Assessment of Infiltration Rate of Soil Using Empirical and Machine Learning‐Based Models†. (7th April 2019)
- Record Type:
- Journal Article
- Title:
- Assessment of Infiltration Rate of Soil Using Empirical and Machine Learning‐Based Models†. (7th April 2019)
- Main Title:
- Assessment of Infiltration Rate of Soil Using Empirical and Machine Learning‐Based Models†
- Authors:
- Kumar, Munish
Sihag, Parveen - Abstract:
- Abstract: The application of several infiltration models in evaluating the infiltration rate of soil is subject to the spatial variability of soil. Infiltration plays an important role in designing and evaluating surface irrigation systems as well as subsurface groundwater recharge systems. The main theme of this paper is to compare the empirical equation‐based models which are used to estimate the infiltration rate of various locations in Kurukshetra, India. Infiltration experiments were conducted at 20 different locations using a mini disc infiltrometer. The least square fitting method was used for each location separately to estimate the equation parameters and infiltration rate of three different empirical models, namely Kostiakov, modified Kostiakov and Novel models. The performance of these empirical infiltration models was further compared with the machine learning‐based adaptive neuro‐fuzzy inference system (ANFIS) and random forest regression (RF) techniques. Statistical performance evaluation parameters ( R 2, CC, RMSE and MAE) are used for the performance comparison of various models. The Novel infiltration model was observed to be the most reasonable amongst the empirical models tested. However, for machine‐learning methods, the RF approach is observed to be the most appropriate technique for the estimation of the infiltration data. © 2019 John Wiley & Sons, Ltd. Résumé: Plusieurs modèles d'infiltration pour évaluer le taux d'infiltration du sol sont utilisés etAbstract: The application of several infiltration models in evaluating the infiltration rate of soil is subject to the spatial variability of soil. Infiltration plays an important role in designing and evaluating surface irrigation systems as well as subsurface groundwater recharge systems. The main theme of this paper is to compare the empirical equation‐based models which are used to estimate the infiltration rate of various locations in Kurukshetra, India. Infiltration experiments were conducted at 20 different locations using a mini disc infiltrometer. The least square fitting method was used for each location separately to estimate the equation parameters and infiltration rate of three different empirical models, namely Kostiakov, modified Kostiakov and Novel models. The performance of these empirical infiltration models was further compared with the machine learning‐based adaptive neuro‐fuzzy inference system (ANFIS) and random forest regression (RF) techniques. Statistical performance evaluation parameters ( R 2, CC, RMSE and MAE) are used for the performance comparison of various models. The Novel infiltration model was observed to be the most reasonable amongst the empirical models tested. However, for machine‐learning methods, the RF approach is observed to be the most appropriate technique for the estimation of the infiltration data. © 2019 John Wiley & Sons, Ltd. Résumé: Plusieurs modèles d'infiltration pour évaluer le taux d'infiltration du sol sont utilisés et soumis à la variabilité spatiale du sol. L'infiltration joue un rôle important dans la conception et l'évaluation des systèmes d'irrigation de surface ainsi que des systèmes de recharge d'eaux souterraines. Le thème principal du document est de comparer les modèles empiriques basés sur des équations qui sont utilisés pour estimer le taux d'infiltration de divers sites de Kurukshetra, en Inde. Des expériences d'infiltration ont été menées à 20 endroits différents à l'aide d'un infiltromètre à minidisques. La méthode des moindres carrés a été utilisée séparément pour chaque emplacement afin d'estimer les paramètres de l'équation et le taux d'infiltration de trois modèles empiriques différents, à savoir les modèles de Kostiakov, Kostiakov Modifié et Novel. Les performances de ces modèles d'infiltration empiriques ont encore été comparées aux techniques du système à base de réseaux neuroniques et de logique floue (NFIS pour 'Neuro Fuzzy Inference system').basé sur l'apprentissage automatique et aux techniques de forêt d'arbres décisionnels (random forest regression (RF)). Les paramètres d'évaluation de performance statistique (R2, CC, RMSE et MAE) sont utilisés pour la comparaison de performance de différents modèles. Le nouveau modèle d'infiltration s'est avéré le plus raisonnable des modèles empiriques testés. Cependant, pour les méthodes d'apprentissage automatique, on considère que l'approche RF est la technique la plus appropriée pour l'estimation des données d'infiltration. © 2019 John Wiley & Sons, Ltd. … (more)
- Is Part Of:
- Irrigation and drainage. Volume 68:Number 3(2019)
- Journal:
- Irrigation and drainage
- Issue:
- Volume 68:Number 3(2019)
- Issue Display:
- Volume 68, Issue 3 (2019)
- Year:
- 2019
- Volume:
- 68
- Issue:
- 3
- Issue Sort Value:
- 2019-0068-0003-0000
- Page Start:
- 588
- Page End:
- 601
- Publication Date:
- 2019-04-07
- Subjects:
- infiltration rate -- empirical models -- random forest -- adaptive neuro‐fuzzy inference system -- mini disc infiltrometer
taux d'infiltration -- modèles empiriques -- forêt aléatoire -- système adaptatif à base de réseaux neuroniques et de logique floue (neuro‐fuzzy inference system) -- infiltromètre à minidisque
Irrigation engineering -- Periodicals
Drainage -- Periodicals
Flood control -- Periodicals
Sustainable agriculture -- Periodicals
627.52 - Journal URLs:
- http://onlinelibrary.wiley.com/ ↗
- DOI:
- 10.1002/ird.2332 ↗
- Languages:
- English
- ISSNs:
- 1531-0353
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 4580.946000
British Library DSC - BLDSS-3PM
British Library STI - ELD Digital store - Ingest File:
- 11167.xml