Data driven model to estimate furrow irrigation sediment loss in western U.S.

Authors: King, Bradley; Bjorneberg, David; PRESTWICH, CLARENCE - Natural Resources Conservation Service (NRCS, USDA)

Submitted to: American Society of Agricultural and Biological Engineers
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/3/2025
Publication Date: 10/10/2025
Citation: King, B.A., Bjorneberg, D.L., Prestwich, C. 2025. Data driven model to estimate furrow irrigation sediment loss in western U.S.. American Society of Agricultural and Biological Engineers. https://doi.org/10.13031/ja.16183.
DOI: https://doi.org/10.13031/ja.16183

Interpretive Summary: The area irrigated by furrow irrigation in the U.S. has been steadily decreasing but still represents about 20% of the total irrigated area. 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 Historical published and unpublished data sets containing measurements of furrow irrigation sediment loss in the western U.S. were assembled into a furrow sediment loss data set comprising over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 using KSOM was under predicted by 57% on average with a linear regression coefficient of determination of 0.51. 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 and linear regression to adjust KSOM cluster mean sediment loss for differences in flow rate and furrow length between input values and cluster mean values. Adopting the transfer learning approach resulting in predicted furrow sediment loss 17% less than measured sediment loss on average with a coefficient of determination of 0.83. When the data set was randomly split into model development (90%) and validation (10%) data sets the prediction results were similar. The furrow sediment loss prediction model was implemented in a spreadsheet for easy prediction of furrow sediment loss without the need for special software.

Technical Abstract: The area irrigated by furrow irrigation in the U.S. has been steadily decreasing but still represents about 20% of the total irrigated area. 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 57% on average with a linear regression coefficient of determination of 0.51. 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 furrow length and cluster mean furrow flow rate and mean furrow length to obtain a prediction of furrow sediment loss. Predicted furrow sediment loss was 17% less than measured sediment loss on average with a coefficient of determination of 0.83. When the data set was randomly split into model development (90%) and validation (10%) data sets the prediction results were similar. The furrow sediment loss prediction model was implemented in a spreadsheet for easy prediction of furrow sediment loss without the need for special software.