scholarly journals A Mixed Data-Based Deep Neural Network to Estimate Leaf Area Index in Wheat Breeding Trials

Agronomy ◽  
2020 ◽  
Vol 10 (2) ◽  
pp. 175 ◽  
Author(s):  
Orly Enrique Apolo-Apolo ◽  
Manuel Pérez-Ruiz ◽  
Jorge Martínez-Guanter ◽  
Gregorio Egea
Keyword(s):  
Leaf Area Index ◽  
Leaf Area ◽  
High Throughput ◽  
Model Performance ◽  
Wheat Breeding ◽  
Plant Phenotyping ◽  
Indirect Methods ◽  
Area Index ◽  
Model Based ◽  
Recent Emergence

Remote and non-destructive estimation of leaf area index (LAI) has been a challenge in the last few decades as the direct and indirect methods available are laborious and time-consuming. The recent emergence of high-throughput plant phenotyping platforms has increased the need to develop new phenotyping tools for better decision-making by breeders. In this paper, a novel model based on artificial intelligence algorithms and nadir-view red green blue (RGB) images taken from a terrestrial high throughput phenotyping platform is presented. The model mixes numerical data collected in a wheat breeding field and visual features extracted from the images to make rapid and accurate LAI estimations. Model-based LAI estimations were validated against LAI measurements determined non-destructively using an allometric relationship obtained in this study. The model performance was also compared with LAI estimates obtained by other classical indirect methods based on bottom-up hemispherical images and gaps fraction theory. Model-based LAI estimations were highly correlated with ground-truth LAI. The model performance was slightly better than that of the hemispherical image-based method, which tended to underestimate LAI. These results show the great potential of the developed model for near real-time LAI estimation, which can be further improved in the future by increasing the dataset used to train the model.

An assessment study of three indirect methods for estimating leaf area density and leaf area index of individual trees

2020 ◽  
Vol 292-293 ◽  
pp. 108101 ◽  
Author(s):  
Shanshan Wei ◽  
Tiangang Yin ◽  
Maria Angela Dissegna ◽  
Andrew J. Whittle ◽  
Genevieve Lai Fern Ow ◽  
...  
Keyword(s):  
Leaf Area Index ◽  
Leaf Area ◽  
Indirect Methods ◽  
Area Index ◽  
Area Density ◽  
Leaf Area Density ◽  
Assessment Study ◽  
Individual Trees

scholarly journals Effect of year-to-year variability of leaf area index on variable infiltration capacity model performance and simulation of streamflow during drought

2014 ◽  
Vol 11 (9) ◽  
pp. 10515-10552 ◽  
Author(s):  
Z. K. Tesemma ◽  
Y. Wei ◽  
M. C. Peel ◽  
A. W. Western
Keyword(s):  
Leaf Area Index ◽  
Leaf Area ◽  
Model Performance ◽  
Hydrologic Model ◽  
Variable Infiltration Capacity ◽  
Infiltration Capacity ◽  
Area Index ◽  
Vic Model ◽  
Monthly Streamflow

Abstract. This study assessed the effect of using observed monthly leaf area index (LAI) on hydrologic model performance and the simulation of streamflow during drought using the variable infiltration capacity (VIC) hydrological model in the Goulburn–Broken catchment of Australia, which has heterogeneous vegetation, soil and climate zones. VIC was calibrated with both observed monthly LAI and long-term mean monthly LAI, which were derived from the Global Land Surface Satellite (GLASS) observed monthly LAI dataset covering the period from 1982 to 2012. The model performance under wet and dry climates for the two different LAI inputs was assessed using three criteria, the classical Nash–Sutcliffe efficiency, the logarithm transformed flow Nash–Sutcliffe efficiency and the percentage bias. Finally, the percentage deviation of the simulated monthly streamflow using the observed monthly LAI from simulated streamflow using long-term mean monthly LAI was computed. The VIC model predicted monthly streamflow in the selected sub-catchments with model efficiencies ranging from 61.5 to 95.9% during calibration (1982–1997) and 59 to 92.4% during validation (1998–2012). Our results suggest systematic improvements from 4 to 25% in the Nash–Sutcliffe efficiency in pasture dominated catchments when the VIC model was calibrated with the observed monthly LAI instead of the long-term mean monthly LAI. There was limited systematic improvement in tree dominated catchments. The results also suggest that the model overestimation or underestimation of streamflow during wet and dry periods can be reduced to some extent by including the year-to-year variability of LAI in the model, thus reflecting the responses of vegetation to fluctuations in climate and other factors. Hence, the year-to-year variability in LAI should not be neglected; rather it should be included in model calibration as well as simulation of monthly water balance.

Comparative Analysis of Two Indirect Methods of Measuring Leaf Area Index as Applied to Minimal and Spur Pruned Grape Vines

1994 ◽  
Vol 21 (2) ◽  
pp. 197 ◽  
Author(s):  
KJ Sommer ◽  
ARG Lang
Keyword(s):  
Comparative Analysis ◽  
Leaf Area Index ◽  
Leaf Area ◽  
Light Transmission ◽  
Accurate Estimate ◽  
Indirect Methods ◽  
Area Index ◽  
Leaf Sampling ◽  
Transmission Measurements

Leaf area index of spur and minimal pruned vines was measured directly by destructive leaf sampling and indirectly from light transmission measurements using the LAI-2000 and the DEMON instruments. Both instruments provided good estimates of plant and leaf area index. The LAI-2000 had a tendency to underestimate leaf area index. The DEMON instrument provided the most accurate estimate of plant and leaf area index. With both instruments it is important to validate indirect with direct estimates of vine leaf area.

Sign in / Sign up

Export Citation Format

Share Document