Groundwater level forecasting in a data-scarce region through remote sensing data downscaling, hydrological modeling, and machine learning: A case study from Morocco

Journal of Hydrology Regional Studies, Год журнала: 2023, Номер 50, С. 101569 - 101569

Опубликована: Ноя. 10, 2023

The upstream part of the Essaouira basin, a data-scare region in Morocco, Northwestern Africa. scarcity hydro-climate data is significant challenge found several regions worldwide, where qualitative and quantitative water resource information remains limited. Estimating predicting groundwater levels (GWL) such areas producing knowledge for effective management. To address this issue, present study aimed to use Soil Water Assessment Tool (SWAT) model conjunction with downscaled total storage (TWS) (9 km) obtained from Gravity Recovery And Climate Experiment (GRACE) machine learning techniques, specifically random forest (RF) support vector (SVM), estimate predict variation GWL. This constitutes first its kind area; SWAT was set up 10 years, warm-up period 2000 2001, calibration 2002 2007, validation 2008 2010. statistical indices (Coefficient Determination (R²) ≥ 0.73, R² 0.78, Nash–Sutcliffe efficiency coefficient (NSE) 0.67, NSE 0.80 respectively validation) highlight correlation, implying model's capability faithfully reproduce streamflow. TWS demonstrates an impressive ability identify monitor fluctuations Using algorithms (RF SVR), prediction GWL yielded satisfactory results, = 0.78 root mean square error (RMSE) 0.33, 0.51 RMSE 0.49 RF SVR, respectively. Despite some limitations, our approach provided promising results prediction, possibility expanding other data-scarce regions.

Язык: Английский

---

How Big Data Can Help to Monitor the Environment and to Mitigate Risks due to Climate Change: A review

IEEE Geoscience and Remote Sensing Magazine, Год журнала: 2024, Номер 12(2), С. 67 - 89

Опубликована: Апрель 12, 2024

Climate change triggers a wide range of hydrometeorological, glaciological, and geophysical processes that span across vast spatiotemporal scales. With the advances in technology analytics, multitude remote sensing (RS), geodetic, situ instruments have been developed to effectively monitor help comprehend Earth's system, including its climate variability recent anomalies associated with global warming. A huge volume data is generated by recording these observations, resulting need for novel methods handle interpret such big datasets. Managing this enormous amount extends beyond current computer storage considerations; it also encompasses complexities processing, modeling, analyzing. Big datasets present unique characteristics set them apart from smaller datasets, thereby posing challenges traditional approaches. Moreover, computational time plays crucial role, especially context geohazard warning response systems, which necessitate low latency requirements.

Язык: Английский

---

Application of the machine learning methods for GRACE data based groundwater modeling, a systematic review

Groundwater for Sustainable Development, Год журнала: 2024, Номер 25, С. 101113 - 101113

Опубликована: Фев. 10, 2024

Язык: Английский

---

Advancing Hydrology through Machine Learning: Insights, Challenges, and Future Directions Using the CAMELS, Caravan, GRDC, CHIRPS, PERSIANN, NLDAS, GLDAS, and GRACE Datasets

Water, Год журнала: 2024, Номер 16(13), С. 1904 - 1904

Опубликована: Июль 3, 2024

Machine learning (ML) applications in hydrology are revolutionizing our understanding and prediction of hydrological processes, driven by advancements artificial intelligence the availability large, high-quality datasets. This review explores current state ML hydrology, emphasizing utilization extensive datasets such as CAMELS, Caravan, GRDC, CHIRPS, NLDAS, GLDAS, PERSIANN, GRACE. These provide critical data for modeling various parameters, including streamflow, precipitation, groundwater levels, flood frequency, particularly data-scarce regions. We discuss type methods used significant successes achieved through those models, highlighting their enhanced predictive accuracy integration diverse sources. The also addresses challenges inherent applications, heterogeneity, spatial temporal inconsistencies, issues regarding downscaling LSH, need incorporating human activities. In addition to discussing limitations, this article highlights benefits utilizing high-resolution compared traditional ones. Additionally, we examine emerging trends future directions, real-time quantification uncertainties improve model reliability. place a strong emphasis on citizen science IoT collection hydrology. By synthesizing latest research, paper aims guide efforts leveraging large techniques advance enhance water resource management practices.

Язык: Английский

---

SAGEA: A toolbox for comprehensive error assessment of GRACE and GRACE-FO based mass changes

Computers & Geosciences, Год журнала: 2025, Номер 196, С. 105825 - 105825

Опубликована: Янв. 6, 2025

Язык: Английский

---

A XGBoost-Based Downscaling-Calibration Scheme for Extreme Precipitation Events

IEEE Transactions on Geoscience and Remote Sensing, Год журнала: 2023, Номер 61, С. 1 - 12

Опубликована: Янв. 1, 2023

Extreme precipitation events have caused severe societal, economic and environmental impacts through the disasters of floods, flash-floods landslides. However, coarse-resolution satellite-derived data makes it difficult to quantitatively capture certain fine-scale heavy rainfall process. Therefore, improve spatial resolution accuracy satellite-based extremes, a downscaling-calibration scheme based on eXtreme Gradient Boosting (XGBoost_DC) was proposed in this study, where XGBoost algorithm applied both downscaling calibration procedures. The performance XGBoost_DC evaluated with other two comparative methods, which only used either (XGBoost_Spline) or (Spline_XGBoost) results showed that: (i) achieved best performance, as obtained highest well reproduced occurrence distribution during typhoon events. (ii) could variations precipitation. Although Spline_XGBoost slightly worse than XGBoost_DC, significantly underestimated variability. (iii) model assessment between illustrated essential contribution process, improved our understanding capability machine learning reproducing variance These findings imply that can be for generating high-resolution high-quality extremes events, would benefit water flood management, various applications hydrological meteorological modelling.

Язык: Английский

---

Harnessing Machine Learning for Assessing Climate Change Influences on Groundwater Resources: A Comprehensive Review

Heliyon, Год журнала: 2024, Номер 10(17), С. e37073 - e37073

Опубликована: Авг. 28, 2024

Язык: Английский

---

GRACE Downscaler: A Framework to Develop and Evaluate Downscaling Models for GRACE

Remote Sensing, Год журнала: 2023, Номер 15(9), С. 2247 - 2247

Опубликована: Апрель 24, 2023

Monitoring and managing groundwater resources is critical for sustaining livelihoods supporting various human activities, including irrigation drinking water supply. The most common method of monitoring well level measurements. These records can be difficult to collect maintain, especially in countries with limited infrastructure resources. However, long-term data collection required characterize evaluate trends. To address these challenges, we propose a framework that uses from the Gravity Recovery Climate Experiment (GRACE) mission downscaling models generate higher-resolution (1 km) predictions. designed flexible, allowing users implement any machine learning model interest. We selected four models: deep model, gradient tree boosting, multi-layer perceptron, k-nearest neighbors regressor. effectiveness framework, offer case study Sunflower County, Mississippi, using validate Overall, this paper provides valuable contribution field resource management by demonstrating remote sensing techniques improve resource, those who seek faster way begin use datasets applications.

Язык: Английский

---

Probabilistic Evaluation of Drought Propagation Using Satellite Data and Deep Learning Model: From Precipitation to Soil Moisture and Groundwater

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Год журнала: 2023, Номер 16, С. 6048 - 6061

Опубликована: Янв. 1, 2023

The frequency of drought events has increased with climate change, making it vital to monitor and predict the response drought. In particular, relationship among meteorological, agricultural, groundwater droughts needs be characterized under different conditions. this study, a probabilistic framework was developed for analyzing spatio-temporal propagation applied South Korea. Three indices were calculated using satellite data deep learning model determine spatial temporal extents average times calculated. time from meteorological agricultural (MD-to-AD) 2.83 months, that (MD-to-GD) 4.34 months. Next, joint distribution three types based on best-fit copula functions constructed. conditional probabilities occurrence scales. For instance, MD-to-GD light, moderate, severe, extreme conditions 38%, 43%, 48%, 53%, respectively. propagated probability confirmed highest antecedent results study provide insight into process viewpoint. use is expected increase efficiency management practices such as vulnerability assessment early warning system development.

Язык: Английский

---

Predictive modeling based on artificial neural networks for membrane fouling in a large pilot-scale anaerobic membrane bioreactor for treating real municipal wastewater

The Science of The Total Environment, Год журнала: 2023, Номер 912, С. 169164 - 169164

Опубликована: Дек. 10, 2023

Язык: Английский

---