Plants diseases constitute a substantial threat for farmers given the high economic and environmental impact of their treatment. Detecting possible pathogen threats in plants based on non-destructive remote sensing and computer vision methods offers an alternative to existing laboratory methods and leads to improved crop management. Vine is an important crop that is mainly affected by fungal diseases. In this study, photos from healthy leaves and leaves infected by a fungal disease of vine are used to create disease identification classifiers. The transfer learning technique was employed in this study and was used to train three different deep convolutional neural network (DCNN) approaches that were compared according to their classification accuracy, namely AlexNet, VGG-19, and Inception v3. The above-mentioned models were trained on the open-source PlantVillage dataset using two training approaches: feature extraction, where the weights of the base deep neural network model were frozen and only the ones on the newly added layers were updated, and fine tuning, where the weights of the base model were also updated during training. Then, the created models were validated on the PlantVillage dataset and retrained using a custom field-grown vine photo dataset. The results showed that the fine-tuning approach showed better validation and testing accuracy, for all DCNNs, compared to the feature extraction approach. As far as the results of DCNNs are concerned, the Inception v3 algorithm outperformed VGG-19 and AlexNet in almost all the cases, demonstrating a validation performance of 100% for the fine-tuned strategy on the PlantVillage dataset and an accuracy of 83.3% for the respective strategy on a custom vine disease use case dataset, while AlexNet achieved 87.5% validation and 66.7% accuracy for the respective scenarios. Regarding VGG-19, the validation performance reached 100%, with an accuracy of 76.7%.

Irrigation plays a crucial role in maize cultivation, as watering is essential for optimizing crop yield and quality, particularly given maize’s sensitivity to soil moisture variations. In the current study, a hybrid Long Short-Term Memory (LSTM) approach is presented aiming to predict irrigation scheduling in maize fields in Bursa, Turkey. A critical aspect of the study was the use of the Aquacrop 7.0 model to simulate soil moisture content (MC) data due to data limitations in the investigated fields. This simulation model, developed by the Food and Agriculture Organization (FAO), helped overcome gaps in soil sensor data, enhancing the LSTM model’s predictions. The LSTM model was trained and tuned using a combination of soil, weather, and satellite-based plant vegetation data in order to predict soil moisture content (MC) reductions. The study’s results indicated that the LSTM model, supported by Aquacrop 7.0 simulations, was effective in predicting MC reduction across various time phases of the maize growing season, attaining R² values ranging from 0.8163 to 0.9181 for Field 1 and from 0.7602 to 0.8417 for Field 2, demonstrating the potential of this approach for precise and efficient agricultural irrigation practices.

Coastal delta plains are areas with high agricultural potential for the Mediterranean region because of their high soil fertility, but they also constitute fragile systems in terms of water resources management because of the interaction of underlying aquifers with the sea. Such a case is the Pinios River delta plain located in central Greece, which also constitutes a significant ecosystem. Soil and Water Assessment Tool (SWAT) and SEAWAT models were combined in order to simulate the impact of current water resources management practices in main groundwater budget components and groundwater salinization of the shallow aquifer developed in the area. Moreover, potential climate change impact was investigated using climate data from Regional Climate Model for two projected periods (2021–2050 and 2071–2100) and two sea level rise scenarios (increase by 0.5 and 1 m). Modeling results are providing significant insight: although the contribution of the river to groundwater inflows is significant, direct groundwater recharge from precipitation was found to be higher, while capillary rise constitutes a major part of groundwater outflows from the aquifer. Moreover, during the simulation period, groundwater flow from the aquifer to the sea were found to be higher than the inflows of seawater to the aquifer. Regarding climate change impact assessment, the results indicate that the variability in groundwater recharge posed by the high variability of precipitation during the projected periods is increasing the aquifer’s deterioration potential of both its quantity and quality status, the latter expressed by the increased groundwater Cl⁻ concentration. This evidence becomes more significant because of the limited groundwater storage capacity of the aquifer. Concerning sea level rise, it was found to be less significant in terms of groundwater salinization impact compared to the decrease in groundwater recharge and increase in crop water needs.

Calibration equations for two capacitance water content probes: This paper presents the calibration equations of two capacitance probes for monitoring the soil water content in a lysimeter field. Capacitance probes provide readings at desired depths and time intervals. The calibration equations are derived by regression analysis between measurements of scaled frequency and volumetric soil water content. The calibration equations are compared with the manufacturer default equations to estimate the irrigation water depth. The accuracy of capacitance probes in monitoring soil water content increased by using the site-specific calibration equations rather than the manufacturer default equation.

The current study investigates the use of a non-destructive hyperspectral imaging approach for the evaluation of kiwifruit cv. “Hayward” internal quality, focusing on physiological traits such as soluble solid concentration (SSC), dry matter (DM), firmness, and tannins, widely used as quality attributes. Regression models, including partial least squares regression (PLSR), bagged trees (BTs), and three-layered neural network (TLNN), were employed for the estimation of the above-mentioned quality attributes. Experimental procedures involving the Specim IQ hyperspectral camera utilization and software were followed for data acquisition and analysis. The effectiveness of PLSR, bagged trees, and TLNN in predicting the firmness, SSC, DM, and tannins of kiwifruit was assessed via statistical metrics, including R squared (R²) values and the root mean square error (RMSE). The obtained results indicate varying degrees of efficiency for each model in predicting kiwifruit quality parameters. The study concludes that machine learning algorithms, especially neural networks, offer substantial accuracy, surpassing traditional methods for evaluating kiwifruit quality traits. Overall, the current study highlights the potential of such non-destructive techniques in revolutionizing quality assessment during postharvest by yielding rapid and reliable predictions regarding the critical quality attributes of fruits.