Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- UAV (1)
- aboveground biomass (1)
- artificial neural network (1)
- climatological water deficit (1)
- farm forestry (1)
- farmland woodlots (1)
- method comparison (1)
- multiple linear regression (1)
- oil palm (1)
- rainfall gradient (1)
Institute
Farmland tree cultivation is considered an important option for enhancing wood production. In South India, the native leaf-deciduous tree species Melia dubia is popular for short-rotation plantations. Across a rainfall gradient from 420 to 2170 mm year\(^{–1}\), we studied 186 farmland woodlots between one and nine years in age. The objectives were to identify the main factors controlling aboveground biomass (AGB) and growth rates. A power-law growth model predicts an average stand-level AGB of 93.8 Mg ha\(^{–1}\) for nine-year-old woodlots. The resulting average annual AGB increment over the length of the rotation cycle is 10.4 Mg ha\(^{–1}\) year\(^{–1}\), which falls within the range reported for other tropical tree plantations. When expressing the parameters of the growth model as functions of management, climate and soil variables, it explains 65% of the variance in AGB. The results indicate that water availability is the main driver of the growth of M. dubia. Compared to the effects of water availability, the effects of soil nutrients are 26% to 60% smaller. We conclude that because of its high biomass accumulation rates in farm forestry, M. dubia is a promising candidate for short-rotation plantations in South India and beyond.
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\(^2\) = 0.87 for trees and r\(^2\) = 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.