Information Processing in Agriculture最新文献

{"title":"Fusing UAV multiple data and phenology to predict crop biomass","authors":"Shuaijie Shen ,&nbsp;Wenjie Li ,&nbsp;Jun Zou ,&nbsp;Matthew Tom Harrison ,&nbsp;Shouyang Liu ,&nbsp;Ehsan Eyshi Rezaei ,&nbsp;Ke Liu ,&nbsp;Bahareh Kamali ,&nbsp;Zechen Wang ,&nbsp;Datong Zhang ,&nbsp;Axiang Zheng ,&nbsp;Fu Chen ,&nbsp;Xiaogang Yin","doi":"10.1016/j.inpa.2025.09.001","DOIUrl":"10.1016/j.inpa.2025.09.001","url":null,"abstract":"<div><div>Robust quantification of crop status in real-time is essential for agile decision-making. While use of unmanned aerial vehicle (UAV) data appears promising in this vein, the contribution and transferability of various features (e.g. vegetation indices, plant height and texture features) in crop above ground biomass (AGB) prediction remain poorly understood. Here, our objectives were to (1) evaluate the performance of various machine learning (ML) algorithms in the synthesis of multiple features, (2) elicit the contribution of various UAV features, (3) assess the transferability of features across growth stages and sites. Four field experiments, incorporating several water and nitrogen treatments across two sites, were assembled for use in AGB prognostics. We invoked four ML algorithms—Random forest (RF), Lasso regression (LR), K-nearest neighbors (KNN) and a stacked ensemble integrating the three methods (SML)—to predict wheat AGB using multiple UAV data and phenological information. Additionally, interpretable ML techniques were employed to elucidate the influence of UAV features on AGB prediction across growth stages. Our results showed that all algorithms exhibited robust performance in predicting wheat biomass, with RMSE values of 1.64, 1.71, 1.71, and 1.57 Mg ha⁻¹ for RF, LR, KNN, and SML, respectively. RF predominantly relied on plant height features, LR leveraged vegetation indices, and KNN prioritized texture features, while SML synthesized the advantages of multiple ML algorithms. Fusion of multiple datasets amplified model prognostic capacity and scalability, with R² and rRMSE of 0.92 and 22 % when using data from external sites. Features pertaining to vegetation indices and plant height during vegetative growth and around flowering had seminal contributions of model predictions. Texture features significantly reduced the saturation effect during the reproductive stage but diminished the model’s transferability during the vegetative stage. Complementarity among data types enhanced effectiveness of ensemble machine learning, which leverages strengths of diverse data to improve the accuracy and robustness of AGB predictions. Future studies could combine multiple sources of remote sensing, such as LiDAR and thermal infrared alongside system modeling, to improve ML accuracy and generalization capability.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 100-118"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147427622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A modular Agritech framework for sustainable horticulture systems: Development and validation in the kiwifruit industry","authors":"Nick Pickering,&nbsp;Mike Duke,&nbsp;ChiKit Au","doi":"10.1016/j.inpa.2025.09.003","DOIUrl":"10.1016/j.inpa.2025.09.003","url":null,"abstract":"<div><div>Horticulture is facing growing challenges, including labour shortages, environmental sustainability, and the need for increased productivity. To address these issues, this paper proposes <em>Modular Agritech Systems for Horticulture (MAS-H)</em>, a modular framework designed to promote the reuse of hardware, software, and capabilities, enabling growers to equitably access and collaboratively use advanced technologies. MAS-H integrates modular edge robotics and an industry-good digital twin to optimize labour, reduce waste, and improve sustainability. The paper presents three case studies within the kiwifruit industry—human assisted harvesting, labour decision support (flower bud thinning) and modular field robot for multitask operations—demonstrating the potential of a framework to address key challenges. Future research will focus on validating MAS-H in real-world settings, exploring its application across other horticulture domains, and developing sustainable support systems. The findings highlight the potential of MAS-H to revolutionize horticulture by delivering Industry 4.0 capabilities where they may not otherwise be commercially viable, desirable, or usable.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 130-141"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147427627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance analysis and parameter optimization of peanut digging shovel operation based on discrete element analysis","authors":"Hao Yang,&nbsp;Dongliang Guo,&nbsp;Yubin Zhai,&nbsp;Jianhui Liang","doi":"10.1016/j.inpa.2025.08.003","DOIUrl":"10.1016/j.inpa.2025.08.003","url":null,"abstract":"<div><div>Digging is the primary process of peanut harvesting. The setting of the operating parameters of peanut digging shovel as a digging tool will greatly influence the resistance and blade wear during peanut digging operation. In this paper, the trapezoidal symmetrical digging shovel is taken as the research object. An interaction model of shovel-soil-root system is established by discrete element software. The working process of peanut digging shovel is simulated by Hertz-mindlin with JKR contact model and Archard Wear model. The test results are analyzed by Design-Expert. The influence of working parameters such as penetration angle, digging depth, working speed and sliding angle on the working resistance and wear of the digging shovel was explored, and the optimal working parameter combination of the peanut digging shovel was determined. When the digging depth is 10 cm, the digging resistance will reach a minimum value within a working speed of 0.86 m /s, a penetration angle of 24.95 degree and a sliding angle of 42.36 degree. At the same depth of 10 cm, the digging shovel wear will reach a minimum value within a working speed of 0.80 m / s, a penetration angle of 24 degree and a sliding angle of 44 degree. Finally, by comparing the variation trend of the working resistance results obtained by the simulation and actual test of the digging shovel at different depths of penetration, the effectiveness of the method for analyzing and optimizing the working parameters of the digging shovel is verified.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 86-99"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147428803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Forecasting the mechanical compaction influence on soybean yield using XGBoost-ANN","authors":"Na Qin ,&nbsp;Xiuli Zhou ,&nbsp;Kaiyu Wang ,&nbsp;Jinyou Qiao ,&nbsp;Hao Sun ,&nbsp;Dawei Wang ,&nbsp;Boxiang Wang","doi":"10.1016/j.inpa.2025.09.002","DOIUrl":"10.1016/j.inpa.2025.09.002","url":null,"abstract":"<div><div>Soil compaction in agricultural fields caused by machinery operations is gradually becoming an important constraint to sustainable agricultural development. Predicting changes in crop yields under compacted environments and warning can help improve crop yields. However, relevant studies are lacking. The objective of this paper is to establish a prediction model for soybean yield changes in the mechanical compaction environment and to explore the predictive ability of the MLR, XGBoost and ANN. We proposed a two-step model to predict the crop yield changes based on the relationship among agricultural machinery operations, soil properties, and crop yield. For acquiring experimental data, we used three types of tractors (large, medium, and small) to complete the field compaction tests. The soybean yield changes model based on XGBoost-ANN hybrid approach has higher precision with R² of 0.889, MAE of 1.47, and RMSE of 1.964. We also verify the effectiveness and robustness of the XGBoost-ANN model using the compaction data from the second year. Moreover, according to the results of the feature importance analysis, we give some suggestions for mitigate the effects of mechanical compaction. We demonstrate the feasibility of predicting changes in crop yields in compaction environments with good results and is important for preserving soil resources and enhancing crop productivity.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 119-129"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147427623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Commercial operation models of agricultural energy internet based on market bidding","authors":"Kun Zheng ,&nbsp;Zhiyuan Sun ,&nbsp;Mosi Liu ,&nbsp;Dechang Yang","doi":"10.1016/j.inpa.2025.08.002","DOIUrl":"10.1016/j.inpa.2025.08.002","url":null,"abstract":"<div><div>This paper conducts an in-depth study on the Agricultural Energy Internet (AEI), covering multiple key areas including business models, market mechanisms, trading markets, bidding models, and trading platform systems. Regarding business models, it analyzes the architecture centered on the deep integration of energy and information, exploring various model types and their operational characteristics. Quantitative results show that AEI business models can improve energy utilization efficiency in agricultural scenarios by 20%–30%. Research on market mechanisms involves the roles of different participants, multi-timescale trading mechanisms, and bidding strategies. The study of renewable energy certificates and carbon markets reveals their critical role in accelerating the decarbonization of agriculture, with multi-modal trading schemes supporting policy compliance and profit generation. A reinforcement learning-based bidding model for electric agricultural machinery is constructed, which reduces electricity procurement costs by an average of 15%, based on simulation training using over 1,000 sets of historical transaction data. The trading platform system, built on the Internet of Energy and blockchain technologies, provides a secure and efficient environment for energy and carbon trading. Overall, the research demonstrates the significant potential of AEI in promoting sustainable agricultural development and supporting the global transition to a low-carbon economy. At the same time, it identifies key challenges and opportunities in areas such as technology application, interdisciplinary integration, policy improvement, and international collaboration.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 72-85"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147427624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MH-YOLO: Multiple heterogeneous YOLO for apple orchard pest detection","authors":"Bo Ma ,&nbsp;Linlin Sun ,&nbsp;Junlin Mu ,&nbsp;Zhuo Ren ,&nbsp;Guanghao Kang ,&nbsp;Ruofei Liu ,&nbsp;Shuangxi Liu ,&nbsp;Xianliang Hu ,&nbsp;Hongjian Zhang ,&nbsp;Jinxing Wang","doi":"10.1016/j.inpa.2025.08.001","DOIUrl":"10.1016/j.inpa.2025.08.001","url":null,"abstract":"<div><div>In apple orchard environments, challenges such as low accuracy and slow speed in pest identification persist, and single improvement strategies fail to balance these requirements effectively. Therefore, this study proposes an apple orchard pest identification method that integrates multiple heterogeneous strategies. This approach encompasses pest sample collection and enhancement, diverse construction of the MH-YOLO model, and model lightweight along with mobile deployment, significantly improving both accuracy and speed in pest identification. Firstly, the MSRCR algorithm adjusts color restoration factors and RGB channel ratios in pest images, enhancing detail and texture information. The zero-sample SAM segmentation model is then employed to accurately extract background-free pest images, providing high-quality datasets for model training. Secondly, using YOLO-v5s as the baseline network, the MH-YOLO model is constructed by integrating Swin-Transformer blocks into the first CSP2_1 module and incorporating the CBAM attention mechanism and ASFF feature fusion module. The model’s learning rate is optimized using a sparrow search algorithm based on an elite reverse strategy, achieving precise pest identification. Finally, channel pruning is applied to the MH-YOLO model for lightweight, and the model is deployed on Android devices to enhance detection efficiency. Comparative experiments with mainstream models such as YOLOv8, YOLOv7, SSD, and Faster R-CNN demonstrate that MH-YOLO exhibits superior performance with an average recognition accuracy of 94.2 %, a model size of 6.92 M, and an FPS of 86. This effectively balances performance and computational resource consumption, providing robust technical support for sustainable pest management in apple orchards.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 47-71"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147427626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Precision pest management in agriculture using Inception V3 and EfficientNet B4: A deep learning approach for crop protection","authors":"Rakesh Kumar Ray ,&nbsp;Sujata Chakravarty ,&nbsp;Satyabrata Dash ,&nbsp;Asit Ghosh ,&nbsp;Sachi Nandan Mohanty ,&nbsp;Venkata Rami Reddy Chirra ,&nbsp;Sarra Ayouni ,&nbsp;M.Ijaz Khan","doi":"10.1016/j.inpa.2025.09.005","DOIUrl":"10.1016/j.inpa.2025.09.005","url":null,"abstract":"<div><div>Ensuring agricultural productivity and sustainability requires timely and accurate pest identification, as pest infestations significantly impact crop yield and food security. With increasing reliance on smart farming practices, artificial intelligence presents an effective solution for early pest detection. This study aims to evaluate and compare the performance of two state-of-the-art deep learning models, Inception V3 and EfficientNet B4, in identifying agricultural pests using transfer learning techniques. Both models were trained and tested on the IP102 dataset, which contains 102 distinct pest classes. The methodology involved leveraging advanced data preprocessing steps, including high-quality image selection and data augmentation, to improve model generalization. Transfer learning and fine-tuning were applied, with optimization of hyperparameters such as learning rate, batch size, and optimizer type to enhance model performance. Experimental results revealed that EfficientNet B4 significantly outperformed Inception V3, achieving a training accuracy of 96.32% and testing accuracy of 82.54%, compared to Inception V3′s 75.23% and 69.00%, respectively. The study also addressed class imbalance, further improving classification accuracy across varied pest types. These findings suggest that EfficientNet B4 is highly effective in detecting a wide range of pests and can be deployed in precision agriculture tools. The application of such AI-powered models holds the potential to revolutionize pest management by enabling early intervention and reducing crop loss. Also, the study contributes to several Sustainable Development Goals (SDGs): SDG 2 by boosting crop yields, SDG 12 by minimizing pesticide usage, SDG 13 by supporting climate-resilient farming, and SDG 15 by preserving biodiversity and encouraging eco-friendly practices.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 142-161"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147428804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decoding drone adoption in agriculture: a comparative analysis of behavioral models","authors":"Nazanin Nafar,&nbsp;Mahsa Fatemi,&nbsp;Kurosh Rezaei-Moghaddam","doi":"10.1016/j.inpa.2025.07.005","DOIUrl":"10.1016/j.inpa.2025.07.005","url":null,"abstract":"<div><div>The adoption of drone technology in agriculture holds transformative potential, offering solutions to improve efficiency, productivity, and sustainability. Understanding the factors that drive or hinder this adoption is critical for leveraging these benefits. This study evaluates the adoption of drone technology among farmers by comparing three predictive models: the Technology Acceptance Model (TAM), the Theory of Planned Behavior (TPB), the Communicative Learning Model (CLM), and a Unified Adoption Behavior Model (UABM) combining the three. A survey was administered to 203 farmers of Fars province, Iran, chosen through stratified random sampling. Data were gathered using a structured questionnaire, and analyzed with SmartPLS3 and SPSS₂₆. The convergent validity, discriminant validity, and reliability of the variables were assessed and confirmed using SmartPLS3. <em>T</em>-test and discriminant analysis was employed to assess the models’ predictive power and their accuracy in classifying drone adopters and non-adopters. The results revealed significant differences between the two groups in variables such as behavioral intention, perceived ease of use, and access to communication channels, with adopters consistently scoring higher than non-adopters. Based on discriminant analysis, the UABM demonstrated superior predictive power, with a classification accuracy of 91.2 %, surpassing TAM, TPB and CLM. Behavioral intention and perceived behavioral control emerged as the most influential factors driving adoption. The findings highlight the importance of addressing resource and confidence barriers among non-adopters and leveraging peer influence and educational programs to foster adoption. The study contributes to a deeper understanding of technology adoption behaviors, particularly in the context of agricultural innovation. It provides practical insights to enhance the adoption and effective utilization of drones in agricultural practices, addressing both theoretical and practical dimensions of this emerging technology.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 1-14"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147427620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Large-scale wheat lodging monitoring by band transformation of UAV and sentinel-2A multispectral imagery","authors":"Baoyuan Zhang ,&nbsp;Meiyan Shu ,&nbsp;Xiaoyuan Bao ,&nbsp;Menglei Dai ,&nbsp;Qian Sun ,&nbsp;Xuguang Sun ,&nbsp;Mingzheng Zhang ,&nbsp;Ying Ren ,&nbsp;Zongpeng Li ,&nbsp;Ya’nan Tian ,&nbsp;Xia Yao ,&nbsp;Xiaohe Gu","doi":"10.1016/j.inpa.2025.07.006","DOIUrl":"10.1016/j.inpa.2025.07.006","url":null,"abstract":"<div><div>Lodging negatively affects wheat yield and quality. Large-scale remote sensing monitoring of wheat lodging is significant for rapidly assessing the impacts of agricultural disasters and formulating precise management strategies. Large-scale remote sensing of wheat lodging requires sufficient in-situ samples, which are faced with the challenges of high cost, low efficiency, and poor real-time performance. This study proposes a method integrating unmanned aerial vehicle (UAV) and satellite (Sentinel-2A) multispectral imagery to achieve low-cost and efficient wheat lodging monitoring. By applying a multilayer perceptron (MLP) algorithm for band transformation, a wheat lodging ratio (WLR) estimation model was constructed based on high-precision UAV data and migrated to satellite data. This model was used to map the distribution of wheat lodging in Henan Province, China. The MLP algorithm achieved high accuracy and stability in band transformation between UAV and Sentinel-2A imagery, with <em>R</em>² values &gt; 0.97 and RMSE values &lt; 0.015. The SPA_XGBoost model delivered the optimal performance in UAV-based WLR monitoring, with a testing set <em>R</em>² of 0.8675, RMSE of 0.0732, and NRMSE of 12.13 %. When applied to satellite imagery for WLR monitoring, the model yielded validation accuracies of <em>R</em>² = 0.8458, RMSE = 0.0985, and NRMSE = 11.24 %. In addition, UAV imagery was used to generate high-accuracy reference data, thereby laying a robust foundation for model construction and transfer. This study significantly reduced the time and economic costs of acquiring ground-truth samples and offered an effective solution for large-scale remote sensing of crop lodging that balances accuracy and scale.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 15-25"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147427621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An insight into productivity, profitability, and sustainable energy use in maize under precision nitrogen management using a smartphone app","authors":"Sayantika Sarkar ,&nbsp;Pravin Kumar Upadhyay ,&nbsp;Abir Dey ,&nbsp;Utpal Ekka ,&nbsp;Kapila Shekhawat ,&nbsp;Sanjay Singh Rathore ,&nbsp;Rajiv Kumar Singh ,&nbsp;G.A. Rajanna ,&nbsp;Subhash Babu ,&nbsp;Anchal Dass ,&nbsp;Rakesh Kumar ,&nbsp;Rabi Narayan Sahoo ,&nbsp;Tarik Mitran ,&nbsp;Kancheti Mrunalini ,&nbsp;Nikita Singh ,&nbsp;Vijay Pooniya ,&nbsp;Mohammad Hasanain ,&nbsp;Navin Kumar Sharma ,&nbsp;Md. Yeasin ,&nbsp;Vinod Kumar Singh","doi":"10.1016/j.inpa.2025.07.007","DOIUrl":"10.1016/j.inpa.2025.07.007","url":null,"abstract":"<div><div>During previous implementation of dark green colour index (DGCI), conventional tools were found inadequate for providing accurate nitrogen (N) recommendations in maize. In contrast, camera-based DGCI methods demonstrated greater effectiveness in predicting the in-season N requirements. To address this incongruity, maize leaf images were captured; resized; white balance corrected; followed by selection of region of interest; normalization; red, green, blue channel extraction; conversion into hue, saturation, brightness spectrum and calculation of DGCI. Simultaneously, NDVI, SPAD, LCC and leaf N% data were collected; and correlated with DGCI; followed by performance analysis; DGCI-based N prescription algorithm development; and its incorporation in “Pusa N Doctor” app developed using Android studio with JNI and Android NDK. The app validation was carried out using basal N dose of 0 kg ha⁻¹ (N₀PK), 50 kg ha⁻¹ (N₅₀PK), &amp; 75 kg ha⁻¹ (N₇₅PK) including 2 split applications of N at 35 &amp; 45 days after sowing (DAS) as per Pusa N Doctor &amp; GreenSeeker™ recommendation. The treatments directed by the mobile application (app-guided) (N₅₀PK + App and N₇₅PK + App) were evaluated with reference to standard RDF as well as those managed using GreenSeeker™ (N₅₀PK + GS^TM and N₇₅PK + GS^TM). The N₅₀PK + App showed at par yield attributes, stover yield (9.34 t ha⁻¹), total biomass yield (17.17 t ha⁻¹), grain protein yield (646.17 kg ha⁻¹), total N uptake (145.96 <!--> <!-->kg ha⁻¹)<!--> <!-->and remobilized vegetative N (89.8 kg ha⁻¹) into grain<!--> <!-->with the RDF.<!--> <!-->Partial factor productivity (PFP_N) and apparent recovery efficiency (ARE_N) of N in N₅₀PK + App was 23% and 22.1% higher than RDF respectively.<!--> <!-->The B:C in<!--> <!-->N₅₀PK + App (2.43)<!--> <!-->was at par with<!--> <!-->N₇₅PK + App (2.44). N₅₀PK + App had the lowest energy consumption (9.72% lower than RDF), highest N energy use efficiency (24.3% higher than RDF) along with the maximum energy profitability, productivity and use efficiency. N₅₀PK + App treatment resulted in marked reductions in GHG emission compared to RDF, with 11.1% lower CO2-eq. emission ha⁻¹, 29.4% lower N₂O emission ha⁻¹, and 11.14% lower CO2-eq. emission t⁻¹. Thus, basal application of 50 kg ha⁻¹ N with two splits of N (35 &amp; 45 DAS) as per Pusa N Doctor can provide at par yield with RDF and GS^TM, while simultaneously promoting N and energy use efficiency thereby, minimising GHG emission.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"13 1","pages":"Pages 26-46"},"PeriodicalIF":7.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147427625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}