Machine learning models for gully erosion susceptibility assessment in the Tensift catchment, Haouz Plain, Morocco for sustainable development

Journal of African Earth Sciences, Journal Year: 2024, Volume and Issue: 213, P. 105229 - 105229

Published: March 11, 2024

Gully erosion is a widespread environmental danger, threatening global socio-economic stability and sustainable development. This study comprehensively applied seven machine learning (ML) models including SVM, KNN, RF, XGBoost, ANN, DT, LR, evaluated gully susceptibility in the Tensift catchment predict it within Haouz plain, Morocco. To ensure reliability of findings, employed robust combination inventory, sentinel images, Digital Surface Model. Eighteen predictors, encompassing topographical, geomorphological, environmental, hydrological factors, were selected after multicollinearity analyses. The revealed that approximately 28.18% at very high risk erosion. Furthermore, 15.13% 31.28% are categorized as low respectively. These findings extend to where 7.84% surface area highly risking erosion, while 18.25% 55.18% characterized areas. gauge performance ML models, an array metrics specificity, precision, sensitivity, accuracy employed. highlights XGBoost KNN most promising achieving AUC ROC values 0.96 0.93 test phase. remaining namely RF (AUC = 0.89), LR 0.80), SVM 0.81), DT 0.86), ANN 0.78), also displayed commendable performance. novelty this research its innovative approach combat through cutting edge offering practical solutions for watershed conservation, management, prevention land degradation. insights invaluable addressing challenges posed by region, beyond geographical boundaries can be used defining appropriate mitigation strategies local national scale.

Language: Английский

---

Rapid estimation of soil Mn content by machine learning and soil spectra in large-scale

Ecological Informatics, Journal Year: 2024, Volume and Issue: 81, P. 102615 - 102615

Published: April 28, 2024

Language: Английский

---

The impact of land-use change on the ecological environment quality from the perspective of production-living-ecological space: A case study of the northern slope of Tianshan Mountains

Ecological Informatics, Journal Year: 2024, Volume and Issue: 83, P. 102795 - 102795

Published: Aug. 25, 2024

Language: Английский

---

Evaluation of tectonic activity using morphometric indices: Study of the case of Taïliloute ridge (middle-Atlas region, Morocco)

Journal of African Earth Sciences, Journal Year: 2024, Volume and Issue: 213, P. 105219 - 105219

Published: March 8, 2024

In the Middle Atlas region, Tizi N'Teghtène Fault System is a network of faults inherited from Hercynian orogeny, which operated as normal during Jurassic and reverse since Miocene. The issue at hand whether this fault system continues to be active today. To address concern, focus has been placed on central portion N'Teghtene System, specifically anticlinal ridge Taïliloute. Determining tectonically segments crucial for structural analysis Quaternary evolution mountain chain. achieve this, morphometric indices related watersheds their streams have employed. These include hypsometry, elongation ratio (Re), drainage asymmetry factor (AF), profiles various watercourses. indicators provide insights into degree longitudinal growth Taïliloute ridge. parameters were determined through satellite image using suitable software geographic information systems (GIS). Tectonic activity analyses reveal that both flanks exhibit ongoing tectonic activity, marked by occurrence strike-slip phase Alpine orogeny. It concluded remains active. This research contributes deeper understanding activities within matter geological significance. By employing ad modern techniques, methodological innovation presented study in assessing mountainous regions. results valuable dynamics Atlas, aiding its evolution. Furthermore, can broader applications seismic hazard assessment land use planning, making it relevant beyond immediate geographical boundaries area.

Language: Английский

---

Unlocking the potential of soil potassium: Geostatistical approaches for understanding spatial variations in Northwestern Himalayas

Ecological Informatics, Journal Year: 2024, Volume and Issue: 81, P. 102592 - 102592

Published: April 9, 2024

This study delves into the heterogeneity of total soil potassium (TSK) in Northwestern Himalayas (NWH) region by employing standard and geostatistical methods on surface soils (0–20 cm) randomly collected from various land use systems. research aims to unveil spatial dynamics TSK challenging context NWH region, unravelling connections between levels, practices, properties. The findings this are instrumental for sustainable agriculture ecological resilience region. results work reveal that levels different types were significantly order: horticulture (13.76 g/kg) > agricultural (11.25 forest (7.38 fallow (4.72 g/kg), which is clearly associated with K application rates. stepwise multiple regression analysis provides a significant correlation organic matter, clay, other fine-grained particles. Spatially, nugget ratios exhibit an apparent decrease correlated types, mixed. Among Gaussian, exponential, linear, spherical models considered, linear model yields best fit. isotropy optimization vary based type. role very important modelling predicting status at scientific industrial scale, ensuring relevance applicability such insights global audiences policymakers. novel contribution science, direct implications management practices fragile agroecological regions beyond geographical boundaries.

Language: Английский

---

Impact of watershed management practices on vegetation, land use changes, and soil erosion in River Basins of the Atlas, Morocco

Notulae Botanicae Horti Agrobotanici Cluj-Napoca, Journal Year: 2024, Volume and Issue: 52(1), P. 13567 - 13567

Published: March 29, 2024

Soil erosion, a land degradation process triggered by natural and anthropogenic factors, seriously impacts landscapes water resources. The influence of vegetation cover use changes on intensity soil erosion two catchments in mountainous regions Morocco is evident, as it alters hydrologic response sediment dynamics. This research aims to analyze the interactions among plants, soil, geology, meteorology, orography, assessing responses using process-oriented IntErO model - Erosion Potential Method determine rates. obtained results indicate that Tiguert river basin experiences higher losses (Ggod = 5184.47 m³/god) per square kilometre (Ggod/km² 508.28 m³/km² god) compared Wanmroud catchment 2555.66 m³/god, Ggod/km² 381.44 god), confirming theory areas with denser more effective experience lower Furthermore, exhibits regular shape watershed development coefficient, implying human impact. study has shown relationships between changes, cover, dynamics, offering valuable insights for sustainable management practices Morocco.

Language: Английский

---

Spatial Mapping for Multi-Hazard Land Management in Sparsely Vegetated Watersheds Using Machine Learning Algorithms

Environmental Earth Sciences, Journal Year: 2024, Volume and Issue: 83(15)

Published: July 1, 2024

Abstract This study breaks new ground by developing a multi-hazard vulnerability map for the Tensift watershed and Haouz plain in Moroccan High Atlas area. The unique juxtaposition of flat mountainous terrain this area increases sensitivity to natural hazards, making it an ideal location research. Previous extreme events region have underscored urgent need proactive mitigation strategies, especially as these hazards increasingly intersect with human activities, including agriculture infrastructure development. In six advanced machine learning (ML) models were used comprehensively assess combined probability three significant hazards: flooding, gully erosion, landslides. These rely on causal factors derived from reputable sources, geology, topography, meteorology, hydrology. research's rigorous validation process, which includes metrics such specificity, precision, sensitivity, accuracy, underlines robust performance all models. process involved comparing model's predictions actual hazard occurrences over specific period. According outcomes terms under curve (AUC), XGBoost model emerged most predictive, remarkable AUC values 93.41% landslides, 91.07% erosion 93.78% flooding. Based overall findings study, risk was created using relationship between flood risk, landslides geographic information system (GIS) architecture. innovative approach presented work, ML algorithms geographical data, demonstrates power tools sustainable land management protection communities their assets regions similar topographical, geological, meteorological conditions that are vulnerable aforementioned risks.

Language: Английский

---

Mathematical vs. machine learning models for particle size distribution in fragile soils of North-Western Himalayas

Journal of Soils and Sediments, Journal Year: 2024, Volume and Issue: 24(6), P. 2294 - 2308

Published: June 1, 2024

Abstract Purpose Particle size distribution (PSD) assessment, which affects all physical, chemical, biological, mineralogical, and geological properties of soil, is crucial for maintaining soil sustainability. It plays a vital role in ensuring appropriate land use, fertilizer management, crop selection, conservation practices, especially fragile soils such as those the North-Western Himalayas. Materials methods In this study, performance eleven mathematical three Machine Learning (ML) models used past was compared to investigate PSD modeling different from Himalayan region, considering that an model must fit data. Results discussion Our study focuses on significance evaluating goodness particle using coefficient determination (R 2 adj = 0.79 0.45), Akaike information criterion (AIC 67 184), root mean square error (RMSE 0.01 0.09). The Fredlund, Weibull, Rosin Rammler exhibited best samples, while Gompertz, S-Curve, Van Genutchen poor. Of ML tested, Random Forest performed 0.99), SVM lowest 0.95). Thus, can be predicted by approaches, model. Conclusion Fredlund among random forest machine learning models. As number parameters increased better accuracy.

Language: Английский

---

Brassinolides signaling pathway: tandem response to plant hormones and regulation under various abiotic stresses

Horticulture Advances, Journal Year: 2024, Volume and Issue: 2(1)

Published: Oct. 25, 2024

Abstract Plant hormones play pivotal roles in stress responses by modulating growth, development, stomatal movement, and the expression of stress-related genes, thereby aiding plants adapting to managing various environmental challenges. Each hormone exhibits distinct functions regulatory mechanisms response, with potential complex interactions among them. Brassinosteroids (BRs) represent a novel that influences its target genes through series phosphorylated cascade reactions involving transcription factors. This signaling pathway regulates diverse growth development processes plants. Additionally, BRs interact other modulate physiological development. review examines biosynthesis metabolism, elucidates between abscisic acid (ABA), jasmonic (JA), gibberellins (GA), explores their regulating drought, salt, cold, heat. The underscores importance hormonal crosstalk nutrient stress, which is vital for understanding plant regulation, enhancing crop resistance, advancing biotechnology applications, furthering science research. Future research directions production application improve resilience are also discussed context current findings.

Language: Английский

---

Machine learning methods for landslide mapping studies: A comparative study of SVM and RF algorithms in the Oued Aoulai watershed (Morocco)

Open Geosciences, Journal Year: 2025, Volume and Issue: 17(1)

Published: Jan. 1, 2025

Abstract Effective management of watershed risks and landslides necessitates comprehensive landslide susceptibility mapping. Support vector machine (SVM) random forest (RF) learning models were used to map the in Morocco’s Taounate Province. Detailed inventory maps generated based on aerial pictures, field research, geotechnical survey reports. Factor correlation analysis carefully eliminated redundant factors from original 14 triggering factors. As a result, 30% sites randomly chosen for testing, whereas 70% locations picked model training. The RF achieved an area under curve (AUC) 94.7%, categorizing 30.07% region as low susceptibility, while SVM reached AUC 80.65%, indicating high sensitivity 53.5% locations. These results provide crucial information local authorities, supporting sound catchment planning development strategies.

Language: Английский

---