scholarly journals A Comparative Estimation of Maize Leaf Water Content Using Machine Learning Techniques and Unmanned Aerial Vehicle (UAV)-Based Proximal and Remotely Sensed Data

2021 ◽  
Vol 13 (20) ◽  
pp. 4091
Author(s):  
Helen S. Ndlovu ◽  
John Odindi ◽  
Mbulisi Sibanda ◽  
Onisimo Mutanga ◽  
Alistair Clulow ◽  
...  
Keyword(s):  
Machine Learning ◽  
Water Content ◽  
Water Status ◽  
Leaf Water ◽  
Machine Learning Techniques ◽  
Spatially Explicit ◽  
Leaf Water Content ◽  
Smallholder Farms ◽  
Maize Leaf ◽  
Learning Techniques

Determining maize water content variability is necessary for crop monitoring and in developing early warning systems to optimise agricultural production in smallholder farms. However, spatially explicit information on maize water content, particularly in Southern Africa, remains elementary due to the shortage of efficient and affordable primary sources of suitable spatial data at a local scale. Unmanned Aerial Vehicles (UAVs), equipped with light-weight multispectral sensors, provide spatially explicit, near-real-time information for determining the maize crop water status at farm scale. Therefore, this study evaluated the utility of UAV-derived multispectral imagery and machine learning techniques in estimating maize leaf water indicators: equivalent water thickness (EWT), fuel moisture content (FMC), and specific leaf area (SLA). The results illustrated that both NIR and red-edge derived spectral variables were critical in characterising the maize water indicators on smallholder farms. Furthermore, the best models for estimating EWT, FMC, and SLA were derived from the random forest regression (RFR) algorithm with an rRMSE of 3.13%, 1%, and 3.48%, respectively. Additionally, EWT and FMC yielded the highest predictive performance and were the most optimal indicators of maize leaf water content. The findings are critical towards developing a robust and spatially explicit monitoring framework of maize water status and serve as a proxy of crop health and the overall productivity of smallholder maize farms.

scholarly journals Plant Water Status and Carbon Dioxide Exchange of Cotton Leaves

1969 ◽  
Vol 22 (2) ◽  
pp. 289 ◽  
Author(s):  
JH Troughton
Keyword(s):  
Water Content ◽  
Water Status ◽  
Light Level ◽  
Co2 Exchange ◽  
Leaf Water ◽  
Plant Water Status ◽  
Leaf Water Content ◽  
Carbon Dioxide Exchange ◽  
Plant Water ◽  
Free Atmosphere

The effect of plant water status on the diffusion of C02 in the gas and liquid phase in leaves of cotton plants was studied in a single leaf chamber under conditions of constant light level and temperature and when photosynthesis was limited by the CO2 supply. A controlled range of relative leaf water contents from 56 to 96% was obtained by varying root temperature from 6 to 30�C while the tops of the plants were -at a constant temperature. Decreasing water content resulted in an increase in the calculated leaf diffusive resistance and a decrease in CO2 exchange. Under the environmental conditions used, plant water status primarily affects C02 exchange by regulating stomatal aperture. The mesophyll resistance, which was estimated in air and in an oxygen-free atmosphere, did not vary with the relative leaf water content down to 75% but increased progressively as relative water content dropped from 75 to 56%.

scholarly journals An indirect approach to predict deadwood biomass in forests of Ukrainian Polissya using Landsat images and terrestrial data

2020 ◽  
Vol 73 (1) ◽  
pp. 107-124
Author(s):  
Maksym Matsala ◽  
Viktor Myroniuk ◽  
Andrii Bilous ◽  
Andrii Terentiev ◽  
Petro Diachuk ◽  
...  
Keyword(s):  
Machine Learning ◽  
Land Cover ◽  
Tree Species ◽  
Forest Biomass ◽  
Machine Learning Techniques ◽  
Spatially Explicit ◽  
Species Classification ◽  
Tree Species Classification ◽  
Learning Techniques ◽  
The Mean

Abstract Spatially explicit and consistent mapping of forest biomass is one of the key tasks towards full and appropriate accounting of carbon budgets and productivity potentials at different scales. Landsat imagery coupled with terrestrial-based data and processed using modern machine learning techniques is a suitable data source for mapping of forest components such as deadwood. Using relationships between deadwood biomass and growing stock volume, here we indirectly map this ecosystem compartment within the study area in northern Ukraine. Several machine learning techniques were applied: Random Forest (RF) for the land cover and tree species classification task, k-Nearest Neighbours (k-NN) and Gradient Boosting Machines (GBM) for the deadwood imputation purpose. Land cover (81.9%) and tree species classification (78.9%) were performed with a relatively high level of overall accuracy. Outputs of deadwood biomass mapping using k-NN and GBM matched quite well (8.4 ± 2.3 t·ha−1 (17% of the mean) vs. 8.1 ± 1.7 t·ha−1 (16% of the mean), respectively mean ± SD deadwood biomass stock), indicating a strong potential of ensemble boosters to predict forest biomass in a spatially explicit manner. The main challenges met in the study were related to the limitations of available ground-based data, thus showing the need for national statistical inventory implications in Ukraine.

scholarly journals Non-invasive measurement of leaf water content and pressure–volume curves using terahertz radiation

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Ran Li ◽  
Yaojie Lu ◽  
Jennifer M. R. Peters ◽  
Brendan Choat ◽  
Andrew J. Lee
Keyword(s):  
Water Content ◽  
Water Status ◽  
Leaf Tissue ◽  
Leaf Water ◽  
Thz Radiation ◽  
Leaf Water Content ◽  
Absorption Characteristic ◽  
Tissue Water ◽  
Non Invasive

AbstractIn this paper we describe a non-invasive method of measuring leaf water content using THz radiation and combine this with psychrometry for determination of leaf pressure–volume relationships. In contrast to prior investigations using THz radiation to measure plant water status, the reported method exploits the differential absorption characteristic of THz radiation at multiple frequencies within plant leaves to determine absolute water content in real-time. By combining the THz system with a psychrometer, pressure–volume curves were generated in a completely automated fashion for the determination of leaf tissue water relations parameters including water potential at turgor loss, osmotic potential at full turgor and the relative water content at the turgor loss point. This novel methodology provides for repeated, non-destructive measurement of leaf water content and greatly increased efficiency in generation of leaf PV curves by reducing user handling time.

Development of a diurnal dehydration index for spring barley phenotyping

2014 ◽  
Vol 41 (12) ◽  
pp. 1249 ◽  
Author(s):  
Pablo Rischbeck ◽  
Peter Baresel ◽  
Salah Elsayed ◽  
Bodo Mistele ◽  
Urs Schmidhalter
Keyword(s):  
Drought Stress ◽  
Drought Tolerance ◽  
Water Content ◽  
Water Status ◽  
Spring Barley ◽  
Leaf Water ◽  
Leaf Angle ◽  
Leaf Water Content ◽  
Diurnal Changes ◽  
Angle Distribution

Spectral and thermal assessments may enable the precise, high-throughput and low-cost characterisation of traits linked to drought tolerance. However, spectral and thermal measurements of the canopy water status are influenced by the crops’ soil coverage, the size of the biomass and other properties such as the leaf angle distribution. The aim of this study was to develop a referenced spectral method that would be minimally influenced by potentially perturbing factors for retrieving the water status of differing cultivars. Sixteen spring barley cultivars were grown in field trials under imposed drought stress, natural drought stress and irrigated conditions. The relative leaf water content of barley plants declines diurnally from pre-dawn until the afternoon, and other plant traits such as the biomass change little throughout the day. As an indicator of the current drought stress, pre-dawn and afternoon values of the relative leaf water content were assessed spectrally. Diurnal changes in reflectance are only slightly influenced by other perturbing factors. A new spectral index (diurnal dehydration index) was developed by using the wavelengths 730 and 457 nm collected from an active spectrometer. This index allowed the differentiation of the drought tolerance of barley plants. The diurnal dehydration index was significantly related to final biomass, grain yield and harvest index and significantly different between cultivars. Compared with other indices, the diurnal dehydration index offered a higher stability in retrieving the water status of barley plants. Due to its diurnal assessment, the index was barely influenced by the differences in cultivars biomass at the time of measurement. It may represent a valuable tool for assessing the water status or drought tolerance in breeding nurseries.

Using machine learning techniques to reduce data annotation time

2006 ◽  
Author(s):  
Christopher Schreiner ◽  
Kari Torkkola ◽  
Mike Gardner ◽  
Keshu Zhang
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Data Annotation ◽  
Learning Techniques

Using Machine Learning Algorithms on Prediction of Stock Price

2020 ◽  
Vol 12 (2) ◽  
pp. 84-99
Author(s):  
Li-Pang Chen
Keyword(s):  
Machine Learning ◽  
Stock Price ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Short Term ◽  
Learning Techniques ◽  
Historical Database ◽  
Long Short Term Memory

In this paper, we investigate analysis and prediction of the time-dependent data. We focus our attention on four different stocks are selected from Yahoo Finance historical database. To build up models and predict the future stock price, we consider three different machine learning techniques including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) and Support Vector Regression (SVR). By treating close price, open price, daily low, daily high, adjusted close price, and volume of trades as predictors in machine learning methods, it can be shown that the prediction accuracy is improved.

389-P: Ability for Detecting or Predicting Hypoglycemia with the Aid of Machine Learning Techniques: A Meta-analysis

Diabetes ◽  
2020 ◽  
Vol 69 (Supplement 1) ◽  
pp. 389-P
Author(s):  
SATORU KODAMA ◽  
MAYUKO H. YAMADA ◽  
YUTA YAGUCHI ◽  
MASARU KITAZAWA ◽  
MASANORI KANEKO ◽  
...  
Keyword(s):  
Machine Learning ◽  
Meta Analysis ◽  
Machine Learning Techniques ◽  
Learning Techniques
Sign in / Sign up

Export Citation Format

Share Document