Image-Based Automatic Diagnostic System for Tomato Plants Using Deep Learning

Tomato production is affected by various threats,including pests,pathogens,and nutritional deciencies during its growth process.If control is not timely,these threats affect the plant-growth,fruit-yield,or even loss of the entire crop,which is a key danger to farmers’livelihood and food security.Traditional plant disease diagnosis methods heavily rely on plant pathologists that incur high processing time and huge cost.Rapid and cost-effective methods are essential for timely detection and early intervention of basic food threats to ensure food security and reduce substantial economic loss.Recent developments in Articial Intelligence(AI)and computer vision allow researchers to develop image-based automatic diagnostic tools to quickly and accurately detect diseases.In this work,we proposed an AI-based approach to detect diseases in tomato plants.Our goal is to develop an end-to-end system to diagnose essential crop problems in real-time,ensuring high accuracy.This paper employs various deep learning models to recognize and predict different diseases caused by pathogens,pests,and nutritional deciencies.Various Convolutional Neural Networks(CNNs)are trained on a large dataset of leaves and fruits images of tomato plants.We compared the performance of ShallowNet(a shallow network trained from scratch)and the state-of-theart deep learning network(models are ne-tuned via transfer learning).In our experiments,DenseNet consistently achieved high performance with an accuracy score of 95.31%on the test dataset.The results verify that deep learning models with the least number of parameters,reasonable complexity,and appropriate depth achieve the best performance.All experiments are implemented in Python,utilizing the Keras deep learning library backend with TensorFlow.

Integrative analysis of the transcriptome and metabolome reveals the response mechanism to tomato spotted wilt virus

Tomato spotted wilt virus(TSWV)is an important virus that has rapidly spread throughout the world.TSWV seriously hinders the production of tomato(Solanum lycopersicum)and other plants.In order to discover more new genes and metabolites related to TSWV resistance in tomato plants,the genes and metabolites related to the resistance of tomato plants inoculated with TSWV were identified and studied herein.The tomato TSWV-resistance line YNAU335(335)and TSWV-susceptible lines NO5 and 96172I(961)were used as the transcriptome and metabolome research materials.Transcriptomic and metabolomic techniques were used to analyze the gene and metabolite response mechanisms to TSWV inoculation.A total of 3566,2951,and 2674 differentially expressed genes(DEGs)were identified in lines 335,NO5,and961,respectively.Meanwhile,208,228,and 273 differentially accumulated metabolites(DAMs)were identified in lines 335,NO5,and 961,respectively.In line 335,the number of DEGs was the highest,but the number of DAMs was lowest.Furthermore,903 DEGs and 94 DAMs were common to the response to TSWV in the three inbred lines.The 903 DEGs and 94 DAMs were mainly enriched in the plant hormone signal transduction and flavonoid synthesis pathways.In addition,many nucleotide-binding site-leucine-rich repeat genes and transcription factors were found that might be involved in the TSWV response.These results provide new insights into TSWV resistance mechanisms.

Detection of Potato Spindle Tuber Viroid, and Its Impact on Growth, Production of Tomatoes in Greenhouse

The viability of most tomato varieties cultivated in Libya have been tested to infect with potato spindle tuber viroid/potatoes （PSTVd） and its impact on growth and production of some of these varieties, which were mechanically inoculated with Libyan isolate of viroid PSTVd as follows： Vlkato, Sankarh, Lebda, Jasmine, Kenza and Hana. The percent of incidence were 95.95%, 90%, 90.80%, 80% and 20%, respectively. The following varieties have been contagious mechanically with viroid of PSTVd： Vlkato, zahra, Toria, Lebda, Hoda, Farwa, Alkaraz, Naziha, Rim Star and Kartika. The percent of incidence were 95.95%, 85%, 85.80%, 80%, 70.40%, 0.0%, 0.0%, respectively. The varied symptoms of wrinkle, twist, warp, swell the veins of the leaves, dark brown spots formation and a large yellow spots turned into white patches. Also the effect of the Egyptian isolate viroid PSTVd in the growth and production of varieties Jasmine, Lebda, Soberhalim, and treasure No. 185 had been studied, as the average rates of decline in the production of the fruits tomatoes/tomato 43.4% and 17% length of plants, and in the fresh weight and dry root of the sum of 35% and 37% respictively.

Functional identification of phenazine biosynthesis genes in plant pathogenic bacteria Pseudomonas syringae pv. tomato and Xanthomonas oryzae pv. oryzae

Phenazines are secondary metabolites with broad spectrum antibiotic activity and thus show high potential in biological control of pathogens. In this study, we identified phenazine biosynthesis （phz） genes in two genome-completed plant pathogenic bacteria Pseudomonas syringae pv. tomato （Pst） DC3000 and Xanthomonas oryzae pv. oryzae （Xoo） PXO99A. Unlike the phz genes in typical phenazine-producing pseudomonads, phz homologs in Pst DC3000 and Xoo PXO99A consisted of phzC/D/E/F/G and phzC/E1/E2/F/G, respectively, and the both were not organized into an operon. Detection experiments demonstrated that phenazine-l-carboxylic acid （PCA） of Pst DC3000 accumulated to 13.4 IJg L-1, while that of Xoo PXO99A was almost undetectable. Moreover, Pst DC3000 was resistant to 1 mg mL-1 PCA, while Xoo PXO99A was sensitive to 50 IJg mL ~ PCA. Furthermore, mutation of phzF blocked the PCA production and significantly reduced the pathogenicity of Pst DC3000 in tomato, while the complementary strains restored these phenotypes. These results revealed that Pst DC3000 produces low level of and is resistant to phenazines and thus is unable to be biologically controlled by phenazines. Additionally, phz-mediated PCA production is required for full pathogenicity of Pst DC3000. To our knowledge, this is the first report of PCA production and its function in pathogenicity of a plant pathogenic P. syringae strain.

Development of Pasteuria penetrans in Meloidogyne javanica females as affected by constantly high vs fluctuating temperature in an in-vivo system

Growth room and glasshouse experiment was conducted to investigate the effect of constant and fluctuating tem- peratures on the development of Pasteuria penetrans a hyperparasite of root-knot nematodes. Tomato plants (Lycopersicon es- culentum Mill) were inoculated with Meloidogyne javanica second-stage juveniles attached with endospores of P. penetrans and were grown in growth room at 26?29 °C and in glasshouse at 20?32 °C. The tomato plants were sampled from the growth room after 600 degree-days based on 17 °C/d, accumulating each day above a base temperature of 10 °C and from the glasshouse after 36 calendar days. Temperature affected the development of P. penetrans directly. The rate of development at constant temperature in growth room was faster than that in the glasshouse at fluctuating temperatures.

The Effect of Organic Biostimulants on Beneficial Soil Microorganism Activity

Organic biostimulants and organic fertilizers can improve soil health for various horticultural crops. The objectives of these experiments were to determine if biostimulants beneficially increase soil microorganism activity in soilless medium, and additionally measure the impact of synthetic and organic fertilizers with blackstrap molasses on plant nutrient uptake nutrient runoff. It was hypothesized that the addition of biostimulants will increase soil microbe activity. Evolution of soil carbon dioxide was measured by comparing different rates (0, 15, 30, and 45 mL/3.8 L of water) of blackstrap molasses using a randomized block design with 3 replications in nursery containers. Also, a second study using St. Augustinegrass and tomatoes fertilized with organic and synthetic fertilizers was evaluated with and without a biostimulant rate (30 mL/3.8 L of water). The plants were arranged in randomized complete block design with 6 replications. Soil biostimulants did significantly increase the microorganism activity at the 0.05 level. The highest rate of blackstrap molasses improved soil biological activity over a 4-week period. Additionally, fertilizer combined with molasses did show significant increases in soil microbiology for over 5 weeks for both tomatoes and St. Augustinegrass. Molasses increased soil microbial activity but not plant nutrition. Organic fertilizer though resulted in higher levels of phosphorus, calcium, magnesium, and sulfur in plant tissue. Further research is being conducted to measure the influence of biostimulants on the breakdown of composting plant matter. Organic fertilizer slightly increased soil water pH but reduced nutrient load pollution based on a 7-day nutrient effluent study. Total nutrients (nitrates, P, Ca, Mg, and S) runoff was significantly less than synthetic fertilizer. Organic fertilizer reduced nutrient dumping in waste effluent. Organic fertilizers can improve nutrient use efficiency.

On-site variety discrimination of tomato plant using visible-near infrared reflectance spectroscopy

The use of visible-near infrared (NIR) spectroscopy was explored as a tool to discriminate two new tomato plant varieties in China (Zheza205 and Zheza207). In this study, 82 top-canopy leaves of Zheza205 and 86 top-canopy leaves of Zheza207 were measured in visible-NIR reflectance mode. Discriminant models were developed using principal component analysis (PCA), discriminant analysis (DA), and discriminant partial least squares (DPLS) regression methods. After outliers detection, the samples were randomly split into two sets, one used as a calibration set (n=82) and the remaining samples as a validation set (n=82). When predicting the variety of the samples in validation set, the classification correctness of the DPLS model after optimizing spectral pretreatment was up to 93%. The DPLS model with raw spectra after multiplicative scatter cor- rection and Savitzky-Golay filter smoothing pretreatments had the best satisfactory calibration and prediction abilities (correlation coefficient of calibration (Rc)=0.920, root mean square errors of calibration=0.196, and root mean square errors of predic- tion=0.216). The results show that visible-NIR spectroscopy might be a suitable alternative tool to discriminate tomato plant varieties on-site.

Model for tomato photosynthetic rate based on neural network with genetic algorithm

A photosynthetic rate model provides a theoretical basis for fine-grained control of light,and has become the key component to determine the effectiveness of light-controlled environments.Therefore,it is critical to identify an intelligent algorithm that can be used to build an efficient and precise photosynthetic rate model.Depending on the initial weights of a BP(Back Propagation)neural network algorithm for arbitrary random numbers,the establishment of a regressive prediction model can be easily trapped in a partially-flat area.Existing photosynthetic rate models based on neural networks are facing problems such as a slow convergence speed and a long training time,and this study presents a photosynthetic rate model of a heuristic neural network for tomatoes based on a genetic algorithm to address the above problems.The performance of the model can be effectively improved using a genetic algorithm to optimize the initial weights.A multi-factor nesting experiment was firstly conducted to obtain 825 groups of tomato seedling photosynthesis rate test data in the foundation,and the photosynthetic rate model of the heuristic neural network for the tomato is established through BP network structure construction and data preprocessing.The genetic algorithm was used to optimize the network weights and threshold,and the LM(Levenberg-Marquardt)training method for network training.On this basis,the training performance and precision of the photosynthetic rate prediction models can be further compared with the genetic neural network model and the neural network model.The test results have shown that the training effects and accuracy of the genetic neural network prediction model of the photosynthetic rate were better than those of the neural network prediction model.The correlation coefficient between the model predicted data and the measured data is 0.987,and the absolute error of the photosynthetic rate is less than±0.5μmol/(m^(2)·s).

Response of tomato growth to continuous elevated CO_(2)concentration 2 under controlled environment

CO_(2)fumigation has been extensively used in greenhouses cultivation to enhance crop yield.The effects under the precise level of elevated CO_(2)(e[CO_(2)])on crop morphology,yield,and fruit quality remain largely elusive yet.To explore the response of plant growth to the continuous RCPs(Representative Concentration Pathways)projected CO_(2)concentration[CO_(2)],tomato(Hezuo 908)plants were grown under ambient CO_(2)(a[CO_(2)],462μmol/mol)and e[CO_(2)](550,700,850 and 1000μmol/mol):named as EC550,EC_(700),EC_(850),and EC_(1000),respectively,under uniform environmental condition for two planting seasons.Collective growth of tomato plants(plant height,stem diameter,and leaf area index)was significantly enhanced under EC_(700)and showed a slightly negative response under EC_(850).The optimum yield was stimulated under EC_(700)by 74.05%and 55.91%,while maximum total dry weight(DW_(t))was enhanced under EC_(1000)by 58.23%and 39.78%during autumn-winter and spring-summer planting seasons,respectively,as compared to a[CO_(2)].The greatest yield and least DWt stimulated under EC_(700)for both seasons indicated that EC_(700)improved the ability of the tomato plants to translocate carbohydrates to fruits.Optimum water use efficiency related to yield(WUE_(y))was enhanced by 55.91-210.87%under EC_(700)compared to a[CO_(2)].The titratable acid(TA)was improved by 19.94%(EC_(700)),29.17%(EC_(850)),and 97.92%(EC_(1000)),and the lycopene(Lp)was increased by 2.22%(EC_(700))and reduced by 2.28%(EC_(1000)).Thus,the overall optimum impact on tomato growth was explored under EC_(700).Super e[CO_(2)]did not positively influence the tomato growth process and yield under adequate water and fertilizer conditions.The present study results are beneficial for greenhouse crop production and might be used as a reference to validate the climate change influence modeling.