A novel approach to groundwater model development

2012 ◽  
pp. 339-348
Keyword(s):  
Model Development ◽  
Groundwater Model ◽  
Novel Approach

scholarly journals Understanding Climate-Hydrologic-Human Interactions to Guide Groundwater Model Development for Southern High Plains

2017 ◽  
Vol 162 (1) ◽  
pp. 79-99 ◽  
Author(s):  
Venkatesh Uddameri ◽  
Sreeram Singaraju ◽  
Abdullah Karim ◽  
Prasanna Gowda ◽  
Ryan Bailey ◽  
...  
Keyword(s):  
Model Development ◽  
High Plains ◽  
Groundwater Model ◽  
Southern High Plains ◽  
Human Interactions

scholarly journals A global-scale two-layer transient groundwater model: Development and application to groundwater depletion

2017 ◽  
Vol 102 ◽  
pp. 53-67 ◽  
Author(s):  
Inge E.M. de Graaf ◽  
Rens L.P.H. van Beek ◽  
Tom Gleeson ◽  
Nils Moosdorf ◽  
Oliver Schmitz ◽  
...  
Keyword(s):  
Model Development ◽  
Global Scale ◽  
Groundwater Depletion ◽  
Groundwater Model

THE "EVERYTHING'S DIFFERENT, EVERY TIME" INNOVATION MANAGEMENT PROBLEM: A PROMISING MODEL DEVELOPMENT

2015 ◽  
Vol 19 (05) ◽  
pp. 1550057
Author(s):  
GLENN BROPHEY ◽  
ANAHITA BAREGHEH ◽  
DAVID HEMSWORTH ◽  
MARK WACHOWIAK ◽  
DEAN HAY ◽  
...  
Keyword(s):  
Decision Making ◽  
Innovation Management ◽  
Model Development ◽  
Opportunity To Learn ◽  
Management Problem ◽  
New Paradigm ◽  
Continuous Innovation ◽  
Management Actions ◽  
Novel Approach ◽  
Context Specific

This study reports on the testing of a promising approach for aiding decision-making during innovation. By focusing on the effects of risk/action dyads on success (the Risk/Action/Success (R/A/S) framework), and because perceived risks do appear repeatedly even though they emanate from differing contexts, the model offers an opportunity to learn from what worked best before. Using Artificial Neural Networks, this novel approach allows for generalisation and applicability of specific innovation management actions that are context specific. For academics, the proposed approach contributes to the risk-management literature by proposing a new paradigm for understanding and analysing innovation processes and identification of the most frequently occurring risks as seen by managers directly involved in continuous innovation. In addition, the model offers the capacity to use quantitative techniques to model the overlapping risks and actions during innovation-related decision-making. For practitioners, it can provide specific recommendations in the form of success-sorted lists of actions taken by other innovation managers that faced similar risks. This paper presents the theoretical and practical rationales underpinning this R/A/S framework and reports on the viability of this approach using pilot data.

scholarly journals A novel approach for big data classification based on hybrid parallel dimensionality reduction using spark cluster

2019 ◽  
Vol 20 (4) ◽  
Author(s):  
Ahmed Hussein Ali ◽  
Mahmood Zaki Abdullah
Keyword(s):  
Big Data ◽  
High Performance ◽  
Distributed Storage ◽  
Model Development ◽  
Feature Reduction ◽  
High Data ◽  
Reduction Techniques ◽  
Novel Approach ◽  
Parallel Feature ◽  
Big Data Classification

The big data concept has elicited studies on how to accurately and efficiently extract valuable information from such huge dataset. The major problem during big data mining is data dimensionality due to a large number of dimensions in such datasets. This major consequence of high data dimensionality is that it affects the accuracy of machine learning (ML) classifiers; it also results in time wastage due to the presence of several redundant features in the dataset. This problem can be possibly solved using a fast feature reduction method. Hence, this study presents a fast HP-PL which is a new hybrid parallel feature reduction framework that utilizes spark to facilitate feature reduction on shared/distributed-memory clusters. The evaluation of the proposed HP-PL on KDD99 dataset showed the algorithm to be significantly faster than the conventional feature reduction techniques. The proposed technique required 1 minute to select 4 dataset features from over 79 features and 3,000,000 samples on a 3-node cluster (total of 21 cores). For the comparative algorithm, more than 2 hours was required to achieve the same feat. In the proposed system, Hadoop’s distributed file system (HDFS) was used to achieve distributed storage while Apache Spark was used as the computing engine. The model development was based on a parallel model with full consideration of the high performance and throughput of distributed computing. Conclusively, the proposed HP-PL method can achieve good accuracy with less memory and time compared to the conventional methods of feature reduction. This tool can be publicly accessed at https://github.com/ahmed/Fast-HP-PL.

Sign in / Sign up

Export Citation Format

Share Document