Predicting Standardized Streamflow index for hydrological drought using machine learning models

Engineering Applications of Computational Fluid Mechanics, Journal Year: 2020, Volume and Issue: 14(1), P. 339 - 350

Published: Jan. 1, 2020

Formulae display:?Mathematical formulae have been encoded as MathML and are displayed in this HTML version using MathJax order to improve their display. Uncheck the box turn off. This feature requires Javascript. Click on a formula zoom.

Language: Английский

---

Groundwater level prediction using machine learning models: A comprehensive review

Neurocomputing, Journal Year: 2022, Volume and Issue: 489, P. 271 - 308

Published: March 14, 2022

Developing accurate soft computing methods for groundwater level (GWL) forecasting is essential enhancing the planning and management of water resources. Over past two decades, significant progress has been made in GWL prediction using machine learning (ML) models. Several review articles have published, reporting advances this field up to 2018. However, existing do not cover several aspects simulations ML, which are scientists practitioners working hydrology resource management. The current article aims provide a clear understanding state-of-the-art ML models implemented modeling milestones achieved domain. includes all types employed from 2008 2020 (138 articles) summarizes details reviewed papers, including models, data span, time scale, input output parameters, performance criteria used, best identified. Furthermore, recommendations possible future research directions improve accuracy enhance related knowledge outlined.

Language: Английский

---

An interpretable machine learning approach based on DNN, SVR, Extra Tree, and XGBoost models for predicting daily pan evaporation

Journal of Environmental Management, Journal Year: 2022, Volume and Issue: 327, P. 116890 - 116890

Published: Nov. 29, 2022

Language: Английский

---

Bim-based energy analysis and optimization using insight 360 (case study)

Case Studies in Construction Materials, Journal Year: 2022, Volume and Issue: 18, P. e01755 - e01755

Published: Dec. 12, 2022

Building information modeling (BIM) is a modern data platform and management tool that promotes the development of green buildings. In Pakistan, building sector consumes more than 50% total energy consumption it growing at annual rates 4.7% 2.5% in household commercial sectors, respectively. The problem biggest single economic drag on Pakistan BIM Council (PBC) attempting to implement adoption construction industry. Using Autodesk Insight 360 Green Studio, an analysis optimization case study A-Block COMSATS Abbottabad, chosen. This explores performance academic as order optimize use by rotating degrees 45-degree intervals utilizing install energy-efficient materials. Existing buildings have lower cost savings. financial savings are 585.10 kWh 550 $, Applying factors can result improved conceptual design with good environmental effectiveness, thus assisting pursuit sustainability.

Language: Английский

---

BIM adoption in sustainability, energy modelling and implementing using ISO 19650: A review

Ain Shams Engineering Journal, Journal Year: 2023, Volume and Issue: 15(1), P. 102252 - 102252

Published: April 19, 2023

The construction industry is adopting a ground-breaking invention called Building Information Modeling (BIM) to virtually manage and plan projects throughout the building's lifespan. In architectural, engineering, (AEC) sector, adoption of BIM growing government sector worldwide, including governmental entities non-profit organizations. This article covers how building information modelling was used produce suggestions help customers operational teams appropriately specify needs for projects. ISO 19650 standards underline this as first most critical stage in ensuring that there adequate available optimize constructed assets over course their whole life cycle. A study gap discovered absence explicit recommendations aimed at helping determine appointing party. research gives action identify promote effective project outcomes. Since Pakistan does not have standard, authors recommended using with minimum modification Pakistan's it offers systemic framework regard.

Language: Английский

---

A Comprehensive Survey of Machine Learning Methodologies with Emphasis in Water Resources Management

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(22), P. 12147 - 12147

Published: Nov. 8, 2023

This paper offers a comprehensive overview of machine learning (ML) methodologies and algorithms, highlighting their practical applications in the critical domain water resource management. Environmental issues, such as climate change ecosystem destruction, pose significant threats to humanity planet. Addressing these challenges necessitates sustainable management increased efficiency. Artificial intelligence (AI) ML technologies present promising solutions this regard. By harnessing AI ML, we can collect analyze vast amounts data from diverse sources, remote sensing, smart sensors, social media. enables real-time monitoring decision making applications, including irrigation optimization, quality monitoring, flood forecasting, demand enhance agricultural practices, distribution models, desalination plants. Furthermore, facilitates integration, supports decision-making processes, enhances overall sustainability. However, wider adoption faces challenges, heterogeneity, stakeholder education, high costs. To provide an management, research focuses on core fundamentals, major (prediction, clustering, reinforcement learning), ongoing issues offer new insights. More specifically, after in-depth illustration algorithmic taxonomy, comparative mapping all specific tasks. At same time, include tabulation works along with some concrete, yet compact, descriptions objectives at hand. leveraging tools, develop plans address world’s supply concerns effectively.

Language: Английский

---

A New K-Nearest Neighbors Classifier for Big Data Based on Efficient Data Pruning

Mathematics, Journal Year: 2020, Volume and Issue: 8(2), P. 286 - 286

Published: Feb. 20, 2020

The K-nearest neighbors (KNN) machine learning algorithm is a well-known non-parametric classification method. However, like other traditional data mining methods, applying it on big comes with computational challenges. Indeed, KNN determines the class of new sample based its nearest neighbors; however, identifying in large amount imposes cost so that no longer applicable by single computing machine. One proposed techniques to make methods datasets pruning. LC-KNN an improved method which first clusters into some smaller partitions using K-means clustering method; and then applies for each partition center one. because have different shapes densities, selection appropriate cluster challenge. In this paper, approach has been improve pruning phase taking account these factors. helps choose more looking neighbors, thus, increasing accuracy. performance evaluated real datasets. experimental results show effectiveness higher accuracy lower time comparison recent relevant methods.

Language: Английский

---

Simulation of seepage flow through embankment dam by using a novel extended Kalman filter based neural network paradigm: Case study of Fontaine Gazelles Dam, Algeria

Measurement, Journal Year: 2021, Volume and Issue: 176, P. 109219 - 109219

Published: March 5, 2021

Language: Английский

---

Data Intelligence Model and Meta-Heuristic Algorithms-Based Pan Evaporation Modelling in Two Different Agro-Climatic Zones: A Case Study from Northern India

Atmosphere, Journal Year: 2021, Volume and Issue: 12(12), P. 1654 - 1654

Published: Dec. 9, 2021

Precise quantification of evaporation has a vital role in effective crop modelling, irrigation scheduling, and agricultural water management. In recent years, the data-driven models using meta-heuristics algorithms have attracted attention researchers worldwide. this investigation, we examined performance employing four meta-heuristic algorithms, namely, support vector machine (SVM), random tree (RT), reduced error pruning (REPTree), subspace (RSS) for simulating daily pan (EPd) at two different locations north India representing semi-arid climate (New Delhi) sub-humid (Ludhiana). The most suitable combinations meteorological input variables as covariates to estimate EPd were ascertained through subset regression technique followed by sensitivity analyses. statistical indicators such root mean square (RMSE), absolute (MAE), Nash–Sutcliffe efficiency (NSE), Willmott index (WI), correlation coefficient (r) graphical interpretations, utilized model evaluation. SVM algorithm successfully performed reconstructing time series with acceptable criteria (i.e., NSE = 0.937, 0.795; WI 0.984, 0.943; r 0.968, 0.902; MAE 0.055, 0.993 mm/day; RMSE 0.092, 1.317 mm/day) compared other applied during testing phase New Delhi Ludhiana stations, respectively. This study also demonstrated discussed potential producing reasonable estimates minimal applicability best candidate vetted diverse agro-climatic settings.

Language: Английский

---

A new insight to the wind speed forecasting: robust multi-stage ensemble soft computing approach based on pre-processing uncertainty assessment

Neural Computing and Applications, Journal Year: 2021, Volume and Issue: 34(1), P. 783 - 812

Published: Aug. 30, 2021

Language: Английский

---