Beatriz Lorente

Grapevine is an essential socio-economic crop in the Mediterranean regions. However, its cultivation is threatened by climate change, particularly due to the increase in drought events. Traditional indicators of plant water status, i.e., predawn leaf water potential (Ψ _pd ), are helpful but labor-intensive. Furthermore, another index based on visual assessment of the shoot apex (i.e., iG-Apex), has been recently used to evaluate the water stress of grapevine plants. The application of remote sensing technologies and machine learning models gives the possibility to monitor grapevine spatio-temporal variability of plant physiological indicators in a non-destructive way. This study aims to develop an explainable artificial intelligence (XAI) framework to predict Ψ _pd and iG-Apex in two rainfed vineyards using high-resolution multispectral imagery from the Planet SuperDove constellation. Five machine learning models—extreme gradient boosting, random forest, support vector regressor, ElasticNet, and Linear Regression—were trained and compared. Extreme gradient boosting achieved the best performance for Ψ _pd prediction (R² = 0.778), while random forest outperformed for iG-Apex prediction (R² = 0.615). SHAP and ICE analyses were carried out for models’ explainability. The analyses revealed that visible and NIR bands were the most important predictors, influencing both Ψ _pd and iG-Apex prediction. Our results highlight the potential of combining XAI and remote sensing to support grapevine management under Mediterranean conditions, providing a useful tool for early water stress detection.

Climate change and increasing drought in the Mediterranean regions provoke serious challenges to agriculture, especially for rainfed crops. Carob tree (Ceratonia siliqua L.) is a resilient tree that is cultivated in dry and poor soils, but the absence of precise data on its irrigation needs limits the possibility of improving its production. In our research, we evaluate the irrigation needs and physiological response of carob trees by applying different irrigation strategies and using precision irrigation technologies.The experiment was conducted from 2022/2024 at an 8-ha commercial carob tree orchard in the region of Murcia, Spain, with subsurface drip irrigation (SDI) installation. Three irrigation strategies were applied: full irrigation (FI), deficit irrigation (DI), and no irrigation (rainfed). Precision irrigation tools were used for supplemental irrigation during the critical growth periods. It is proven that supplemental irrigation, in addition to rainfall, can increase the yield. Soil probes and dendrometers were used to record moisture content and indicate the water stress. Additionally, stomatal conductance (gs) and stem water potential was measured.The SDI system played a key role, as it allows for a more precise distribution of water directly in the root zone, improving the tree's access to water and reducing losses due to evaporation. From the physiological point of view, the stomatal conductance was the best indicator, responding faster to water supply. In terms of sensors, the combination of soil moisture sensors (at 30 and 60cms) to understand the correct soil water distribution, and dendometers which at each phenological stage (Bud-break, summer stop and post-summer growth) allow to determine whether the trees were growing, in standby, or water stress. The results showed increased fruit production and more consistent yields with full irrigation treatment, suggesting it supports uniform growth. However, variability due to factors like root damage through SDI installation, own variety variability, soil and alternate bearing was noted. The integration for the new seasons of new tools as remote sensing and machine learning will help reduce deviations.This experiment has demonstrated the value of carob cultivation as an alternative, profitable and sustainable production, since this crop survives with low irrigation water quality and very low irrigation supplies, from 100 to 200 mm/year, applying complementary and deficit irrigation strategies.

Chlorophyll fluorescence is a useful indicator of a plant’s physiological status, particularly under stress conditions. Remote sensing is an increasingly adopted technology in modern agriculture, allowing the acquisition of crop information (e.g., chlorophyll fluorescence) without direct contact, reducing fieldwork. The objective of this study is to improve the monitoring of olive tree fluorescence (Fv′/Fm′) via remote sensing in a Mediterranean environment, where the frequency of stress factors, such as drought, is increasing. An advanced approach combining explainable artificial intelligence and multispectral Sentinel-2 satellite data was developed to predict olive tree fluorescence. Field measurements were conducted in southeastern Italy on two olive groves: one irrigated and the other one under rainfed conditions. Sentinel-2 reflectance bands and vegetation indices were used as predictors and different machine learning algorithms were tested and compared. Random Forest showed the highest predictive accuracy, particularly when Sentinel-2 reflectance bands were used as predictors. Using spectral bands preserves more information per observation, enabling models to detect variations that VIs might miss. Additionally, raw reflectance data minimizes potential bias that could arise from selecting specific indices. SHapley Additive exPlanations (SHAP) analysis was performed to explain the model. Random Forest showed the highest predictive accuracy, particularly when using Sentinel-2 reflectance bands as predictors. Key spectral regions associated with Fv′/Fm′, such as red-edge and NIR, were identified. The results highlight the potential of integrating remote sensing and machine learning to improve olive grove management, providing a useful tool for early stress detection and targeted interventions.

Climate change is making water management increasingly difficult due to rising temperatures and unpredictable rainfall patterns, impacting crop water availability and irrigation needs. This study investigated the ability of machine learning and satellite remote sensing to monitor water status and physiology. The research focused on predicting different eco-physiological parameters in an irrigated peach orchard under Mediterranean conditions, utilizing multispectral reflectance data and machine learning algorithms (extreme gradient boosting, random forest, support vector regressor); ground data were acquired from 2021 to 2023 in the south of Italy. The random forest model outperformed in predicting net assimilation (R² = 0.61), while the support vector machine performed best in predicting electron transport rate (R² = 0.57), Fv/Fm ratio (R² = 0.66) and stomatal conductance (R² = 0.56). Random forest also proved to be the most effective in predicting stem water potential (R² = 0.62). These findings highlighted the potential of integrating machine learning techniques with high-resolution satellite imagery to assist farmers in monitoring crop health and optimizing irrigation practices, thereby addressing the challenges determined by climate change.

El Mediterráneo es una de las áreas más sensibles del planeta y está altamente expuesto al riesgo de sequía. El cambio climático y la explotación excesiva de los recursos naturales desembocarán en una reducción aún mayor de la disponibilidad de agua, energía y alimentos, así como a un desequilibrio en el ecosistema. Esto tendrá un impacto significativo en la capacidad de adaptación de los sistemas alimentarios y afectará la calidad de vida de la población; por lo que, para hacer frente a esta situación crítica, se requiere la implementación de nuevos sistemas agrícolas. Los principales problemas de la agricultura de la Región de Murcia son la escasez de recursos hídricos y su calidad, principalmente la salinidad. Por ello, es necesario optimizar la gestión de recursos hídricos naturales, sin afectar a la producción, mediante cultivos que puedan desarrollarse bajo estas condiciones, como pueda ser el caso del algarrobo. La información bibliográfica sobre este cultivo es escasa y, la mayoría, se centra en árboles jóvenes en condiciones no semiáridas; por lo que el objetivo de este ensayo es analizar los efectos fisiológicos de regar una parcela comercial de algarrobos (7 años), bajo una estrategia de riego por goteo subterráneo (RGS) con una mezcla de agua de lluvia recogida y agua de pozo salina con una conductividad eléctrica (CE) media de 1,76 dS/m, estableciendo valores umbrales de riego en los periodos fenológicos críticos y ver su efecto en producción y calidad del fruto. Tras diferentes aplicaciones de riego (uno de 12 horas, un segundo riego de 12 horas (dividido en dos períodos de 6 horas) y un tercer riego de 6 horas) y análisis de los datos fisiológicos y de los sensores, observamos que la reacción del cultivo en los dos últimos riegos, es similar. Comprobamos como los niveles de fotosíntesis neta (Pn) y conductancia estomática (gs) aumentaron en el último riego respecto a los anteriores y, en cuanto al potencial hídrico de hoja (Ψl) y la temperatura foliar (Tª), los valores obtenidos disminuyeron en el riego de 6 horas. A nivel de suelo, se observó cómo se mantuvieron niveles de agua similares en las zonas más profundas de desarrollo radicular. Por lo tanto, en base a estos resultados preliminares, establecemos los valores umbrales iniciales de riego hasta la recolección del fruto con riegos de 6 horas, ya que obtuvimos resultados fisiológicos y de contenido de agua en el suelo similares que con un riego de 12 horas (6+6 h), reduciendo así el consumo de agua y esperando obtener una mayor productividad de la misma en término de Kg algarrobo/m3.

Plant growth regulators (PGRs) are commonly used in horticulture to improve crop quality, save water, and enhance plant resilience to stress. In this study, we examined the effects of two PGRs, paclobutrazol (PBZ) and mepiquat chloride (MC), on the growth and health of Salvia officinalis ‘Icterina’, a popular ornamental and aromatic plant. Parameters such as growth and development, water status, chlorophyll levels, nutrient content, photosynthetic performance, and gas exchange were evaluated. The study took place in a greenhouse with automatic watering and three plant groups: one treated with PBZ, another with MC, and a control group (untreated). Only one application of growth retardants was made, with 0.1 L per pot of a 100 mg/L solution of PBZ, and 0.1 L per pot of a 2.5 g/L solution of MC. The results showed that both PBZ and MC treatments reduced the plant’s water consumption, with PBZ being more effective in limiting leaf growth and promoting the accumulation of substances in the leaves. Both PGRs resulted in smaller plants, reducing the need for soil and potting materials. The MC treatment improved nutrient absorption, reducing the requirement for fertilizers. When subjected to environmental stress from March to June in the greenhouse, Salvia plants benefited from the application of both PGRs, as they helped maintain photosynthetic activity. These findings contribute to improving the sustainability of nursery practices by utilizing PGRs to conserve resources and mitigate the impact of stressful environmental conditions on sage plants.

The objective of this study was to identify the physiological mechanisms used by Cistus heterophyllus Desf. Subsp. carthaginensis (Pau) M. B. Crespo & Mateo, a species in critical danger of extinction, to cope with two typical abiotic conditions. During the summer of 2021, plants were cultivated under a shade mesh that intercepted 50% of the incident solar radiation (SHADE) and in natural conditions (SUN). Three irrigation treatments were also applied: control, T1, moderate water deficit; T2, 60% of the control, severe deficit; and T3, 30% of the control. Therefore, there were six treatments (SUN-T1, SUN-T2, SUN-T3, SHADE-T1, SHADE-T2, SHADE-T3). Plants were more affected by solar radiation than by deficit irrigation. Although leaf water potential, stomatal conductance and root biomass decreased by up to 45%, 63% and 65%, respectively, as deficit irrigation increased, plants were able to develop a leaf osmotic adjustment and an improved intrinsic water-use efficiency to maintain their growth and survival rate. Shade conditions improved gas exchange, reduced leaf temperature and induced the synthesis of chlorophylls, regardless of the irrigation level imposed. This indicated that radiation was the most limiting factor in our experiment. Applying 50% of the radiation and a moderate water deficit would help to obtain a good plant development and high survival rate in future recovery and conservation programs for the species.

The use of reclaimed water is considered an efficient tool for agricultural irrigation; however, the high salinity associated to this water could compromise plant quality and yields. Balm and spearmint plants were submitted for 15 days to three irrigation treatments in a controlled chamber: control with EC: 1.2 dS m⁻¹ (control), reclaimed water from secondary effluent (EC: 1.6 dS m⁻¹) (S) and water from secondary effluent with brine (EC: 4.4 dS m⁻¹) (SB). The plant water status, stomatal and hormonal regulation, nutritional response, concentration of amino acids and plant oxidative stress-based markers, as well as growth were evaluated. Both species irrigated with saline reclaimed water reduced leaf water potential and gas exchange in comparison with control plants, following 2 days of exposure to irrigation treatments. Nevertheless, spearmint plants recovered photosynthetic activity from the seventh day onwards, maintaining growth. This was attributed to hormonal changes and a greater accumulation of some amino acids and some plant oxylipins (phytoprostanes) in comparison to balm plants, which contributed to the improvement in the organoleptic and health-promoting properties of spearmint. A longer irrigation period with saline reclaimed water would be necessary to assess whether the quality of both species, especially spearmint, could further improve without compromising their growth.

Although the use of marginal-quality water can be an effective measure to alleviate water scarcity, it often contains a high concentration of salts that can compromise crop growth. As a result, farmers apply more water than necessary to leach salts away from the root zone, resulting in wasted water and the release of fertilizers into the groundwater. In this study, we assessed the effects of three salinity levels of irrigation water (1.8 dS m⁻¹, 3.3 dS m⁻¹, and 4.9 dS m⁻¹) on the physiology and ornamental traits of Hebe andersonii cv. Variegata. The experiment was carried out with potted plants in a greenhouse for seven months. We also studied the feasibility of growing this cultivar without leaching salts. The results showed that Hebe plants can be grown without leaching using water up to 3 dS m⁻¹. This setup produces plants with high water use efficiency and without reducing their ornamental value. Meanwhile, irrigation with 5 dS m⁻¹ water reduced the quality of Hebe but did not compromise its physiological processes. The photosynthesis of Hebe under salinity conditions was mainly controlled by stomata, which was related to the level of salt stress and water status of the plant. Salinity had no significant effects on photosystem II, which can be explained by the fact that Hebe was able to dissipate the excess excitation energy as heat effectively. Hebe was able to avoid ion toxicity and maintain a suitable nutrient balance under the salinity levels tested in this experiment.

This work attempts to identify which of two species with different levels of salinity tolerance, Salvia officinalis L. or Asteriscus maritimus L., is more suitable for irrigation with reclaimed wastewater, as well as the effect of the arbuscular mycorrhiza Glomus iranicum on the plant. The experiment was carried out in a growth chamber with a first phase, where both species were irrigated with good quality water, a second phase in which the plants were irrigated with reclaimed wastewater, and a third phase in which the plants were irrigated with good quality water again (recovery). Salinity caused a reduction in leaf water potential, stomatal conductance and net photosynthesis in both species. The percentage of mycorrhization was higher in Asteriscus than in Salvia, mitigating the decrease in leaf water potential. There was osmotic adjustment in Salvia, although the proline content increased in both species. The damages produced were clearer in Salvia, in which lipid peroxidation values were higher. Likewise, the visual appearance of the leaves showed symptoms of toxicity in this species, although the mycorrhizae diminished these effects. Irrigation with good quality water induced the recovery of lipid peroxidation in both species, as well as the appearance of new leaves in Salvia.