Development of an Artificial Neural Network Approach for Predicting Plant Water Status in Almonds

2019 ◽  
Vol 62 (1) ◽  
pp. 19-32 ◽  
Author(s):  
Julie N. Meyers ◽  
Julie N. Meyers ◽  
Isaya Kisekka ◽  
Shrinivasa K. Upadhyaya ◽  
Gabriela Karoline Michelon ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Water Potential ◽  
Water Status ◽  
Plant Water Status ◽  
Plant Water ◽  
Stem Water Potential ◽  
Stem Water ◽  
Artificial Neural

Abstract. Stem water potential (SWP) is a commonly used method for determining plant water status (PWS) but requires a significant amount of time and is tedious to measure. To eliminate the necessity for this fieldwork, artificial neural networks (ANNs) were designed to predict PWS using information that is easier to measure, such as leaf temperature and microclimatic variables including ambient air temperature, relative humidity, incident radiation, and soil water content. To collect these variables, leaf and soil water sensors were placed in a 1.6 ha almond orchard. The sensors were interconnected through a wireless mesh network, which allowed remote data access. SWP values were taken in the field at midday three times a week during the growing season. The ANNs were trained using the Levenberg-Marquardt algorithm with the data divided into 70% training, 15% validation, and 15% test data. Each network contained one hidden layer with one to three hidden neurons. For each unique combination of inputs, the network was retrained five times, and the best network was selected based on the lowest mean squared error for the test data. When compared with multiple linear regression models fitting the same data, the networks consistently resulted in better R2 values, and higher values may be achieved with further optimization. These results suggest that there is potential for machine learning techniques that use ANNs to model the relationship between environmental conditions and PWS, which may be used for predicting acceptable temperature differences from target SWP. Keywords: Almonds, Artificial neural network, Leaf monitor, Machine learning, Plant water status, Precision irrigation, Stem water potential.

scholarly journals Determination of an efficient irrigation schedule for the cultivation of rose cv. Freedom under greenhouse conditions in Colombia

2014 ◽  
Vol 32 (1) ◽  
pp. 95-102 ◽  
Author(s):  
Jhon Jairo Arévalo ◽  
Javier Enrique Vélez S. ◽  
Diego Sebastiano Intrigliolo
Keyword(s):  
Water Potential ◽  
Water Status ◽  
Irrigation Schedule ◽  
Experimental Period ◽  
Plant Water Status ◽  
Base Line ◽  
Plant Water ◽  
Stem Water Potential ◽  
Evaporative Demand ◽  
Stem Water

An experiment on rose (Rosa sp.) cv. Freedom was performed in a greenhouse on the Bogota Plateau, Colombia, to identify an efficient irrigation regime for this crop. The tested treatments were based on three irrigation doses, applying different fractions of the estimated crop evapotranspiration (ETc), calculated using a class A evaporation tank: i) 100% ETc (ETc100), ii) 80% ETc (ETc80) and iii) 70% ETc (ETc70). During the entire experimental period, from mid-May to early September, the crop had a constant production of floral stems. In all of the irrigation treatments, the soil and plant water status were monitored using tensiometers and the midday stem water potential, respectively (ystem). In the fully irrigated roses, the actual water use was determined using a drainage lysimeter in order to obtain the local crop coefficients (Kc) by means of a water balance. From June to August, the obtained monthly Kc values varied between 1.10 and 1.26. Compared to the ETc100 treatment, 14.5 and 21.8% less water was applied in treatments ETc80 and ETc70, respectively. Despite this fact, no statistically significant differences were found among the treatments for rose production or quality. Finally, in the more irrigated roses, tight relationships between the stem water potential and vapor pressure deficit were obtained. The reported base-line equations can be used for predicting the optimum rose plant water status, depending on the environmental conditions. Overall, the reported results can be used for an efficient irritation schedule for rose crops under greenhouse conditions, using the local Kc and direct determinations of plant water status corrected for the evaporative demand.

scholarly journals An Index for User-Friendly Proximal Detection of Water Requirements to Optimized Irrigation Management in Vineyards

Agronomy ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 323
Author(s):  
Ana Fernandes de Oliveira ◽  
Massimiliano Giuseppe Mameli ◽  
Mauro Lo Cascio ◽  
Costantino Sirca ◽  
Daniela Satta
Keyword(s):  
Water Potential ◽  
Leaf Gas Exchange ◽  
Water Status ◽  
Water Productivity ◽  
Linear Regression Analysis ◽  
Plant Water Status ◽  
Plant Water ◽  
Stem Water Potential ◽  
Water Requirements ◽  
Stem Water

We propose an index for proximal detection of water requirements to optimize the use of water resources in arid and semi-arid wine growing regions. To test the accuracy and representativeness of the proposed irrigation need index (IIN), plant water status and physiological performances were monitored during seasons 2019 and 2020 in two grapevine varieties with different anisohydric degree (Vermentino and Cannonau) grown in 3 sites in Sardinia (Italy). Daily leaf gas exchange curves and stem water potential were recorded. Canopy temperature was monitored, using both thermistor sensors (Tc) and infrared thermometry (IR). Meteorological data, including dry and wet bulb temperatures were collected to compute and parametrize IIN, based on energy balance equation. Vineyard water balance, thermal time and irrigation water productivity were characterized. Linear regression analysis allowed to validate IIN for both varieties and to establish target thresholds for mild, moderate and severe water deficit to optimize irrigation for high yield and quality objectives. IIN well represents plant water status, using either Tc or IR, and allows rapid and easy detection of water and heat stress condition, even when a stricter stomatal control determines slighter variation and lower response of stem water potential, as in plants with low anisohydric degree.

scholarly journals Plant Water Status as an Index of Irrigation Need in Deciduous Fruit Trees

1997 ◽  
Vol 7 (1) ◽  
pp. 23-29 ◽  
Author(s):  
Kenneth A. Shackel ◽  
H. Ahmadi ◽  
W. Biasi ◽  
R. Buchner ◽  
D. Goldhamer ◽  
...  
Keyword(s):  
Water Potential ◽  
Deficit Irrigation ◽  
Shoot Growth ◽  
Water Status ◽  
Plant Stress ◽  
Irrigation Treatment ◽  
Plant Water Status ◽  
Plant Water ◽  
Stem Water Potential ◽  
Stem Water

To be useful for indicating plant water needs, any measure of plant stress should be closely related to some of the known short- and medium-term plant stress responses, such as stomatal closure and reduced rates of expansive growth. Midday stem water potential has proven to be a useful index of stress in a number of fruit tree species. Day-to-day fluctuations in stem water potential under well-irrigated conditions are well correlated with midday vapor-pressure deficit, and, hence, a nonstressed baseline can be predicted. Measuring stem water potential helped explain the results of a 3-year deficit irrigation study in mature prunes, which showed that deficit irrigation could have either positive or negative impacts on tree productivity, depending on soil conditions. Mild to moderate water stress was economically beneficial. In almond, stem water potential was closely related to overall tree growth as measured by increases in trunk cross-sectional area. In cherry, stem water potential was correlated with leaf stomatal conductance and rates of shoot growth, with shoot growth essentially stopping once stem water potential dropped to between −1.5 to −1.7 MPa. In pear, fruit size and other fruit quality attributes (soluble solids, color) were all closely associated with stem water potential. In many of these field studies, systematic tree-to-tree differences in water status were large enough to obscure irrigation treatment effects. Hence, in the absence of a plant-based measure of water stress, it may be difficult to determine whether the lack of an irrigation treatment effect indicates the lack of a physiological response to plant water status, or rather is due to treatment ineffectiveness in influencing plant water status. These data indicate that stem water potential can be used to quantify stress reliably and guide irrigation decisions on a site-specific basis.

scholarly journals Microtensiometers Accurately Measure Stem Water Potential in Woody Perennials

Plants ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 2780
Author(s):  
Victor Blanco ◽  
Lee Kalcsits
Keyword(s):  
Water Potential ◽  
Leaf Gas Exchange ◽  
Water Status ◽  
Full Range ◽  
Canopy Temperature ◽  
Plant Water ◽  
Stem Water Potential ◽  
Woody Tissue ◽  
Woody Perennials ◽  
Stem Water

Stem water potential (Ψstem) is considered to be the standard measure of plant water status. However, it is measured with the pressure chamber (PC), an equipment that can neither provide continuous information nor be automated, limiting its use. Recent developments of microtensiometers (MT; FloraPulse sensors), which can continuously measure water tension in woody tissue of the trunk of the tree, can potentially highlight the dynamic nature of plant water relations. Thus, this study aimed to validate and assess the usefulness of the MT by comparing the Ψstem provided by MT with those same measurements from the PC. Here, two irrigation treatments (a control and a deficit treatment) were applied in a pear (Pyrus communis L.) orchard in Washington State (USA) to capture the full range of water potentials in this environment. Discrete measurements of leaf gas exchange, canopy temperature and Ψstem measured with PC and MT were made every two hours for four days from dawn to sunset. There were strong linear relationships between the Ψstem-MT and Ψstem-PC (R2 > 0.8) and with vapor pressure deficit (R2 > 0.7). However, Ψstem-MT was more variable and lower than Ψstem-PC when Ψstem-MT was below −1.5 MPa, especially during the evening. Minimum Ψstem-MT occurred later in the afternoon compared to Ψstem-PC. Ψstem showed similar sensitivity and coefficients of variation for both PC and MT acquired data. Overall, the promising results achieved indicated the potential for MT to be used to continuously assess tree water status.

scholarly journals Effect of Fall Irrigation Level in `Mauritius' and `Floridian' Lychee on Soil and Plant Water Status, Flowering Intensity, and Yield

1998 ◽  
Vol 123 (1) ◽  
pp. 150-155 ◽  
Author(s):  
R.A. Stern ◽  
M. Meron ◽  
A. Naor ◽  
R. Wallach ◽  
B. Bravdo ◽  
...  
Keyword(s):  
Water Stress ◽  
Water Potential ◽  
Shoot Growth ◽  
Water Status ◽  
Plant Water ◽  
Stem Water Potential ◽  
Irrigation Level ◽  
Irrigation Control ◽  
Stem Water ◽  
Flowering Intensity

The effect of fall irrigation level in `Mauritius' and `Floridian' lychee (Litchi chinensis Sonn.) on soil and plant water status, flowering intensity, and yield the following year was studied in a field during 2 consecutive years. At the end of the second vegetative flush after harvest (1 Oct. 1994 and 10 Oct. 1995), four irrigation treatments were initiated: 0.5, 0.25, 0.125, and 0 Class A pan evaporation coefficients designated 100%, 50%, 25%, and 0%. The three lower irrigation levels effectively stopped shoot growth, suggesting the 50% treatment to be the threshold for shoot growth cessation in both years. For both years, flowering intensity and yield in the 100% treatment were lower than those following the other three treatments. Soil and plant water-stress indicators responded to the water-stress irrigation treatments. However soil water-potential values were highly variable relative to plant water potentials. Stem water potential differed more markedly between treatments than leaf water potential. Midday stem water potential appeared to be the best water-stress indicator for irrigation control. Midday stem water potential in both years was correlated with midday vapor-pressure deficit, suggesting that the threshold for irrigation control should take into account evaporative demand.

scholarly journals 593 A Lightweight, Hand-operated Pressure Chamber for Determining Plant Water Status

HortScience ◽  
2000 ◽  
Vol 35 (3) ◽  
pp. 499B-499
Author(s):  
Ken Shackel ◽  
David Paige
Keyword(s):  
Water Potential ◽  
Water Status ◽  
Irrigation Management ◽  
Nitrogen Pressure ◽  
Irrigation Scheduling ◽  
Pressure Chamber ◽  
Plant Water ◽  
Stem Water Potential ◽  
Stem Water ◽  
Time Required

In a number of tree crops, we have found that the water potential of lower canopy, nontranspiring leaves, measured with the pressure chamber at midday (midday stem water potential), is an excellent index of plant water stress and can be used for irrigation scheduling. Because stem water potential is typically much higher than transpiring leaf water potential, a lower pressure is required for the measurement, allowing us to design and build a lightweight device that could be easily operated by hand. The prototype was designed for pressures up to 2 MPa, which is sufficient for most irrigation conditions. A number of design features were incorporated into the sealing gland to eliminate the need for retightening during the pressurization process, reduce the amount of tissue external to the pressure chamber, and allow a greater visibility of the petiole. Identical values to those obtained with the standard, compressed nitrogen pressure chamber were obtained over the entire 2-MPa range, and the time required using either device under field conditions was the same (about 1 min per measurement). A number of alternative protocols were tested, and we found that even substantial recutting of the petiole had no influence on the measured water potential, contrary to popular belief. We also found that the same sample could be remeasured multiple times (five), with no net change in the water potential, allowing the measurement to be checked if necessary. This device should be of great utility in field irrigation management.

Artificial neural network models for coronary artery disease

2020 ◽  
Vol 15 ◽  
Author(s):  
Elham Shamsara ◽  
Sara Saffar Soflaei ◽  
Mohammad Tajfard ◽  
Ivan Yamshchikov ◽  
Habibollah Esmaili ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Coronary Artery Disease ◽  
Pattern Recognition ◽  
Artificial Neural Network ◽  
Coronary Artery ◽  
Diagnostic Model ◽  
Early Prediction ◽  
Artificial Neural ◽  
Artery Disease

Background: Coronary artery disease (CAD) is an important cause of mortality and morbidity globally. Objective : The early prediction of the CAD would be valuable in identifying individuals at risk, and in focusing resources on its prevention. In this paper, we aimed to establish a diagnostic model to predict CAD by using three approaches of ANN (pattern recognition-ANN, LVQ-ANN, and competitive ANN). Methods: One promising method for early prediction of disease based on risk factors is machine learning. Among different machine learning algorithms, the artificial neural network (ANN) algo-rithms have been applied widely in medicine and a variety of real-world classifications. ANN is a non-linear computational model, that is inspired by the human brain to analyze and process complex datasets. Results: Different methods of ANN that are investigated in this paper indicates in both pattern recognition ANN and LVQ-ANN methods, the predictions of Angiography+ class have high accuracy. Moreover, in CNN the correlations between the individuals in cluster ”c” with the class of Angiography+ is strongly high. This accuracy indicates the significant difference among some of the input features in Angiography+ class and the other two output classes. A comparison among the chosen weights in these three methods in separating control class and Angiography+ shows that hs-CRP, FSG, and WBC are the most substantial excitatory weights in recognizing the Angiography+ individuals although, HDL-C and MCH are determined as inhibitory weights. Furthermore, the effect of decomposition of a multi-class problem to a set of binary classes and random sampling on the accuracy of the diagnostic model is investigated. Conclusion : This study confirms that pattern recognition-ANN had the most accuracy of performance among different methods of ANN. That’s due to the back-propagation procedure of the process in which the network classify input variables based on labeled classes. The results of binarization show that decomposition of the multi-class set to binary sets could achieve higher accuracy.

scholarly journals Burst Pressure Prediction of API 5L X-Grade Dented Pipelines Using Deep Neural Network

2020 ◽  
Vol 8 (10) ◽  
pp. 766
Author(s):  
Dohan Oh ◽  
Julia Race ◽  
Selda Oterkus ◽  
Bonguk Koo
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
Machine Learning Techniques ◽  
Burst Pressure ◽  
Comparison Results ◽  
Artificial Neural

Mechanical damage is recognized as a problem that reduces the performance of oil and gas pipelines and has been the subject of continuous research. The artificial neural network in the spotlight recently is expected to be another solution to solve the problems relating to the pipelines. The deep neural network, which is on the basis of artificial neural network algorithm and is a method amongst various machine learning methods, is applied in this study. The applicability of machine learning techniques such as deep neural network for the prediction of burst pressure has been investigated for dented API 5L X-grade pipelines. To this end, supervised learning is employed, and the deep neural network model has four layers with three hidden layers, and the neural network uses the fully connected layer. The burst pressure computed by deep neural network model has been compared with the results of finite element analysis based parametric study, and the burst pressure calculated by the experimental results. According to the comparison results, it showed good agreement. Therefore, it is concluded that deep neural networks can be another solution for predicting the burst pressure of API 5L X-grade dented pipelines.

scholarly journals Towards Vine Water Status Monitoring on a Large Scale Using Sentinel-2 Images

2021 ◽  
Vol 13 (9) ◽  
pp. 1837
Author(s):  
Eve Laroche-Pinel ◽  
Sylvie Duthoit ◽  
Mohanad Albughdadi ◽  
Anne D. Costard ◽  
Jacques Rousseau ◽  
...  
Keyword(s):  
Climate Change ◽  
Water Potential ◽  
Large Scale ◽  
Water Status ◽  
Vegetation Indices ◽  
Machine Learning Algorithms ◽  
Severe Drought ◽  
Stem Water Potential ◽  
Stem Water ◽  
Sentinel 2

Wine growing needs to adapt to confront climate change. In fact, the lack of water becomes more and more important in many regions. Whereas vineyards have been located in dry areas for decades, so they need special resilient varieties and/or a sufficient water supply at key development stages in case of severe drought. With climate change and the decrease of water availability, some vineyard regions face difficulties because of unsuitable variety, wrong vine management or due to the limited water access. Decision support tools are therefore required to optimize water use or to adapt agronomic practices. This study aimed at monitoring vine water status at a large scale with Sentinel-2 images. The goal was to provide a solution that would give spatialized and temporal information throughout the season on the water status of the vines. For this purpose, thirty six plots were monitored in total over three years (2018, 2019 and 2020). Vine water status was measured with stem water potential in field measurements from pea size to ripening stage. Simultaneously Sentinel-2 images were downloaded and processed to extract band reflectance values and compute vegetation indices. In our study, we tested five supervised regression machine learning algorithms to find possible relationships between stem water potential and data acquired from Sentinel-2 images (bands reflectance values and vegetation indices). Regression model using Red, NIR, Red-Edge and SWIR bands gave promising result to predict stem water potential (R2=0.40, RMSE=0.26).

Sign in / Sign up

Export Citation Format

Share Document