Estimation of Furrow Irrigation Sediment Loss Using an Artificial Neural Network

King, Bradley A.; Bjorneberg, David L.; Trout, Thomas J.; Mateos, Luciano; Araújo, Danielle Ferreira de; Costa, Raimundo Nonato Távora

doi:10.1061/(asce)ir.1943-4774.0000932

Cited by 10 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The collective data set included nine common hydraulic and field condition variables: freshly cultivated or previously eroded by prior irrigation; compacted by wheel traffic or uncompacted; irrigation duration (T, h); furrow length (L, m); furrow inflow rate (Q, L min -1 ); furrow slope (S, %); soil sand and clay fractions (%); and furrow sediment loss (SL, kg). Additional details on the data sources are provided by King et al (2016).…”

Section: Databasementioning

confidence: 99%

“…Linear regression and feedforward neural networks (FFNN) are examples of supervised learning where model parameters are adjusted to minimize the sum of square errors between model predications and a measured value. King et al (2016) used a feed-forward artificial neural network (FFNN) to model furrow sediment loss resulting in an R 2 = 0.71 between predicted and measured sediment loss. The desire to maximize prediction performance resulted in an over-trained model where the model learned the data set rather than underlying physical relationships representing the furrow sediment loss process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Use of Self-Organizing Maps to Estimate Furrow Sediment Loss in Western U.S.

King¹,

Bjorneberg²

2022

2022 Houston, Texas July 17-20, 2022

Self Cite

View full text Add to dashboard Cite

The area irrigated by furrow irrigation in the U.S. has been steadily decreasing but still represents about 20% of the total irrigated area in the U.S. Furrow irrigation sediment loss is a major water quality issue in the western U.S. and a method for estimating sediment loss is needed to quantify the environmental impacts and estimate effectiveness and economic value of conservation practices. The objective of the study was to investigate the use of the unsupervised machine learning technique Kohonen self-organizing maps (KSOM) to predict furrow sediment loss. Historical published and unpublished data sets containing measurements of furrow irrigation sediment loss in the western U.S. were assembled into a furrow sediment loss data set comprising over 2000 measurements. Despite the immunity of KSOMs to measurement variability, the inherent variability in measured furrow sediment loss limited the ability of a KSOM model to reliability predict furrow sediment loss. Furrow sediment loss was under predicted by 44% on average with a linear regression coefficient of determination of 0.6. The KSOM model was placing little weight on measured sediment loss in the input data set, indicating that it was clustering the data based on input parameters defining the hydraulic and soil conditions. This outcome was used to develop a transfer learning approach for predicting furrow sediment loss. The transfer learning approach used a KSOM to cluster data records of similar hydraulic and soil conditions in the data set. Mean measured sediment loss and furrow flow rate of each cluster was determined based on data set vectors assigned to a cluster by the KSOM. Furrow sediment loss prediction was obtained by applying an input vector to the KSOM to identify the cluster the input vector most closely matches. Then the mean measured sediment loss of the identified cluster was adjusted for any difference between the input vector furrow flow rate and cluster mean furrow flow rate to obtain a prediction of furrow sediment loss. Predicted furrow sediment loss was 16% less than measured sediment loss on average with a coefficient of determination of 0.82. When the data set was randomly split into model development (90%) and validation (10%) data sets the prediction results were similar.

show abstract

Section: Databasementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Use of Self-Organizing Maps to Estimate Furrow Sediment Loss in Western U.S.

King¹,

Bjorneberg²

2022

2022 Houston, Texas July 17-20, 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The loss of surface soil reduces soil fertility and ultimately prevents agricultural cultivation. Factors affecting soil erosion in furrow‐irrigated land include field slope, soil type (soil texture and structure), field dimensions, inflow rate, crop characteristics and the duration of the irrigation event (Fernández‐Gómez et al, 2004; King et al, 2016; Truman & Nuti, 2009; Westermann et al, 2001). In open‐end furrow irrigation, a large part of the inflow water is released from the end of the furrow as runoff.…”

Section: Introductionmentioning

confidence: 99%

Reduction of soil and phosphorus losses by using micro‐dams in furrow irrigation

Keshavarz

Ebrahimian

Abbasi

et al. 2022

Water & Environment J

View full text Add to dashboard Cite

The suspension of eroded soil in surface runoff ultimately leads to the transfer of nutrients to land and water resources. Placing soil or straw (as a barrier) inside irrigated furrows in order to reduce water flow velocity, as a traditional local practice, has not been investigated from the environmental point of view. In this research, the effect of micro‐dams (barriers built inside the irrigated furrows, also known as tied ridges or furrow dikes) on the reduction of soil and phosphorus losses was investigated. Field experiments were performed in four consequent irrigation events. Two erosive inflow discharges (0.6 and 0.9 L/s) and two micro‐dam distances (10 and 20 m) were implemented as test treatments. A control treatment, without micro‐dams, was used for comparison purposes. For the discharge of 0.6 L/s, micro‐dams reduced furrow soil loss by 25% and 33% for distances of 20 and 10 m, respectively. For 0.9 L/s, soil loss was reduced by 25% and 59% for distances of 20 and 10 m, respectively. Micro‐dams also reduced dissolved phosphorus losses in runoff water by 13% to 37%, depending on discharge and distance, as compared to the control treatment. Micro‐dams can effectively reduce water, soil and phosphorus losses.

show abstract

“…For example, King et al . () utilized ANNs for estimation of sediment loss in furrow irrigation based on hydraulic and soil conditions. They demonstrated that the performance of ANNs was better than the efficiency of previously employed sediment loss prediction approaches including physical and empirical models.…”

Section: Introductionmentioning

confidence: 99%

“…The applications of ANNs in various fields of water resources are promising and description of all related references is beyond the scope of this study and only some related works are presented here. For example, King et al (2015) utilized ANNs for estimation of sediment loss in furrow irrigation based on hydraulic and soil conditions. They demonstrated that the performance of ANNs was better than the efficiency of previously employed sediment loss prediction approaches including physical and empirical models.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Wind Drift and Evaporation Losses from Sprinkler Irrigation systemS by Different Data‐Driven Methods

Maroufpoor

Hadi

Emamgholizadeh

et al. 2017

Irrigation and Drainage

View full text Add to dashboard Cite

An accurate estimation of losses created by wind drift and evaporation is necessary for water management in sprinkler irrigation systems. In the current study, three artificial intelligence (AI) methods, namely artificial neural network (ANN), adaptive neuro‐fuzzy inference system (ANFIS) and gene expression programming (GEP), were used to estimate the wind drift and evaporation losses (WDEL) based on influential variables such as operating pressure (P), wind speed (W), nozzle diameter (D) and vapour pressure deficit (es − ea). Field measurements data were applied to training and testing of ANN, ANFIS and GEP models. The results of these AI models were also compared with previous studies. Three statistical metrics, namely coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE), were utilized to assess the performance of the models. The results indicate that the AI models (i.e. ANFIS, ANN and GEP) predict the WDEL more accurately than in previous studies. Moreover, the results show that the GEP model (with RMSE = 1.19% and R2 = 0.97) provides a better estimation of WDEL compared to the ANN model (with RMSE = 2.56% and R2 = 0.87) and ANFIS model (with RMSE = 1.64% and R2 = 0.94). Copyright © 2017 John Wiley & Sons, Ltd.

show abstract

Estimation of Furrow Irrigation Sediment Loss Using an Artificial Neural Network

Cited by 10 publications

References 19 publications

Use of Self-Organizing Maps to Estimate Furrow Sediment Loss in Western U.S.

Use of Self-Organizing Maps to Estimate Furrow Sediment Loss in Western U.S.

Reduction of soil and phosphorus losses by using micro‐dams in furrow irrigation

Estimation of Wind Drift and Evaporation Losses from Sprinkler Irrigation systemS by Different Data‐Driven Methods

Contact Info

Product

Resources

About