Improved soil carbon stock spatial prediction in a Mediterranean soil erosion site through robust machine learning techniques

Environmental Monitoring and Assessment, Journal Year: 2024, Volume and Issue: 196(2)

Published: Jan. 10, 2024

Language: Английский

---

Projected climate change impacts on streamflow in the Upper Oum Er Rbia Basin, Upstream of the Ahmed El Hansali Dam, Morocco

Environmental Challenges, Journal Year: 2025, Volume and Issue: 18, P. 101101 - 101101

Published: Feb. 3, 2025

Language: Английский

---

Spatial Mapping and Prediction of Groundwater Quality Using Ensemble Learning Models and SHapley Additive exPlanations with Spatial Uncertainty Analysis

Water, Journal Year: 2024, Volume and Issue: 16(17), P. 2375 - 2375

Published: Aug. 24, 2024

The spatial mapping and prediction of groundwater quality (GWQ) is important for sustainable management, but several research gaps remain unexplored, including the inaccuracy interpolation, limited consideration geological environment human activity effects, limitation to specific pollutants, unsystematic indicator selection. This study utilized entropy-weighted water index (EWQI), LightGBM model, pressure-state-response (PSR) framework SHapley Additive exPlanations (SHAP) analysis address above gaps. normalized importance (NI) shows that NO3− (0.208), Mg2+ (0.143), SO42− (0.110), Cr6+ (0.109) Na+ (0.095) should be prioritized as parameters remediation, skewness EWQI distribution indicates although most sampled locations have acceptable GWQ, a few areas suffer from severely poor GWQ. PSR identifies 13 indicators environments activities SMP Despite high AUROCs (0.9074, 0.8981, 0.8885, 0.9043) across four random training testing sets, it was surprising significant uncertainty observed, with Pearson correlation coefficients (PCCs) 0.5365 0.8066. We addressed this issue by using spatial-grid average probabilities maps. Additionally, population nighttime light are key indicators, while net recharge, land use cover (LULC), degree urbanization lowest importance. SHAP highlights both positive negative impacts on identifying point-source pollution main cause GWQ in area. Due field, future studies focus six aspects: multi-method assessment, quantitative relationships between comparisons various models, application selection, development methods reduce uncertainty, explainable machine learning techniques management.

Language: Английский

---

Future groundwater drought analysis under data scarcity using MedCORDEX regional climatic models and machine learning: The case of the Haouz Aquifer

Journal of Hydrology Regional Studies, Journal Year: 2025, Volume and Issue: 58, P. 102249 - 102249

Published: Feb. 18, 2025

Language: Английский

---

Real-time monitoring of soil moisture in cotton fields using electromagnetic induction technology

Agricultural Water Management, Journal Year: 2025, Volume and Issue: 313, P. 109466 - 109466

Published: April 8, 2025

Language: Английский

---

Monitoring changes in soil organic carbon using satellite-based variables and machine learning algorithms in arid and semi-arid regions

Environmental Earth Sciences, Journal Year: 2024, Volume and Issue: 83(20)

Published: Oct. 1, 2024

Language: Английский

---

Characterizing soil hydrology in the Indo-Gangetic plain of Bihar, India: Methods and preliminary results

Geoderma Regional, Journal Year: 2024, Volume and Issue: 37, P. e00784 - e00784

Published: March 16, 2024

In the Eastern Gangetic Plain (EGP) soil hydrology is a major determinant of land use and also governs ecosystem services derived from cropping systems, particularly greenhouse gas (GHG) emissions rice fields. To characterize patterns in these, daily field monitoring water levels was conducted during monsoon (kharif) season comparatively wet (2021) dry (2022) year with flooding depth drainage tracked tubes across 47 183 locations. Fields were clustered into hydrologic response types (HRT) which can then be used for surface modelling, recommendations, to target agronomic interventions that contribute sustainable development outcomes. Clusters based on two methods summarizing single information source compared. The time-series water-level observations, (1) original their first differences (2) set descriptors are conceptually related emissions. Clustering by k-means an optimization cluster numbers hierarchical clustering same number clusters as identified k-means. Hydrologic behaviour shifted dramatically between growing seasons, it not possible identify consistent HRT's years. had only weak relation properties, almost no farmer perception relative landscape position, establishment method. moderately well predicted 2022 optimized random forest models, most important predictors being irrigations, seasonal precipitation, pre-monsoon groundwater levels, level change, pH, this latter surrogate position other properties. 2021 (poorly) just precipitation levels. This shows complex management, synoptic climate. By contrast, well-matched those time-series, could models. different criteria may result interpretations thus heuristics anticipating given under management choices.

Language: Английский

---

Dam Siltation in the Mediterranean Region Under Climate Change: A Case Study of Ahmed El Hansali Dam, Morocco

Water, Journal Year: 2024, Volume and Issue: 16(21), P. 3108 - 3108

Published: Oct. 30, 2024

Dams are vital for irrigation, power generation, and domestic water needs, but siltation poses a significant challenge, especially in areas prone to erosion, potentially shortening dam’s lifespan. The Ahmed El Hansali Dam Morocco faces heightened due its upstream region being susceptible erosion-prone rocks high runoff. This study estimates the at dam from construction up 2014 using bathymetric data Brown model, which is widely-used empirical model that calculates reservoir trap efficiency. Additionally, evaluates impact of Land Use Cover (LULC) changes projected future rainfall until around 2076 based on rates. results indicate LULC, particularly temporal variations precipitation, have dam. Notably, strongly correlated with rate, an R2 0.92. efficiency sediment trapping (TE) 97.64%, meaning 97.64% catchment area trapped or deposited bottom estimated annual specific yield about 32,345.79 tons/km2/yr, accumulation rate approximately 4.75 Mm3/yr. half-life be 2076, precipitation projections may extend this timeframe strong correlation between precipitation. soil erosion driven by land management practices plays crucial role dynamics. Hence, offers comprehensive assessment dynamics dam, providing essential information long-term effects use changes, climate projections. These findings assist decision makers managing sedimentation more effectively, ensuring durability extending life.

Language: Английский

---

Lithological Descrimination and Slope Gradient for the Adjusted Hydrologic Soil Group Mapping in the Hodna Watershed

Published: April 15, 2024

This paper aims to develop a concept for the adjusting Hydrologic Soil Group mapping using lithological discrimination techniques and slope gradient. adjustment process will refine delineation of hydrological groups by taking into account gradient variation. approach provides enhanced accuracy in classifying soils based on their behavior, considering topographical nuances that may impact soil infiltration capacity. By integrating these insights, resulting becomes more detailed better suited specific conditions study area.

Language: Английский

---

A Novel Vegetation Index for Monitoring the Degree of Insect Pest Caused by Dusky Cotton Bug

Published: Jan. 1, 2024

Language: Английский

---