Explore the vast range of titles available.

Early and accurate tomato disease detection using easily available leaf photos is essential for farmers and stakeholders as it help reduce yield loss due to possible disease epidemics. This paper aims to visually identify nine different infectious diseases (bacterial spot, early blight, Septoria leaf spot, late blight, leaf mold, two-spotted spider mite, mosaic virus, target spot, and yellow leaf curl virus) in tomato leaves in addition to healthy leaves. We implemented EfficientNetB5 with a tomato leaf disease (TLD) dataset without any segmentation, and the model achieved an average training accuracy of 99.84% ± 0.10%, average validation accuracy of 98.28% ± 0.20%, and average test accuracy of 99.07% ± 0.38% over 10 cross folds.The use of gradient-weighted class activation mapping (GradCAM) and local interpretable model-agnostic explanations are proposed to provide model interpretability, which is essential to predictive performance, helpful in building trust, and required for integration into agricultural practice.

The management and marketing of fruit requires data on expected numbers, size, quality and timing. Current practice estimates orchard fruit load based on the qualitative assessment of fruit number per tree and historical orchard yield, or manually counting a subsample of trees. This review considers technological aids assisting these estimates, in terms of: (i) improving sampling strategies by the number of units to be counted and their selection; (ii) machine vision for the direct measurement of fruit number and size on the canopy; (iii) aerial or satellite imagery for the acquisition of information on tree structural parameters and spectral indices, with the indirect assessment of fruit load; (iv) models extrapolating historical yield data with knowledge of tree management and climate parameters, and (v) technologies relevant to the estimation of harvest timing such as heat units and the proximal sensing of fruit maturity attributes. Machine vision is currently dominating research outputs on fruit load estimation, while the improvement of sampling strategies has potential for a widespread impact. Techniques based on tree parameters and modeling offer scalability, but tree crops are complicated (perennialism). The use of machine vision for flowering estimates, fruit sizing, external quality evaluation is also considered. The potential synergies between technologies are highlighted.

Eight depth cameras varying in operational principle (stereoscopy: ZED, ZED2, OAK-D; IR active stereoscopy: Real Sense D435; time of flight (ToF): Real Sense L515, Kinect v2, Blaze 101, Azure Kinect) were compared in context of use for in-orchard fruit localization and sizing. For this application, a specification on bias-corrected root mean square error of 20 mm for a camera-to-fruit distance of 2 m and operation under sunlit field conditions was set. The ToF cameras achieved the measurement specification, with a recommendation for use of Blaze 101 or Azure Kinect made in terms of operation in sunlight and in orchard conditions. For a camera-to-fruit distance of 1.5 m in sunlight, the Azure Kinect measurement achieved an RMSE of 6 mm, a bias of 17 mm, an SD of 2 mm and a fill rate of 100% for depth values of a central 50 × 50 pixels group. To enable inter-study comparisons, it is recommended that future assessments of depth cameras for this application should include estimation of a bias-corrected RMSE and estimation of bias on estimated camera-to-fruit distances at 50 cm intervals to 3 m, under both artificial light and sunlight, with characterization of image distortion and estimation of fill rate.

The forecast of fruit weight at harvest requires (i) a non-destructive method for assessment of weight (Fw) of fruit-on-tree and (ii) the knowledge of fruit growth dynamics. To address the first issue for mango fruit, several allometric relationships between Fw and fruit-lineal dimensions of length (L), width (W), and thickness (T) were considered, with the relationship Fw=kLWT recommended. A k value of 0.5146 was established for fruit of the cultivar Honey Gold for fruit past the stone-hardening stage, based on assessment of 1091 fruit from 13 season/orchard populations and preliminary values of 0.5376, 0.5151, and 0.5239 for the Keitt, Kensington Pride, and R2E2, respectively, on the basis of more limited datasets. A combined cultivar model was recommended across all cultivars considered, except Keitt. The variation in k between populations of Keitt and Honey Gold fruit was due to the difference in fruit density, rather than shape. This conclusion should be tested in context of other cultivars and fruit development. A correction for developmental age was established for Honey Gold fruit, viz., kcorr=−0.0009× DAFB+0.5975 for fruit up to ~1224 growing degree days. The need for similar corrections for other cultivars should be investigated. For the second issue, the use of a linear function based on measurements of Fw in the weeks immediately before harvest was recommended for forecasting harvest-time weight to an accuracy of approximately 10%. A Logistic function described Fw increase better than a Gompertz function; however, a change in growing conditions during fruit development limits the reliability of such models for forecasting fruit weight at harvest maturity. Rather, it is proposed that a set of reference models based on a set of reference Logistic model parameters for a suite of growing conditions be developed for use in guiding agronomic interventions earlier in fruit development to maintain growth on a trajectory to achieve a desired weight at harvest.

A farm management information system (MIS) entails record keeping based on a database management system, typically using a client-server architecture, i.e., an information system, IS, coupled with a variety of tools/methods/models for the support of operational management. The current review adopts a multivocal approach to consider academic and commercial developments in MISs for orchard management, based primarily on the refereed literature but extending to grey literature and interviews of Australian mango orchard managers. Drivers for orchard MIS development include increasing the orchard size and management complexity, including regulatory requirements around labour, chemical spray use and fertilisation. The enablers include improvements in within-orchard communications, distributed (web) delivery systems using desktop and mobile devices, and sensor systems and predictive models, e.g., for pest management. Most orchard MIS-related publications target the commodities of apple, grape, mango and olive in the context of management of plant health (pest and disease), plant development, irrigation and labour management. Harvest forecast and MIS modules are only now beginning to emerge, in contrast to a long history of use in grain production. The commercial systems trend towards an incorporation of financial information, an integration of data from multiple sources and a provision of dashboards that are tailored to the user. Requirements for industry adoption of a MIS are discussed in terms of technical and design features, with a focus on usability and scalability.

A web mapping XYZ Tile Layer Service, such as Google Earth (GE), provides an amazing resource for the visualization of spatial data against aerial and satellite imagery with global coverage, typically at a resolution finer than 5 m. However, the increasing requirement on spatial accuracy in farm information requires a greater appreciation of the issues involved in the use of such services. Position errors can be created in the georeferencing and orthorectification of images, transformation between reference frames (datums) in map projection, e.g., using a spheroid as compared to an ellipsoid earth model, and tectonic shifts. A review is provided of these issues, and a case study is provided of the horizontal positional accuracy of web map imagery for Australian mango orchards. Positional accuracies varied from 1.804 to 6.131 m across four farms using GE 2021 imagery, between 1.556 and 3.365 m in one farm for the most recent imagery available from each of four web map providers, and from 0.806 m (in 2016) to 10.634 m (in 2003) in one farm for the period of 2003 and 2021 using the historical GE imagery resource. A procedure involving the estimation of four transformation parameters was demonstrated for the alignment of GNSS data with GE imagery. However, as the scale factor was unity and the rotational value was near zero, the use of a simple horizontal mean shift vector was recommended. Further recommendations are provided on (i) the use of web mapping services, with a comparison of the use of UAV survey imagery, and (ii) the need for metadata, particularly the date of collection, on collected position data, in the context of use in farm management information systems.

Mungbean is susceptible to waterlogging stress; therefore, breeding tolerant varieties would provide Australian growers with management options for wet summer season planting. Selection for waterlogging tolerance could be improved using vegetative indices that correlate to yield. Five mungbean genotypes were exposed to waterlogging stress at the pod-filling stage and characterised for various morphological and physiological traits governing seed yield. Waterlogging during pod filling decreased stomatal conductance (gs) and photosynthetic rate (Asat) to ~27% and 25% compared to control, respectively, resulting in a decline in effective quantum yield of PSII (ФPSII) and maximum efficiency of PSII of dark-adapted leaves (Fv/Fm) and leaf chlorophyll while increasing excitation pressure (1-qP) significantly. Waterlogging at pod filling reduced leaf count (19%), plant height (23%), leaf dry weight (38%), stem dry weight (33%), pod dry weight (36%), above-ground biomass (34%), root biomass (26%), and 100-seed weight (4%). Seed yield was highly positively correlated with Asat (0.86), gs (0.69), chlorophyll content (0.63), and ФPSII (0.59), with a highly negative correlation with 1-qP (−0.87) at 30 days of treatment imposition. A yield penalty of 32% was recorded under waterlogging stress compared to control plants, while the performance of all genotypes was found to be similar in terms of seed yield. Interestingly, genotype AVTMB#3 produced significantly larger seeds under waterlogging stress relative to other genotypes, including the leading Australian mungbean variety, Jade-AU. Based on a robust and significantly strong correlation with seed yield under waterlogging stress, 1-qP and photosynthetic rates (Asat) are recommended as potential indicators for the screening of mungbean genotypes. Thus, the current study presents a framework for screening waterlogging tolerance, which can provide a reasonable basis for the selection of various genotypes in future mungbean breeding programs.

The performance of a multi-view machine vision method was documented at an orchard level, relative to packhouse count. High repeatability was achieved in night-time imaging, with an absolute percentage error of 2% or less. Canopy architecture impacted performance, with reasonable estimates achieved on hedge, single leader and conventional systems (3.4, 5.0, and 8.2 average percentage error, respectively) while fruit load of trellised orchards was over-estimated (at 25.2 average percentage error). Yield estimations were made for multiple orchards via: (i) human count of fruit load on ~5% of trees (FARM), (ii) human count of 18 trees randomly selected within three NDVI stratifications (CAL), (iii) multi-view counts (MV-Raw) and (iv) multi-view corrected for occluded fruit using manual counts of CAL trees (MV-CAL). Across the nine orchards for which results for all methods were available, the FARM, CAL, MV-Raw and MV-CAL methods achieved an average percentage error on packhouse counts of 26, 13, 11 and 17%, with SD of 11, 8, 11 and 9%, respectively, in the 2019–2020 season. The absolute percentage error of the MV-Raw estimates was 10% or less in 15 of the 20 orchards assessed. Greater error in load estimation occurred in the 2020–2021 season due to the time-spread of flowering. Use cases for the tree level data on fruit load was explored in context of fruit load density maps to inform early harvesting and to interpret crop damage, and tree frequency distributions based on fruit load per tree.

Inconsistent yield of subtropical table grape across seasons is often associated with low carbohydrate reserves during flowering. In an attempt to increase TNC and thus yield, sucrose was injected into treated trunks during periods of high carbohydrate demand (i.e., between budburst and flowering). Total non-structural carbohydrate (TNC) concentration dynamics were assessed in the grapevine root and trunk tissues of both control and treated vines. In the control (untreated) vines, the TNC concentration in root and trunk tissues was 13.5% and 7.5% w/dw at leaf fall and 7.2% and 3.7% w/dw at flowering, respectively. This decrease in carbohydrate reserve was estimated at ~500 g/vine and is associated with the re-establishment of the plant canopy in early spring. Carbohydrate reserves remained stable or rose slightly between flowering and harvest and recovered between crop harvest and leaf fall. In treated vines, a constantly pressurised low-pressure in situ trunk injection system (69 kPa) with 5% w/v sucrose solution over 45 days from budburst (to flowering), in each of the two seasons, delivered a widely variable amount of sucrose into each vine with variation ascribed to the amount of internal dead wood in the trunk. In the best circumstances, an average of 150 g sucrose/vine/season was injected, and sucrose-injected vines had higher trunk TNC reserve (4.1% compared to 3.6% w/dw in the control) at flowering. A δ13C (‰) analysis confirmed the presence of injected sucrose in the shoot at flowering. However, the correlation between the amount of loaded sucrose and δ13C in young shoot tissue was poor, indicative of variable partitioning patterns. Inflorescence number per vine and berry yield were markedly higher in sucrose-injected vines, but differences were not significant given the high variation between vines. The addition of KCl to the sucrose solution and use of the healthy vines are recommended to increase sucrose loading using the injection method to address inconsistent yielding of subtropical table grape.

A method based on Vis-NIR spectroscopy and machine learning-based modeling for non-destructive detection of the internal disorders of black flesh, spongy tissue, jelly seed, and soft nose in mango fruit was developed using the vis-NIR spectra of intact mango fruit of three cultivars sourced from three orchards in each of the two seasons, with spectra collected both at harvest and after storage. After spectra were acquired of the stored fruit, the fruit cheeks were cut longitudinally to allow visual assessment of the incidence of the internal disorders. Five models were evaluated: two tree-based algorithms (J48 and random forest), one neural network (multilayer perceptron, MLP), and two SVM training algorithms (sequential minimal optimization, SMO, and LibSVM). The models were evaluated using a tenfold cross-validation approach. Non-destructive discrimination of health from all disordered and healthy fruit from fruit with specific disorders was achieved with an accuracy ranging from 72.3 to 97.0% when using spectra collected at harvest and 63.7 to 96.2% when using spectra collected after ripening. No one machine learning algorithm out-performed other methods—for spectra collected at harvest, the highest discrimination accuracy was achieved with RF and MLP for black flesh, J48 for spongy tissue, and LibSVM for soft nose and jelly seed. For spectra collected of stored fruit, the highest discrimination accuracy was achieved with SMO for jelly seed and RF for soft nose. A recommendation is made for the consideration of ensemble models in future. The ability to predict the development of the disorder using spectra of at-harvest fruit offers the potential to guide postharvest practices and reduce incidence of internal disorders in mangoes.