Artificial olfaction, i.e., e‐nose, plays a critical function in robotics by mimicking the human olfactory organ that can recognize different smells that correlate with a range of fields, including environment monitoring, disease diagnosis, public security affairs, agricultural production, food industry, etc. The advances in the artificial olfaction (electronic nose) technology and its applications are concisely reviewed herein. Three main elements are investigated and presented, with an emphasis on the emerging sensors and algorithm of the artificial neural network in the relevant fields. The first element is the diverse applications of e‐nose in medical care, food industry, environment monitoring, public security affairs, and agricultural production. The second element is the investigation of the sensors in e‐nose and representative and promising advances, which is the building block of e‐nose through mimicking the olfactory receptors. The third element is the introduction to the algorithm of the artificial neural network to serve in the recognition of the pattern of odors (i.e., their chemical profiles). Promises and challenges of the separately reviewed parts and the combined parts are presented and discussed. Ideas regarding further orientation and development of the e‐nose system are also considered.
Amitava Chatterjee, Kelly R. Thorp, Peter L. O’Brien
et al.
Cereal rye (Secale cereale L.) as winter cover crop can reduce nitrate (NO3) loss through subsurface tile drainage under corn (Zea mays L.) -soybean (Glycine max L.) production system. The Decision Support System for Agrotechnology Transfer (DSSAT) model can simulate processes of subsurface drainage flow and NO3 loss to artificial subsurface drainage, but few model evaluations with field-measured data are available. The objective of this study was to evaluate the DSSAT model for simulating crop yield and flow and NO3 losses to tile drainage in a corn -soybean rotation with (CC) and without (NCC) winter rye cover crop in Central Iowa during the 2002–2010 growing seasons. Simulations successfully reproduced the cumulative (9 years) subsurface drainage flow, observed and predicted values were 331 cm and 309 cm for NCC and, 323 cm and 284 cm for CC. Similarly, for cumulative NO3 loss in tile flow, observed and predicted values were 444 kg N ha−1 and 459 kg N ha−1 for NCC and 187 kg N ha−1 and 196 kg N ha−1 for CC; simulated and observed indicated CC treatment could reduce NO3 in drainage by 57 %. Early (-10 d) and late (+ 10 d) termination did not influence main crop yield and tile NO3 loss. Simulation of the long-term (23-years) influence of CC suggest that tile flow and NO3 load could be reduced by 15 % and 73 %, respectively for a corn-soybean production system in central Iowa.
Krishnagopal Halder, Amit Kumar Srivastava, Wenzhi Zheng
et al.
Monitoring agricultural systems is increasingly essential as we address the pressing challenges of climate change, biodiversity loss, population growth, and rising food demands. High-resolution, large-scale maps of agricultural lands are fundamental for creating sustainable strategies but mapping extensive and diverse croplands over time remains complex. To tackle this, our study presents an efficient and reproducible framework for annual crop type mapping using multi-temporal satellite data and deep learning.We integrate 10-day composites from Sentinel-1 SAR and Sentinel-2 MSI data with machine learning (XGBoost, CatBoost) and deep learning models, including a Bidirectional LSTM (BiLSTM) and a Self-Attention-enhanced architecture. The approach focuses on five major crops—winter wheat, winter rapeseed, winter barley, silage maize, and sugar beet—and was applied across three German states (Lower Saxony, North Rhine-Westphalia, and Brandenburg) for 2021 and 2023.The BiLSTM model achieved the best performance among the tested approaches, with an overall accuracy of approximately 93 %. Data fusion improved classification accuracy by 2–3 % compared to single-sensor inputs. Feature importance analysis highlighted key temporal intervals related to crop phenology. To ensure consistency, we implemented linear interpolation for gap filling and tested multiple scaling techniques, with percentile-based normalization offering a good balance of simplicity and effectiveness.Our framework also demonstrated strong spatial transferability and adaptability, achieving high performance in new regions even with limited training data, and outperforming established benchmark datasets. Its integration with open platforms like Google Earth Engine enables scalable, field-level monitoring across Europe. These results support the development of robust, transferable tools for agricultural decision-making and long-term agroecosystem monitoring.
Fagopyrum tataricum, a nutritionally valuable buckwheat species, is increasingly recognized for its rich flavonoid content. However, its cultivation faces mounting challenges due to drought stress, a problem exacerbated by global climate change. While endophytic fungi have demonstrated potential in enhancing plant drought resistance, their application in F. tataricum and the underlying mechanisms remain underexplored. In this study, two endophytic fungal strains, Botryosphaeria dothidea J46 and Irpex lacteus J79, were isolated and screened for their drought-resistance-promoting effects in F. tataricum. Pot experiments demonstrated successful root colonization of F. tataricum by inoculating these strains under drought conditions. Both Botryosphaeria dothidea J46 and Irpex lacteus J79 promoted root growth, increasing the fresh weight of F. tataricum roots by 49.94 % and 48.80 %, respectively. The content of flavonoids, an important bioactive compound in F. tataricum, was also enhanced. J46 and J79 increased flavonoid content in the leaves of F. tataricum by 28.39 % and 19.54 %, respectively, and in the seeds by 17.79 % and 14.06 %, respectively. Metabolite analysis revealed elevated levels of osmotic regulatory substances and antioxidants, while photosynthetic inhibition caused by drought stress was effectively alleviated upon fungal inoculation. Integrated metabolomic and transcriptomic analyses revealed distinct mechanisms of action for the two strains: B. dothidea J46 upregulated key genes in the flavonoid biosynthesis pathway, including Cinnamate-4-hydroxylase (C4H), Chalcone synthase (CHS), and Chalcone isomerase (CHI), whereas I. lacteus J79 enhanced the expression of genes associated with photosynthesis. Specifically, B. dothidea J46 promotes the plant’s drought resistance by enhancing the expression of genes in the flavonoid biosynthesis pathway, while I. lacteus J79 improves the plant’s photosynthetic efficiency under drought conditions by increasing the activity of genes associated with photosynthesis. Future research will focus on exploring the combined effects of multiple fungal strains, conducting field trials to assess practical applicability, and further elucidating the metabolic pathways involved. This study provides critical insights into the metabolic and molecular mechanisms underlying endophyte-mediated drought resistance, offering a foundation for the development of microbial agents to support the sustainable cultivation of F. tataricum under water-limited conditions.
Abstract:: Accurate estimation of fractional vegetation cover (FVC) and aboveground biomass (AGB) is essential for large-scale grassland monitoring. However, this process is often constrained by the labor-intensive nature of field surveys. In this study, we propose a fully non-destructive framework that integrates deep learning, image segmentation, vegetation indices, and structural auxiliary variables to retrieve FVC and AGB in meadow grasslands. By combining a U-Net network with convex-hull masking, we automatically delineate 1 m × 1 m quadrats from 574 smartphone RGB images collected in western Jilin, China. This approach improves the mean intersection-over-union (mIoU) from 61.8 % (using raw U-Net bounding boxes) to 90.1 % (with final quadrat masks). We evaluate five vegetation indices and identify the color index of vegetation extraction (CIVE) as the most robust. CIVE achieves correlation coefficients of 0.85 for FVC and 0.54 for AGB in fresh grass plots. To address spectral confusion between dry grass and soil—particularly in images where dry grass covers >10 %—we introduce a “segment-then-reclassify” pipeline. This pipeline incorporates TurboPixels superpixels, edge-guided watershed segmentation, and k-means clustering for improved discrimination. Two predictor sets are used to train five inversion models (ridge regression, k-nearest neighbors, support vector regression, random forest, and partial least squares regression): one using only the vegetation pixel ratio, and the other combining the vegetation pixel ratio with vegetation density and mean height. Modeling the FVC of fresh and dry grass separately improves performance, increasing the R2 by an average of 0.23 and reducing the root mean square error (RMSE) by up to 41 %. Structural variables play a key role in AGB estimation, improving R2 by up to 0.28 and decreasing RMSE by 17 %. The proposed framework, based solely on lightweight RGB imagery and low-cost computation, enables real-time and non-destructive data acquisition in the field and offers reliable support for multi-scale grassland remote sensing and ecological assessments.
Rice-ratoon rice double cropping (RR) offers a substantial reduction in labor and resource inputs while significantly enhancing water use efficiency compared to conventional double cropping (DR). This system holds promises in tropical monsoon regions with limited water resources. However, the differences in irrigation periods and water requirements between DR and RR call for region-specific water resource management. This study evaluated the potential of introducing RR on reservoir management in tropical monsoon climates, simulating its effects using 23 years of hydrological data. The findings show that starting RR in early June can cut irrigation supply by up to 51 %, boost water productivity by 60–87 % compared to DR, and sustain a high reservoir reliability index. Yet, challenges persist, including the complexities of mechanical harvesting during the monsoon season and the risk of yield reduction due to delayed crop cultivation. While triple cropping with rice and two ratoons (RRR) is possible, it demonstrated lower water productivity and was less effective in water resource management than other cropping patterns. Despite RR’s potential to enhance water use efficiency in tropical monsoon regions, further research and technical advancements are needed for practical application. This study offers valuable insights into sustainable rice production and water resource management in water-scarce regions.
Osama Zafar, Rosemarie Santa González, Alfonso Morales
et al.
Digital agriculture is transforming the way we grow food by utilizing technology to make farming more efficient, sustainable, and productive. This modern approach to agriculture generates a wealth of valuable data that could help address global food challenges, but farmers are hesitant to share it due to privacy concerns. This limits the extent to which researchers can learn from this data to inform improvements in farming. This paper presents the Digital Agriculture Sandbox, a secure online platform that solves this problem. The platform enables farmers (with limited technical resources) and researchers to collaborate on analyzing farm data without exposing private information. We employ specialized techniques such as federated learning, differential privacy, and data analysis methods to safeguard the data while maintaining its utility for research purposes. The system enables farmers to identify similar farmers in a simplified manner without needing extensive technical knowledge or access to computational resources. Similarly, it enables researchers to learn from the data and build helpful tools without the sensitive information ever leaving the farmer's system. This creates a safe space where farmers feel comfortable sharing data, allowing researchers to make important discoveries. Our platform helps bridge the gap between maintaining farm data privacy and utilizing that data to address critical food and farming challenges worldwide.
Weeds significantly reduce crop yields worldwide and pose major challenges to sustainable agriculture. Traditional weed management methods, primarily relying on chemical herbicides, risk environmental contamination and lead to the emergence of herbicide-resistant species. Precision weeding, leveraging computer vision and machine learning methods, offers a promising eco-friendly alternative but is often limited by reliance on high-power computational platforms. This work presents an optimized, low-power edge AI system for weeds detection based on the YOLOv8n object detector deployed on the STM32U575ZI microcontroller. Several compression techniques are applied to the detection model, including structured pruning, integer quantization and input image resolution scaling in order to meet strict hardware constraints. The model is trained and evaluated on the CropAndWeed dataset with 74 plant species, achieving a balanced trade-off between detection accuracy and efficiency. Our system supports real-time, in-situ weeds detection with a minimal energy consumption of 51.8mJ per inference, enabling scalable deployment in power-constrained agricultural environments.
This study investigates the impact of artificial intelligence (AI) adoption on job loss rates using the Global AI Content Impact Dataset (2020--2025). The panel comprises 200 industry-country-year observations across Australia, China, France, Japan, and the United Kingdom in ten industries. A three-stage ordinary least squares (OLS) framework is applied. First, a full-sample regression finds no significant linear association between AI adoption rate and job loss rate ($β\approx -0.0026$, $p = 0.949$). Second, industry-specific regressions identify the marketing and retail sectors as closest to significance. Third, interaction-term models quantify marginal effects in those two sectors, revealing a significant retail interaction effect ($-0.138$, $p < 0.05$), showing that higher AI adoption is linked to lower job loss in retail. These findings extend empirical evidence on AI's labor market impact, emphasize AI's productivity-enhancing role in retail, and support targeted policy measures such as intelligent replenishment systems and cashierless checkout implementations.
The evolution of agentic systems represents a significant milestone in artificial intelligence and modern software systems, driven by the demand for vertical intelligence tailored to diverse industries. These systems enhance business outcomes through adaptability, learning, and interaction with dynamic environments. At the forefront of this revolution are Large Language Model (LLM) agents, which serve as the cognitive backbone of these intelligent systems. In response to the need for consistency and scalability, this work attempts to define a level of standardization for Vertical AI agent design patterns by identifying core building blocks and proposing a \textbf{Cognitive Skills } Module, which incorporates domain-specific, purpose-built inference capabilities. Building on these foundational concepts, this paper offers a comprehensive introduction to agentic systems, detailing their core components, operational patterns, and implementation strategies. It further explores practical use cases and examples across various industries, highlighting the transformative potential of LLM agents in driving industry-specific applications.
Wine influencers have emerged as one of the crucial elements in shaping consumer perceptions and behaviours. However, the specific characteristics of these influencers that effectively influence consumer attitudes, purchase intentions, and actual buying decisions remain inadequately understood. Therefore, using the Elaboration Likelihood Model, this study examines the impact of wine influencers’ characteristics on consumers’ attitudes, purchase intentions, and actual buying behaviour. A survey of 404 social media users was conducted using a structured questionnaire. The structural equation modelling analysis found that perceived credibility impacts attitudes toward influencers but not recommended brands. However, perceived expertise and trust strongly predict attitudes toward influencers and brands. Congruence has no significant impact. Attitudes toward influencers and brands positively correlate with purchase intention, which, in turn, leads to actual purchases. These insights offer marketers a roadmap for leveraging wine influencers’ characteristics to impact consumer behaviour effectively.
Jorge Luis Sánchez-Navarro, Narciso Arcas-Lario, Jos Bijman
et al.
Abstract The convergence of emerging sustainability regulations and recommendations outlined in the European, national and regional agricultural policies, coupled with the growing demand from retailers for food produced through more sustainable agriculture practices, presents a substantial challenge for farmers. This challenge is further exacerbated by their limited access to essential information, knowledge, and resources necessary for compliance, which are often acquired through interactions with various stakeholders within the agri-food supply chain. Moreover, the inherent power asymmetry between small-scale farmers and their considerably larger counterparts, including input suppliers and agricultural product buyers, exposes farmers to opportunistic behaviours. In response to these challenges, agri-food cooperatives have been proposed as an organizational solution to mitigate opportunistic behaviour. However, empirical data-supported evidence of this proposition remains scarce. Drawing upon data obtained from Spanish farmers, our study investigates the impact of agri-food cooperatives on the incidence of opportunistic practices experienced by farmers during their interactions with suppliers and buyers. Through a propensity score matching analysis, our findings reveal that cooperative membership exerts a statistically significant negative influence on both supplier and buyer opportunism in the context of complying with sustainability requirements. These findings provide compelling empirical evidence of the pivotal role played by agri-food cooperatives in addressing opportunism within the supply chain. Importantly, they underscore the vital importance of cooperatives in mitigating the challenges associated with enhancing sustainability in agriculture.
Nutrition. Foods and food supply, Agricultural industries
Chitooligosaccharides (COS) is homo- or heterooligomers of N-acetylglucosamine and D-glucosamine obtained via degradation of chitin or chitosan. COS is useful for remarkably wide spectrum of applications in the pharmaceutical, food, and agricultural industries due in part to their antimicrobial, antioxidant, antitumor, and immunomodulatory activities. Enzymatic, physical, and chemical methods for the preparation of COS has been reported. At present, the preparation of COS by any single method faces limitations, including difficulty in obtaining target products with specific degrees of polymerization and acetylation. Therefore, COS preparation protocols have shifted from single method strategies to explorations of cooperative catalytic systems. COS purity can also be improved by incorporating separation and purification techniques including ultrafiltration, activated carbon adsorption, and chromatography. In this paper, progress in COS preparation and purification methods and COS applications are reviewed, with the objective of providing a theoretical basis for improved production and expansion of applications for high quality COS.
Following the EU's decision to ban neonics, this article investigates the impacts of virus yellows on sugar beet yields under the ban and under current and future climates. Using a model that factors in key variables such as sowing dates, phenological stages, first aphid flight and aphid abundance, simulations are performed using long-period climate datasets as inputs. Coupled with incidence and sugar yield loss assumptions, this model allows to reconstruct the impact of virus yellows on sugar beet yields using a so called ‘as if’ approach. By simulating the effects of viruses over a long period-of-time, as if neonics weren't used in the past, this methodology allows an accurate assessment of risks associated with virus yellows, as well as impact of future agro-ecological measures.The analysis provides in addition an actuarial rating for an insurance policy that compensates the losses triggered by those viruses.
We introduce a multimodal rapid identification and growth status discrimination method for morchella. Based on the unique biological characteristics and growth environmental requirements of morchella, the efficient and accurate identification of key growth stages of morchella is achieved through the integration of multimodal information acquisition technology. During the rapid identification process of the growth stage of Morchella, the Multi Stage Vision Enhanced Position Encoding Vision Transformer (MS-EP ViT) model is adopted. By introducing multi-stage input embedding, enhanced position encoding, and optimized Transformer Encoder layers, the performance of the model in identifying different growth stages of Morchella mushrooms is significantly improved. In the multimodal Morchella growth state discrimination method, text and image modalities are integrated, a Non downsampled Contourlet Transform Mask Region based Convolutional Neural Network (NSCT Mask R-CNN) model is designed, and a multimodal feature extraction strategy combining Non downsampled Contourlet Transform (NSCT) features with environmental features is explored. This strategy effectively achieves the goals of object detection and instance segmentation, and thus we have accurately evaluated the growth status of Morchella in the later stages of mulberry, young mushroom, and mature. The experimental results show that both models have achieved significant improvements in recognition accuracy and stability, and the rationality of hyperparameter settings has been verified through convergence and parameter sensitivity experiments. Overall, we provide a more accurate and efficient identification method for monitoring the growth of Morchella, which helps to better understand the growth of Morchella and provides scientific basis for optimizing its growth environment.