Estimation of soil water content in watershed using artificial neural networks

Oliveira, Marquis Henrique Campos de; Sari, Vanessa; Castro, Nilza Maria dos Reis; Pedrollo, Olavo Correa

doi:10.1080/02626667.2017.1364844

Cited by 16 publications

(9 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method, here called the weighted mean approach, is used in forecasting systems that deal with inaccurate prediction caused by the insufficiency of historical observations and allows for a self‐starting forecasting process without having to store past data (Yu et al., 2020). The method is used in a variety of applications in forecasting, from estimating soil moisture from precipitation (Campos de Oliveira et al., 2017) to vegetation acclimation processes (e.g., Vanderwel et al., 2015).…”

Section: Methodsmentioning

confidence: 99%

Ecosystem Photosynthesis in Land‐Surface Models: A First‐Principles Approach Incorporating Acclimation

Mengoli

Agustı́-Panareda

Boussetta

et al. 2022

J Adv Model Earth Syst

View full text Add to dashboard Cite

Vegetation plays a key role in the Earth system, regulating carbon, water, and energy exchanges between vegetation and atmosphere. Transpiration, photosynthesis, and respiration are the main processes that govern these exchanges and link vegetation to the climate (Bonan, 2008;Bonan et al., 1992Bonan et al., , 2003. Evapotranspiration (ET, with accompanying latent-heat release) and photosynthesis are tightly linked. Transpiration is the dominant component of ET, hence plants are the main conduit of water from the soil to the atmosphere. Plants control both transpiration and the flux of carbon dioxide (CO 2 ) into leaves by regulating the opening or closing of stomata.

show abstract

Section: Methodsmentioning

confidence: 99%

Ecosystem Photosynthesis in Land‐Surface Models: A First‐Principles Approach Incorporating Acclimation

Mengoli

Agustı́-Panareda

Boussetta

et al. 2022

J Adv Model Earth Syst

View full text Add to dashboard Cite

show abstract

“…During recent decades, artificial neural network (ANN) methods have become widely applied in various approaches of hydrological studies, such as modelling of soil water reserves (Moreira de Melo & Correa Pedrollo ; Alexakis et al ; Campos de Oliveira et al ); modelling and interpolation of precipitation, evapotranspiration and surface water levels (Altunkaynak ; Sivapragasam et al ; Dadaser‐Celik & Cengiz ; Deo & Şahin ); modelling of groundwater table (GWT) variabilities (Nayak et al ; Banerjee et al ; Karthikeyan et al ; Mohanty et al ; Hong ; Pasandi et al ) and assessments of groundwater pollution (Sahoo et al ; Khaki et al ). In general, the ANN modelling does not require detailed information about the input data as with the case of various physical models (Deo & Şahin ).…”

Section: Introductionmentioning

confidence: 99%

“…During recent decades, artificial neural network (ANN) methods have become widely applied in various approaches of hydrological studies, such as modelling of soil water reserves (Moreira de Melo & Correa Pedrollo 2015; Alexakis et al 2017;Campos de Oliveira et al 2017); modelling and interpolation of precipitation, evapotranspiration and surface water levels (Altunkaynak 2007;Sivapragasam et al 2009;Dadaser-Celik & Cengiz 2013;Deo & Şahin 2015); modelling of groundwater table (GWT) variabilities (Nayak et al 2006;Banerjee et al 2009;models (Deo & Şahin 2015). It utilises the relationships between input parameters and variables by testing data trends as nonlinear regression.…”

Section: Introductionmentioning

confidence: 99%

Assessing the applicability of groundwater monitoring data in the modelling of soil water retention characteristics

Orzepowski

Paruch

Kowalczyk

et al. 2018

Water & Environment J

View full text Add to dashboard Cite

The present work focuses on an assessment of the applicability of groundwater table (GWT) measures in the modelling of soil water retention characteristics (SWRC) using artificial neural network (ANN) methods. Model development, testing, validation and verification were performed using data collected across two decades from soil profiles at full‐scale research objects located in Southwest Poland. A positive effect was observed between the initial GWT position data and the accuracy of soil water reserve estimation. On the other hand, no significant effects were observed following the implementation of GWT fluctuation data over the entire growing season. The ANN tests that used data of either soil water content or GWT position gave analogous results. This revealed that the easily obtained data (temperature, precipitation and GWT position) are the most accurate modelling parameters. These outcomes can be used to simplify modelling input data/parameters/variables in the practical implementation of the proposed SWRC modelling variants.

show abstract

“…Similar functions were developed and tested later by Minasny et al (1999), Tomasella et al (2000), and Børgesen et al (2008) for soils from New Zealand, Brazil, and Denmark, respectively. Further developments beyond the classical regression analysis include techniques like artificial neural networks (Schaap and Leij, 1998a, 1998b; Minasny and McBratney, 2002; Merdun et al, 2006; Baker and Ellison, 2008; Campos de Oliveira et al, 2017; D’Emilio et al, 2018), pattern recognition based methods including support vector machine (Nemes et al, 2006; Lamorski et al, 2008; Khlosi et al, 2016), Gaussian process regression (Kotlar et al, 2019b), and the ensemble approach (Baker and Ellison, 2008; Cichota et al, 2013; Liao et al, 2015), all of which contributed to the improvement of PTF performance in predicting soil hydraulic properties.…”

mentioning

confidence: 99%

“…2002; Merdun et al, 2006;Baker and Ellison, 2008;Campos de Oliveira et al, 2017;D'Emilio et al, 2018), pattern recognition based methods including support vector machine (Nemes et al, 2006;Lamorski et al, 2008;Khlosi et al, 2016), Gaussian process regression (Kotlar et al, 2019b), and the ensemble approach (Baker and Ellison, 2008;Cichota et al, 2013;Liao et al, 2015), all of which contributed to the improvement of PTF performance in predicting soil hydraulic properties.…”

mentioning

confidence: 99%

Development and Uncertainty Assessment of Pedotransfer Functions for Predicting Water Contents at Specific Pressure Heads

Kotlar

Lier

Barros

et al. 2019

Vadose Zone Journal

View full text Add to dashboard Cite

PTFs for water contents at specific pressure heads were developed. Covariate shift increased uncertainty in PTF predictions. Relative importance of predictors in machine learning PTFs was determined. There has been much effort to improve the performance of pedotransfer functions (PTFs) using intelligent algorithms, but the issue of covariate shift, i.e., different probability distributions in training and testing datasets, and its impact on prediction uncertainty of PTFs has been rarely addressed. The common practice in PTF generation is to randomly separate the dataset into training and testing subsets, and the outcomes of this random selection may be different if the process is subject to covariate shift. We evaluated the impact of covariate shift generated by data shuffling and detected by Kolmogorov–Smirnov test for the prediction of water contents using soil databases from Denmark and Brazil. The soil water contents at different pressure heads were predicted by developing linear and stepwise regression besides machine learning based PTFs including Gaussian process regression and ensemble method. Regression based PTFs for the Brazilian dataset resulted in better predictions compared with machine learning methods, which in their turn estimated high water contents in Danish soils more accurately. One hundred PTFs were developed for water content at specific pressure heads by data shuffling. From these, 100 sets of fitted van Genuchten parameters were obtained representing the generated uncertainty. Data shuffling led to covariate shift, resulting in uncertainty in water content prediction by the PTFs. Inherent variability of data may lead to increased prediction uncertainty. For correlated data, simple regression models performed as good as sophisticated machine learning methods. Using PTF‐predicted water contents for van Genuchten retention parameter fitting may lead to a high uncertainty.

show abstract

Estimation of soil water content in watershed using artificial neural networks

Cited by 16 publications

References 52 publications

Ecosystem Photosynthesis in Land‐Surface Models: A First‐Principles Approach Incorporating Acclimation

Ecosystem Photosynthesis in Land‐Surface Models: A First‐Principles Approach Incorporating Acclimation

Assessing the applicability of groundwater monitoring data in the modelling of soil water retention characteristics

Development and Uncertainty Assessment of Pedotransfer Functions for Predicting Water Contents at Specific Pressure Heads

Contact Info

Product

Resources

About