Predicting Tree Sap Flux and Stomatal Conductance from Drone-Recorded Surface Temperatures in a Mixed Agroforestry System—A Machine Learning Approach
Plant transpiration is a key element in the hydrological cycle. Widely used methods for its assessment comprise sap flux techniques for whole-plant transpiration and porometry for leaf stomatal conductance. Recently emerging approaches based on surface temperatures and a wide range of machine learni...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/24/4070 |
| _version_ | 1827700221638868992 |
|---|---|
| author | Florian Ellsäßer Alexander Röll Joyson Ahongshangbam Pierre-André Waite Hendrayanto Bernhard Schuldt Dirk Hölscher |
| author_facet | Florian Ellsäßer Alexander Röll Joyson Ahongshangbam Pierre-André Waite Hendrayanto Bernhard Schuldt Dirk Hölscher |
| author_sort | Florian Ellsäßer |
| collection | DOAJ |
| description | Plant transpiration is a key element in the hydrological cycle. Widely used methods for its assessment comprise sap flux techniques for whole-plant transpiration and porometry for leaf stomatal conductance. Recently emerging approaches based on surface temperatures and a wide range of machine learning techniques offer new possibilities to quantify transpiration. The focus of this study was to predict sap flux and leaf stomatal conductance based on drone-recorded and meteorological data and compare these predictions with in-situ measured transpiration. To build the prediction models, we applied classical statistical approaches and machine learning algorithms. The field work was conducted in an oil palm agroforest in lowland Sumatra. Random forest predictions yielded the highest congruence with measured sap flux (r<sup>2</sup> = 0.87 for trees and r<sup>2</sup> = 0.58 for palms) and confidence intervals for intercept and slope of a Passing-Bablok regression suggest interchangeability of the methods. Differences in model performance are indicated when predicting different tree species. Predictions for stomatal conductance were less congruent for all prediction methods, likely due to spatial and temporal offsets of the measurements. Overall, the applied drone and modelling scheme predicts whole-plant transpiration with high accuracy. We conclude that there is large potential in machine learning approaches for ecological applications such as predicting transpiration. |
| first_indexed | 2024-03-10T14:08:15Z |
| format | Article |
| id | doaj.art-db931c705f4049fa836d75228c9b7812 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T14:08:15Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-db931c705f4049fa836d75228c9b78122023-11-21T00:31:08ZengMDPI AGRemote Sensing2072-42922020-12-011224407010.3390/rs12244070Predicting Tree Sap Flux and Stomatal Conductance from Drone-Recorded Surface Temperatures in a Mixed Agroforestry System—A Machine Learning ApproachFlorian Ellsäßer0Alexander Röll1Joyson Ahongshangbam2Pierre-André Waite3Hendrayanto4Bernhard Schuldt5Dirk Hölscher6Tropical Silviculture and Forest Ecology, University of Goettingen, Büsgenweg 1, 37077 Göttingen, GermanyTropical Silviculture and Forest Ecology, University of Goettingen, Büsgenweg 1, 37077 Göttingen, GermanyTropical Silviculture and Forest Ecology, University of Goettingen, Büsgenweg 1, 37077 Göttingen, GermanyPlant Ecology and Ecosystems Research, University of Goettingen, Untere Karspüle 2, 37073 Göttingen, GermanyForest Management, Kampus IPB Darmaga, Bogor Agricultural University, Bogor 16680, IndonesiaJulius-von-Sachs-Institute for Biological Sciences, Chair of Ecophysiology and Vegetation Ecology, University of Wuerzburg, Julius-von-Sachs-Platz 3, 97082 Wuerzburg, GermanyTropical Silviculture and Forest Ecology, University of Goettingen, Büsgenweg 1, 37077 Göttingen, GermanyPlant transpiration is a key element in the hydrological cycle. Widely used methods for its assessment comprise sap flux techniques for whole-plant transpiration and porometry for leaf stomatal conductance. Recently emerging approaches based on surface temperatures and a wide range of machine learning techniques offer new possibilities to quantify transpiration. The focus of this study was to predict sap flux and leaf stomatal conductance based on drone-recorded and meteorological data and compare these predictions with in-situ measured transpiration. To build the prediction models, we applied classical statistical approaches and machine learning algorithms. The field work was conducted in an oil palm agroforest in lowland Sumatra. Random forest predictions yielded the highest congruence with measured sap flux (r<sup>2</sup> = 0.87 for trees and r<sup>2</sup> = 0.58 for palms) and confidence intervals for intercept and slope of a Passing-Bablok regression suggest interchangeability of the methods. Differences in model performance are indicated when predicting different tree species. Predictions for stomatal conductance were less congruent for all prediction methods, likely due to spatial and temporal offsets of the measurements. Overall, the applied drone and modelling scheme predicts whole-plant transpiration with high accuracy. We conclude that there is large potential in machine learning approaches for ecological applications such as predicting transpiration.https://www.mdpi.com/2072-4292/12/24/4070transpirationmethod comparisonUAVoil palmmultiple linear regressionsupport vector machine |
| spellingShingle | Florian Ellsäßer Alexander Röll Joyson Ahongshangbam Pierre-André Waite Hendrayanto Bernhard Schuldt Dirk Hölscher Predicting Tree Sap Flux and Stomatal Conductance from Drone-Recorded Surface Temperatures in a Mixed Agroforestry System—A Machine Learning Approach Remote Sensing transpiration method comparison UAV oil palm multiple linear regression support vector machine |
| title | Predicting Tree Sap Flux and Stomatal Conductance from Drone-Recorded Surface Temperatures in a Mixed Agroforestry System—A Machine Learning Approach |
| title_full | Predicting Tree Sap Flux and Stomatal Conductance from Drone-Recorded Surface Temperatures in a Mixed Agroforestry System—A Machine Learning Approach |
| title_fullStr | Predicting Tree Sap Flux and Stomatal Conductance from Drone-Recorded Surface Temperatures in a Mixed Agroforestry System—A Machine Learning Approach |
| title_full_unstemmed | Predicting Tree Sap Flux and Stomatal Conductance from Drone-Recorded Surface Temperatures in a Mixed Agroforestry System—A Machine Learning Approach |
| title_short | Predicting Tree Sap Flux and Stomatal Conductance from Drone-Recorded Surface Temperatures in a Mixed Agroforestry System—A Machine Learning Approach |
| title_sort | predicting tree sap flux and stomatal conductance from drone recorded surface temperatures in a mixed agroforestry system a machine learning approach |
| topic | transpiration method comparison UAV oil palm multiple linear regression support vector machine |
| url | https://www.mdpi.com/2072-4292/12/24/4070 |
| work_keys_str_mv | AT florianellsaßer predictingtreesapfluxandstomatalconductancefromdronerecordedsurfacetemperaturesinamixedagroforestrysystemamachinelearningapproach AT alexanderroll predictingtreesapfluxandstomatalconductancefromdronerecordedsurfacetemperaturesinamixedagroforestrysystemamachinelearningapproach AT joysonahongshangbam predictingtreesapfluxandstomatalconductancefromdronerecordedsurfacetemperaturesinamixedagroforestrysystemamachinelearningapproach AT pierreandrewaite predictingtreesapfluxandstomatalconductancefromdronerecordedsurfacetemperaturesinamixedagroforestrysystemamachinelearningapproach AT hendrayanto predictingtreesapfluxandstomatalconductancefromdronerecordedsurfacetemperaturesinamixedagroforestrysystemamachinelearningapproach AT bernhardschuldt predictingtreesapfluxandstomatalconductancefromdronerecordedsurfacetemperaturesinamixedagroforestrysystemamachinelearningapproach AT dirkholscher predictingtreesapfluxandstomatalconductancefromdronerecordedsurfacetemperaturesinamixedagroforestrysystemamachinelearningapproach |