Leaf Wetness Duration Research Articles

Utilizing High-Resolution Imaging and Artificial Intelligence for Accurate Leaf Wetness Detection for the Strawberry Advisory System (SAS).

In strawberry cultivation, precise disease management is crucial for maximizing yields and reducing unnecessary fungicide use. Traditional methods for measuring leaf wetness duration (LWD), a critical factor in assessing the risk of fungal diseases such as botrytis fruit rot and anthracnose, have been reliant on sensors with known limitations in accuracy and reliability and difficulties with calibrating. To overcome these limitations, this study introduced an innovative algorithm for leaf wetness detection systems employing high-resolution imaging and deep learning technologies, including convolutional neural networks (CNNs). Implemented at the University of Florida's Plant Science Research and Education Unit (PSREU) in Citra, FL, USA, and expanded to three additional locations across Florida, USA, the system captured and analyzed images of a reference plate to accurately determine the wetness and, consequently, the LWD. The comparison of system outputs with manual observations across diverse environmental conditions demonstrated the enhanced accuracy and reliability of the artificial intelligence-driven approach. By integrating this system into the Strawberry Advisory System (SAS), this study provided an efficient solution to improve disease risk assessment and fungicide application strategies, promising significant economic benefits and sustainability advances in strawberry production.

Asian rust of soybean favorability Mato Grosso-Brazil

This study presents the map that indicates favorable environmental conditions for the development of Asian soybean rust in Mato Grosso, for a given period. It’s about a plant's disease caused by the fungus Phakopsora pachyrhizi, which has soybean as its main host. By affecting the plantation, anticipates the ripening of the grains, which can considerably reduce your productivity. The map is the reproduction, for Mato Grosso, of the image developed by Alves et al. (2011) for the state of Minas Gerais, generated from a fuzzy logic-based rule system. The input variables for this system are temperature and leaf wetness duration, while the output is the area below the disease progression curve. To supply it, data were collected from automatic meteorological stations located in the state and neighboring regions. Records were made available hourly for January 2019. In possession of these results, for interpolation were tested the inverse distance weighting and kriging models. The method that showed the best results was the first, with an exponent equal to two.

Non-contact leaf wetness measurement with laser-induced light reflection and RGB imaging

Leaf wetness duration is a crucial factor in plant disease management. Current optical methods use standard RGB images to classify leaf wetness as a binary problem, i.e., wet or dry. Green leaves absorb red light, whereas water reflects it. Based on this difference, an experimental platform was built to semi-automatically measure droplet deposition on grape leaves while capturing red laser images using an RGB camera. The setup measured changes in leaf mass and area of scanned leaves to determine the water mass per leaf area as a measure of leaf wetness. A sprayer was used to apply water droplets to the leaves. As the amount of deposited water increased, the mean red channel intensity decreased, with more bright spots in the images. These bright spots were more distinguishable as droplets in the green channel. Segmented leaf area, mean red channel intensity, and the number of identified droplets were used as image features. A generalised additive model was employed to predict the leaf wetness value with extracted features. The R-squared value for the prediction of the validation dataset was 0.71. Image resolution and leaf orientation were identified as factors that influenced the model accuracy. The measurement method introduced in this study shows potential for accurately quantifying leaf wetness, and implies that in practice detecting leaf wetness can be integrated into a multi-classification problem, thereby broadening the potential applications of optical methods.

Utilizing Disease Prediction Models to Time Fungicide Applications for Controlling Ripe Rot, Caused by Colletotrichum spp., in Maryland Vineyards.

Two previously published ripe rot prediction models, DF2-NN and GH2-DT, were evaluated for fungicide application timing efficacy in Maryland vineyards. Both models utilize leaf wetness duration (LWD), temperature, and grape cluster phenological stages as model parameters. These three parameters were tracked throughout the 2021 to 2023 seasons in three vineyards. The fungicide efficacy trials started at the veraison phenological stage and included a nontreated control, a 12-day interval treatment, and two model-triggered treatments when risk predicted by the models crossed a threshold. The severity of ripe rot on the clusters in each treatment was assessed when the fruit were mature. Ripe rot severity in the nontreated controls was higher during seasons with more LWD and more precipitation. Days in which the models were triggered by the environmental conditions primarily coincided with precipitation events and lengthy LWDs. The model-triggered treatments never had significantly higher ripe rot severity than the 12-day interval treatment but had significantly lower severities than the nontreated control in most trials which had high ripe rot pressure. Furthermore, the model-triggered treatments resulted in fewer fungicide applications than the 12-day interval treatment on average. The DF2-NN model appeared to be more accurate and useful for ripe rot prediction and treatment than the GH2-DT model because it triggered fewer fungicide applications while reducing ripe rot. This model may be useful for improving or maintaining ripe rot control with fewer fungicide inputs, which may be beneficial for the environment and the reduction of fungicide resistance selection.

Climate and disease: tackling coffee brown-eye spot with advanced forecasting models.

Climate influences the interaction between pathogens and their hosts significantly. This is particularly evident in the coffee industry, where fungal diseases like Cercospora coffeicola, causing brown-eye spot, can reduce yields drastically. This study focuses on forecasting coffee brown-eye spot using various models that incorporate agrometeorological data, allowing for predictions at least 1 week prior to the occurrence of disease. Data were gathered from eight locations across São Paulo and Minas Gerais, encompassing the South and Cerrado regions of Minas Gerais state. In the initial phase, various machine learning (ML) models and topologies were calibrated to forecast brown-eye spot, identifying one with potential for advanced decision-making. The top-performing models were then employed in the next stage to forecast and spatially project the severity of brown-eye spot across 2681 key Brazilian coffee-producing municipalities. Meteorological data were sourced from NASA's Prediction of Worldwide Energy Resources platform, and the Penman-Monteith method was used to estimate reference evapotranspiration, leading to a Thornthwaite and Mather water-balance calculation. Six ML models - K-nearest neighbors (KNN), artificial neural network multilayer perceptron (MLP), support vector machine (SVM), random forests (RF), extreme gradient boosting (XGBoost), and gradient boosting regression (GradBOOSTING) - were employed, considering disease latency to time define input variables. These models utilized climatic elements such as average air temperature, relative humidity, leaf wetness duration, rainfall, evapotranspiration, water deficit, and surplus. The XGBoost model proved most effective in high-yielding conditions, demonstrating high precision and accuracy. Conversely, the SVM model excelled in low-yielding scenarios. The incidence of brown-eye spot varied noticeably between high- and low-yield conditions, with significant regional differences observed. The accuracy of predicting brown-eye spot severity in coffee plantations depended on the biennial production cycle. High-yielding trees showed superior results with the XGBoost model (R2 = 0.77, root mean squared error, RMSE = 10.53), whereas the SVM model performed better under low-yielding conditions (precision 0.76, RMSE = 12.82). The study's application of agrometeorological variables and ML models successfully predicted the incidence of brown-eye spot in coffee plantations with a 7 day lead time, illustrating that they were valuable tools for managing this significant agricultural challenge. © 2024 Society of Chemical Industry.

Risco climático para ocorrência da ferrugem asiática da soja no Mato Grosso, Rio Grande do Sul e Paraná

ABSTRACT Asian soybean rust is a primary factor affecting soybean production. Climate risk knowledge optimizes agricultural management, reduces pesticide use, and promotes environmental sustainability. The objective of this study was to evaluate the climatic risk of the occurrence of Asian soybean rust in the states of Mato Grosso, Rio Grande do Sul, and Paraná, Brazil, verifying the months with temperature and relative air humidity that are more favorable for disease development. Hourly meteorological data were obtained from the National Institute of Meteorology, collected from 36 automatic weather stations in Mato Grosso state, 44 in Rio Grande do Sul state, and 26 in Paraná state, from the beginning of the operation until December 31, 2021. The climatic risk values for Asian soybean rust occurrence were calculated daily, obtained by the product of the response functions to leaf wetness duration and air temperature during this period. The average total climatic risk of Asian soybean rust occurrence in Mato Grosso, Rio Grande do Sul, and Paraná states, was 44, 30, and 36%, respectively. Relative air humidity was the meteorological element with the greatest climatic risk for the development of the disease in the states of Rio Grande do Sul and Paraná, Brazil, and air temperature was the most limiting, the opposite was observed for the state of Mato Grosso, where air temperature was favorable and relative air humidity was more limiting.

Macrospora leaf spot development conditions and resistance/tolerance of Brazilian commercially grown maize genotypes

Macrospora leaf spot (MLS), caused by the fungus Stenocarpella macrospora, is one of the most important diseases affecting maize in Brazil. However, there are no MLS-resistant cultivars commercially available. Therefore, this study aimed to investigate the lesion expansion rate of MLS in four maize genotypes, leaf wetness duration (0-, 6-, 12-, 18-, 24-, 30-, 36-, 42-, and 54-hour post-inoculation), disease development severity in three maize genotypes, and resistance/tolerance levels to MLS in 141 maize genotypes commercially grown in Brazil. The estimates were performed using logistic models adjusted to the parameters analyzed, except for resistance/tolerance levels, which were analyzed using proposed severity and resistance scales. The experiment was carried out at the Laboratory of Plant Phytopathology of the Epagri/Cepaf, Santa Catarina State, Brazil, from 2016 to 2020. Disease resistance was significantly different among genotypes and fungal isolates. However, none of the genotypes showed resistance or high tolerance levels to MLS. Leaf wetness duration influenced maximum disease severity, and lesion expansion rate differed significantly among the genotypes tested. All information generated in this study is essential for breeding programs of maize for MLS resistance

Fractional Derivative Based TVD Smoothening and Baseline Correction for Extracting Leaf Wetness Duration From LW Sensor: A Novel Approach

Fractional Derivative Based TVD Smoothening and Baseline Correction for Extracting Leaf Wetness Duration From LW Sensor: A Novel Approach

Epidemiological Dynamics of Xanthomonas xonopodis pv. phaseoli in French bean (Phaseolus vulgaris): Unraveling the Factors Governing Bacterial Blight Pathogenesis

The study was conducted during May, 2020 to June, 2021 in the Department of Plant Pathology Laboratory of Dr. Y.S Parmar University of Horticulture and Forestry, Nauni, located in Solan district of Himachal Pradesh, India to study the role of various epidemiological parameters on the development of common bacterial blight of French bean. The diseased samples were collected and the pathogen was isolated and purified on Luria Bertani (LB) agar plates. The pathogenicity test was performed on the potted plants as well as on the detached leaves using carborundum abrasion and pin prick method of inoculation. The incubation period on potted plants using carborundum abrasion and pin prick method revealed the initial symptoms after 117.60 h and 120.30 h, respectively, while on detached leaves they were visible after 72.30 h and 84.50 h of inoculation, respectively. Further to study the effect of different epidemiological factors on disease development, the leaves inoculated using carborundum abrasion were subjected to four temperature levels, five relative humidity levels and five different durations of leaf wetness under controlled conditions in relative humidity cum temperature control cabinet. The observations were recorded at different intervals and the data revealed that the pathogen caused severe symptoms on the leaves with high apparent rate of infection under 30°C temperature, 100% RH and a maximum of 24 h of leaf wetness. It was observed that the severity of disease decreased as the temperature raised from 30°C and increased with the rise in RH levels and leaf wetness duration.

Influence of Temperature and Wetness on Taphrina deformans Ascospore and Blastospore Germination: Disease Forecasting and Validation

Peach leaf curl is a fungal disease caused by Taphrina deformans, and it can severely affect the health and productivity of peach and nectarine trees (Prunus persica) if left unmanaged. This study was carried out to investigate the temperature and wetness conditions that affect the germination of blastospores and ascospores of local isolates of the fungus T. deformans. The results showed that the rate of both ascospore and blastospore germination was reduced as the temperature increased from 0 to 20 °C. A decrease in temperature from the range of 25 °C to 30 °C caused a reduction in the germination of conidia for both ascospores and blastospores. Ascospore and blastospore germination were totally inhibited at −3 and 35 °C. Under constant temperatures of 20 °C, the percentage of both ascospore and blastospore germination of T. deformans gradually increased as the wetness period increased from 9 to 15 h. However, there was no further increase in germination observed beyond the 15 h wetness period. Additionally, this study aimed to validate the predictive models of T. deformans, developed based on the favorable temperatures and leaf wetness durations, under the specific field conditions of Naoussa, Greece. The results indicate that while both the ascosporic and blastosporic models were capable of correctly predicting infection periods, there were differences in their predictions of infection risk. The ascosporic model predicted lower risk infection, which aligned well with the observed symptoms of the disease. In contrast, the blastosporic model predicted higher risk infection, but this did not match the actual intensity of the symptoms. Finally, this study also provided insights into the potential benefits of using predictive models to guide fungicide applications, potentially leading to more targeted and efficient disease management strategies for commercial peach orchards.

Leaf wetness duration modeling for the improvement of fungal risk evaluation in low tech greenhouse

Leaf wetness duration modeling for the improvement of fungal risk evaluation in low tech greenhouse

Development of hypothetical infection model based on environmental variables for Plasmopara viticola (Berk. & M.A. Curtis) Berl. & De Ton

Development of a hypothetical infection model for Plasmopara viticola based on environmental variables was applied to black grape variety Vranec. The infected leaves were digitally quantified using the software platform 'ImageJ' to determine disease severity. The resulting data, along with inputs of average temperature and leaf wetness duration, were used to establish a regression relationship. Downy mildew infection reaches its maximum when we have an average of 2 hours and 29 minutes of leaf wetness duration and an average daily temperature of 26.8 ° C. The regression relationship then by used to describe the results, and based on this, a hypothetical infection model for P. viticola was developed.

Effects of Leaf Wetness Duration, Temperature, and Host Phenological Stage on Infection of Walnut by Xanthomonas arboricola pv. juglandis.

Bacterial blight, caused by Xanthomonas arboricola pv. juglandis, is a significant disease affecting walnut production worldwide. Outbreaks are most severe in spring, and closely tied to host phenology and weather conditions. Pathogen infections are mainly observed in catkins, female flowers, leaves, and fruits. In this study, the effect of wetness duration and temperature on walnut infections by X. arboricola pv. juglandis was determined through two independent experiments conducted under controlled environmental conditions. The combined effect of both climatic parameters on disease severity was quantified using a third-order polynomial equation. The model obtained by linear regression and backward elimination technique fitted well to the data (R2 = 0.94 and R2adj = 0.93). The predictive capacity of the forecasting model was evaluated on pathogen-inoculated walnut plants exposed to different wetness duration-temperature combinations under Mediterranean field conditions. Observed disease severity in all events aligned with predicted infection risk. Additionally, the relationship between leaf and fruit age and the disease severity was quantified and modelled. A prediction model, which has been referred to as the WalBlight-risk model, is proposed for evaluation as an advisory system for timing bactericide sprays to manage bacterial blight in Mediterranean walnut orchards.

Effects of temperature and leaf wetness duration on pathogens causing preharvest fruit rots on tomato

Preharvest fruit rots are serious tomato diseases. This study showed that Botrytis cinerea was a significant problem, and that Alternaria (A. alternata, A. solani) was the main pathogen identified from tomatoes showing the symptoms of preharvest fruit rots. Fusarium oxysporum and Rhizoctonia solani were also found causing important preharvest fruit rots in tomatoes. This is the first time F. oxysporum and R. solani have been identified in Greece as pathogens causing preharvest fruit rots on tomatoes. The optimal temperatures for A. alternata, A. solani, B. cinerea, and F. oxysporum mycelial growth and conidial germination were generally found to be between 20 and 30 °C, while the wetness duration of 24 hours seemed to be optimal for conidial germination and 84 hours for R. solani sclerotial germination. Based on the above findings, logistic regression models that adequately described the impact of pre-inoculation temperature and wetness on infection incidence in tomato fruit can be created. As the minimum, maximum, optimal temperatures and wetness duration are generally similar for the main pathogens causing preharvest fruit rots in tomato, it is possibly to develop a predicting predictive model to forecast the preharvest infection of tomato fruit. So enabling advice to be given to growers to when control methods should be applied.

A Bio‐Mimetic Leaf Wetness Sensor from Replica Molding of Leaves

AbstractPlant diseases cause hundreds of billions of dollars in global crop production each year. Many plant diseases develop when pathogens germinate and proliferate in the fertile environment of excess water on the leaf surfaces. Accurate measurement of how long a leaf stays wet is important to assess the risk of pathogen infestation and decide on appropriate management tactics. Commercial leaf wetness sensors estimate the duration of leaf wetness by monitoring the water accumulated on the sensor surface. However, this one‐size‐fits‐all sensor surface does not replicate the wetting behavior of specific leaves resulting in an imprecise measurement of leaf wetness. Here it is developed a leaf wetness sensor with replica molded surfaces that closely mimic the leaf of interest and provide a more accurate measurement of leaf wetness duration compared to commercial sensors. This simple approach allows for better prediction of leaf wetness duration for each plant species, affording individualized and more effective disease forecasting for the management of plant diseases.

Experimental Investigation of Leaf Wetness Sensing Properties of MoS2 Nanoflowers-Based Flexible Leaf Wetness Sensor

To abate crop loss, it is important to explore the plant disease management systems, where leaf wetness sensors (LWS) are widely used. The leaf wetness duration (LWD) extracted from the LWS is related to plant diseases. In this work, we have fabricated the LWS on the polyamide flexible substrate where Molybdenum disulfide (MoS <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) is used as the sensing film to explore the leaf wetness sensing mechanism. Further, we have passivated the MoS <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> with the help of acrylic protective lacquer (APL) conformal coating (MoS <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> + APL), which reduce the interaction of the water molecules with the sensor. Lab measurements indicated that fabricated LWS on the flexible substrate with MoS <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> and MoS <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> + APL as the sensing film offers a response of about ≈ 40 000% and ≈ 250%, respectively, at 500 Hz excitation frequency when the entire sensing area is filled with the water molecule. The response time of the MoS <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> and APL-coated flexible sensor is about 180 s. Fabricated LWS sensors offer hysteresis of about ± 4% in wetness. Further, we have identified that oxidation of the sulphur in the MoS <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> plays an important role in the leaf wetness sensing mechanism. Furthermore, we understood that MoS <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> when passivated with APL coating, the oxidation effect is reduced and the sensor response is negligible.

Impact of floating row cover and sensor placement on strawberry anthracnose and Botrytis fruit rot risk assessment

AbstractDuring the 2019–2020 and 2020–2021 growing seasons, six trials at four sites in Maryland and Virginia, USA were conducted, with leaf wetness and temperature sensors placed at 2 m height at the edge of the field (elevated sensor placement) or at the canopy level (0.5 m) on strawberry beds (canopy sensor placement). Temperature and leaf wetness duration (LWD) data from these sensors were used as input for anthracnose fruit rot (AFR) and Botrytis fruit rot (BFR) infection risk models, and fungicide spray trials were conducted to evaluate the ability of these predictions to control AFR and BFR. On average, the canopy level sensors reported significantly (p &lt; 0.05) longer LWD and higher temperature than elevated sensors during the fruit ripening period. The AFR and BFR risk calculated from the canopy sensors was also significantly higher than that from the elevated sensors. Fungicide spray programmes based on data from either canopy or elevated sensors resulted in fewer applications than weekly spray programmes, but the increased estimated risk based upon conditions within the canopy led to more applications than the elevated sensor treatment in four trials. In one trial with considerable incidence of BFR, plots that were sprayed based on the canopy sensor data controlled BFR significantly better than the elevated sensor spray programme. Springtime temperature, LWD, AFR risk and BFR risk were largely unaffected by autumn row cover deployment. The difference in temperature, LWD and AFR and BFR risk based on sensor placement warrants careful consideration of sensor placement when implementing a disease warning spray programme.

Analytical Evaluation of a Coplanar Interdigitated Sensor Capacitance for 1-N-1 Multilayered Structure

In this article, an analytical expression (model) for the capacitance of coplanar interdigitated (IDT) capacitive sensors of four 1- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula> -1 patterns (such as 1-1-1, 1-3-1, 1-5-1, and 1-11-1) based on conformal mapping (CM) techniques has been obtained. An important feature of the proposed model is that it is universal and independent of any specific application. The proposed model can be used for any number of layers (variable permittivity and thickness), finger width, and the gap between the fingers. In general, the capacitance of a particular IDT sensor depends on finger (electrode) length, the number of fingers, potential distribution of the fingers, dielectric permittivity (substrate and sensitive layers), and geometric parameters (nondimensional): 1) the ratio between the finger widths and gap and 2) the ratio between the top sensitive layer thickness and the sensor wavelength (spatial). Keeping these parameters in mind, comparisons with finite element analysis and experimental results have been made. Also, to confirm the effectiveness of the proposed model, different patterns of 1- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula> -1 structured IDT sensors have been developed to measure the water droplets on the leaf canopy by a noncontact method. The proposed sensor structure can be said to be a noncontact leaf wetness sensor (LWS), generally employed to quantify the leaf wetness duration (LWD).

Improved Estimation of Leaf Wetness Duration Using Deep-Learning-Based Time-Resolution Technique

Plant diseases are one of the leading causes of the loss of crops. Monitoring the plant growth conditions could help prevent the spread of diseases and ensure healthy agricultural productivity. A leaf wetness sensor (LWS) is used to detect wetness on the surface of the leaves. Leaf wetness duration (LWD) is an essential parameter that governs the possibility of the occurrence of diseases in plants. The sensor system used in this work for monitoring the environmental conditions transmits data every 30 min due to power consumption considerations. To improve the time resolution of the signal and accurate estimation of LWD, a deep-learning-based architecture is proposed. The data from LWS has been used to train the architecture and the results obtained have been compared with the existing methods to analyze its performance. Using the proposed architecture, the signal from LWS was benchmarked with the commercially available Phythos-31. The time resolution of data has been improved from ±30 to ±4 min. The average signal-to-noise ratio (SNR) values for three test signals with improved time resolution have increased from 19.36 to 22.16 dB. Similarly, the average root means square error (RMSE) of the estimated LWD values after time resolution improved from 0.55 to 0.20. During the experimental analysis, it has been observed that the proposed architecture estimates the LWD values better compared to the other time-resolution techniques.

Attention-Based Multi-Input Multi-Output Neural Network for Plant Disease Prediction Using Multisensor System

Disease detection and prevention in plants are crucial for generating healthy crops and securing the livelihood of farmers. Leaf wetness duration (LWD), ambient temperature, and relative humidity (RH) are essential parameters that lead to the germination of fungal diseases in plants. In this work, an in-house-developed leaf wetness sensor (LWS) is used to capture LWD, and commercial temperature and humidity sensors are used to record the ambient temperature and humidity, respectively. Subsequently, these sensors are interfaced with an in-house-developed Internet of Things (IoT)-enabled electronics and deployed (three sensor nodes) in the field. We have proposed an attention-based multi-input multi-output neural network (A-MIMONN) to predict diseases using self-collected data. The data for training the model are collected from the three sensors nodes, each comprising of temperature, humidity, and LWSs. The designed network is an ensemble of various submodels, trained individually using data from different sensor nodes. The findings of these individually trained networks are then combined to give the final output. The network is designed to achieve better results by employing the attention mechanism, reinforcing the influence of the most important feature on the predicted results. The average accuracy of the model was found to be about 94%. The model displayed a high average precision of 96% and a high average recall value of 97%. The average F1 score of 97% indicated an excellent balance of precision and accuracy.