Climate change poses a major challenge to agricultural sustainability, particularly in regions where variations in temperature and precipitation directly affect crop productivity. This study examines the relationship between interannual climate variations and corn production in northeastern Romania, using official data from the National Institute of Statistics and the National Meteorological Administration for the period 2017-2022. Pearson correlation coefficients were applied to assess the direction and strength of associations between yield, temperature, and precipitation in six representative counties. The results indicate predominantly negative correlations between average annual temperature and yield (r = −0.808, p = 0.052 in NeamÈ›; r ≈ −0.406, p > 0.10 in IaÈ™i), suggesting that high temperatures limit production by increasing evapotranspiration and heat stress during sensitive growth stages. In contrast, precipitation shows positive and often statistically significant correlations (r = 0.957, p = 0.003 in BotoÈ™ani; r = 0.890, p = 0.017 in Bacău; r = 0.799, p = 0.057 in NeamÈ›), confirming the decisive role of moisture availability in maintaining yield stability. Spatial differences in correlation strength reflect local interactions between precipitation timing, soil water retention, and crop management practices, including hybrid selection, planting density, and access to irrigation. The analysis found no significant link between cultivated area and yield, indicating that interannual fluctuations are primarily driven by climate, rather than the result of land expansion. Despite the short observation period, the findings underscore the need for regionally tailored climate change adaptation strategies, such as the use of drought- and heat-tolerant hybrids, optimized planting schedules, conservation tillage, and efficient irrigation systems, supported by agrometeorological monitoring and forecasting tools. Integrating these measures into local and national agricultural policies is essential for maintaining corn productivity under conditions of increased hydrothermal stress.

Abstract
The growing global emphasis on sustainable agricultural practices has accelerated the search for eco-friendly alternatives to synthetic pesticides. Among natural solutions, mint essential oil—extracted from Mentha species—has emerged as a promising bio-insecticide due to its high content of bioactive compounds such as menthol and menthone. These components are known for their insecticidal, repellent, and antimicrobial properties, making mint essential oil a viable candidate for integrated pest management (IPM) systems in organic and agro-ecological farming. This study is a comprehensive literature review analyzing peer-reviewed research published over the last two decades concerning the pesticidal efficacy of mint essential oil. This review focuses on its effects on common agricultural pests, the mode of action of its active compounds, environmental safety, and limitations related to formulation and application. The findings reveal that mint essential oil demonstrates significant insecticidal activity against a broad spectrum of pests, including aphids, whiteflies, and beetles. It is also considered safe for beneficial insects, such as pollinators, and poses minimal risks to human health and the environment. Nonetheless, its high volatility and sensitivity to environmental factors (e.g., sunlight, temperature) can limit field efficacy. Research also highlights the importance of microencapsulation and emulsification techniques to enhance the stability and controlled release of the oil. Mint essential oil offers a sustainable and low-toxicity alternative to synthetic pesticides. While its insecticidal potential is well-documented, addressing challenges related to formulation and delivery systems is essential for broader field adoption. Continued research and technological innovation are necessary to fully integrate mint essential oil into commercial pest management strategies and support the global transition toward sustainable agriculture.

Climate change, with its growing impact on agriculture, demands resilient, sustainable, and resource-efficient food production systems. Edible fungi, traditionally valued for their nutritional and culinary qualities, are increasingly recognised for their potential in sustainable crop diversification. While Agaricus bisporus (button mushroom) dominates global production, species with higher adaptability and lower environmental footprints are gaining attention. Among these, Pleurotus ostreatus (commonly known in Latin America as “orellana”) stands out as a promising alternative due to its ability to grow on various agro-industrial residues, rapid production cycles, and suitability for small- and medium-scale farming. This study developed and assessed cultivation protocols for substrate preparation, harvesting, postharvest handling, and transportation to enhance product quality and shelf life. The proposed procedures incorporated agricultural by-products such as coffee husks, sawdust, and sugarcane bagasse, alongside detailed recommendations for sterilisation, inoculation, and incubation. Harvesting and postharvest strategies emphasised optimal timing, humidity control, and packaging methods to minimise mechanical damage, microbial contamination, and senescence. Implementing these guidelines resulted in higher yields, improved texture, and extended fruiting-body freshness, thereby increasing their commercial value. Systematising these practices reinforces P. ostreatus as a sustainable alternative crop under climate change scenarios, contributing to rural income diversification and food security. Future research should focus on scaling up under varied agroecological conditions, assessing energy efficiency in controlled environments, and exploring biodegradable packaging solutions to further strengthen sustainability across the value chain.

The phytobiome—comprising plants, their associated microbiota, and the surrounding environment—represents a dynamic network critical to plant health and agricultural productivity. Recent advances highlight the phytobiome as a powerful lever for improving food quality and resilience through sustainable practices. This paper explores the use of natural bioprotective agents—beneficial microbes, microbial consortia, and plant-derived compounds—as key tools in promoting phytobiome integrity and, by extension, healthier food systems.

Natural bioprotectants enhance plant defense mechanisms, suppress phytopathogens, and stabilize plant–microbe interactions, contributing to reduced chemical input and increased ecological balance. By supporting native microbial communities within the rhizosphere and phyllosphere, these agents not only reduce susceptibility to pests and diseases, but also improve nutrient uptake, abiotic stress tolerance, and food nutritional quality. The integration of bioprotective agents into agricultural systems represents a shift from reactive crop management to a proactive, systems-based approach rooted in ecological principles.

This work discusses the mechanisms through which microbial agents such as Bacillus, Trichoderma, and Pseudomonas species act as bio-shields and growth promoters, while also highlighting the emerging role of microbial metabolites and plant signaling pathways in steering community dynamics. We propose a framework for assessing phytobiome functionality as a predictor of crop performance and advocate for multi-strain, niche-specific applications tailored to crop and climate.

Ultimately, fostering a healthy phytobiome through natural bioprotectants represents a pathway toward cleaner food, restored soil health, and reduced agricultural dependence on synthetic inputs. This approach aligns with global goals for sustainable food production and offers promising solutions to the intertwined challenges of climate change, biodiversity loss, and food security.

Climate change has led to a significant increase in the frequency and intensity of hailstorms, posing a major threat to produce supply and tuber quality in the potato industry. This study investigated yield and tuber quality hail recovery responses of four potato cultivars to different hail intensities, aiming to develop a cultivar-driven strategy for hail resilience. Field experiments were conducted during the 2023/2024 and 2024/2025 seasons, using a 5 [0, 25, 50, 75 and 100% canopy disruption levels] × 4 [early- (Sababa), mid- (Tyson, Mondial), and late-maturing (Panamera) cultivars] factorial arrangement in a randomized complete block design. Data collected included yield, tuber grading, dry matter and starch recovery. Yield and tuber quality recovery were statistically consistent across seasons (P > 0.05), indicating that seasonal variation did not influence yield or quality traits. Therefore, values were averaged across the two seasons to provide a single comparative estimate for each cultivar. Panamera exhibited superior yield recovery (63.75%), large tuber recovery (88.61%), dry matter recovery (66.36%) and starch content recovery (56.36%) across planting seasons. The superior recovery was attributed to its high yield potential and environmental adaptability, supported by a higher canopy cover and long growing season enabling extended recovery. Sababa, on the other hand, even though it had lower recovery in other traits, maintained relatively high starch recovery (52.8%), which was statistically similar to Panamera. This suggests that Sababa adopts a more conservative allocation strategy, prioritizing starch biosynthesis under hail stress over other traits. This recovery is likely supported by elevated ADP-glucose pyrophosphorylase (AGPase), a key enzyme in starch biosynthesis, which may have enabled Sababa to sustain starch production and retention despite canopy damage. These traits can be exploited for cultivar selection and breeding to reduce climate-related risks in hail-prone potato-producing regions.

Arbuscular mycorrhizal fungi (AMF) are recognized for their role in enhancing plant growth and productivity, leading to increased interest in their application as biofertilizers. This study aimed to evaluate and compare the efficacy of an autochthonous AMF consortium, the "Rhizolive consortium" (RC), against a widely used commercial strain of Rhizophagus irregularis (RI) on the growth, biomass accumulation, and key physiological characteristics of "Picholine Marocaine" olive cultivar under greenhouse conditions. Our findings revealed that both AMF successfully established symbiotic relationships with the olive root systems, with RC showing 100% mycorrhizal frequency and RI the highest intensity. Additionally, the application of RC inoculum resulted in superior growth performance, shoot height reaching an average of 52 cm, and a higher number of leaves being developed, averaging 55 per plant. Furthermore, RC inoculation significantly boosted the accumulation of both fresh and dry shoot biomass by 34% and 38%, respectively. Beyond growth parameters, RC-inoculated plants exhibited markedly improved physiological efficiency. Stomatal conductance and chlorophyll fluorescence were significantly increased (p < 0.05) by approximately 21% and 2.5%, respectively. In addition, biochemical analyses revealed that RC inoculation led to substantial increases in the foliar content of chlorophyll a, total chlorophyll, and protective carotenoid pigments. These comprehensive results underscore the significant potential of "Rhizolive consortium" isolated from the olive-growing regions of Morocco, to not only promote robust root colonization and vegetative growth but also to enhance the physiological efficiency of the "Picholine Marocaine" olive cultivar. This study provides compelling evidence for the relevance of native AMF consortia as sustainable and potentially more effective alternatives to commercial mycorrhizal inoculants in olive cultivation, contributing to more environmentally friendly and economically viable agricultural practices. Further research is warranted to explore the specific mechanisms underlying the enhanced performance observed with the RC and to evaluate its efficacy under field conditions.

Paddy, Oryza sativa, is a widely consumed staple food worldwide, feeding over 50% of the global population and Sri Lanka has been producing paddy for centuries. Because of the rapid increase in population, forecasting paddy yield has become essential. This research aims to predict Sri Lankan district wise paddy yield with openly available data: CHIRPS 2.0, NASA POWER APIs, Sri Lankan Rice Research and Development Institute’s PH and Salinity Maps, Paddy Statistics from the Department of Census and Statistics - Sri Lanka for local agro zones using an XGB regressor-based stacked ensemble learning framework. For the three major agro-climatic zones and 25 administrative districts, data from 2004 to 2024 were collected for the two harvesting seasons “Yala” and “Maha”, with the specific target being the total paddy production per district (in metric tons) with the range (185, 530356) MT. lowest recorded for “Mannar” district in 2006 “Yala” season and highest “Anuradhapura” district in 2019-2020 “Maha” season. The crop calendar template provided by the Department of Agriculture - Sri Lanka was used to simulate end-to-end crop harvesting patterns for the selected time span as the foundation for dataset construction. By combining harvesting simulations with climate variables, soil properties and historical yield records, we created 12 heterogeneous datasets. These datasets were used to train 12 base models, whose out-of-fold predictions were subsequently integrated into two intermediate meta models. Finally, the outputs of the intermediate meta models were stacked for the final meta model to evaluate predictive performance, showcasing RMSE of 3,535 MT and R² of 0.9986 on the validation set with a NRMSE of 0.76%, indicating that the model can predict district level seasonal paddy yield with high accuracy. These results highlight the potential of integrating openly available data to support reliable, data driven decision making for sustainable paddy production in Sri Lanka.

Rice (Oryza sativa) is the main cereal crop in the province of Corrientes, Argentina. Biotic constraints are a constant threat to rice production. Studies conducted with microorganisms as alternatives for controlling economically important diseases have demonstrated their biostimulant action in plants. The use of microorganisms was evaluated as an alternative and sustainable measure to increase crop yields through biostimulation as a complement to nutrition plans. During 2022 and 2023, in two locations in the province of Corrientes (Argentina), the individual and combined effect of Trichoderma virens and Bacillus subtilis on rice yield was measured. The design was a completely randomized block design with nine treatments and three replicates per treatment. A control without application, one commercial treatment, and seven treatments with both individual and combined applications of the organisms were included. The grain yield obtained in each treatment was measured. The results indicated that the highest yields in both locations were obtained for the treatments with microorganisms. In the Itá Ibaté location, three of the treatments with biological agents exceeded the conventional treatment by 700 kg/ha, and in the Perrugorria location, conventional treatment was exceeded by 1870 kg/ha. These results demonstrate the biostimulant effect of microorganisms on the crop and suggest the need to investigate the metabolic pathways that benefit from the interaction between both organisms.

Plant diseases represent a persistent challenge to global food security, causing an estimated 16% annual loss in crop yield and quality. As global food demand is projected to rise by 70% by 2050, developing reliable and scalable detection systems has become increasingly critical. Traditional disease identification methods based on manual inspection are labor-intensive, subjective, and impractical for large-scale agricultural monitoring. Early automated systems that relied on handcrafted features and classical classifiers achieved only limited success because they were unable to adapt to complex, variable field environments. Although deep learning, particularly convolutional neural networks (CNNs), has significantly improved detection performance by learning discriminative features directly from images, these models depend heavily on large, annotated datasets collected under controlled conditions—restricting their generalization to real-world settings. Furthermore, the scarcity of labeled data for rare or emerging diseases limits the scalability of supervised approaches.

Anomaly detection offers a promising solution by training models solely on healthy plant samples and identifying diseases as deviations from normal patterns. However, CNN-based autoencoders used for this task often struggle to capture the long-range dependencies required to recognize subtle or spatially distributed disease symptoms. To address this limitation, we propose a semi-supervised anomaly detection framework built upon a hybrid autoencoder with a Vision Transformer (ViT) encoder backbone. By leveraging the ViT’s self-attention mechanism, our model learns rich global representations of healthy foliage and detects anomalies through reconstruction errors. Experimental evaluations on multiple plant disease datasets demonstrate that our framework achieves an F1-score of 80%, representing a 7% improvement over the state-of-the-art anomaly detection methods. These results highlight the framework’s potential for robust, scalable, and early detection of plant diseases across diverse agricultural environments.

Introduction: Chickpea (Cicer arietinum L.) is a critical source of dietary protein in semi-arid regions, which are increasingly vulnerable to climate change. Rising temperatures and erratic rainfall patterns, particularly during the sensitive reproductive stage, pose a severe threat to global chickpea yield. While drought tolerance is a known trait in chickpeas, the synergistic impact of combined drought and heat stress remains poorly characterized, limiting the development of resilient cultivars. This study aimed to physiologically and biochemically dissect the responses of diverse chickpea genotypes to individual and combined stress scenarios.

Methods: A controlled-environment experiment was conducted using ten chickpea genotypes with varying genetic backgrounds. Plants were subjected to four treatments at the flowering stage: well-watered control, drought stress, heat stress, and combined drought-heat stress. Physiological parameters (photosynthetic rate, stomatal conductance, canopy temperature) and biochemical markers (proline content, antioxidant enzyme activity) were measured. Yield components, including pod set percentage and seed weight, were quantified at maturity.

Results: The results demonstrated that combined stress inflicted significantly greater damage than individual stresses. While all stresses reduced photosynthetic efficiency by over 50%, the combined stress led to a near-complete shutdown (85% reduction). Genotype ICC 4958 maintained superior relative water content and photosystem integrity under drought, but its advantage diminished under heat and combined stress. In contrast, genotype ICC 15614 exhibited a robust antioxidant response, with a 3-fold increase in catalase activity under combined stress, correlating with a 30% higher pod retention compared to the most sensitive genotype.

Conclusions: This study demonstrates that combined heat-drought stress is the critical limiter of chickpea productivity, requiring distinct tolerance mechanisms beyond drought resilience alone. Genotypes with robust antioxidant responses offer a key target for breeding programs aimed at safeguarding yields under future climates.