Information Processing in Agriculture最新文献

Analysis of seedling-picking trajectory error in gear train seedling pick-up mechanisms considering center-distance errors 考虑中心距误差的齿轮传动采苗机构采苗轨迹误差分析

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2026-02-03 DOI: 10.1016/j.inpa.2026.02.002

Jiangang Liu, Fengjiao Du, Peng Qi, Tengfei Shen, Jingguo Shen

{"title":"Analysis of seedling-picking trajectory error in gear train seedling pick-up mechanisms considering center-distance errors","authors":"Jiangang Liu, Fengjiao Du, Peng Qi, Tengfei Shen, Jingguo Shen","doi":"10.1016/j.inpa.2026.02.002","DOIUrl":"10.1016/j.inpa.2026.02.002","url":null,"abstract":"<div><div>To improve the success rate of seedling-picking, this study investigates the influence of center-distance errors (CDE) on the seedling-picking trajectory of a planetary gear–based seedling pick-up mechanism (SPUM). The mathematical model of kinematic parameters of needle-tip was developed to characterize the resulting variations in coordinates and associated, incorporating multiple types of CDE—including first-stage transmission (FST), second-stage transmission (SST), and angular misalignment between the two stages. The effects of first-stage CDE (△<em>h</em> = 0.05–0.30 mm), second-stage CDE (Δ<em>L</em><sub>2</sub> <em>=</em> 0.05–0.30 mm), and angular misalignment (Δ<em>δ</em><sub>1</sub> = −1–1°) between the two stages on the displacement, velocity, and acceleration of the needle-tip were quantitatively analyzed. In addition, the relationships among CDE, tooth backlash, and trajectory deviation were examined. The results show that a first-stage CDE of 0.3 mm leads to a maximum needle-tip coordinate deviation of approximately 4 mm, and larger CDE cause markedly greater fluctuations in the seedling-picking trajectory. These findings demonstrate that precise calibration and control of center-distance are essential during both the design and manufacturing of SPUM.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 451-465"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148861754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Harnessing technology: A systematic review of artificial intelligence and expert systems in date palm agriculture 利用技术：人工智能和专家系统在枣椰树农业的系统回顾

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2026-05-17 DOI: 10.1016/j.inpa.2026.05.005

A.M. Mutawa

{"title":"Harnessing technology: A systematic review of artificial intelligence and expert systems in date palm agriculture","authors":"A.M. Mutawa","doi":"10.1016/j.inpa.2026.05.005","DOIUrl":"10.1016/j.inpa.2026.05.005","url":null,"abstract":"<div><div>Date palms are an essential agricultural asset in arid and semi-arid areas, considerably enhancing local economies and food security. Recent research has examined several facets of date palm production, including genetic diversity, water management, anddisease detection,underscoring the need to understand these elements to improve productivity and sustainability. This systematic review seeks to consolidate research on date palm farming, emphasizing techniques such as Artificial Intelligence (AI) and expert systems in date palm production. The search was conducted across five databases to identify relevant studies published from 2020 to October 2024. The non-English, non-peer-reviewed, and full-text-unavailable papers were excluded. A total of 39 papers covering the date palm in AI and expert systems were included in the review. Though scalability and real-time adaptation were limited, expert systems showed promise in combining sensor data for monitoringand offering valuable insights. While AI models achieved excellent accuracy in illness detection and classification tasks, they struggled to generalize to new datasets and to apply in real-world settings. The detection and management of date palm cultivation could be significantly improved by expert systems and AImodels. Nonetheless, its practical implementation is constrained by issues related to data quality, adaptability, and integrating systems. Future research should focus on developing robust, adaptable structures and integrating diverse datasets to address these constraints.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 479-497"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148861753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Accessible drone image processing for sustainable resource management of 3D tree-like crops using unsupervised algorithms 使用无监督算法的3D树状作物可持续资源管理的无障碍无人机图像处理

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2025-11-30 DOI: 10.1016/j.inpa.2025.11.009

Xizhi Xia, Jaydeep Sachar, Khail Alibhai, Jeannifer Labelle, Dmitry Demin, Emmanuel Sulle, Woo Soo Kim

{"title":"Accessible drone image processing for sustainable resource management of 3D tree-like crops using unsupervised algorithms","authors":"Xizhi Xia, Jaydeep Sachar, Khail Alibhai, Jeannifer Labelle, Dmitry Demin, Emmanuel Sulle, Woo Soo Kim","doi":"10.1016/j.inpa.2025.11.009","DOIUrl":"10.1016/j.inpa.2025.11.009","url":null,"abstract":"<div><div>This study presents a novel AI-driven solution designed to enhance sustainable resource management and increase accessibility for farmers through visualized and digitalized tree information. The proposed methodology includes optimizing drone mapping for effective data coverage, capturing high-resolution imagery, and generating a 3D Point Cloud, with a particular emphasis on the integration of Weighted K-means, Density-based spatial clustering of applications with noise (DBSCAN), and cluster separation algorithms to develop a high-precision, training-free stepwise crop segmentation algorithm for extracting essential phenotypic traits such as crop height and canopy volume. The algorithm was validated using avocado trees in Tanzania and hazelnut trees in Canada, demonstrating its robustness across different tree types and planting conditions. Notably, this study highlights the feasibility of extracting crop height without constructing a Digital Terrain Model (DTM), thereby mitigating errors associated with DTM inaccuracies. The proposed stepwise segmentation algorithm achieved a height estimation R<sup>2</sup> of 0.967 and volume estimation R<sup>2</sup> of 0.91 for avocado trees, demonstrating high accuracy without the need for DTM or training data. The developed algorithm, coupled with a user-friendly graphical user interface (GUI), provides farmers with a reliable tool for monitoring crop health and optimizing field management, representing a significant advancement in precision agriculture technology with wide-ranging applicability.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 373-382"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic energy consumption modeling of V-belt in combine harvesters 联合收割机v带动态能耗建模

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2026-01-30 DOI: 10.1016/j.inpa.2026.01.016

Baoyan Xu, Yehong Liu, Yining Fu, Xin Wang

{"title":"Dynamic energy consumption modeling of V-belt in combine harvesters","authors":"Baoyan Xu, Yehong Liu, Yining Fu, Xin Wang","doi":"10.1016/j.inpa.2026.01.016","DOIUrl":"10.1016/j.inpa.2026.01.016","url":null,"abstract":"<div><div>V-belts in combine harvesters are prone to burnout failures under high-load continuous operations, compromising transmission reliability. However, the underlying thermomechanical coupling mechanisms remain poorly understood. To address this limitation, this study presents a dynamic energy dissipation model that decouples multiple heat generation mechanisms—bending hysteresis, compressive deformation, tensile strain, and external sliding friction—in V-belt drives. Finite element analysis is used to characterize the spatiotemporal loading behavior of internal friction sources, and energy dissipation quantification methods are developed based on viscoelastic theory and Coulomb friction law. A steady-state heat transfer framework is established, and critical thermal boundary parameters are identified through inverse modeling. The integrated thermomechanical model is validated by comparing simulated surface temperature fields with experimental data obtained from a custom-built test rig. The results show that predicted steady-state temperatures are marginally overestimated, with relative errors below 5%, exhibiting clear dependence on driving pulley speed and driven pulley load. The analysis reveals that high-speed operation intensifies internal hysteresis heating, whereas high-load conditions amplify external friction losses—synergistically leading to elevated thermal stress and increased burnout risk. Thus, the study elucidates the failure mechanisms under combined dynamic loads, enabling physics-driven design optimization and predictive maintenance for agricultural machinery powertrains.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 433-450"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Grassland ecosystem assessments: Integrating UAV-derived features for aboveground biomass estimation 草地生态系统评估：整合无人机衍生的地上生物量估算特征

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2026-01-11 DOI: 10.1016/j.inpa.2026.01.003

Clara Oliva Gonçalves Bazzo, Bahareh Kamali, Murilo dos Santos Vianna, Dominik Behrend, Hubert Hueging, Farshid Jahanbakhshi, Inga Schleip, Paul Mosebach, Almut Haub, Axel Behrendt, Thomas Gaiser

{"title":"Grassland ecosystem assessments: Integrating UAV-derived features for aboveground biomass estimation","authors":"Clara Oliva Gonçalves Bazzo, Bahareh Kamali, Murilo dos Santos Vianna, Dominik Behrend, Hubert Hueging, Farshid Jahanbakhshi, Inga Schleip, Paul Mosebach, Almut Haub, Axel Behrendt, Thomas Gaiser","doi":"10.1016/j.inpa.2026.01.003","DOIUrl":"10.1016/j.inpa.2026.01.003","url":null,"abstract":"<div><div>Monitoring grasslands presents significant challenges due to temporal and spatial dynamics in their vegetation. This is particularly pronounced in wet grasslands, where moisture dynamics also impact vegetation patterns. Recent advancements in data acquisition and analysis via Unmanned Aerial Vehicles (UAVs) have shown potential for a more comprehensive understanding of vegetation dynamics. However, current UAV-based methods focus predominantly on structural and spectral data analysis. This often overlooks the horizontal heterogeneity within vegetation. This study addresses this gap by integrating texture analysis, alongside structural and spectral data, to enhance aboveground biomass (AGB) estimation. The research was conducted in a heterogeneous wet grassland in eastern Germany under three different cutting frequencies. Regular UAV flights were carried out to obtain RGB (Red, Green, and Blue) and multispectral images, analyzed alongside ground-reference data from 108 plots, to evaluate canopy height and biomass. We tested the performance of Random Forest and Partial Least Squares Regression models for AGB estimation considering different combinations of features including canopy height model vegetation indices and texture analysis. The results demonstrate that texture analysis when combined with traditional spectral and structural data, enhances predictive accuracy, yielding the best R<sup>2</sup> values of up to 0.84 for AGB and reducing the relative root mean square errors to 26.6 %. The results underline the potential of combining UAV-based features in AGB estimation of heterogeneous grassland ecosystems offering a path forward for more effective ecological monitoring and sustainable grassland management.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 396-414"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Information processing and enabling technologies for agricultural energy Internet applications 农业能源互联网应用信息处理与使能技术

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2026-01-22 DOI: 10.1016/j.inpa.2026.01.010

Xiurong Zhang, Xuanye Zhao, Hamed Badihi, Ammar Al-Bazi, Zhengmao Li, Dawei Qiu

{"title":"Information processing and enabling technologies for agricultural energy Internet applications","authors":"Xiurong Zhang, Xuanye Zhao, Hamed Badihi, Ammar Al-Bazi, Zhengmao Li, Dawei Qiu","doi":"10.1016/j.inpa.2026.01.010","DOIUrl":"10.1016/j.inpa.2026.01.010","url":null,"abstract":"<div><div>This study provides a systematic exposition of the Agricultural Energy Internet (AEI), offering an in-depth analysis within the context of smart agriculture. This work elucidates the evolutionary pathway and emerging trends of AEI, along with the technologies underpinning its implementation. Through a systematic analysis of literature published over the past five years, the study focuses on three key research domains: (1) agricultural electrification, (2) rural energy systems, and (3) smart agriculture, thereby mapping the current research landscape of AEI. Representative studies across different developmental stages are examined to trace the evolution of AEI and its future directions, revealing a clear shift toward integrated multi-scale system-level energy modeling and large-scale AI-driven optimization. This study systematically delineates the technical architecture and evolutionary trajectory of the AEI. Finally, drawing on recent high-impact publications, three frontier research directions are identified: (1) generative AI for smart agriculture, (2) high-efficiency carbon capture technologies, and (3) low-cost energy harvesting systems.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 415-432"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating image analysis and ensemble learning for predictive modeling of wood density and MC using line scanner and camera systems 整合图像分析和集成学习木材密度和MC使用线扫描仪和相机系统的预测建模

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2025-12-01 DOI: 10.1016/j.inpa.2025.11.008

Benedictus Reynaldo Hartanto, Te Ma, Yohei Kurata, Hikaru Kobori, Satoru Tsuchikawa, Tetsuya Inagaki

{"title":"Integrating image analysis and ensemble learning for predictive modeling of wood density and MC using line scanner and camera systems","authors":"Benedictus Reynaldo Hartanto, Te Ma, Yohei Kurata, Hikaru Kobori, Satoru Tsuchikawa, Tetsuya Inagaki","doi":"10.1016/j.inpa.2025.11.008","DOIUrl":"10.1016/j.inpa.2025.11.008","url":null,"abstract":"<div><div>Conventional wood quality assessments often involve invasive methods that increase costs and weaken material integrity. Recent studies using machine learning, particularly convolutional neural networks (CNNs) and ensemble learning, have shown high accuracy in predicting wood density and mechanical properties from images. However, real-time evaluation of moisture content (MC) across different species remains underexplored. This research introduces a non-destructive approach that integrates 2D image analysis with an advanced ensemble learning model to predict both wood density and MC, using high-resolution images from Line Scanner and Camera Systems to extract key color features and wood attributes. A novel real-time MC determination method employing a gravimetric formula based on actual sample dimensions and weights further enhances immediate wood evaluation. The model achieves reliable predictions with a Coefficient of Determination (R<sup>2</sup>) of 0.94 for oven-dry density and 0.85 for MC, and Root Mean Square Errors (RMSE) of 0.01 g/cm<sup>3</sup> and 8.33 %, respectively, offering a precise, viable tool for real-time wood quality and moisture assessment, and advancing sustainable industry practices.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 358-372"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Continuous route planning method based on density grading for thinning of walnut male flowers 基于密度分级的核桃雄花间伐连续路线规划方法

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2026-03-20 DOI: 10.1016/j.inpa.2026.03.012

Pingyi Liu, Xu Zhang, Hengda Li, Jialin Zhang, Yizheng Wang, Jie Zhang, Haichao Li

{"title":"Continuous route planning method based on density grading for thinning of walnut male flowers","authors":"Pingyi Liu, Xu Zhang, Hengda Li, Jialin Zhang, Yizheng Wang, Jie Zhang, Haichao Li","doi":"10.1016/j.inpa.2026.03.012","DOIUrl":"10.1016/j.inpa.2026.03.012","url":null,"abstract":"<div><div>Walnut male catkins commonly appear in clusters and are irregularly distributed across the tree, which makes it difficult to generate a continuous path during mechanical thinning. To reduce energy consumption and simplify route planning, a method termed continuous route planning of extensive and efficient mechanical thinning for walnut male flower based on density grading (CRPE′-DG) is proposed via a sub-regional route-planning strategy along the main branches. This method incorporates and improves the Density-Based Spatial Clustering of Applications with Noise (DBSCAN), B-Spline fitting, and Makima interpolation algorithm to generate end-effector motion routes for the robotic arm. The performance of CRPE′-DG is evaluated in terms of dispersion degree, thinning rate, and route length. The Interquartile Range (<em>IQR</em>) of the dispersion of male flowers at high-density levels is consistently lower than that at low-density levels. On average, the dispersion degree is reduced by 57.5% and 31.9% compared with the 5th-order and 7th-order polynomial fitting algorithms, respectively. The average thinning rate using the CRPE′-DG method has been increased to 83.6%, which is 11.3% and 6.3% higher than the 5th-order and 7th-order algorithms. Meanwhile, the average route length is shortened by 15.3%, 18.0%, and 14.1% compared with the 5th-order, 7th-order, and traditional B-spline algorithms, respectively, with a maximum reduction of 28.0% in sample 1. These results demonstrate that CRPE′-DG can effectively improve thinning efficiency, generate more continuous routes, and reduce energy consumption, thereby supporting sustainable agricultural development.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 466-478"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine learning for asymptomatic Ratoon stunting disease detection with freely available satellite based multispectral imaging 利用免费的基于卫星的多光谱成像进行无症状Ratoon发育不良疾病检测的机器学习

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2025-12-01 DOI: 10.1016/j.inpa.2025.12.001

Ethan Kane Waters, Carla Chia-Ming Chen, Mostafa Rahimi Azghadi

{"title":"Machine learning for asymptomatic Ratoon stunting disease detection with freely available satellite based multispectral imaging","authors":"Ethan Kane Waters, Carla Chia-Ming Chen, Mostafa Rahimi Azghadi","doi":"10.1016/j.inpa.2025.12.001","DOIUrl":"10.1016/j.inpa.2025.12.001","url":null,"abstract":"<div><div>Disease detection in sugarcane, particularly the identification of asymptomatic infectious diseases such as Ratoon Stunting Disease (RSD), is critical for effective crop management. This study employed various machine learning techniques to detect the presence of RSD in different sugarcane varieties, using vegetation indices derived from freely available satellite-based spectral data. Our results show that the Support Vector Machine with a Radial Basis Function Kernel (SVM-RBF) was the most effective algorithm, achieving classification accuracy between 85.64% and 96.55%, depending on the variety. Gradient Boosting and Random Forest also demonstrated high performance achieving accuracy between 83.33% to 96.55%, while Logistic Regression and Quadratic Discriminant Analysis showed variable results across different varieties. The inclusion of sugarcane variety and vegetation indices was important in the detection of RSD. This agreed with what was identified in the current literature. Our study highlights the potential of satellite-based remote sensing as a cost-effective and efficient method for large-scale sugarcane disease detection alternative to traditional manual laboratory testing methods.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 383-395"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148861755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A hyperspectral and RGB crop pests/diseases image fusion method based on SADAE-GAN with combined perceptual gradient loss 结合感知梯度损失的SADAE-GAN高光谱与RGB作物病虫害图像融合方法

IF 8.9

Information Processing in Agriculture Pub Date : 2026-09-01 Epub Date: 2025-12-05 DOI: 10.1016/j.inpa.2025.11.007

Min Dai, Youzhi Dai, Wenjing Sun, Xin Ji, Hong Miao, Yuanyuan Gao, Xinhua Wei

{"title":"A hyperspectral and RGB crop pests/diseases image fusion method based on SADAE-GAN with combined perceptual gradient loss","authors":"Min Dai, Youzhi Dai, Wenjing Sun, Xin Ji, Hong Miao, Yuanyuan Gao, Xinhua Wei","doi":"10.1016/j.inpa.2025.11.007","DOIUrl":"10.1016/j.inpa.2025.11.007","url":null,"abstract":"<div><div>Accurate monitoring of crop pests and diseases is essential due to their diversity, widespread impact, and increasing severity. However, RGB images lack spectral richness, and hyperspectral images suffer from resolution loss caused by long exposure times. Existing fusion methods often lose important features, reducing the accuracy and practicality of pest and disease monitoring. To address these issues, this paper proposes a SADAE-GAN model, which combines Deep Convolutional Generative Adversarial Networks (DCGAN), Self-Attention (SA), and Denoising Auto-Encoders (DAE) techniques. The model enhances both local and global feature extraction through a primary processing module and DAE in the generator, while the discriminator uses an SA attention mechanism to improve image reconstruction quality. Additionally, a novel perceptual gradient loss function and an Autoencoder and Continuous Wavelet Transform (Auto-CWT) image transformation method are introduced to optimize image generation and monitoring performance. Experimental results across multiple datasets demonstrate that the proposed SADAE-GAN outperforms existing popular fusion methods like CycleGAN, ResNet, SSRNET, InfoGAN, and QIS-GAN. For evaluation metrics <em>SSIM</em>, <em>PSNR</em>, <em>MSE</em>, and <em>IS</em>, the maximum performance improvement reached 20.7 %, 68.2 %, 39.7 %, and 33.0 %, respectively. In addition, ablation studies confirm the effectiveness of the proposed model, and robustness tests further reveal the model’s strong practical applicability. These results demonstrate that SADAE-GAN excels in fusion quality, robust feature preservation, and strong generalization capability, providing a promising and efficient solution for precise agricultural pest and disease monitoring.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 3","pages":"Pages 343-357"},"PeriodicalIF":8.9,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148859385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0