Evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in Nepal
Accurate estimation of reference evapotranspiration (ET0) is essential for optimizing water resource management. The widely accepted Penman-Monteith (FAO-56PM) model is commonly used for ET0 estimation but relies on numerous weather variables that are often unavailable in developing countries like N...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025003391 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861211527118848 |
|---|---|
| author | Erica Shrestha Suyog Poudyal Anup Ghimire Shrena Maharjan Manoj Lamichhane Sushant Mehan |
| author_facet | Erica Shrestha Suyog Poudyal Anup Ghimire Shrena Maharjan Manoj Lamichhane Sushant Mehan |
| author_sort | Erica Shrestha |
| collection | DOAJ |
| description | Accurate estimation of reference evapotranspiration (ET0) is essential for optimizing water resource management. The widely accepted Penman-Monteith (FAO-56PM) model is commonly used for ET0 estimation but relies on numerous weather variables that are often unavailable in developing countries like Nepal. The suitability of both empirical and machine learning (ML) models with limited climatic variables for estimating ET0 in Nepal remains unexplored. We used 19 meteorological stations across Nepal that measured climatic variables, including maximum and minimum temperatures, wind speed, relative humidity, and sunshine hours. We assessed the performance of six widely used empirical models (Hargreaves Samani, modified Hargreaves Samani, Romanenko, Schendel, Priestley-Taylor, and Makkink) and four ML models (random forest, extreme gradient boosting, deep neural network, and long short-term memory) to estimate ET0 with limited climatic variables in Nepal. Two strategies were applied: (1) the proposed ML models were tested at each weather station using leave-one-out cross-validation (LOOCV), (2) meteorological stations were grouped into three clusters using the K-means clustering and model performance were evaluated on each cluster. Results indicate that radiation-based models outperformed humidity and temperature-based models, with R² increasing from 23 to 38 % and RMSE decreasing by 27 to 41 % across empirical and ML models. Notably, all ML models outperformed empirical models, with clustering of weather stations further reducing prediction error in ET0 estimation by 10 to 18 %. These findings demonstrate the potential of ML models for accurate ET0 estimation with limited data, supporting agricultural water management and enhancing resilience in water-stressed areas. |
| format | Article |
| id | doaj-art-c8118c9f6d934ef3badd8d0ee22596a0 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-c8118c9f6d934ef3badd8d0ee22596a02025-02-10T04:34:47ZengElsevierResults in Engineering2590-12302025-03-0125104254Evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in NepalErica Shrestha0Suyog Poudyal1Anup Ghimire2Shrena Maharjan3Manoj Lamichhane4Sushant Mehan5Department of Civil Engineering, Advanced College of Engineering and Management, Kathmandu 44600, Nepal; Corresponding author.Department of Civil Engineering, Advanced College of Engineering and Management, Kathmandu 44600, NepalDepartment of Civil Engineering, Advanced College of Engineering and Management, Kathmandu 44600, NepalDepartment of Civil Engineering, Advanced College of Engineering and Management, Kathmandu 44600, NepalDepartment of Agricultural and Biosystems Engineering, South Dakota State University, Brookings, SD 57007, USADepartment of Agricultural and Biosystems Engineering, South Dakota State University, Brookings, SD 57007, USAAccurate estimation of reference evapotranspiration (ET0) is essential for optimizing water resource management. The widely accepted Penman-Monteith (FAO-56PM) model is commonly used for ET0 estimation but relies on numerous weather variables that are often unavailable in developing countries like Nepal. The suitability of both empirical and machine learning (ML) models with limited climatic variables for estimating ET0 in Nepal remains unexplored. We used 19 meteorological stations across Nepal that measured climatic variables, including maximum and minimum temperatures, wind speed, relative humidity, and sunshine hours. We assessed the performance of six widely used empirical models (Hargreaves Samani, modified Hargreaves Samani, Romanenko, Schendel, Priestley-Taylor, and Makkink) and four ML models (random forest, extreme gradient boosting, deep neural network, and long short-term memory) to estimate ET0 with limited climatic variables in Nepal. Two strategies were applied: (1) the proposed ML models were tested at each weather station using leave-one-out cross-validation (LOOCV), (2) meteorological stations were grouped into three clusters using the K-means clustering and model performance were evaluated on each cluster. Results indicate that radiation-based models outperformed humidity and temperature-based models, with R² increasing from 23 to 38 % and RMSE decreasing by 27 to 41 % across empirical and ML models. Notably, all ML models outperformed empirical models, with clustering of weather stations further reducing prediction error in ET0 estimation by 10 to 18 %. These findings demonstrate the potential of ML models for accurate ET0 estimation with limited data, supporting agricultural water management and enhancing resilience in water-stressed areas.http://www.sciencedirect.com/science/article/pii/S2590123025003391Radiation-basedK-means clusteringDeep neural networksWater resource managementSoutheast Asia |
| spellingShingle | Erica Shrestha Suyog Poudyal Anup Ghimire Shrena Maharjan Manoj Lamichhane Sushant Mehan Evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in Nepal Results in Engineering Radiation-based K-means clustering Deep neural networks Water resource management Southeast Asia |
| title | Evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in Nepal |
| title_full | Evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in Nepal |
| title_fullStr | Evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in Nepal |
| title_full_unstemmed | Evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in Nepal |
| title_short | Evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in Nepal |
| title_sort | evaluating empirical and machine learning approaches for reference evapotranspiration estimation using limited climatic variables in nepal |
| topic | Radiation-based K-means clustering Deep neural networks Water resource management Southeast Asia |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025003391 |
| work_keys_str_mv | AT ericashrestha evaluatingempiricalandmachinelearningapproachesforreferenceevapotranspirationestimationusinglimitedclimaticvariablesinnepal AT suyogpoudyal evaluatingempiricalandmachinelearningapproachesforreferenceevapotranspirationestimationusinglimitedclimaticvariablesinnepal AT anupghimire evaluatingempiricalandmachinelearningapproachesforreferenceevapotranspirationestimationusinglimitedclimaticvariablesinnepal AT shrenamaharjan evaluatingempiricalandmachinelearningapproachesforreferenceevapotranspirationestimationusinglimitedclimaticvariablesinnepal AT manojlamichhane evaluatingempiricalandmachinelearningapproachesforreferenceevapotranspirationestimationusinglimitedclimaticvariablesinnepal AT sushantmehan evaluatingempiricalandmachinelearningapproachesforreferenceevapotranspirationestimationusinglimitedclimaticvariablesinnepal |