Please wait, while we are loading the content...
Please wait, while we are loading the content...
| Content Provider | Springer Nature Link |
|---|---|
| Author | Sahoo, Sasmita Jha, Madan K. |
| Copyright Year | 2013 |
| Abstract | The potential of multiple linear regression (MLR) and artificial neural network (ANN) techniques in predicting transient water levels over a groundwater basin were compared. MLR and ANN modeling was carried out at 17 sites in Japan, considering all significant inputs: rainfall, ambient temperature, river stage, 11 seasonal dummy variables, and influential lags of rainfall, ambient temperature, river stage and groundwater level. Seventeen site-specific ANN models were developed, using multi-layer feed-forward neural networks trained with Levenberg-Marquardt backpropagation algorithms. The performance of the models was evaluated using statistical and graphical indicators. Comparison of the goodness-of-fit statistics of the MLR models with those of the ANN models indicated that there is better agreement between the ANN-predicted groundwater levels and the observed groundwater levels at all the sites, compared to the MLR. This finding was supported by the graphical indicators and the residual analysis. Thus, it is concluded that the ANN technique is superior to the MLR technique in predicting spatio-temporal distribution of groundwater levels in a basin. However, considering the practical advantages of the MLR technique, it is recommended as an alternative and cost-effective groundwater modeling tool.Les potentialités des techniques de régression linéaire multiple (RLM) et de réseau neuronal artificiel (RNA), en matière de prédiction des niveaux d’eau transitoires dans un bassin souterrain, sont comparées. Les modélisations RLM et RNA ont été mises en œuvre dans 17 sites au Japon, en prenant en compte toutes les données importantes : précipitations, température ambiante, état de la rivière, 11 variables muettes saisonnières et le déphasage des précipitations, de la température ambiante, de l’état de la rivière et du niveau de l’eau souterraine. Dix sept modèles de RNA spécifiques à chacun des sites ont été développés, en utilisant des réseaux neuronaux directs multicouches formés par les algorithmes de rétro-propagation de Levenberg-Marquardt. La performance des modèles a été évaluée en recourant aux indicateurs statistiques et graphiques La comparaison des statistiques sur la qualité d’ajustement des modèles RLM et des modèles RNA indique qu’il y a, pour tous les sites, un meilleur calage entre les niveaux d’eau souterraine prédits par RNA et les niveaux observés. Les résultats sont fondés sur les indicateurs graphiques et l’analyse résiduelle. Ainsi, la conclusion est que la technique RNA est supérieure à la technique RLM pour la prédiction de la distribution spatio-temporelle des niveaux d’eau souterraine dans un bassin. Cependant, en prenant en compte ses avantages pratiques, la technique RLM est recommandée, en tant qu’outil alternatif rentable, pour la modélisation des eaux souterraines.Se compararon el potencial de las técnicas de regresión linear múltiple (MLR) y de redes neuronales artificiales (ANN) para predecir los niveles transitorios de agua en una cuenca de agua subterránea. El modelado de MLR y ANN fue llevado a cabo en 17 sitios en Japón, considerando todas las entradas significativas: precipitación, temperatura ambiente, estados de los ríos, 11 variables estacionales mudas, y la influencia de los retardos de la precipitación, temperatura ambiente, estado del río y nivel de agua subterránea. Se desarrollaron diecisiete modelos ANN en sitios específicos, usando redes neuronales multicapas de alimentación progresiva entrenadas con algoritmos de retropropagación de Levenberg-Marquardt. Se evaluó el rendimiento de los modelos usando indicadores estadísticos y gráficos. La comparación de la bondad de ajuste estadístico de los modelos MLR con aquellos de los modelos ANN indicó que existe un mejor acuerdo entre los niveles de agua subterránea predichos por ANN y los niveles observados de agua subterránea en todos los sitios, comparados con los MLR. Este hallazgo fue apoyado por los indicadores gráficos y los análisis de residuos. Así, se concluyó que la técnica ANN es superior a la técnica MLR para la predicción espacio – temporal de los niveles de agua subterránea en una cuenca. Sin embargo, considerando las ventajas prácticas de la técnica MLR, se recomienda como una herramienta y una alternativa de modelado de agua subterránea a costo razonable.多元线性回归(MLR)和人工神经网络技术(ANN)在预测地下水盆地中的瞬时水位的精确度进行了对比分析。考虑到所有重要的输入因子:雨量充沛,环境温度,河流水位,11个季节雨量的虚拟变量,以及降雨的影响力的滞后和地下水位,在日本的17个地点进行了MLR和ANN模拟。采用多层前馈神经网络的Levenberg—Marquardt反向传播算法对17个特定站点进行了ANN模拟并利用统计和图形标志对模型的性能进行了评估。MLR模型和ANN模型的拟合优度统计结果显示,与MLR模型相比,ANN模型预测的所有地点的地下水位值与实际观测到的地下水位值的吻合性更好。图形指标和残差分析也证实了这一点。因此,在预测一个盆地的地下水位时空分布时,ANN技术要优于MLR技术。但是,考虑到MLR技术的优势,可以将它作为一个具有替代性和经济效益的地下水建模工具。Foi feita a comparação do potencial das técnicas de regressão linear múltipla (RLM) e de redes neuronais artificiais (RNA) na predição de níveis piezométricos transitórios numa bacia de água subterrânea. Foi aplicada a RLM e a modelação de RNA em 17 sítios no Japão tendo em conta todos os dados de entrada significativos: precipitação, temperatura ambiente, níveis hidrométricos do rio, 11 variáveis sazonais assumidas e episódios de chuva influente, temperatura ambiente, níveis hidrométricos do rio e níveis piezométricos. Foram desenvolvidos dezassete modelos de RNA específicos de cada local, usando redes neuronais de alimentação progressiva multi-camada treinadas com algoritmos de retropropagação Levenberg-Marquardt. O desempenho dos modelos foi testado usando indicadores estatísticos e gráficos. A comparação da estatística do ajuste da simulação dos modelos de RLM com os modelos de RNA indica que existe uma maior concordância entre os níveis piezométricos previstos pelas RNA e os níveis piezométricos observados em todos os locais, comparativamente com os resultados obtidos pela RLM. Esta constatação é corroborada pelos indicadores gráficos e a análise residual. Assim, conclui-se que a técnica de RNA é superior à de RLM na predição espácio-temporal da distribuição de níveis de água subterrânea numa bacia. No entanto, tendo em conta as vantagens práticas da técnica de RLM, esta é recomendada como uma ferramenta de modelação de água subterrânea alternativa e rentável. |
| Starting Page | 1865 |
| Ending Page | 1887 |
| Page Count | 23 |
| File Format | |
| ISSN | 14312174 |
| Journal | Hydrogeology Journal |
| Volume Number | 21 |
| Issue Number | 8 |
| e-ISSN | 14350157 |
| Language | Portuguese |
| Publisher | Springer Berlin Heidelberg |
| Publisher Date | 2013-10-04 |
| Publisher Institution | International Association of Hydrogeologists |
| Publisher Place | Berlin, Heidelberg |
| Access Restriction | One Nation One Subscription (ONOS) |
| Subject Keyword | Groundwater-level prediction Multiple linear regression Artificial neural network Statistical modeling Japan Hydrogeology Hydrology/Water Resources Geology Waste Water Technology Water Pollution Control Water Management Aquatic Pollution |
| Content Type | Text |
| Resource Type | Article |
| Subject | Earth and Planetary Sciences Water Science and Technology |
National Digital Library of India (NDLI) is a virtual repository of learning resources which is not just a repository with search/browse facilities but provides a host of services for the learner community. It is sponsored and mentored by Ministry of Education, Government of India, through its National Mission on Education through Information and Communication Technology (NMEICT). Filtered and federated searching is employed to facilitate focused searching so that learners can find the right resource with least effort and in minimum time. NDLI provides user group-specific services such as Examination Preparatory for School and College students and job aspirants. Services for Researchers and general learners are also provided. NDLI is designed to hold content of any language and provides interface support for 10 most widely used Indian languages. It is built to provide support for all academic levels including researchers and life-long learners, all disciplines, all popular forms of access devices and differently-abled learners. It is designed to enable people to learn and prepare from best practices from all over the world and to facilitate researchers to perform inter-linked exploration from multiple sources. It is developed, operated and maintained from Indian Institute of Technology Kharagpur.
Learn more about this project from here.
NDLI is a conglomeration of freely available or institutionally contributed or donated or publisher managed contents. Almost all these contents are hosted and accessed from respective sources. The responsibility for authenticity, relevance, completeness, accuracy, reliability and suitability of these contents rests with the respective organization and NDLI has no responsibility or liability for these. Every effort is made to keep the NDLI portal up and running smoothly unless there are some unavoidable technical issues.
Ministry of Education, through its National Mission on Education through Information and Communication Technology (NMEICT), has sponsored and funded the National Digital Library of India (NDLI) project.
| Sl. | Authority | Responsibilities | Communication Details |
|---|---|---|---|
| 1 | Ministry of Education (GoI), Department of Higher Education |
Sanctioning Authority | https://www.education.gov.in/ict-initiatives |
| 2 | Indian Institute of Technology Kharagpur | Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project | https://www.iitkgp.ac.in |
| 3 | National Digital Library of India Office, Indian Institute of Technology Kharagpur | The administrative and infrastructural headquarters of the project | Dr. B. Sutradhar bsutra@ndl.gov.in |
| 4 | Project PI / Joint PI | Principal Investigator and Joint Principal Investigators of the project |
Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon |
| 5 | Website/Portal (Helpdesk) | Queries regarding NDLI and its services | support@ndl.gov.in |
| 6 | Contents and Copyright Issues | Queries related to content curation and copyright issues | content@ndl.gov.in |
| 7 | National Digital Library of India Club (NDLI Club) | Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach | clubsupport@ndl.gov.in |
| 8 | Digital Preservation Centre (DPC) | Assistance with digitizing and archiving copyright-free printed books | dpc@ndl.gov.in |
| 9 | IDR Setup or Support | Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops | idr@ndl.gov.in |
|
Loading...
|