Can Satellites Predict Yield? Ensemble Machine Learning and Statistical Analysis of Sentinel-2 Imagery for Processing Tomato Yield Prediction.

In this paper, we propose an innovative approach for robust prediction of processing tomato yield using open-source AutoML techniques and statistical analysis. Sentinel-2 satellite imagery was deployed to obtain values of five (5) selected vegetation indices (VIs) during the growing season of 2021 (April to September) at 5-day intervals. Actual recorded yields were collected across 108 fields, corresponding to a total area of 410.10 ha of processing tomato in central Greece, to assess the performance of Vis at different temporal scales. In addition, VIs were connected with the crop phenology to establish the annual dynamics of the crop. The highest Pearson coefficient (r) values occurred during a period of 80 to 90 days, indicating the strong relationship between the VIs and the yield. Specifically, RVI presented the highest correlation values of the growing season at 80 (r = 0.72) and 90 days (r = 0.75), while NDVI performed better at 85 days (r = 0.72). This output was confirmed by the AutoML technique, which also indicated the highest performance of the VIs during the same period, with the values of the adjusted R2 ranging from 0.60 to 0.72. The most precise results were obtained with the combination of ARD regression and SVR, which was the most successful combination for building an ensemble (adj. R2 = 0.67 ± 0.02).

Predicting Grape Sugar Content under Quality Attributes Using Normalized Difference Vegetation Index Data and Automated Machine Learning.

Wine grapes need frequent monitoring to achieve high yields and quality. Non-destructive methods, such as proximal and remote sensing, are commonly used to estimate crop yield and quality characteristics, and spectral vegetation indices (VIs) are often used to present site-specific information. Analysis of laboratory samples is the most popular method for determining the quality characteristics of grapes, although it is time-consuming and expensive. In recent years, several machine learning-based methods have been developed to predict crop quality. Although these techniques require the extensive involvement of experts, automated machine learning (AutoML) offers the possibility to improve this task, saving time and resources. In this paper, we propose an innovative approach for robust prediction of grape quality attributes by combining open-source AutoML techniques and Normalized Difference Vegetation Index (NDVI) data for vineyards obtained from four different platforms-two proximal vehicle-mounted canopy reflectance sensors, orthomosaics from UAV images and Sentinel-2 remote sensing imagery-during the 2019 and 2020 growing seasons. We investigated AutoML, extending our earlier work on manually fine-tuned machine learning methods. Results of the two approaches using Ordinary Least Square (OLS), Theil-Sen and Huber regression models and tree-based methods were compared. Support Vector Machines (SVMs) and Automatic Relevance Determination (ARD) were included in the analysis and different combinations of sensors and data collected over two growing seasons were investigated. Results showed promising performance of Unmanned Aerial Vehicle (UAV) and Spectrosense+ GPS data in predicting grape sugars, especially in mid to late season with full canopy growth. Regression models with both manually fine-tuned ML (R² = 0.61) and AutoML (R² = 0.65) provided similar results, with the latter slightly improved for both 2019 and 2020. When combining multiple sensors and growth stages per year, the coefficient of determination R² improved even more averaging 0.66 for the best-fitting regressions. Also, when considering combinations of sensors and growth stages across both cropping seasons, UAV and Spectrosense+ GPS, as well as Véraison and Flowering, each had the highest average R² values. These performances are consistent with previous work on machine learning algorithms that were manually fine-tuned. These results suggest that AutoML has greater long-term performance potential. To increase the efficiency of crop quality prediction, a balance must be struck between manual expert work and AutoML.

Agricultural Robotics for Field Operations.

Modern agriculture is related to a revolution that occurred in a large group of technologies (e.g., informatics, sensors, navigation) within the last decades. In crop production systems, there are field operations that are quite labour-intensive either due to their complexity or because of the fact that they are connected to sensitive plants/edible product interaction, or because of the repetitiveness they require throughout a crop production cycle. These are the key factors for the development of agricultural robots. In this paper, a systematic review of the literature has been conducted on research and commercial agricultural robotics used in crop field operations. This study underlined that the most explored robotic systems were related to harvesting and weeding, while the less studied were the disease detection and seeding robots. The optimization and further development of agricultural robotics are vital, and should be evolved by producing faster processing algorithms, better communication between the robotic platforms and the implements, and advanced sensing systems.

SpectroFood dataset: A comprehensive fruit and vegetable hyperspectral meta-dataset for dry matter estimation.

In the dataset presented in this article, samples belonging to one of the following crops, apple, broccoli, leek, and mushroom, were measured by hyperspectral cameras in the visible/near-infrared spectral domain (430-900 nm). The dataset was compiled by putting together measurements from different calibrated hyperspectral imaging cameras and crops to facilitate the training of artificial intelligence models, helping to overcome the generalization problem of hyperspectral models. In particular, this dataset focuses on estimating dry matter content across various crops by a single model in a non-destructive way using hyperspectral measurements. This dataset contains extracted mean reflectance spectra for each sample (n=1028) and their respective dry matter content (%).

Assessment of microbial biocontrol agent (BCA) viability to mechanical and thermal stress by simulating spray application conditions.

BACKGROUND: In order to improve the biological control agent (BCA) efficacy, stress factors threatening the viability of microorganisms during spray application need to be determined. The effect of spray mixture temperature and exposure time on Trichoderma harzianum T 22 and Bacillus amyloliquefaciens QST713 viability were tested. Concurrently the combined effect of mechanical and thermal stress effect on BCA viability were tested at two initial spray mixture temperatures (14 and 25 °C) by simulating a spray application using airblast sprayers featured by different tank capacity and a spray liquid circuit (without and with hydraulic agitation system). To assess the BCA microorganism viability, spray mixture samples were collected at time intervals along trials and plated to count the colony forming units (CFU). RESULTS: The critical temperature threshold that inhibited BCA viability was 35 °C with 30 min of exposure. The sprayer type, the initial temperature of the spray mixture and the temperature increment during the trials significantly decreased the number of CFU recovered. When simulating a spray application, the spray mixture temperature increase rate was determined mainly by the residual amount of spray mixture in the tank. Even if the tank capacity does not substantially affect the final temperature reached by the spray mixture, the higher residual spray mixture in bigger tanks can expose the BCAs for a longer time to critical temperatures. CONCLUSIONS: Experimental trials allowed us to identify the effect of factors affecting the viability of tested BCAs, providing information about the actual chance to guarantee the biological efficacy of BCA treatments. © 2023 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Investigating a Selection of Methods for the Prediction of Total Soluble Solids Among Wine Grape Quality Characteristics Using Normalized Difference Vegetation Index Data From Proximal and Remote Sensing.

The most common method for determining wine grape quality characteristics is to perform sample-based laboratory analysis, which can be time-consuming and expensive. In this article, we investigate an alternative approach to predict wine grape quality characteristics by combining machine learning techniques and normalized difference vegetation index (NDVI) data collected at different growth stages with non-destructive methods, such as proximal and remote sensing, that are currently used in precision viticulture (PV). The study involved several sets of high-resolution multispectral data derived from four sources, including two vehicle-mounted crop reflectance sensors, unmanned aerial vehicle (UAV)-acquired data, and Sentinel-2 (S2) archived imagery to estimate grapevine canopy properties at different growth stages. Several data pre-processing techniques were employed, including data quality assessment, data interpolation onto a 100-cell grid (10 × 20 m), and data normalization. By calculating Pearson's correlation matrix between all variables, initial descriptive statistical analysis was carried out to investigate the relationships between NDVI data from all proximal and remote sensors and the grape quality characteristics in all growth stages. The transformed dataset was then ready and applied to statistical and machine learning algorithms, firstly trained on the data distribution available and then validated and tested, using linear and nonlinear regression models, including ordinary least square (OLS), Theil-Sen, and the Huber regression models and Ensemble Methods based on Decision Trees. Proximal sensors performed better in wine grapes quality parameters prediction in the early season, while remote sensors during later growth stages. The strongest correlations with the sugar content were observed for NDVI data collected with the UAV, Spectrosense+GPS (SS), and the CropCircle (CC), during Berries pea-sized and the Veraison stage, mid-late season with full canopy growth, for both years. UAV and SS data proved to be more accurate in predicting the sugars out of all wine grape quality characteristics, especially during a mid-late season with full canopy growth, in Berries pea-sized and the Veraison growth stages. The best-fitted regressions presented a maximum coefficient of determination (R 2) of 0.61.

A multi-source data fusion approach to assess spatial-temporal variability and delineate homogeneous zones: A use case in a table grape vineyard in Greece.

Precision Viticulture requires very fine-scale spatial and temporal resolution to assess quite accurately variation in a vineyard. Many studies have used proximal sensing technology and spatial-temporal data analysis to characterize the local variation of plant vigour over time. The objective of this study was to present the potential of multivariate geostatistical techniques to fuse multi-temporal data from a multi-band radiometer and a geophysical sensor with different support for delineation of a vineyard into homogeneous zones, to be submitted to differential agricultural management. The study was conducted in a commercial table grape vineyard located in southern Greece during the years 2016 and 2017. Soil electrical conductivity was measured using an EM38 sensor, while Crop Circle canopy sensor, with the sensor located at 1.5 m height from the soil surface and 1.2 m horizontally from the vines, was used for scanning the side canopy area at different crop stages. The temporal multi-sensor data were analysed with the geostatistical data fusion techniques of block cokriging, to produce thematic maps, and factorial block cokriging to estimate synthetic scale-dependent regionalized factors. The factor maps at different scales are characterised by random variability with several micro-structures of different plant and soil properties, which leads to difficulties in delineating macro-areas with homogeneous features. In such conditions, high resolution VRA technology should be preferred to management by homogeneous zones for precision viticulture. The results have shown the potential of the proposed approach to deal with multi-source data in precision viticulture. However, further statistical research on data fusion of the outcomes from different sensors is still needed.