Deep learning in hydrology and water resources disciplines: concepts, methods, applications, and research directions

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 628, P. 130458 - 130458

Published: Nov. 15, 2023

Language: Английский

---

Spatio-temporal deep learning model for accurate streamflow prediction with multi-source data fusion

Environmental Modelling & Software, Journal Year: 2024, Volume and Issue: 178, P. 106091 - 106091

Published: May 28, 2024

Language: Английский

---

Deep learning in statistical downscaling for deriving high spatial resolution gridded meteorological data: A systematic review

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2024, Volume and Issue: 208, P. 14 - 38

Published: Jan. 9, 2024

Language: Английский

---

Study on Runoff Simulation with Multi-source Precipitation Information Fusion Based on Multi-model Ensemble

Water Resources Management, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 25, 2024

Language: Английский

---

Probabilistic flood inundation mapping through copula Bayesian multi-modeling of precipitation products

Natural hazards and earth system sciences, Journal Year: 2024, Volume and Issue: 24(8), P. 2647 - 2665

Published: Aug. 2, 2024

Abstract. Accurate prediction and assessment of extreme flood events are crucial for effective disaster preparedness, response, mitigation strategies. One factor influencing the intensity magnitude is precipitation. Precipitation patterns, particularly during intense weather phenomena such as hurricanes, can play a significant role in triggering widespread flooding over densely populated areas. Traditional models typically rely on single-source precipitation data, which may not adequately capture inherent variability uncertainty associated with due to certain limitations generation framework, availability, or both spatial temporal resolutions. Moreover, coastal regions, complex interaction between local precipitation, river flows, processes (i.e., storm tide) result compound amplify overall impact complexity patterns. This study presents an implementation global copula-embedded Bayesian model averaging (BMA) (Global Cop-BMA) framework improving accuracy reliability modeling. The proposed integrates collection products different spatiotemporal resolutions account forcing data hydrodynamic modeling generating probabilistic inundation maps. methodology evaluated respect Hurricane Harvey, was catastrophic event characterized by city Houston state Texas 2017. results show improvement predictive compared those based single product (e.g., Nash–Sutcliffe efficiency (NSE) performance quantitative estimation (QPE) range 0.695 0.846, while Cop-BMA yields NSE 0.858), demonstrating merits Global approach. Furthermore, this research extends its extension maps that only primary influence driver but also intricate nature environments.

Language: Английский

---

Remote Sensing Data Assimilation in Crop Growth Modeling from an Agricultural Perspective: New Insights on Challenges and Prospects

Agronomy, Journal Year: 2024, Volume and Issue: 14(9), P. 1920 - 1920

Published: Aug. 27, 2024

The frequent occurrence of global climate change and natural disasters highlights the importance precision agricultural monitoring, yield forecasting, early warning systems. data assimilation method provides a new possibility to solve problems low accuracy prediction, strong dependence on field, poor adaptability model in traditional applications. Therefore, this study makes systematic literature retrieval based Web Science, Scopus, Google Scholar, PubMed databases, introduces detail strategies many remote sensing sources, such as satellite constellation, UAV, ground observation stations, mobile platforms, compares analyzes progress models compulsion method, parameter state update Bayesian paradigm method. results show that: (1) platform shows significant advantages agriculture, especially emerging constellation UAV assimilation. (2) SWAP is most widely used simulating crop growth, while Aquacrop, WOFOST, APSIM have great potential for application. (3) Sequential strategy algorithm field assimilation, ensemble Kalman filter algorithm, hierarchical considered be promising (4) Leaf area index (LAI) preferred variable, soil moisture (SM) vegetation (VIs) has also been strengthened. In addition, quality, resolution, applicability sources are key bottlenecks that affect application development agriculture. future, tends more refined, diversified, integrated. To sum up, can provide comprehensive reference by using model.

Language: Английский

---

A Cluster‐Based Data Assimilation Approach to Generate New Daily Gridded Time Series Precipitation Data in the Himalayan River Basins

Water Resources Research, Journal Year: 2025, Volume and Issue: 61(1)

Published: Jan. 1, 2025

Abstract Recent studies show variations in precipitation‐gridded data set accuracy with changing geographical parameters. Ensemble precipitation products, combining diverse sets, offer global‐scale effectiveness, but applying them to regional studies, particularly small medium‐sized sub‐basins, presents challenges addressing dependence on specific conditions. Here, we present a newly developed Clusters Based‐Minimum Error approach assimilate different open‐source gridded sets for forming an accurate product over hilly terrain basins, limited gauges. This methodology generates the New Gridded Precipitation Data Set (NGPD) from 1991 2022 Upper Ganga Basin western Himalaya, covering approximately 22,292 km 2 . The study utilizes nine and 11 observed gauges, NGPD is evaluated through station‐wise, grid‐wise, elevation‐wise analyses using statistical parameters, quantile‐quantile plots, daily coefficient of determination, Rainfall Anomaly Index, seasonality/precipitation pattern analyses. Results demonstrate superior performance compared other sources across various evaluation metrics. Nash‐Sutcliffe Efficiency (NSE), Coefficient determination ( R ), Root mean squared error (RMSE) range 0.67 0.90, 0.73–0.93, 4.4–10.69 mm/day, respectively, w.r.t outperforms widely used IMD India, exhibiting monthly scale improvement 18.47% 17.7% average NSE values, respectively. Additionally, also successfully applied Tamor Nepal, proving its reliability Himalayan regions. reliably creates especially regions station data.

Language: Английский

---

Fine-tuning long short-term memory models for seamless transition in hydrological modelling: From pre-training to post-application

Environmental Modelling & Software, Journal Year: 2025, Volume and Issue: unknown, P. 106350 - 106350

Published: Jan. 1, 2025

Language: Английский

---

Preface: Advancing deep learning for remote sensing time series data analysis

Remote Sensing of Environment, Journal Year: 2025, Volume and Issue: unknown, P. 114711 - 114711

Published: March 1, 2025

Language: Английский

---

PARAN: A novel physics-assisted reconstruction adversarial network using geostationary satellite data to reconstruct hourly sea surface temperatures

Remote Sensing of Environment, Journal Year: 2025, Volume and Issue: 323, P. 114749 - 114749

Published: April 9, 2025

Language: Английский

---