Predicting Tree Sap Flux and Stomatal Conductance from Drone-Recorded Surface Temperatures in a Mixed Agroforestry System—A Machine Learning Approach

Florian Ellsäßer,Bernhard Schuldt,Pierre-André Waite,Joyson Ahongshangbam,Alexander Röll,Hendrayanto Hendrayanto,Dirk Hölscher

doi:10.3390/rs12244070

Florian Ellsäßer, Bernhard Schuldt + Show 5 more

Open Access

https://doi.org/10.3390/rs12244070

Copy DOI

Abstract

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 (r2 = 0.87 for trees and r2 = 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.

Highlights

Transpiration is the largest water flux from terrestrial surfaces, accounting for 80%–90% of terrestrial evapotranspiration [1]
Emerging approaches based on surface temperatures and a wide range of machine learning techniques offer new possibilities to quantify transpiration
Daytime maxima for sap flux ranged from 0.831 mm·h−1 (Parkia speciosa) to 2.544 mm·h−1 (Archidendron pauciflorum) daytime maxima for stomatal conductance ranged from 2153.7 mol·m−2·h−1(Shorea leprosula) to 11813.4 mol·m−2·h−1(Peronema canescens)

Summary

Introduction

Transpiration is the largest water flux from terrestrial surfaces, accounting for 80%–90% of terrestrial evapotranspiration [1]. Model and understand the effects of altered transpiration on the hydrological cycle, measurements at the plant and leaf scale with sap flux probes and porometers are frequently applied [3,6,7]. Since leaf surface temperatures are highly variable during the course of the day, depending e.g., on solar irradiance [20] diurnal temperature patterns can be captured and evapotranspiration patterns can be calculated To some extent, this might be possible using other non-temperature-based approaches such as the normalized difference vegetation index (NDVI) that can capture the photosynthetic activity during the day [21]. Prerequisites for successful quantification include choice of an appropriate algorithm, a set of representative prediction variables and a sufficiently large data set [37]

Objectives

Methods

Results

Discussion

Conclusion