Soil water erosion susceptibility assessment using deep learning algorithms

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 618, P. 129229 - 129229

Published: Feb. 6, 2023

Accurate assessment of soil water erosion (SWE) susceptibility is critical for reducing land degradation and loss, mitigating the negative impacts on ecosystem services, quality, flooding infrastructure. Deep learning algorithms have been gaining attention in geoscience due to their high performance flexibility. However, an understanding potential these provide fast, cheap, accurate predictions lacking. This study provides first quantification this potential. Spatial are made using three deep – Convolutional Neural Network (CNN), Recurrent (RNN) Long-Short Term Memory (LSTM) Iranian catchment that has historically experienced severe erosion. Through a comparison predictive analysis driving geo-environmental factors, results reveal: (1) elevation was most effective variable SWE susceptibility; (2) all developed models had good prediction performance, with RNN being marginally superior; (3) maps revealed almost 40 % highly or very susceptible 20 moderately susceptible, indicating need control catchment. algorithms, catchments can potentially be predicted accurately ease readily available data. Thus, reveal great use data poor catchments, such as one studied here, especially developing nations where technical modeling skills processes occurring may

Language: Английский

---

Modelling and accessing land degradation vulnerability using remote sensing techniques and the analytical hierarchy process approach

Geocarto International, Journal Year: 2021, Volume and Issue: 37(24), P. 7122 - 7142

Published: July 22, 2021

Land degradation and desertification have recently become a critical problem in Ethiopia. Accordingly, identification of land vulnerable zonation mapping was conducted Wabe Shebele River Basin, Precipitation derived from Global Measurement Mission (GMP), the Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized difference vegetation index (NDVI) surface temperature (LST), topography (slope), pedological properties (i.e., soil depth, pH, texture, drainage) were used current study. NDVI has been considered as most significant parameter followed by slope, precipitation temperature. Geospatial techniques Analytical Hierarchy Process (AHP) approach to model index. Validation results with google earth image shows applicability The result is classified into very highly (17.06%), (15.01%), moderately (32.72%), slightly (16.40%), (18.81%) degradation. Due small rate which evaporation high region, downstream section basis categorized Degradation (LD) vice versa upstream basin. Moreover, validation using Receiver Operating Characteristic (ROC) curve analysis an area under ROC value 80.92% approves prediction accuracy AHP method assessing modelling LD vulnerability zone study area. provides substantial understanding effect on sustainable use management development

Language: Английский

---

Land degradation risk dynamics assessment in red and lateritic zones of eastern plateau, India: A combine approach of K-fold CV, data mining and field validation

Ecological Informatics, Journal Year: 2022, Volume and Issue: 69, P. 101653 - 101653

Published: April 27, 2022

Language: Английский

---

Assessment of land degradation in the North China Plain driven by food security goals

Ecological Engineering, Journal Year: 2022, Volume and Issue: 183, P. 106766 - 106766

Published: Aug. 11, 2022

Language: Английский

---

Prioritizing sub-watersheds based on soil-erosion potential by integrating RUSLE and game-theory algorithms

Advances in Space Research, Journal Year: 2023, Volume and Issue: 72(2), P. 471 - 487

Published: March 25, 2023

Language: Английский

---

MachIne learning for nutrient recovery in the smart city circular economy – A review

Process Safety and Environmental Protection, Journal Year: 2023, Volume and Issue: 173, P. 529 - 557

Published: March 16, 2023

Language: Английский

---

Assessment of land degradation risks in the Loess Plateau

Land Degradation and Development, Journal Year: 2024, Volume and Issue: 35(7), P. 2409 - 2424

Published: Feb. 29, 2024

Abstract Human activity and climate change are degrading the environmentally fragile Loess Plateau in dry semiarid regions. Land deterioration threatens human ecological existence. To prevent additional land degradation ensure development quality of arable region, China launched “Grain for Green” late 1990s. This effort greatly boosted vegetation. However, is complex, so we must also examine natural social variables to degradation. Thus, this study presents a comprehensive index system quantify on uses machine learning anticipate high‐risk locations. The project improved degradation, spatial distribution risk high northern low eastern southern regions Plateau. Gross Domestic Product population density main drivers Industrialization urbanization have raised which now accounts 1%–2% area. emphasizes sustainable management Plateau, critical area China. integrated assessment indicator random forest modeling help grasp current status future preventive measures. outcome advances research management. findings possess significant scientific reference value terms mitigating managing vulnerable worldwide.

Language: Английский

---

Impact of land use/land cover changes on evapotranspiration and model accuracy using Google Earth engine and classification and regression tree modeling

Geomatics Natural Hazards and Risk, Journal Year: 2023, Volume and Issue: 15(1)

Published: Dec. 22, 2023

This research uses a Classification and Regression Tree (CART) model with Google Earth Engine (GEE) to assess the winter season's land cover change detection mapping impact on evapotranspiration (crop water requirement) parameters. Winter seasons, crucial for agricultural planning, irrigation requirement challenges in accurately detecting changes due dynamic nature of farming practices during this period. In study, Landsat-8 OLI images have been combined map Land use (LULC) other Akola Block, Maharashtra, India, 2018–2022 season. As an discoverer researcher that found detailed information LULC classes last 2018 2022 CART combination cloud-computing GEE demonstrates be practical approach accurate classification maps create pixel-based seasons study area. The novelty lies its innovative GEE, powerful platform remote sensing geospatial analysis, remarkable accuracy. Achieving 100% training accuracy across four years under consideration is exceptional feat, highlighting reliability stability methodology. Furthermore, validation values, ranging from 89 94% 2022, underscore robustness approach. Such consistently high over time groundbreaking achievement offers new dimension field hydrology. For hydrological community, implications are profound. Accurate provide critical data modeling analyzing effects resources, watershed management, quality. User, Kappa, Producer metrics used highlight model's performance suitability applications. These can aid development models, forecasting, decision-making processes, ultimately contributing more effective resource management environmental conservation. summary, study's mapping, relevance community demonstrate potential advanced tools significantly improve our understanding their resources management.

Language: Английский

---

Evaluating the effects of climate and land use change on the future flood susceptibility in the central region of Vietnam by integrating land change modeler, machine learning methods

Geocarto International, Journal Year: 2022, Volume and Issue: 37(26), P. 12810 - 12845

Published: April 27, 2022

The crucial importance of land cover and use changes climate for worldwide sustainability results from their negative effects on flood risk. In a watershed, particularly important research question concerning the relationship between change risk is subject controversy in literature. This study aims to assess susceptibility watershed Nhat Le–Kien Giang, Vietnam using machine learning Land Change Modeler. show that Social Ski Driver Optimization (SSD), Fruit Fly (FFO), Sailfish (SFO), Particle Swarm (PSO) successfully improve Support Vector Machine (SVM) model's performance, with value Area Under Receiver Operating Characteristic curve (AUC) > 0.96. Among them, SVM-FFO model was better AUC 0.984, followed by SVM-SFO (AUC = 0.983), SVM-SSD 0.98), SVM-PSO 0.97), respectively. addition, areas high very area increased about 30 km2 2020 2050 model. Our underline consequences unplanned development. Thus, applying theoretical framework this study, decision makers can take sound more planning measures, such as avoiding construction often affected floods, etc. Although studied Central Coast province, be applied other rapidly developing flood-prone provinces Vietnam.

Language: Английский

---

Modeling and Assessment of Land Degradation Vulnerability in Arid Ecosystem of Rajasthan Using Analytical Hierarchy Process and Geospatial Techniques

Land, Journal Year: 2022, Volume and Issue: 12(1), P. 106 - 106

Published: Dec. 29, 2022

Wind erosion is a major natural disaster worldwide, and it key problem in western Rajasthan India. The Analytical Hierarchy Process (AHP), the Geographic Information System (GIS), remote sensing satellite images are effective tools for modeling risk assessment of land degradation. present study aimed to assess model degradation vulnerable (LDV) zones based on AHP geospatial techniques Luni River basin Rajasthan, This was carried out by examining important thematic layers, such as vegetation parameters (normalized difference index use/land cover), terrain parameter (slope), climatic (mean annual rainfall surface temperature), soil (soil organic carbon, erosion, texture, depth), using Hierarchical (AHP) weights derived layers were follows: NDVI (0.27) > MAR (0.22) LST (0.15) (0.12) slope (0.08) LULC (0.06) SOC (0.04) texture (0.03) depth (0.02). result indicates that nearly 21.4 % total area prone very high risks; 12.3% 16%, 24.3%, 26% moderate, low, low risks, respectively. validation LDV high-resolution Google Earth field photographs. Additionally, Receiver Operating Characteristic (ROC) curve found an under (AUC) value 82%, approving prediction accuracy technique area. contributes providing better understanding neutrality sustainable water management practices river basin.

Language: Английский

---