Benchmarking farm-level cotton water productivity using on-farm irrigation measurements and remotely sensed yields
Benchmarking farm-level irrigation water productivity (WPI) and water productivity (WP) can assist in understanding the irrigation effectiveness of individual farms and in developing strategies to improve their irrigation management. This study introduces a method to integrate on-farm irrigation mea...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-04-01
|
| Series: | Agricultural Water Management |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0378377425000988 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850251543815651328 |
|---|---|
| author | Zitian Gao Danlu Guo Dongryeol Ryu Andrew W. Western |
| author_facet | Zitian Gao Danlu Guo Dongryeol Ryu Andrew W. Western |
| author_sort | Zitian Gao |
| collection | DOAJ |
| description | Benchmarking farm-level irrigation water productivity (WPI) and water productivity (WP) can assist in understanding the irrigation effectiveness of individual farms and in developing strategies to improve their irrigation management. This study introduces a method to integrate on-farm irrigation measurements, remotely sensed yields and publicly available rainfall data for multi-year farm-level WPI and WP benchmarking. The method was tested over cotton farms located in south-eastern Australia during the 2011–19 cropping seasons. We trained remote sensing (RS)-based machine learning (ML) models – Random Forest Regression (RFR), Gradient Boosting Regression (GBR) and Support Vector Regression (SVR) – to predict yields for over 400 cotton fields with ground-truth yield data. Predicted cotton yields from the best-performing model were then combined with irrigation and rainfall data for WPI and WP benchmarking. We also examined: 1) if the yield model is transferable to unseen years and 2) if sub-field-scale yield data from a harvester over a small number of fields are effective for training ML models, in case field-scale yield data are insufficient. The results showed that field-scale cotton yield could be predicted with the best accuracy using the GBR model (R2 = 0.7, RMSE = 235 kg/ha, mean absolute error = 176 kg/ha and Pearson correlation = 0.84) when applied to the period of training. The average WPI and WP varied between 0.18–0.36 kg/m3 and 0.16–0.23 kg/m3, respectively. However, the RS-based yield model showed reduced performance outside of the training period. In addition, when field-scale yield samples were used in combination with many sub-field-scale samples for calibration, the model performance was biased to favour the sub-field-scale samples. Our findings demonstrate the ability of RS and ML models to provide yields for benchmarking analysis but highlight the potential risk of reduced accuracy of yield prediction in future years. |
| format | Article |
| id | doaj-art-e8e5b5f6b63f41df84e6af428a6c1f82 |
| institution | OA Journals |
| issn | 1873-2283 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Agricultural Water Management |
| spelling | doaj-art-e8e5b5f6b63f41df84e6af428a6c1f822025-08-20T01:57:52ZengElsevierAgricultural Water Management1873-22832025-04-0131110938410.1016/j.agwat.2025.109384Benchmarking farm-level cotton water productivity using on-farm irrigation measurements and remotely sensed yieldsZitian Gao0Danlu Guo1Dongryeol Ryu2Andrew W. Western3Department of Infrastructure Engineering, The University of Melbourne, Parkville, VIC 3010, Australia; Environment, Commonwealth Scientific and Industrial Research Organisation, Clayton, VIC 3168, Australia; Corresponding author at: Department of Infrastructure Engineering, The University of Melbourne, Parkville, VIC 3010, Australia.Department of Infrastructure Engineering, The University of Melbourne, Parkville, VIC 3010, Australia; School of Engineering, College of Systems & Society, The Australian National University, Canberra, ACT, AustraliaDepartment of Infrastructure Engineering, The University of Melbourne, Parkville, VIC 3010, AustraliaDepartment of Infrastructure Engineering, The University of Melbourne, Parkville, VIC 3010, AustraliaBenchmarking farm-level irrigation water productivity (WPI) and water productivity (WP) can assist in understanding the irrigation effectiveness of individual farms and in developing strategies to improve their irrigation management. This study introduces a method to integrate on-farm irrigation measurements, remotely sensed yields and publicly available rainfall data for multi-year farm-level WPI and WP benchmarking. The method was tested over cotton farms located in south-eastern Australia during the 2011–19 cropping seasons. We trained remote sensing (RS)-based machine learning (ML) models – Random Forest Regression (RFR), Gradient Boosting Regression (GBR) and Support Vector Regression (SVR) – to predict yields for over 400 cotton fields with ground-truth yield data. Predicted cotton yields from the best-performing model were then combined with irrigation and rainfall data for WPI and WP benchmarking. We also examined: 1) if the yield model is transferable to unseen years and 2) if sub-field-scale yield data from a harvester over a small number of fields are effective for training ML models, in case field-scale yield data are insufficient. The results showed that field-scale cotton yield could be predicted with the best accuracy using the GBR model (R2 = 0.7, RMSE = 235 kg/ha, mean absolute error = 176 kg/ha and Pearson correlation = 0.84) when applied to the period of training. The average WPI and WP varied between 0.18–0.36 kg/m3 and 0.16–0.23 kg/m3, respectively. However, the RS-based yield model showed reduced performance outside of the training period. In addition, when field-scale yield samples were used in combination with many sub-field-scale samples for calibration, the model performance was biased to favour the sub-field-scale samples. Our findings demonstrate the ability of RS and ML models to provide yields for benchmarking analysis but highlight the potential risk of reduced accuracy of yield prediction in future years.http://www.sciencedirect.com/science/article/pii/S0378377425000988Irrigation benchmarkingIrrigation water productivityWater productivityYieldLandsatCotton |
| spellingShingle | Zitian Gao Danlu Guo Dongryeol Ryu Andrew W. Western Benchmarking farm-level cotton water productivity using on-farm irrigation measurements and remotely sensed yields Agricultural Water Management Irrigation benchmarking Irrigation water productivity Water productivity Yield Landsat Cotton |
| title | Benchmarking farm-level cotton water productivity using on-farm irrigation measurements and remotely sensed yields |
| title_full | Benchmarking farm-level cotton water productivity using on-farm irrigation measurements and remotely sensed yields |
| title_fullStr | Benchmarking farm-level cotton water productivity using on-farm irrigation measurements and remotely sensed yields |
| title_full_unstemmed | Benchmarking farm-level cotton water productivity using on-farm irrigation measurements and remotely sensed yields |
| title_short | Benchmarking farm-level cotton water productivity using on-farm irrigation measurements and remotely sensed yields |
| title_sort | benchmarking farm level cotton water productivity using on farm irrigation measurements and remotely sensed yields |
| topic | Irrigation benchmarking Irrigation water productivity Water productivity Yield Landsat Cotton |
| url | http://www.sciencedirect.com/science/article/pii/S0378377425000988 |
| work_keys_str_mv | AT zitiangao benchmarkingfarmlevelcottonwaterproductivityusingonfarmirrigationmeasurementsandremotelysensedyields AT danluguo benchmarkingfarmlevelcottonwaterproductivityusingonfarmirrigationmeasurementsandremotelysensedyields AT dongryeolryu benchmarkingfarmlevelcottonwaterproductivityusingonfarmirrigationmeasurementsandremotelysensedyields AT andrewwwestern benchmarkingfarmlevelcottonwaterproductivityusingonfarmirrigationmeasurementsandremotelysensedyields |