Daily River flow Simulation Using Ensemble Disjoint Aggregating M5-Prime Model

Heliyon, Год журнала: 2024, Номер 10(20), С. e37965 - e37965

Опубликована: Сен. 30, 2024

Accurate prediction of daily river flow (Q t ) remains a challenging yet essential task in hydrological modeling, particularly crucial for flood mitigation and water resource management. This study introduces an advanced M5 Prime (M5P) predictive model designed to estimate Q as well one- two-day-ahead forecasts (i.e. t+1 t+2 ). The performance M5P ensembles incorporating Bootstrap Aggregation (BA), Disjoint Aggregating (DA), Additive Regression (AR), Vote (V), Iterative classifier optimizer (ICO), Random Subspace (RS), Rotation Forest (ROF) were comprehensively evaluated. proposed models applied case data Tuolumne County, US, using dataset comprising measured precipitation (P ), evaporation (E t), . A wide range input scenarios explored predicting , t+1, t+2. Results indicate that P significantly influence accuracy. Notably, relying solely on the most correlated variable (e.g., t-1) does not guarantee robust However, extending forecast horizon mitigates low-correlation variables Performance metrics DA-M5P achieves superior results, with Nash-Sutcliff Efficiency 0.916 root mean square error 23 m3/s, followed by ROF-M5P, BA-M5P, AR-M5P, RS-M5P, V-M5P, ICO-M5P, standalone model. ensemble modeling framework enhanced capability stand-alone algorithm 1.2 %-22.6 %, underscoring its efficacy potential advancing forecasting.

Язык: Английский

---

Groundwater potential mapping in Jashore, Bangladesh

Heliyon, Год журнала: 2023, Номер 9(3), С. e13966 - e13966

Опубликована: Фев. 23, 2023

The global groundwater crisis is a perplexing issue, and for its resolution, it of the utmost importance delineating potential zones. This research aims to create precise map Bangladesh's Jashore district by combining geospatial approach an analytical hierarchy process. Fourteen parameters, namely, lineament density, drainage land use cover, slope, curvature, topographic position index, wetness rainfall, geology, roughness, fractional impervious surface, topsoil texture, soil permeability, general types, were considered study after extensive literature review. weights these parameters determined using process, scores each sub-parameter assigned based on published literature. final was then generated weighted overlay analysis tool in ArcGIS 10.3 categorized into five classes. reveals that very high, moderate, low, low zones cover 3.96 km

Язык: Английский

---

Exploring forest fire susceptibility and management strategies in Western Himalaya: Integrating ensemble machine learning and explainable AI for accurate prediction and comprehensive analysis

Environmental Technology & Innovation, Год журнала: 2024, Номер 35, С. 103655 - 103655

Опубликована: Май 5, 2024

Forest fires pose a significant threat to ecosystems and socio-economic activities, necessitating the development of accurate predictive models for effective management mitigation. In this study, we present novel machine learning approach combined with Explainable Artificial Intelligence (XAI) techniques predict forest fire susceptibility in Nainital district. Our innovative methodology integrates several robust — AdaBoost, Gradient Boosting Machine (GBM), XGBoost Random Deep Neural Network (DNN) as meta-model stacking framework. This not only utilises individual strengths these models, but also improves overall prediction performance reliability. By using XAI techniques, particular SHAP (SHapley Additive exPlanations) LIME (Local Interpretable Model-agnostic Explanations), improve interpretability provide insights into decision-making processes. results show effectiveness ensemble model categorising different zones: very low, moderate, high high. particular, identified extensive areas susceptibility, precision, recall F1 values underpinning their effectiveness. These achieved ROC AUC above 0.90, performing exceptionally well an 0.94. The are remarkably inclusion confidence intervals most important metrics all emphasises robustness reliability supports practical use management. Through summary plots, analyze global variable importance, revealing annual rainfall Evapotranspiration (ET) key factors influencing susceptibility. Local analysis consistently highlights importance rainfall, ET, distance from roads across models. study fills research gap by providing comprehensive interpretable modelling that our ability effectively manage risk is consistent environmental protection sustainable goals.

Язык: Английский

---

Empowered machine learning algorithm to identify sustainable groundwater potential zone map in Jashore District, Bangladesh

Groundwater for Sustainable Development, Год журнала: 2024, Номер 25, С. 101168 - 101168

Опубликована: Апрель 5, 2024

Язык: Английский

---

Advancing groundwater vulnerability assessment in Bangladesh: a comprehensive machine learning approach

Groundwater for Sustainable Development, Год журнала: 2024, Номер 25, С. 101128 - 101128

Опубликована: Март 2, 2024

Язык: Английский

---

Groundwater delineation for sustainable improvement and development aided by GIS, AHP, and MIF techniques

Applied Water Science, Год журнала: 2024, Номер 14(2)

Опубликована: Янв. 18, 2024

Abstract Exploration of groundwater is an integral part viable resource growth for society, economy, and irrigation. However, uncontrolled utilization mainly reported in urban industries due to the increasing demand water semi-arid arid regions world. In background, demarcation potential areas vital meeting necessary demand. The current study applied integrated method comprising analytical hierarchy process (AHP), multiple influence factors (MIF), combined with a linear regression curve observatory well data prospects mapping. Thematic maps such as flow direction, accumulation, elevation map, land use cover, slope, soil texture, hill shade, geomorphology, normalized vegetation index, depth map were generated utilizing remote sensing techniques. relative weight each parameter was estimated then assigned major minor parameters. Potential zones classified into five classes, namely very good, moderate, poor, based on AHP MIF methods. A spatially explicit sensitivity uncertainty analysis GIS-based multi-criteria zone model presented this research. addressed flaw way mapping results are typically decision studies, where discrete class outputs used without any assessment their certainty respect variations criteria weighting, which one main contributors output uncertainty. region categorized inferred marginal, good ground quality 3.04 km 2 considered extremely 3.33 64.42 85.84 marginal zones, shows reliable implementation. outcomes validated by actual table area. help formulate future sustainable planning development sources. This may be helpful provide cost-effective solution resources crises. finding decision-makers administrative professionals management present demands.

Язык: Английский

---

Sustainable Groundwater Potential Zoning with Integrating GIS, Remote Sensing, and AHP Model: A Case from North-Central Bangladesh

Sustainability, Год журнала: 2022, Номер 14(9), С. 5640 - 5640

Опубликована: Май 7, 2022

Groundwater is one of the most valuable natural resources, and dependable source fresh water. For sustainable groundwater management, present study aimed to model potential zones in north–central region Bangladesh using GIS, remote sensing, analytical hierarchy process. The included eight thematic layers: lineament density, geomorphology, soil types, slope, land use/land cover, drainage elevation, rainfall features delineate a zone area. Integration layers was performed through weighted overlay analysis, which assisted delineating zones. This simple systematic method successfully provides satisfactory result concerning delineation resulted map, identifies about 11.51% area as being under very high zone, covering an 504.09 km2. AHP analysis shows that physiographical parameters, such meteorological factors annual rainfall, have greater influence over potentiality. obtained from verified with actual well yield depth data, show significant positive correlation. outcome will help taking effective measures ensure use extraction this region.

Язык: Английский

---

Developing Robust Flood Susceptibility Model with Small Numbers of Parameters in Highly Fertile Regions of Northwest Bangladesh for Sustainable Flood and Agriculture Management

Sustainability, Год журнала: 2022, Номер 14(7), С. 3982 - 3982

Опубликована: Март 28, 2022

The present study intends to improve the robustness of a flood susceptibility (FS) model with small number parameters in data-scarce areas, such as northwest Bangladesh, by employing machine learning-based sensitivity analysis and an analytical hierarchy process (AHP). In this study, nine most relevant elements (such distance from river, rainfall, drainage density) were chosen conditioning variables for modeling. FS was produced using AHP technique. We used empirical binormal receiver operating characteristic (ROC) curves validating models. performed Sensitivity analyses random forest (RF)-based mean Gini decline (MGD), decrease accuracy (MDA), information gain ratio find out sensitive variables. After performing analysis, least eliminated. re-ran rest enhance model’s performance. Based on previous studies weighting approach, general soil type, river/canal (Dr), land use/land cover (LULC) had higher factor weights 0.22, 0.21, 0.19, 0.15, respectively. without well study. According RF-based ratio, factors slope, elevation, while curvature density less parameters, which excluded re-running just vital parameters. Using ROC curves, new yields AUCs 0.835 0.822, It is discovered that predicted may be maintained or increased removing factors. This will aid decision-makers developing management plans examined region.

Язык: Английский

---

Groundwater level estimation in northern region of Bangladesh using hybrid locally weighted linear regression and Gaussian process regression modeling

Theoretical and Applied Climatology, Год журнала: 2022, Номер 149(1-2), С. 131 - 151

Опубликована: Апрель 6, 2022

Язык: Английский

---

A novel hybrid random forest linear model approach for forecasting groundwater fluoride contamination

Environmental Science and Pollution Research, Год журнала: 2023, Номер 30(17), С. 50661 - 50674

Опубликована: Фев. 17, 2023

Язык: Английский

---