A5082030549- Hydrological Forecasting Using AI
- Hydrology and Watershed Management Studies
- Flood Risk Assessment and Management
- Hydrology and Drought Analysis
- Neural Networks and Applications
- Software Engineering Techniques and Practices
- Software Engineering Research
- Climate variability and models
- Resource-Constrained Project Scheduling
- Semantic Web and Ontologies
- Construction Project Management and Performance
- Software System Performance and Reliability
- Business Process Modeling and Analysis
- Meteorological Phenomena and Simulations
- Advanced Software Engineering Methodologies
- Sports Performance and Training
- Evolutionary Algorithms and Applications
- Energy Load and Power Forecasting
- Sport Psychology and Performance
- Artificial Intelligence in Games
- Service-Oriented Architecture and Web Services
- Sports injuries and prevention
- Fire Detection and Safety Systems
- Digital Storytelling and Education
- Metaheuristic Optimization Algorithms Research
Loughborough University
2015-2024
Manipal Academy of Higher Education
2024
Loughborough College
2018
University of Derby
1994-1999
This review considers the application of artificial neural networks (ANNs) to rainfall-runoff modelling and flood forecasting. is an emerging field research, characterized by a wide variety techniques, diversity geographical contexts, general absence intermodel comparisons, inconsistent reporting model skill. article begins outlining basic principles ANN modelling, common network architectures training algorithms. The discussion then addresses related themes division preprocessing data for...
Abstract This paper provides a discussion of the development and application Artificial Neural Networks (ANNs) to flow forecasting in two flood-prone UK catchments using real hydrometric data. Given relatively brief calibration data sets it was possible construct robust models 15-min flows with six hour lead times for Rivers Amber Mole. Comparisons were made between performance ANN those conventional flood systems. The results obtained validation forecasts comparable quality from operational...
ABSTRACT The Statistical DownScaling Model (SDSM) is a freely available tool that produces high resolution climate change scenarios. first public version of the software was released in 2001 and since then there have been over 170 documented studies worldwide. This article recounts underlining conceptual technical evolution SDSM, drawing upon independent assessments model capabilities. These show SDSM yields reliable estimates extreme temperatures, seasonal precipitation totals, areal...
This paper traces two decades of neural network rainfall-runoff and streamflow modelling, collectively termed ‘river forecasting’. The field is now firmly established the research community involved has much to offer hydrological science. First, however, it will be necessary converge on more objective consistent protocols for: selecting treating inputs prior model development; extracting physically meaningful insights from each proposed solution; improving transparency in benchmarking...
Abstract The internal behaviour of an artificial neural network rainfall—runoff model is examined and it demonstrated that specific architectural features can be interpreted with respect to the quasi-physical dynamics a parsimonious water balance model. Neural solutions were developed for daily discharge series simulated by conceptual given observed precipitation totals evaporation rates Test River basin in southern England. outputs associated each hidden node, produced from output node...
CR Climate Research Contact the journal Facebook Twitter RSS Mailing List Subscribe to our mailing list via Mailchimp HomeLatest VolumeAbout JournalEditorsSpecials 61:259-276 (2014) - DOI: https://doi.org/10.3354/cr01254 The Statistical DownScaling Model Decision Centric (SDSM-DC): conceptual basis and applications R. L. Wilby1,*, C. W. Dawson2, Murphy3, P. O’Connor3, E. Hawkins4 1Department of Geography, 2Department Computer Science, Loughborough University, LE11 3TU, UK 3Department...
CR Climate Research Contact the journal Facebook Twitter RSS Mailing List Subscribe to our mailing list via Mailchimp HomeLatest VolumeAbout JournalEditorsSpecials 23:183-194 (2003) - doi:10.3354/cr023183 Multi-site simulation of precipitation by conditional resampling R. L. Wilby1,*, O. J. Tomlinson2, C. W. Dawson3 1Department Geography, King¹s College London, London WC2R 2LS, United Kingdom 2Division University Derby, Derby DE11 2GB, 3Department Computer Science, Loughborough University,...
Abstract. While engineers have been quantifying rainfall-runoff processes since the mid-19th century, it is only in last decade that artificial neural network models applied to same task. This paper evaluates two networks this context: popular multilayer perceptron (MLP), and radial basis function (RBF). Using six-hourly data for River Yangtze at Yichang (upstream of Three Gorges Dam) period 1991 1993, shown both types can simulate river flows beyond range training set. In addition, an...
Abstract. This paper compares the performance of two artificial neural network (ANN) models – multi layer perceptron (MLP) and radial basis function (RBF) with a stepwise multiple linear regression model (SWMLR) zero order forecasts (ZOF) river flow. All were trained using 15 minute rainfall-runoff data for River Mole, flood-prone tributary Thames, UK. The then used to forecast flows 6 hour lead time resolution, given only antecedent rainfall discharge measurements. Two seasons (winter...
The physical demands of soccer match-play have typically been assessed using a low-resolution whole match approach ignoring whether the ball is in or out play (BIP/BOP) and during these periods which team has possession. This study investigated effect fundamental structure variables (BIP/BOP, in/out possession) on demands, especially intensity, elite match-play. For 1083 matches from major European league, duration, player tracking data, were divided into BIP/BOP, possession throughout...
This paper presents a Colombian-based study on hydrological modelling metrics, arguing that redundancies and overlap in statistical assessment can be resolved using principal component analysis. Numerous scores for optimal operator water level models developed at 20 monitoring stations, producing daily, weekly ten-day forecasts, are first reduced to set of five composite orthogonal metrics not interdependent. Each is next replaced by single surrogate measure, selected from several original...