Hasil untuk "Agriculture"

Sourish Suri, Yifei Shao

Crop diseases present a significant barrier to agricultural productivity and global food security, especially in large-scale farming where early identification is often delayed or inaccurate. This research introduces a Convolutional Neural Network (CNN)-based image classification system designed to automate the detection and classification of eight common crop diseases using leaf imagery. The methodology involves a complete deep learning pipeline: image acquisition from a large, labeled dataset, preprocessing via resizing, normalization, and augmentation, and model training using TensorFlow with Keras' Sequential API. The CNN architecture comprises three convolutional layers with increasing filter sizes and ReLU activations, followed by max pooling, flattening, and fully connected layers, concluding with a softmax output for multi-class classification. The system achieves high training accuracy (~90%) and demonstrates reliable performance on unseen data, although a validation accuracy of ~60% suggests minor overfitting. Notably, the model integrates a treatment recommendation module, providing actionable guidance by mapping each detected disease to suitable pesticide or fungicide interventions. Furthermore, the solution is deployed on an open-source, mobile-compatible platform, enabling real-time image-based diagnostics for farmers in remote areas. This research contributes a scalable and accessible tool to the field of precision agriculture, reducing reliance on manual inspection and promoting sustainable disease management practices. By merging deep learning with practical agronomic support, this work underscores the potential of CNNs to transform crop health monitoring and enhance food production resilience on a global scale.

Wentao Zhang, Tao Fang, Lina Lu et al.

Accurate and interpretable crop disease diagnosis is essential for agricultural decision-making, yet existing methods often rely on costly supervised fine-tuning and perform poorly under domain shifts. We propose Caption--Prompt--Judge (CPJ), a training-free few-shot framework that enhances Agri-Pest VQA through structured, interpretable image captions. CPJ employs large vision-language models to generate multi-angle captions, refined iteratively via an LLM-as-Judge module, which then inform a dual-answer VQA process for both recognition and management responses. Evaluated on CDDMBench, CPJ significantly improves performance: using GPT-5-mini captions, GPT-5-Nano achieves \textbf{+22.7} pp in disease classification and \textbf{+19.5} points in QA score over no-caption baselines. The framework provides transparent, evidence-based reasoning, advancing robust and explainable agricultural diagnosis without fine-tuning. Our code and data are publicly available at: https://github.com/CPJ-Agricultural/CPJ-Agricultural-Diagnosis.

Juan Cañada, Raúl Alonso, Julio Molleda et al.

The increasing availability of open Earth Observation (EO) and agricultural datasets holds great potential for supporting sustainable land management. However, their high technical entry barrier limits accessibility for non-expert users. This study presents an open-source conversational assistant that integrates multimodal retrieval and large language models (LLMs) to enable natural language interaction with heterogeneous agricultural and geospatial data. The proposed architecture combines orthophotos, Sentinel-2 vegetation indices, and user-provided documents through retrieval-augmented generation (RAG), allowing the system to flexibly determine whether to rely on multimodal evidence, textual knowledge, or both in formulating an answer. To assess response quality, we adopt an LLM-as-a-judge methodology using Qwen3-32B in a zero-shot, unsupervised setting, applying direct scoring in a multi-dimensional quantitative evaluation framework. Preliminary results show that the system is capable of generating clear, relevant, and context-aware responses to agricultural queries, while remaining reproducible and scalable across geographic regions. The primary contributions of this work include an architecture for fusing multimodal EO and textual knowledge sources, a demonstration of lowering the barrier to access specialized agricultural information through natural language interaction, and an open and reproducible design.

Mengisti Berihu Girmay, Jakob Droste, Hannah Deters et al.

Artificial Intelligence (AI) promises new opportunities across many domains, including agriculture. However, the adoption of AI systems in this sector faces several challenges. System complexity can impede trust, as farmers' livelihoods depend on their decision-making and they may reject opaque or hard-to-understand recommendations. Data privacy concerns also pose a barrier, especially when farmers lack transparency regarding who can access their data and for what purposes. This paper examines dairy farmers' explainability requirements for technical recommendations and data privacy, along with the influence of socio-demographic factors. Based on a mixed-methods study involving 40 German dairy farmers, we identify five user personas through k-means clustering. Our findings reveal varying requirements, with some farmers preferring little detail while others seek full transparency across different aspects. Age, technology experience, and confidence in using digital systems were found to correlate with these explainability requirements. The resulting user personas offer practical guidance for requirements engineers aiming to tailor digital systems more effectively to the diverse requirements of farmers.

Mohey Eldeen H. H. Ali, Ahmed F. Tayel, Hossam M. Ezzat et al.

Energy plays a crucial role in national development, influencing critical sectors such as industry, agriculture, healthcare, and education. Accurate energy consumption prediction is essential for efficient energy management, helping prevent imbalances between supply and demand and potential energy shortages. This study aims to forecast the total primary energy supply (TPES), using Egypt as a case study for the first time in literature and utilizing several models (ordinary differential equations (ODEs), regression, and ANN models). Although ordinary differential equations (ODEs) offer flexibility and convenience, their application in energy forecasting remains limited. One of the main objectives of this research is to evaluate the effectiveness of ODEs in predicting energy consumption. Various ODE and regression models are employed to identify the most suitable model amongst each category for forecasting energy demand. Additionally, an artificial neural network (ANN) is developed, trained, validated, and tested for the same forecasting task. The study compares the performance of the selected ODE model (Mendelsohn), with the selected regression model (Polynomial), and an ANN model predicting Egypt’s TPES until 2035. By assessing multiple forecasting methods, this work improves the accuracy and reliability of energy consumption predictions, which is crucial for sustainable energy planning and policy development.

Abdullah Al Faruq, Oky Setyo Widodo, Mitsuhiro Takagi et al.

Reproductive failure in cattle production is a global concern and is influenced by various factors, including genetic alterations. This study explored the relationship between an X-linked single-nucleotide variant (NC_037357.1: g.87298881A>G, rs135720414) in the upstream of the bovine forkhead box P3 (<i>FOXP3</i>) gene and infertility. To this end, we examined the genotypes of the variant in old Asian cattle breeds, including 48 Bali and 5 Jaliteng cattle, and 20 water buffaloes, which have recently shown subclinical signs of infertility and repeated breeding problems among populations in Indonesia. We also examined the genotypes in 69 parous and 39 non-parous Holstein Friesian (HF) cows and investigated the relationship between the genotypes and serum concentration of anti-Müllerian hormone (AMH). The G allele frequency was markedly high in Bali (0.944) and Jaliteng cattle (0.714), and water buffaloes (1), suggesting that the G allele may be originally a wild-type variant in old Asian cattle and buffaloes. In HF cows, the G allele frequency was moderately high, and the AMH concentration was significantly lower (<i>p</i> < 0.05) in parous cows carrying the G allele (A/G and G/G genotypes) than in parous cows with the A/A genotype. In contrast, there were no significant differences in AMH concentrations among the three genotypes of non-parous HF cows. This suggests that both G allele and aging are associated with infertility in HF cows. In conclusion, the G allele of the <i>FOXP3</i> gene variant may potentially be associated with infertility in different bovine breeds and species. Therefore, special attention should be paid to this variant, and infertility in bovine herds may be improved by selection and/or introduction of the A allele.

Suganthi Pazhanivel Koushika, Anbalagan Krishnaveni, Sellaperumal Pazhanivelan et al.

The loss of soil organic carbon (SOC) poses a severe danger to agricultural sustainability around the World. This review examines various farming practices and their impact on soil organic carbon storage. After a careful review of the literature, most of the research indicated that different farming practices, such as organic farming, cover crops, conservation tillage, and agroforestry, play vital roles in increasing the SOC content of the soil sustainably. Root exudation from cover crops increases microbial activity and helps break down complex organic compounds into organic carbon. Conservation tillage enhances the soil structure and maintains carbon storage without disturbing the soil. Agroforestry systems boost organic carbon input and fasten nutrient cycling because the trees and crops have symbiotic relationships. Intercropping and crop rotations have a role in changing the composition of plant residues and promoting carbon storage. There were many understanding on the complex interactions between soil organic carbon dynamics and agricultural practices. Based on the study, the paper reveals, the role of different agricultural practices like Carbon storage through cover crops, crop rotation, mulching Conservation tillage, conventional tillage, zero tillage and organic amendments in organic carbon storage in the soil for maximum crop yield to improve the economic condition of the cultivators.

Vesna Bacheva, Imani Madison, Mathew Baldwin et al.

Feeding the growing human population sustainably amidst climate change is one of the most important challenges in the 21st century. Current practices often lead to the overuse of agronomic inputs, such as synthetic fertilizers and water, resulting in environmental contamination and diminishing returns on crop productivity. The complexity of agricultural systems, involving plant-environment interactions and human management, presents significant scientific and technical challenges for developing sustainable practices. Addressing these challenges necessitates transdisciplinary research, involving intense collaboration among fields such as plant science, engineering, computer science, and social sciences. Here, we present five case studies from two research centers demonstrating successful transdisciplinary approaches toward more sustainable water and fertilizer use. These case studies span multiple scales. Starting from whole-plant signaling, we explore how reporter plants can transform our understanding of plant communication and enable efficient application of water and fertilizers. We then show how new fertilizer technologies could increase the availability of phosphorus in the soil. To accelerate advancements in breeding new cultivars, we discuss robotic technologies for high-throughput plant screening in different environments at a population scale. At the ecosystem scale, we investigate phosphorus recovery from aquatic systems and methods to minimize phosphorus leaching. Finally, as agricultural outputs affect all people, we show how to integrate stakeholder perspectives and needs into the research. With these case studies, we hope to encourage the scientific community to adopt transdisciplinary research and promote cross-training among biologists, engineers, and social scientists to drive discovery and innovation in advancing sustainable agricultural systems.

Sudarssan N

The main aim of the paper is to create a trust and transparency in the food supply chain system, ensuring food safety for everyone with the help of Blockchain Technology. Food supply chain is the process of tracing a crop from the farmer or producer to the buyer. With the advent of blockchain, providing a safe and fraud-free environment for the provision of numerous agricultural necessities has become much easier. Because of the globalization of trade, the present supply chain market today includes various companies involving integration of data, complex transactions and distribution. Information tamper resistance, supply-demand relationships, and traceable oversight are all difficulties that arise as a result of this. Blockchain is a distributed ledger technology that can provide information that is resistant to tampering. This strategy can eliminate the need for a centralized trusted authority, intermediaries, and business histories, allowing for increased production and security while maintaining the highest levels of integrity, liability, and safety. In order to have an integrity and transparency in food supply chain in the agricultural sector, a framework is proposed here based on block chain and IoT.

Alexander Becker, Jan D. Wegner, Evans Dawoe et al.

Reconciling agricultural production with climate-change mitigation is a formidable sustainability problem. Retaining trees in agricultural systems is one proposed solution, but the magnitude of the current and future-potential benefit that trees contribute to climate-change mitigation remains uncertain. Here, we help to resolve these issues across a West African region that produces ~60% of the world's cocoa, a crop contributing one of the highest carbon footprints of all foods. Using machine learning, we mapped shade-tree cover and carbon stocks across the region and found that existing average cover is low (~13%) and poorly aligned with climate threats. Yet, increasing shade-tree cover to a minimum of 30% could sequester an additional 307 million tonnes of CO2e, enough to offset ~167% of contemporary cocoa-related emissions in Ghana and Côte d'Ivoire--without reducing production. Our approach is transferable to other shade-grown crops and aligns with emerging carbon market and sustainability reporting frameworks.

Yu-Fan Lin, Ching-Heng Cheng, Bo-Cheng Qiu et al.

Fusarium Head Blight (FHB) is a serious fungal disease affecting wheat (including durum), barley, oats, other small cereal grains, and corn. Effective monitoring and accurate detection of FHB are crucial to ensuring stable and reliable food security. Traditionally, trained agronomists and surveyors perform manual identification, a method that is labor-intensive, impractical, and challenging to scale. With the advancement of deep learning and Hyper-spectral Imaging (HSI) and Remote Sensing (RS) technologies, employing deep learning, particularly Convolutional Neural Networks (CNNs), has emerged as a promising solution. Notably, wheat infected with serious FHB may exhibit significant differences on the spectral compared to mild FHB one, which is particularly advantageous for hyperspectral image-based methods. In this study, we propose a self-unsupervised classification method based on HSI endmember extraction strategy and top-K bands selection, designed to analyze material signatures in HSIs to derive discriminative feature representations. This approach does not require expensive device or complicate algorithm design, making it more suitable for practical uses. Our method has been effectively validated in the Beyond Visible Spectrum: AI for Agriculture Challenge 2024. The source code is easy to reproduce and available at {https://github.com/VanLinLin/Automated-Crop-Disease-Diagnosis-from-Hyperspectral-Imagery-3rd}.

Samarth Chopra, Fernando Cladera, Varun Murali et al.

Neural Radiance Fields (NeRFs) have shown significant promise in 3D scene reconstruction and novel view synthesis. In agricultural settings, NeRFs can serve as digital twins, providing critical information about fruit detection for yield estimation and other important metrics for farmers. However, traditional NeRFs are not robust to challenging lighting conditions, such as low-light, extreme bright light and varying lighting. To address these issues, this work leverages three different sensors: an RGB camera, an event camera and a thermal camera. Our RGB scene reconstruction shows an improvement in PSNR and SSIM by +2.06 dB and +8.3% respectively. Our cross-spectral scene reconstruction enhances downstream fruit detection by +43.0% in mAP50 and +61.1% increase in mAP50-95. The integration of additional sensors leads to a more robust and informative NeRF. We demonstrate that our multi-modal system yields high quality photo-realistic reconstructions under various tree canopy covers and at different times of the day. This work results in the development of a resilient NeRF, capable of performing well in visibly degraded scenarios, as well as a learnt cross-spectral representation, that is used for automated fruit detection.

Xiangyu Huang, Guihu Yin, Yiqin Cai et al.

In the original publication [...]

Abhishesh Pal, Antonio C. Leite, Jon G. O. Gjevestad et al.

In farming systems, harvesting operations are tedious, time- and resource-consuming tasks. Based on this, deploying a fleet of autonomous robots to work alongside farmworkers may provide vast productivity and logistics benefits. Then, an intelligent robotic system should monitor human behavior, identify the ongoing activities and anticipate the worker's needs. In this work, the main contribution consists of creating a benchmark model for video-based human pickers detection, classifying their activities to serve in harvesting operations for different agricultural scenarios. Our solution uses the combination of a Mask Region-based Convolutional Neural Network (Mask R-CNN) for object detection and optical flow for motion estimation with newly added statistical attributes of flow motion descriptors, named as Correlation Sensitivity (CS). A classification criterion is defined based on the Kernel Density Estimation (KDE) analysis and K-means clustering algorithm, which are implemented upon in-house collected dataset from different crop fields like strawberry polytunnels and apple tree orchards. The proposed framework is quantitatively analyzed using sensitivity, specificity, and accuracy measures and shows satisfactory results amidst various dataset challenges such as lighting variation, blur, and occlusions.

Justin Hastings, David Ubilava

We examine whether harvest-time transitory shifts in employment and income lead to changes in political violence and social unrest in rice-producing croplands of Southeast Asia. Using monthly data from 2010 to 2023 on over 86,000 incidents covering 376 one-degree cells across eight Southeast Asian countries, we estimate a general increase in political violence and a decrease in social unrest in croplands with rice production during the harvest season relative to the rest of the crop year. In a finding that is least sensitive to alternative model specifications and data subsetting, we estimate a nine percent increase in violence against civilians in locations with considerable rice production compared to other parts of the region during the harvest season, relative to the rest of the year. We show that the harvest-time changes in conflict are most evident in rural cells with rainfed agriculture. Using location-specific annual variation in growing season rainfall, we then show that the harvest-time increase in violence against civilians occurs in presumably good harvest years, whereas increase in battles between actors of political violence follows growing seasons with scarce rainfall. The harvest-time decrease in social unrest, protests in particular, occurs after presumably bad harvest years. These findings contribute to research on the agroclimatic and economic roots of conflict and offer insights to policymakers by suggesting the spatiotemporal concentration of conflict as well as diverging effects by forms of conflict at harvest time in the rice-producing regions of Southeast Asia.

Jean Bouchat, Emma Tronquo, Anne Orban et al.

The BELSAR dataset is a unique collection of high-resolution airborne mono- and bistatic fully-polarimetric synthetic aperture radar (SAR) data in L-band, alongside concurrent measurements of vegetation and soil bio-geophysical variables measured in maize and winter wheat fields during the summer of 2018 in Belgium. This innovative dataset, the collection of which was funded by the European Space Agency (ESA), helps addressing the lack of publicly-accessible experimental datasets combining multistatic SAR and in situ measurements. As such, it offers an opportunity to advance the development of SAR remote sensing science and applications for agricultural monitoring and hydrology. This paper aims to facilitate its adoption and exploration by offering comprehensive documentation and integrating its multiple data sources into a unified, analysis-ready dataset.

Haohao Du

To address the challenges of delayed scheduling information, heavy reliance on manual labour, and low operational efficiency in traditional large-scale agricultural machinery operations, this study proposes a method for multi-agricultural machinery collaborative task assignment based on an improved genetic hybrid optimisation algorithm. The proposed method establishes a multi-agricultural machinery task allocation model by combining the path pre-planning of a simulated annealing algorithm and the static task allocation of a genetic algorithm. By sequentially fusing these two algorithms, their respective shortcomings can be overcome, and their advantages in global and local search can be utilised. Consequently, the search capability of the population is enhanced, leading to the discovery of more optimal solutions. Then, an adaptive crossover operator is constructed according to the task assignment model, considering the capacity, path cost, and time of agricultural machinery; two-segment coding and multi-population adaptive mutation are used to assign tasks to improve the diversity of the population and enhance the exploration ability of the population; and to improve the global optimisation ability of the hybrid algorithm, a 2-Opt local optimisation operator and an Circle modification algorithm are introduced. Finally, simulation experiments were conducted in MATLAB to evaluate the performance of the multi-agricultural machinery collaborative task assignment based on the improved genetic hybrid algorithm. The algorithm's capabilities were assessed through comparative analysis in the simulation trials. The results demonstrate that the developed hybrid algorithm can effectively reduce path costs, and the efficiency of the assignment outcomes surpasses that of the classical genetic algorithm. This approach proves particularly suitable for addressing large-scale task allocation problems.

Yi Wang, Chenying Liu, Arti Tiwari et al.

Discovering ancient agricultural terraces in desert regions is important for the monitoring of long-term climate changes on the Earth's surface. However, traditional ground surveys are both costly and limited in scale. With the increasing accessibility of aerial and satellite data, machine learning techniques bear large potential for the automatic detection and recognition of archaeological landscapes. In this paper, we propose a deep semantic model fusion method for ancient agricultural terrace detection. The input data includes aerial images and LiDAR generated terrain features in the Negev desert. Two deep semantic segmentation models, namely DeepLabv3+ and UNet, with EfficientNet backbone, are trained and fused to provide segmentation maps of ancient terraces and walls. The proposed method won the first prize in the International AI Archaeology Challenge. Codes are available at https://github.com/wangyi111/international-archaeology-ai-challenge.

Zhiman Zan, Nianyuan Jiao, Rentian Ma et al.

The intercropping of maize (<i>Zea mays</i> L.) and peanuts (<i>Arachis hypogaea</i> L.) (M||P) significantly enhances crop yield. In a long-term M||P field experiment with two P fertilizer levels, we examined how long-term M||P affects topsoil aggregate fractions and stability, organic carbon (SOC), available phosphorus (AP), and total phosphorus (TP) in each aggregate fraction, along with crop yields. Compared to their respective monocultures, long-term M||P substantially increased the proportion of topsoil mechanical macroaggregates (7.6–16.3%) and water-stable macroaggregates (>1 mm) (13.8–36.1%), while reducing the unstable aggregate index (E_LT) and the percentage of aggregation destruction (PAD). M||P significantly boosted the concentration (12.9–39.9%) and contribution rate (4.1–47.9%) of SOC in macroaggregates compared to single crops. Moreover, the concentration of TP in macroaggregates (>1 mm) and AP in each aggregate fraction of M||P exceeded that of the respective single crops (<i>p</i> < 0.05). Furthermore, M||P significantly increased the Ca₂-P, Ca₈-P, Al-P, and Fe-P concentrations of intercropped maize (IM) and the Ca₈-P, O-P, and Ca₁₀-P concentrations of intercropped peanuts (IP). The land equivalent ratio (LER) of M||P was higher than one, and M||P stubble improved the yield of subsequent winter wheat (<i>Triticum aestivum</i> L.) compared with sole-crop maize stubble. P application augmented the concentration of SOC, TP, and AP in macroaggregates, resulting in improved crop yields. In conclusion, our findings suggest that long-term M||P combined with P application sustains farmland productivity in the North China Plain by increasing SOC and macroaggregate fractions, improving aggregate stability, and enhancing soil P availability.

Supriyanta B, Wahyurini E, Alana A D

Plant breeding programs in assembling high yielding varieties of melon need to know the qualitative and quantitative characters. The superior melon plants that people are interested in are fresh fruit, sweet taste, thick and durable fruit flesh. The study was to obtain character nine of strains melon, clustering analysis, determine the estimated value of genetic diversity and determine potential melon strains for future breeding programs. The research method was a field experiment in a Completely Randomized Block Design with a single factor and three replications. The treatments used were 9 strains of melons DS-1-2-10-21-11, DS-1-2-10-21-22, DS-1-2-10-21-31, DNG-1-47-13, DNG-1-47-22, DNG-1-47-31, DNG-1-47-32, APL-11 and APL-12. The data were analyzed using Analysis of variance followed by Duncan’s Multiple Range Test (DMRT) with a level 5%. Estimation of genetic diversity is done by calculating the coefficient of diversity and heritability values in a broad sense. Clustering was analyzed using the Agglomerative Hierarchical Clustering Method. The coefficient of similarity between strains was measured using the Euclidian Distance measurement transformation matrix. The character of the melon strains 1-2-10-21-31 is shorter, the stem diameter is large, the female flowering ages faster, the fruit diameter is large and the fruit flesh is thick. There are three clusters formed based on parameters. Variable plant height at 2 wap has a wide range of genetic diversity coefficients. A potential strains for further breeding programs is DS-1-2-10-21-31.