2026-04-01
Manisha Panigrahy, Narayan Panda, Sarmistha Priyadarshini, Akhilesh Kumar Gupta, Anshuman Nayak, Kshitipati Padhan, Shraddha Mohanty, Munmun Dash, Sanjib Kumar Sahoo, Hrusikesh Patro, Debadatta Sethi
IntroductionSoil culturable bacterial population dynamics is crucial for soil health which suffers due to overexploitation and other unsustainable practices. Long-term manurial endowments are becoming more common as a component of regenerative agriculture linked to crop productivity.MethodsThe present study was undertaken to give an insight into regenerative agriculture. A total of 10 manurial practices formulated with integrating soil test-based inorganic fertilizers (STD), farmyard manure (FYM), vermicompost (VC), consortia biofertilizers (BFs), lime (L), organic I, and organic II were evaluated.ResultsThe integrated treatments T8 (STD + VC at 2.5 t ha−1 + BFs + L) significantly enhanced the diversity of beneficial bacterial genera such as Bacillus, Pseudomonas, Rhizobium, Azotobacter, Azospirillum, and Alcaligenes. Biological activities like soil enzyme activities (urease and dehydrogenase), microbial biomass carbon, and nitrogen were synergistically proliferated in T8 (STD + VC at 2.5 t ha−1 + BFs + L). After long-term utilization of STD + VC at 2.5 t ha−1 + BFs + L (T8) MBC, MBN, and DHA were enhanced by 36%, 85%, and 12% over soil test doses of the fertilizer application package. Physiological plant traits, leading to the highest cabbage yield (22 t ha−1), head circumference (42.53 cm), and total chlorophyll content (2.11 mg g−1), demonstrated strong interdependence between microbial health and plant performance. Combining bio-inoculants and liming techniques increased the economic yield of cabbage by 13%-21% at P = 0.05 over control. The antibiotic sensitivity profiling reflected adaptive responses by long-term manurial endowment on soil ecological dynamics. Multivariate analyses, including PCA, regression, and path modelling, confirmed the pivotal role of culturable soil bacterial population dynamics for optimizing both microbial functions and cabbage productivity.ConclusionThe study underscores the importance of integrating inorganics, organics, bio-inoculants, and strategic chemical amendments for a regenerative agriculture in acid Inceptisols.
DOI: 10.3389/fagro.2026.17651162026-03-31
Rongchuan Yu, Yongsheng Xie, Rifeng Wang, Wenxin Li
Agricultural robotics-enabled crop health monitoring faces critical trade-offs: standalone on-device models sacrifice accuracy for real-time responsiveness, while cloud-dependent approaches suffer from high latency and communication overhead. Additionally, data-driven models often lack biophysical plausibility, leading to unreliable predictions for agronomic decision-making under resource constraints. We propose a hybrid LSTM-edge correction architecture that hierarchically integrates lightweight Long Short-Term Memory (LSTM) networks on field robots with physics-informed neural networks (PINNs) at the edge. On-device LSTMs process localized sensor data (soil moisture, spectral reflectance) to generate initial crop stress probability estimates with minimal latency. Edge-based PINNs refine these predictions by embedding biophysical dynamics—modeled via coupled partial differential equations (PDEs) governing the soil-plant-atmosphere continuum (SPAC)—to ensure agronomic validity, mitigate sensor noise, and account for spatial variability. The framework is deployed on NVIDIA Jetson Nano (local inference) and AMD EPYC servers (edge processing), seamlessly integrating with existing farming infrastructures to replace rule-based thresholds with adaptive, physics-grounded control commands. A Fourier Neural Operator (FNO) optimizes the edge PINN’s computational efficiency for high-dimensional PDE solving. Experimental evaluations on two real-world datasets (soybean and citrus) demonstrate that the hybrid approach improves prediction accuracy by 18% compared to standalone LSTMs (F1-score: 0.89±0.02 for soybean, 0.83±0.03 for citrus) while maintaining real-time performance (end-to-end latency: 210 ms, energy consumption: 5.1 J/prediction). Field deployment on a 50-hectare soybean farm yields tangible agronomic benefits: 22% reduction in irrigation water usage, 18% fewer pesticide applications, and 95% system uptime under field conditions. The framework exhibits robust performance against sensor noise (≥80% accuracy at 30% noise-to-signal ratio) and outperforms cloud-based PINNs (72.8% lower energy consumption) and threshold-based methods (28–33% higher F1-score). This work advances distributed agricultural robotics by bridging data-driven machine learning and domain-specific physics, delivering a scalable, interpretable, and resource-efficient solution for precision agriculture. The hierarchical prediction-correction pipeline balances real-time responsiveness with biological plausibility, making it suitable for resource-constrained field robots. By integrating legacy sensors and adaptive actuation control, the architecture offers a practical pathway to upgrade existing farming systems, enabling data-informed interventions while reducing environmental impact.
DOI: 10.3389/fagro.2026.17640022026-03-27
Wilfredo Barrera, Francesco Morbidini, Carmelo Maucieri, Maria Giordano, Tjaša Pogačar, Marko Flajšman, Graziano Ghinassi, Leonardo Verdi, Roberto Ferrise, Anna Dalla Marta
DOI: 10.3389/fagro.2026.18081282026-03-26
Salim Bourras, Miguel Ángel Corrales Gutiérrez, Jiasui Zhan
DOI: 10.3389/fagro.2026.17243312026-03-25
Suja Subhash, Bhoomi Thampy, Abhijith Shibu, Khaderbad Yasaswi, Ashwin Nambiar, Nidhin Thambi, Sreelekshmi Sreekumar, Arya Ramachandran, Muhammed Ashil, Akshay Nair, Pradeesh Babu, Anu Melge, Sanjay Pal, Bipin Nair, Chinchu Bose
Ginger (Zingiber officinale) is an economically important spice crop widely cultivated for its culinary and medicinal values. However, its productivity is severely constrained by soft rot disease, causing substantial yield losses, quality, and persistent challenges in ginger cultivation. In this study, the major pathogenic fungus GI-FS1 was isolated from Z. officinale with typical symptoms and was identified as Fusarium species through morphological and molecular identification. The antifungal potential of plumbagin, a plant-derived naphthoquinone from Plumbago rosea, noted for antibacterial, antioxidant, and anticancer properties, was evaluated against GI-FS1. Plumbagin treatment significantly inhibited conidial germination and mycelial growth with Minimum Inhibitory Concentration (MIC) and Minimum Fungicidal Concentration (MFC) values of 10 µg/mL and 15 µg/mL, respectively. Conidial germination assays, microscopy, onion peel epidermis penetration confirmed inhibition, as plumbagin-treated spores failed to germinate and penetrate epidermis. 4’,6-Diamidino-2-phenylindole (DAPI) staining showed chromatin condensation and Acridine orange/ethidium bromide (AO/EB) revealed membrane disruption, coupled with 2,7-dichlorodihydrofluorescein diacetate (DCFH-DA) detected Reactive oxygen species (ROS) accumulation, signifying oxidative stress-induced cell death by plumbagin. Elevated electrolyte leakage and DNA fragmentation supported apoptosis-like mechanisms underlying fungal growth inhibition; however, further studies on apoptotic factor gene expression are required to confirm this mechanism. Scanning Electron Microscopy (SEM) analysis revealed spore shrinkage and thinner, collapsed, rough mycelia, indicating loss of cell integrity on treatment with plumbagin. Overall, these findings provide the first report on the targeted mechanisms of plumbagin in inhibiting Fusarium conidial germination and inducing apoptotic-like cell death. By disrupting fungal viability through oxidative stress and apoptosis-related pathways, the study highlights plumbagin’s potential as a natural antifungal agent for the sustainable management of soft rot disease in ginger.
DOI: 10.3389/fagro.2026.17702722026-03-24
Mojtaba Keykhasaber, Georgios Tzelepis, Vahideh Rafiei
Contemporary agriculture is facing an escalating crisis caused by fungal pathogens. Soil-borne and vascular fungi, such as Verticillium and Fusarium species, are becoming more destructive under climate change, which alters pathogen ranges and virulence. Meanwhile, overreliance on broad-spectrum fungicides accelerates resistance evolution and imposes untenable environmental costs. This review critically synthesizes cross-disciplinary innovations and proposes an integrated framework for next-generation fungal disease management. Unlike analyses that treat technological advances in isolation, we adopt a convergence-driven perspective to construct a systems-level roadmap. We examine the synergistic roles of four interconnected domains: omics technologies and bioinformatics for decoding pathogen virulence and host resistance mechanisms, advanced biotechnologies (including CRISPR for genome editing and RNA interference (RNAi) for sequence-specific silencing), nanotechnology (enabling the stabilization, targeted delivery, and controlled release of bioactive agents), and artificial intelligence (AI) and digital agriculture (encompassing UAV-based remote sensing, predictive modeling, and automated decision-support systems). This review’s core establishes how integrating these fields creates a responsive, closed-loop defense architecture. We detail how omics-driven discovery informs CRISPR and RNAi targets, how nanocarriers translate these molecular tools into field-deployable interventions, and how AI-powered sensing guides their precise spatial and temporal deployment. This paradigm shift moves plant protection from reactive, calendar-based spraying to proactive, site-specific management. However, we also rigorously address the economic, regulatory, and societal barriers, including fragmented policies for edited crops and nano-agrochemicals and public acceptance concerns, which hinder large-scale implementation. By bridging the gap between molecular discovery and practical field application, this review articulates a transformative vision in which data-driven, targeted interventions enhance agricultural resilience, reduce ecological footprints, and safeguard global food security against mounting pressure from evolving fungal threats.
DOI: 10.3389/fagro.2026.17606932026-03-20
Shyam Venkatraman, Muralikrishnan Mani, Ananthakrishnan Balasundaram, Ayesha Shaik
Proper categorization of diseases in coffee plants is critical for their early detection and good crop management, which in turn has a direct impact on the quantity, quality, and long-term sustainability of agriculture. Early detection of diseases makes it possible to resort to selective interventions, which not only reduce the chance of total crop loss, but also help in the control of outbreaks. Until now, detection methods have relied on manual inspections that are slow, inconsistent and prone to human errors, making them very much dependent on experts. The present research uses deep learning along with machine feature extraction techniques for coffee disease identification using PhytoV2Net and InceptionV3, respectively. Both networks were trained on the JMuBEN and JMuBEN2 datasets, which consist of a total of 58,549 leaf images. These networks can differentiate between healthy and diseased leaves by learning to identify visual symptoms such as spots, discolorations, and lesions. The custom PhytoV2Net model produced an accuracy score of 99.87%, while InceptionV3 was based on 99.55% under K-fold cross-validation. PhytoV2Net performance was also above 95% in both precision and recall, indicating the high dependability and constancy of the model in its disease identification. The environmental changes posed difficulties, such as variations in lighting, leaf blocking, and background noise. Preprocessing techniques, particularly data augmentation applied to the JMuBEN dataset from an open-source data repository, helped improve image quality and enhance model robustness. Deploying these models in real time can significantly advance smart farming. When integrated into edge devices, handheld tools, or drone systems, they enable autonomous on-site detection of coffee leaf diseases and turn these platforms into intelligent assistants for plant health monitoring.
DOI: 10.3389/fagro.2026.1767554