scholarly journals Deep Learning Sensor Fusion in Plant Water Stress Assessment: A Comprehensive Review

2021 ◽  
Vol 11 (4) ◽  
pp. 1403
Author(s):  
Mohd Hider Kamarudin ◽  
Zool Hilmi Ismail ◽  
Noor Baity Saidi
Keyword(s):  
Deep Learning ◽  
Water Stress ◽  
Sensor Fusion ◽  
Water Status ◽  
System Modeling ◽  
Economic Loss ◽  
Plant Water ◽  
Plant Water Stress ◽  
Stress Assessment ◽  
Intelligence System

Water stress is one of the major challenges to food security, causing a significant economic loss for the nation as well for growers. Accurate assessment of water stress will enhance agricultural productivity through optimization of plant water usage, maximizing plant breeding strategies, and preventing forest wildfire for better ecosystem management. Recent advancements in sensor technologies have enabled high-throughput, non-contact, and cost-efficient plant water stress assessment through intelligence system modeling. The advanced deep learning sensor fusion technique has been reported to improve the performance of the machine learning application for processing the collected sensory data. This paper extensively reviews the state-of-the-art methods for plant water stress assessment that utilized the deep learning sensor fusion approach in their application, together with future prospects and challenges of the application domain. Notably, 37 deep learning solutions fell under six main areas, namely soil moisture estimation, soil water modelling, evapotranspiration estimation, evapotranspiration forecasting, plant water status estimation and plant water stress identification. Basically, there are eight deep learning solutions compiled for the 3D-dimensional data and plant varieties challenge, including unbalanced data that occurred due to isohydric plants, and the effect of variations that occur within the same species but cultivated from different locations.

Development of a Continuous Leaf Monitoring System to Predict Plant Water Status

2017 ◽  
Vol 60 (5) ◽  
pp. 1445-1455 ◽  
Author(s):  
Rajveer S. Dhillon ◽  
Shrini K. Upadhaya ◽  
Francisco Rojo ◽  
Jed Roach ◽  
Robert W. Coates ◽  
...  
Keyword(s):  
Water Stress ◽  
Data Collection ◽  
Water Status ◽  
Irrigation Scheduling ◽  
Leaf Temperature ◽  
Plant Water Status ◽  
Mesh Network ◽  
Plant Water ◽  
Plant Water Stress ◽  
Precision Irrigation

Abstract. There is increased demand for irrigation scheduling tools that support effective use of the limited supply of irrigation water. An efficient precision irrigation system requires water to be delivered based on crop needs by measuring or estimating plant water stress. Leaf temperature is a good indicator of water stress. In this study, a system was developed to monitor leaf temperature and microclimatic environmental variables to predict plant water stress. This system, called the leaf monitor, monitored plant water status by continuously measuring leaf temperature, air temperature, relative humidity, ambient light, and wind conditions in the vicinity of a shaded leaf. The system also included a leaf holder, a solar radiation diffuser dome, and a wind barrier for improved performance of the unit. Controlled wind speed and consistent light conditions were created around the leaf to reduce the effect of nuisance variables on leaf temperature. The leaf monitor was incorporated into a mesh network of wireless nodes for sensor data collection and remote valve control. The system was evaluated for remote data collection in commercial orchards. Experiments were conducted during the 2013 and 2014 growing seasons in walnut () and almond () orchards. The system was found to be reliable and capable of providing real-time visualization of the data remotely, with minimal technical problems. Leaf monitor data were used to develop modified crop water stress index (MCWSI) values for quantifying plant water stress levels. Keywords: Almonds, CWSI, Infrared sensor, Irrigation scheduling, Leaf temperature, Nut crops, Plant water stress, Precision irrigation, Stem water potential, Walnuts, Wireless mesh network.

Efficient registration of optical and IR images for automatic plant water stress assessment

2010 ◽  
Vol 74 (2) ◽  
pp. 230-237 ◽  
Author(s):  
Xuezhi Wang ◽  
Weiping Yang ◽  
Ashley Wheaton ◽  
Nicola Cooley ◽  
Bill Moran
Keyword(s):  
Water Stress ◽  
Plant Water ◽  
Plant Water Stress ◽  
Stress Assessment

scholarly journals Grazing winter wheat relieves plant water stress and transiently enhances photosynthesis

2010 ◽  
Vol 37 (8) ◽  
pp. 726 ◽  
Author(s):  
Matthew T. Harrison ◽  
Walter M. Kelman ◽  
Andrew D. Moore ◽  
John R. Evans
Keyword(s):  
Water Stress ◽  
Leaf Area ◽  
Water Status ◽  
Leaf Water ◽  
Plant Water ◽  
Rubisco Activity ◽  
Leaf Water Status ◽  
Area Index ◽  
Plant Water Stress ◽  
The Impact

To model the impact of grazing on the growth of wheat (Triticum aestivum L.), we measured photosynthesis in the field. Grazing may affect photosynthesis as a consequence of changes to leaf water status, nitrogen content per unit leaf area (Na) or photosynthetic enzyme activity. While light-saturated CO2 assimilation rates (Asat) of field-grown wheat were unchanged during grazing, Asat transiently increased by 33–68% compared with ungrazed leaves over a 2- to 4-week period after grazing ended. Grazing reduced leaf mass per unit area, increased stomatal conductance and increased intercellular CO2 concentrations (Ci) by 36–38%, 88–169% and 17–20%, respectively. Grazing did not alter Na. Using a photosynthesis model, we demonstrated that the increase in Asat after grazing required an increase in Rubisco activity of up to 53%, whereas the increase in Ci could only increase Asat by up to 13%. Increased Rubisco activity was associated with a partial alleviation of leaf water stress. We observed a 68% increase in leaf water potential of grazed plants that could be attributed to reduced leaf area index and canopy evaporative demand, as well as to increased rainfall infiltration into soil. The grazing of rain-fed grain cereals may be tailored to relieve plant water stress and enhance leaf photosynthesis.

Study on Plant Water Stress Based on Ultrasonic Acoustic Emissions

2013 ◽  
Vol 367 ◽  
pp. 292-296
Author(s):  
Jian Xin Wang ◽  
Xian Wei Gao ◽  
Mei Li Sui ◽  
Xiu Ying Li
Keyword(s):  
Water Stress ◽  
Soil Water ◽  
Water Status ◽  
Acoustic Emissions ◽  
Signal Strength ◽  
Acoustic Emission Event ◽  
Plant Water ◽  
Plant Water Stress ◽  
Noise Interference ◽  
Content Status

The soil water deficit and strong transpiration can give rise to the phenomenon of plant water stress. Because of the water stress produces the fracture of the water column in conduits, and the fracture is the reflection of energy release which can be detected by the ultrasonic acoustic emissions (UAEs) technology. In order to avoid background noise interference, the UAEs detecting frequency is between 100K Hz and 1 MHz. The PCI-2 data acquisition (DAQ) card and R15 sensors are used to improve the precision of UAEs detection. When the water stress and dehydration gets heavier, the UAEs get higher. Use the tomato plant data with the empirical deduction under the modern greenhouse conditions, the relationships among UAEs, transpiration and UAEs signal strength is described by curve. The UAEs signals occur generally from 5:00~7:00 am, and stop after 20:00 at night. In the daytime, when the plant body water storage is few, and transpiration is strong, the UAEs occur two peaks, called the “Twin Peaks Area” (TPA). In the different conditions of soil water content status and environmental factors, the TPA occur time will be advance or lag, which is generally in the range of 8:00~15:00. An acoustic emission event maybe produces several UAEs counts, while the UAEs counts have a correspondence with the UAEs signal strength. It is better to use UAEs technique to diagnose the plant water status and carry out automatic and precise irrigation for the plant and to improve the effect of Water-saving irrigation.

scholarly journals HortNet417v1—A Deep-Learning Architecture for the Automatic Detection of Pot-Cultivated Peach Plant Water Stress

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7924
Author(s):  
Md Parvez Islam ◽  
Takayoshi Yamane
Keyword(s):  
Deep Learning ◽  
Water Stress ◽  
Plant Stress ◽  
High Stress ◽  
Classification Performance ◽  
Stress Conditions ◽  
Test Accuracy ◽  
Plant Water ◽  
Plant Water Stress ◽  
Learning Techniques

The biggest challenge in the classification of plant water stress conditions is the similar appearance of different stress conditions. We introduce HortNet417v1 with 417 layers for rapid recognition, classification, and visualization of plant stress conditions, such as no stress, low stress, middle stress, high stress, and very high stress, in real time with higher accuracy and a lower computing condition. We evaluated the classification performance by training more than 50,632 augmented images and found that HortNet417v1 has 90.77% training, 90.52% cross validation, and 93.00% test accuracy without any overfitting issue, while other networks like Xception, ShuffleNet, and MobileNetv2 have an overfitting issue, although they achieved 100% training accuracy. This research will motivate and encourage the further use of deep learning techniques to automatically detect and classify plant stress conditions and provide farmers with the necessary information to manage irrigation practices in a timely manner.

scholarly journals Leaf compatible “eco-friendly” temperature sensor clip for high density monitoring wireless networks

2017 ◽  
Vol 4 (1) ◽  
pp. 55-60 ◽  
Author(s):  
Valeria Palazzari ◽  
Paolo Mezzanotte ◽  
Federico Alimenti ◽  
Francesco Fratini ◽  
Giulia Orecchini ◽  
...  
Keyword(s):  
Decision Support ◽  
Water Stress ◽  
Temperature Sensor ◽  
Irrigation System ◽  
Fuel Oil ◽  
Plant Water ◽  
Temperature Differential ◽  
Water Pump ◽  
Plant Water Stress ◽  
System A

This paper describes the design, realization, and application of a custom temperature sensor devoted to the monitoring of the temperature differential between the leaf and the air. This difference is strictly related to the plant water stress and can be used as an input information for an intelligent and flexible irrigation system. A wireless temperature sensor network can be thought as a decision support system used to start irrigation when effectively needed by the cultivation, thus saving water, pump fuel oil, and preventing plant illness caused by over-watering.

Single hyperspectral bands are highly sensitive to water stress in adult mandarin trees

2021 ◽  
Author(s):  
Pablo Berríos ◽  
Abdelmalek Temnani ◽  
Susana Zapata ◽  
Manuel Forcén ◽  
Sandra Martínez-Pedreño ◽  
...  
Keyword(s):  
Water Stress ◽  
Water Deficit ◽  
Phase Ii ◽  
Irrigation Water ◽  
Water Status ◽  
Irrigation Scheduling ◽  
Plant Water Status ◽  
Phase Iii ◽  
Plant Water ◽  
Severe Water Stress

<p>Mandarin is one of the most important Citrus cultivated in Spain and the sustainability of the crop is subject to a constant pressure for water resources among the productive sectors and to a high climatic demand conditions and low rainfall (about 250 mm per year). The availability of irrigation water in the Murcia Region is generally close to 3,500 m<sup>3</sup> per ha and year, so it is only possible to satisfy 50 - 60% of the late mandarin ETc, which requires about 5,500 m<sup>3</sup> per ha. For this reason, it is necessary to provide tools to farmers in order to control the water applied in each phenological phase without promoting levels of severe water stress to the crop that negatively affect the sustainability of farms located in semi-arid conditions. Stem water potential (SWP) is a plant water status indicator very sensitive to water deficit, although its measurement is manual, discontinuous and on a small-scale.  In this way, indicators measured on a larger scale are necessary to achieve integrating the water status of the crop throughout the farm. Thus, the aim of this study was to determine the sensitivity to water deficit of different hyperspectral single bands (HSB) and their relationship with the midday SWP in mandarin trees submitted to severe water stress in different phenological phases. Four different irrigation treatments were assessed: i) a control (CTL), irrigated at 100% of the ETc throughout the growing season to satisfy plant water requirements and three water stress treatments that were irrigated at 60% of ETc throughout the season – corresponding to the real irrigation water availability – except  during: ii) the end of phase I and beginning of phase II (IS IIa), iii) the first half of phase II (IS IIb) and iv) phase III of fruit growth (IS III), which irrigation was withheld until values of -1.8 MPa of SWP or a water stress integral of 60 MPa day<sup>-1</sup>. When these threshold values were reached, the spectral reflectance values were measured between 350 and 2500 nm using a leaf level spectroradiometer to 20 mature and sunny leaves on 4 trees per treatment. Twenty-four HVI and HSB were calculated and a linear correlation was made between each of them with SWP, where the ρ940 and ρ1250 nm single bands reflectance presented r-Pearson values of -0.78** and -0.83***, respectively. Two linear regression curves fitting were made: SWP (MPa) = -11.05 ∙ ρ940 + 7.8014 (R<sup>2</sup> =0.61) and SWP (MPa) = -13.043 ∙ ρ1250 + 8.9757 (R<sup>2</sup> =0.69). These relationships were obtained with three different fruit diameters (35, 50 and 65 mm) and in a range between -0.7 and -1.6 MPa of SWP. Results obtained show the possibility of using these single bands in the detection of water stress in adult mandarin trees, and thus propose a sustainable and efficient irrigation scheduling by means of unmanned aerial vehicles equipped with sensors to carry out an automated control of the plant water status and with a suitable temporal and spatial scale to apply precision irrigation.</p>

Sign in / Sign up

Export Citation Format

Share Document