Estimating Canopy Resistance Using Machine Learning and Analytical Approaches
Canopy resistance is a key parameter in the Penman–Monteith (P–M) equation for calculating evapotranspiration (ET). In this study, we compared a machine learning algorithm–support vector machine (SVM) and an analytical solution (Todorovic, 1999) for estimating canopy resistances. Then, these estimat...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/21/3839 |
| _version_ | 1797631196900884480 |
|---|---|
| author | Cheng-I Hsieh I-Hang Huang Chun-Te Lu |
| author_facet | Cheng-I Hsieh I-Hang Huang Chun-Te Lu |
| author_sort | Cheng-I Hsieh |
| collection | DOAJ |
| description | Canopy resistance is a key parameter in the Penman–Monteith (P–M) equation for calculating evapotranspiration (ET). In this study, we compared a machine learning algorithm–support vector machine (SVM) and an analytical solution (Todorovic, 1999) for estimating canopy resistances. Then, these estimated canopy resistances were applied to the P–M equation for estimating ET; as a benchmark, a constant (fixed) canopy resistance was also adopted for ET estimations. ET data were measured using the eddy-covariance method above three sites: a grassland (south Ireland), Cypress forest (north Taiwan), and Cryptomeria forest (central Taiwan) were used to test the accuracy of the above two methods. The observed canopy resistance was derived from rearranging the P–M equation. From the measurements, the average canopy resistances for the grassland, Cypress forest, and Cryptomeria forest were 163, 346, and 321 (s/m), respectively. Our results show that both methods tend to reproduce canopy resistances within a certain range of intervals. In general, the SVM model performs better, and the analytical solution systematically underestimates the canopy resistances and leads to an overestimation of evapotranspiration. It is found that the analytical solution is only suitable for low canopy resistance (less than 100 s/m) conditions. |
| first_indexed | 2024-03-11T11:18:32Z |
| format | Article |
| id | doaj.art-784a3e24c1364ce89e21b1c9e172a3ca |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-11T11:18:32Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-784a3e24c1364ce89e21b1c9e172a3ca2023-11-10T15:15:30ZengMDPI AGWater2073-44412023-11-011521383910.3390/w15213839Estimating Canopy Resistance Using Machine Learning and Analytical ApproachesCheng-I Hsieh0I-Hang Huang1Chun-Te Lu2Department of Bioenvironmental Systems Engineering, National Taiwan University, Taipei 10673, TaiwanDepartment of Bioenvironmental Systems Engineering, National Taiwan University, Taipei 10673, TaiwanDepartment of Bioenvironmental Systems Engineering, National Taiwan University, Taipei 10673, TaiwanCanopy resistance is a key parameter in the Penman–Monteith (P–M) equation for calculating evapotranspiration (ET). In this study, we compared a machine learning algorithm–support vector machine (SVM) and an analytical solution (Todorovic, 1999) for estimating canopy resistances. Then, these estimated canopy resistances were applied to the P–M equation for estimating ET; as a benchmark, a constant (fixed) canopy resistance was also adopted for ET estimations. ET data were measured using the eddy-covariance method above three sites: a grassland (south Ireland), Cypress forest (north Taiwan), and Cryptomeria forest (central Taiwan) were used to test the accuracy of the above two methods. The observed canopy resistance was derived from rearranging the P–M equation. From the measurements, the average canopy resistances for the grassland, Cypress forest, and Cryptomeria forest were 163, 346, and 321 (s/m), respectively. Our results show that both methods tend to reproduce canopy resistances within a certain range of intervals. In general, the SVM model performs better, and the analytical solution systematically underestimates the canopy resistances and leads to an overestimation of evapotranspiration. It is found that the analytical solution is only suitable for low canopy resistance (less than 100 s/m) conditions.https://www.mdpi.com/2073-4441/15/21/3839evapotranspirationcanopy resistancesupport vector machineTodorovic’s methodPenman–Monteith equation |
| spellingShingle | Cheng-I Hsieh I-Hang Huang Chun-Te Lu Estimating Canopy Resistance Using Machine Learning and Analytical Approaches Water evapotranspiration canopy resistance support vector machine Todorovic’s method Penman–Monteith equation |
| title | Estimating Canopy Resistance Using Machine Learning and Analytical Approaches |
| title_full | Estimating Canopy Resistance Using Machine Learning and Analytical Approaches |
| title_fullStr | Estimating Canopy Resistance Using Machine Learning and Analytical Approaches |
| title_full_unstemmed | Estimating Canopy Resistance Using Machine Learning and Analytical Approaches |
| title_short | Estimating Canopy Resistance Using Machine Learning and Analytical Approaches |
| title_sort | estimating canopy resistance using machine learning and analytical approaches |
| topic | evapotranspiration canopy resistance support vector machine Todorovic’s method Penman–Monteith equation |
| url | https://www.mdpi.com/2073-4441/15/21/3839 |
| work_keys_str_mv | AT chengihsieh estimatingcanopyresistanceusingmachinelearningandanalyticalapproaches AT ihanghuang estimatingcanopyresistanceusingmachinelearningandanalyticalapproaches AT chuntelu estimatingcanopyresistanceusingmachinelearningandanalyticalapproaches |