IWRAM: A hybrid model for irrigation water demand forecasting to quantify the impacts of climate change
The phenomenon of climate change exerts a substantial influence on the water consumption patterns of agricultural crops, thereby affecting the overall demand for irrigation water and regional water security. The quantitative assessment of future changes in irrigation water requirements has great imp...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | Agricultural Water Management |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0378377423005085 |
| _version_ | 1797365610241327104 |
|---|---|
| author | Chiheng Dang Hongbo Zhang Congcong Yao Dengrui Mu Fengguang Lyu Yu Zhang Shuqi Zhang |
| author_facet | Chiheng Dang Hongbo Zhang Congcong Yao Dengrui Mu Fengguang Lyu Yu Zhang Shuqi Zhang |
| author_sort | Chiheng Dang |
| collection | DOAJ |
| description | The phenomenon of climate change exerts a substantial influence on the water consumption patterns of agricultural crops, thereby affecting the overall demand for irrigation water and regional water security. The quantitative assessment of future changes in irrigation water requirements has great importance for long-term water resource planning and the water-energy-food-ecosystem nexus. This work employed a comprehensive approach (IWRAM) by integrating many models and techniques, including a global climate model (CanESM2), a statistical downscaling model (SDSM), a bias correction technique (QTM), a temperature-based crop phenology method (GDD), and deep learning technology (LSTM), in order to assess the potential impact of climate change on irrigation water demand. Therein, the QTM is utilized for the purpose of bias correction for the CanESM2-SDSMed daily precipitation data. Additionally, the LSTM is implemented to forecast ETo using the CanESM2-SDSMed daily temperature data. The findings from the case study conducted in the Jinghuiqu irrigation area (JIA) indicate that the application of bias correction techniques resulted in notable enhancements in the frequency distribution of predicted precipitation data. Consequently, this led to a more coherent relationship between historical observed data and anticipated future data, aligning them more closely with natural patterns. The deep learning technique exhibited a strong degree of concordance, suggesting its exceptional capacity for modeling daily reference evapotranspiration. By using the IWRAM model, relatively accurate predictions were made for future precipitation, temperature, crop evapotranspiration, and effective precipitation. Consequently, an estimation was made regarding the anticipated need for irrigation water in JIA. These results highlighted that JIA total irrigation water demand (or net irrigation water demand) will increase by 121 mm (net irrigation water: 189 mm) and 119 mm (net irrigation water: 187 mm) in the year 2050 under RCP 2.6 and 8.5 scenarios, respectively. Climate change could potentially affect the seasonal distribution of precipitation. Therefore, it is crucial for the authorities in JIA to not only take into account the overall irrigation water requirement but also give priority to the water requirements of each stage of crop growth. |
| first_indexed | 2024-03-08T16:52:19Z |
| format | Article |
| id | doaj.art-c60ef75fce7242898645001b674f4229 |
| institution | Directory Open Access Journal |
| issn | 1873-2283 |
| language | English |
| last_indexed | 2024-03-08T16:52:19Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Agricultural Water Management |
| spelling | doaj.art-c60ef75fce7242898645001b674f42292024-01-05T04:22:57ZengElsevierAgricultural Water Management1873-22832024-02-01291108643IWRAM: A hybrid model for irrigation water demand forecasting to quantify the impacts of climate changeChiheng Dang0Hongbo Zhang1Congcong Yao2Dengrui Mu3Fengguang Lyu4Yu Zhang5Shuqi Zhang6School of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, China; Key Laboratory of Eco-hydrology and Water Security in Arid and Semi-arid Regions of the Ministry of Water Resources, Chang’an University, Xi’an 710054, China; Key Laboratory of Subsurface Hydrology and Ecological Effect in Arid Region of Ministry of Education, Chang’an University, Xi’an 710054, China; Corresponding author at: School of Water and Environment, Chang’an University, Xi’an 710054, China.School of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, ChinaSchool of Water and Environment, Chang’an University, Xi’an 710054, ChinaThe phenomenon of climate change exerts a substantial influence on the water consumption patterns of agricultural crops, thereby affecting the overall demand for irrigation water and regional water security. The quantitative assessment of future changes in irrigation water requirements has great importance for long-term water resource planning and the water-energy-food-ecosystem nexus. This work employed a comprehensive approach (IWRAM) by integrating many models and techniques, including a global climate model (CanESM2), a statistical downscaling model (SDSM), a bias correction technique (QTM), a temperature-based crop phenology method (GDD), and deep learning technology (LSTM), in order to assess the potential impact of climate change on irrigation water demand. Therein, the QTM is utilized for the purpose of bias correction for the CanESM2-SDSMed daily precipitation data. Additionally, the LSTM is implemented to forecast ETo using the CanESM2-SDSMed daily temperature data. The findings from the case study conducted in the Jinghuiqu irrigation area (JIA) indicate that the application of bias correction techniques resulted in notable enhancements in the frequency distribution of predicted precipitation data. Consequently, this led to a more coherent relationship between historical observed data and anticipated future data, aligning them more closely with natural patterns. The deep learning technique exhibited a strong degree of concordance, suggesting its exceptional capacity for modeling daily reference evapotranspiration. By using the IWRAM model, relatively accurate predictions were made for future precipitation, temperature, crop evapotranspiration, and effective precipitation. Consequently, an estimation was made regarding the anticipated need for irrigation water in JIA. These results highlighted that JIA total irrigation water demand (or net irrigation water demand) will increase by 121 mm (net irrigation water: 189 mm) and 119 mm (net irrigation water: 187 mm) in the year 2050 under RCP 2.6 and 8.5 scenarios, respectively. Climate change could potentially affect the seasonal distribution of precipitation. Therefore, it is crucial for the authorities in JIA to not only take into account the overall irrigation water requirement but also give priority to the water requirements of each stage of crop growth.http://www.sciencedirect.com/science/article/pii/S0378377423005085Irrigation water requirementBias correctionEToLSTMQTM |
| spellingShingle | Chiheng Dang Hongbo Zhang Congcong Yao Dengrui Mu Fengguang Lyu Yu Zhang Shuqi Zhang IWRAM: A hybrid model for irrigation water demand forecasting to quantify the impacts of climate change Agricultural Water Management Irrigation water requirement Bias correction ETo LSTM QTM |
| title | IWRAM: A hybrid model for irrigation water demand forecasting to quantify the impacts of climate change |
| title_full | IWRAM: A hybrid model for irrigation water demand forecasting to quantify the impacts of climate change |
| title_fullStr | IWRAM: A hybrid model for irrigation water demand forecasting to quantify the impacts of climate change |
| title_full_unstemmed | IWRAM: A hybrid model for irrigation water demand forecasting to quantify the impacts of climate change |
| title_short | IWRAM: A hybrid model for irrigation water demand forecasting to quantify the impacts of climate change |
| title_sort | iwram a hybrid model for irrigation water demand forecasting to quantify the impacts of climate change |
| topic | Irrigation water requirement Bias correction ETo LSTM QTM |
| url | http://www.sciencedirect.com/science/article/pii/S0378377423005085 |
| work_keys_str_mv | AT chihengdang iwramahybridmodelforirrigationwaterdemandforecastingtoquantifytheimpactsofclimatechange AT hongbozhang iwramahybridmodelforirrigationwaterdemandforecastingtoquantifytheimpactsofclimatechange AT congcongyao iwramahybridmodelforirrigationwaterdemandforecastingtoquantifytheimpactsofclimatechange AT dengruimu iwramahybridmodelforirrigationwaterdemandforecastingtoquantifytheimpactsofclimatechange AT fengguanglyu iwramahybridmodelforirrigationwaterdemandforecastingtoquantifytheimpactsofclimatechange AT yuzhang iwramahybridmodelforirrigationwaterdemandforecastingtoquantifytheimpactsofclimatechange AT shuqizhang iwramahybridmodelforirrigationwaterdemandforecastingtoquantifytheimpactsofclimatechange |