context merging. each three scenarios, popular ensemble tree-based algorithms, i.e., random forest, gradient boosting extreme algorithm, are employed resulting nine merged products. To provide empirical evidence, employ datacube composed by daily observations, reanalysis estimates, well auxiliary covariates, from 1009 uniformly distributed cells (representative sampling area 25 × km), over four countries around world (Australia, USA, India Italy). large-scale experiment indicates that: (i) strategy competitive alternative since it enables methods improved accuracy, respect metrics reproduction statistics, but also higher capability applicability, (ii) much better occurrence characteristics, reflected improvement relevant categorical metrics, probability autocorrelation coefficient, (iii) no significant difference was noticed

Language: Английский

---

Assessment of groundwater quality in a highly urbanized coastal city using water quality index model and bayesian model averaging

Frontiers in Environmental Science, Journal Year: 2023, Volume and Issue: 11

Published: March 2, 2023

Prediction and assessment of water quality are important aspects resource management. To date, several index (WQI) models have been developed improved for effective However, the application these is limited because their inherent uncertainty. improve reliability WQI model quantify its uncertainty, we a WQI-Bayesian averaging (BMA) based on BMA method to merge different comprehensive groundwater assessment. This comprised two stages: i) stage, four traditional were used calculate values, ii) stage integrating results from multiple determine final status. In this study, machine learning method, namely, extreme gradient boosting algorithm was also adopted systematically assign weights sub-index functions aggregation function. It can avoid time consumption computational effort required find most parameters. The showed that status in study area mainly maintained fair good categories. values ranged 35.01 98.45 prediction area. Temporally, category exhibited seasonal fluctuations 2015 2020, with highest percentage lowest marginal category. Spatially, sites fell under fair-to-good category, few scattered areas falling indicating has well maintained. WQI-BMA relatively easy implement interpret, which significant implications regional

Language: Английский

---

Merging precipitation scheme design for improving the accuracy of regional precipitation products by machine learning and geographical deviation correction

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 620, P. 129560 - 129560

Published: April 23, 2023

Language: Английский

---