European Journal of Agronomy最新文献

{"title":"Artificial intelligence for pest identification and decision support in sustainable crop protection: A critical review","authors":"Azam Amiri ,&nbsp;Ali R. Bandani","doi":"10.1016/j.eja.2026.128040","DOIUrl":"10.1016/j.eja.2026.128040","url":null,"abstract":"<div><div>Plant pest and disease management is a critical pillar of global food security because insect pests and pathogens significantly reduce crop yield and quality. Integrating artificial intelligence (AI) into pest management is an emerging frontier that can transform how crop protection decisions are made and implemented in the field. Here, we consider AI as an umbrella covering machine learning and deep learning, which learn patterns from data to support prediction and classification. This review synthesizes recent AI-based approaches for field-relevant identification and decision support in sustainable crop protection, with an emphasis on image-based diagnostics and their integration into operational Integrated Pest Management (IPM). AI can complement manual scouting and broad-spectrum pesticide use, which are increasingly constrained by resistance evolution, non-target impacts, regulatory pressure, and labor demands. Beyond describing tools, we critically map how AI-enabled sensing and inference (e.g., automated identification, counting, forecasting, and uncertainty/explainability) become decision-relevant outputs that can be linked to action/economic thresholds and embedded in decision-support systems (DSS) under real field variability. Key limitations include biased and geographically concentrated datasets, difficulty separating pests from beneficials or morphologically similar taxa, weak transferability under real field conditions, and barriers related to interpretability, infrastructure, and adoption in low-resource settings. By organizing the evidence around an end-to-end operational IPM workflow (moving from monitoring to pest pressure indicators, thresholds to DSS recommendations, and interventions to feedback and field validation), this review clarifies where AI adds actionable value and what must be validated to deliver robust, context-appropriate tools for sustainable crop protection.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"176 ","pages":"Article 128040"},"PeriodicalIF":5.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From UAV imagery to mapping: Detecting sunflower heads in fields using a novel lightweight deep learning network","authors":"Rui Jing ,&nbsp;Qinglin Niu ,&nbsp;Qingqing Zhao ,&nbsp;Jingcui Shao ,&nbsp;Zongpeng Li ,&nbsp;Bowei Qi ,&nbsp;Guize Chao ,&nbsp;Yuanzhi Ma ,&nbsp;Dongwei Li ,&nbsp;Xinguo Zhou","doi":"10.1016/j.eja.2026.128018","DOIUrl":"10.1016/j.eja.2026.128018","url":null,"abstract":"<div><div>Efficient and non-invasive field-scale detection and localization of sunflower heads (SHs), together with spatial distribution mapping, can support pre-harvest yield prediction, optimization of mechanical harvesting, field management, and high-throughput phenotyping. Unmanned aerial vehicle (UAV) imagery, with its low cost and high spatiotemporal resolution, makes such field-scale monitoring practically feasible. However, accurately detecting and mapping individual SHs from high-resolution UAV images remains challenging, especially under resource-constrained computing environments. To address this, we used UAV RGB imagery to construct a sunflower head detection dataset covering both flowering and maturity stages. Furthermore, a lightweight deep learning network, built upon YOLOv8n improvements, was proposed to enable efficient head detection and mapping. First, the DWCSP module is introduced, utilizing depthwise convolution and multi-branch feature fusion for feature extraction, thereby significantly reducing the network complexity. Additionally, a lightweight detection head integrating partial convolution was designed to further accelerate inference speed, and the WIoU loss function was adopted to enhance detection performance. Experimental results revealed that, when compared to the baseline, the computational complexity and parameters of the proposed model were reduced by 60.5 % and 49.5 %, respectively, with values reaching 3.2 GFLOPs and 1.52 M and a model size of only 3.1 MB. This model achieved an impressive 96.2 % [email protected]. When deployed on a CPU and the Jetson Orin Nano platform, inference speeds of 16 FPS and 67 FPS were attained, representing improvements of 33.3 % and 24.1 % over the baseline. Additionally, the model was employed to perform overlapping slice detection on UAV orthomosaic images from two sample fields, mapping individual SHs locations to geographic coordinates and generating spatial and density distribution maps of the heads. This produces an end-to-end workflow from UAV imagery to geospatial data, which provides an effective approach for pre-harvest yield estimation and analysis of agronomic variability in sunflowers, with the potential to reduce resource waste and labor demands, while providing cost-effective tools for breeding evaluation and decision-making.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"176 ","pages":"Article 128018"},"PeriodicalIF":5.5,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146161963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep fertilization effects on potato production and GHG emissions depend on soil C:N:P-enzyme interactions: Evidence from a 4-year study","authors":"Zhaoyang Li ,&nbsp;Nan Shi ,&nbsp;Yixuan Yuan ,&nbsp;Haiyang Chang ,&nbsp;Yuling Meng ,&nbsp;Weixing Shan ,&nbsp;Moskvicheva Elena ,&nbsp;Ansabayeva Assiya ,&nbsp;Zhikuan Jia ,&nbsp;Xiaolong Ren ,&nbsp;Kadambot H.M. Siddique ,&nbsp;Ruixia Ding ,&nbsp;Peng Wu ,&nbsp;Huaze Li ,&nbsp;Jiangang Liu ,&nbsp;Peng Zhang","doi":"10.1016/j.eja.2026.128001","DOIUrl":"10.1016/j.eja.2026.128001","url":null,"abstract":"<div><h3>Context and problem</h3><div>As potato is one of the four major food crops, enhancing yield is crucial, particularly when considering the mitigation of environmental impacts. Deep fertilization represents a potential strategy for efficient nutrient utilization; however, its specific on potato yield, quality and greenhouse gas emissions require further elucidation.</div></div><div><h3>Methods</h3><div>We conducted a four-year field experiment (2020–2023) using potatoes as the test crop. We investigated the impacts of four fertilization depths (D5, 5 cm, control with locally conventional fertilization depth; D15, 15 cm; D25, 25 cm; D35, 35 cm) on soil C, N, and P content and ratios, enzyme activity, greenhouse gas emissions, potato growth, yield, and quality.</div></div><div><h3>Results</h3><div>Deep fertilization significantly increased the soil SOC:TN, SOC:TP, MBC:MBN, and SIC:SIN ratios, while decreasing the MBC:MBP, MBN:MBP, and POC:PON ratios. In addition to soil catalase, the activities of invertase, urease and phosphatase were closely related to the soil C:N:P ratio. Specifically, deep fertilization increased soil invertase and phosphatase activities but decreased catalase and urease activities. Correlation analysis showed that N₂O and CO₂ emissions were positively correlated with soil urease activity, whereas CH₄ uptake and CO₂ emissions were negatively correlated with soil phosphatase and sucrase activities, respectively. Furthermore, increase of soil phosphatase activity enhanced the leaf area index, net photosynthetic rate, and dry matter accumulation of potato while reducing stem lodging, ultimately improving yield and quality. Among these treatments, D25 achieved the highest improvements in large potato rate (16.4 %) and yield (11.5 %), while simultaneously resulting in high tuber quality in starch (42.5 %), reducing sugar (52.7 %), protein (33.4 %), and vitamin C (31.9 %) content. In addition, its greenhouse gas emission intensity was also at the lowest level (decreased by 32.7 %).</div></div><div><h3>Conclusions</h3><div>Deep fertilization affects enzyme activity by altering soil C:N:P ratios, thereby promoting potato production and reducing greenhouse gas emissions. In this region, fertilization depths of 15–25 cm exhibited distinct advantage in terms of yield enhancement, whereas depths exceeding 35 cm were more effective in reducing emissions.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"175 ","pages":"Article 128001"},"PeriodicalIF":5.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145961721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reducing pesticide use through the adaptation of crop management strategies has little impact on farm economic performance","authors":"Nandillon Romain ,&nbsp;Guinet Maé ,&nbsp;Munier-Jolain Nicolas","doi":"10.1016/j.eja.2026.128030","DOIUrl":"10.1016/j.eja.2026.128030","url":null,"abstract":"<div><div>Although necessary for environmental and human health reasons, pesticide use reduction has been limited, partly due to the perceived risk of lower farm economic performance in case of reduced pest control. Previous research, based on comparisons of farms with contrasted pesticide use, showed that low pesticide use is compatible with maintaining economic performances. However, these results may be suspected of being biased because the production context of the compared farms could differ slightly. Moreover, the economic feasibility to transition to farming systems with low pesticide input remains to be demonstrated on a large scale. We used a diachronic approach, monitoring over time 867 arable French farms classified into eight farm types according to their crop productions. Many farmers re-designed their cropping system during the monitoring period, and adopted measures reducing pest pressure, and therefore succeeded in reducing pesticide inputs. We studied the link between changes in pesticide use, driven by changes in pest management strategies, and two metrics of farm economic performance: gross product and gross margin, both expressed in euros per hectare. In all farm types, some farms were able to reduce pesticide use while maintaining economic performances. For most farms, no antagonism was found between pesticide use reduction and either gross margin or gross product. We bring additional evidence that farmers can reduce pesticide use without impacting these metrics of farm economic performances.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"175 ","pages":"Article 128030"},"PeriodicalIF":5.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146173188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Layered nitrogen application drives changes in nitrogen nutrition status of wheat by affecting key soil microbial clusters","authors":"Yang Zhou,&nbsp;Pengjia Wu,&nbsp;Yanjie Qu,&nbsp;Shengyan Pang,&nbsp;Haimeng Mu,&nbsp;Min Yang,&nbsp;Xiang Lin,&nbsp;Dong Wang","doi":"10.1016/j.eja.2026.128011","DOIUrl":"10.1016/j.eja.2026.128011","url":null,"abstract":"<div><div>Optimizing nitrogen (N) fertilizer management is essential for improving wheat yield and nitrogen use efficiency, yet the mechanisms by which layered N application regulates crop N nutrition through soil microbial processes across growth stages remain unclear. Here, we conducted a four-year field experiment to examine how layered N fertilization modulates soil microbial communities and nutrient dynamics to better match wheat N demand and enhance productivity. Treatments included conventional N application at 8 cm soil depth (N8), layered N application at 8, 16, and 24 cm in a 1:2:1 ratio (N1–2–1), and a no-N control (NCK). Layered N fertilization increased grain yield by 18.7 % and total N accumulation by 19.0 % compared with conventional N application, while maintaining an optimal nitrogen nutrition index throughout wheat development. These yield gains were associated with a marked increase in soil available phosphorus (AP), which enhanced bacterial diversity (Shannon index) and richness (Chao1 index). Co-occurrence network analysis identified two key microbial modules (Module 1 and Module 5) that strongly predicted wheat N accumulation and yield (p &lt; 0.01). The functional roles of these modules shifted from saprotrophic and nitrifying processes at the regreening stage to aromatic compound degradation and root symbiosis at anthesis. Dominant taxa within these modules, particularly Stanjemonium and Coniochaeta, were the strongest contributors to wheat N concentration at the regreening and anthesis stages, respectively. Random forest analysis further indicated that AP exerted a direct regulatory effect on microbial module abundance, while soil N availability influenced wheat N nutrition indirectly through its interactions with AP and microbial network structure. Structural equation modeling confirmed that these pathways ultimately determined wheat nitrogen nutritional status and yield. Overall, layered N fertilization enhances wheat N uptake and productivity by reshaping soil microbial network organization through AP-mediated mechanisms, highlighting the importance of microbial ecological clusters in synchronizing crop N demand with nutrient supply across growth stages.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"175 ","pages":"Article 128011"},"PeriodicalIF":5.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146014944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synergistic effects of subsoil vertical drilling and fodder maize on soil physical properties and fodder beet yield","authors":"Muhammad Ali,&nbsp;Muhammad Qaswar,&nbsp;Ajit Borundia,&nbsp;Abdul Mounem Mouazen","doi":"10.1016/j.eja.2026.128005","DOIUrl":"10.1016/j.eja.2026.128005","url":null,"abstract":"<div><div>Subsoil compaction remains a critical constraint to agricultural productivity, necessitating effective mitigation strategies to enhance soil health and crop performance. This study investigates the synergistic effects of subsoil vertical drilling and fodder maize cropping on fodder beet (<em>Beta vulgaris</em> L.) yield and soil physical properties compared to direct beet cultivation in a Cambisol sandy-textured soil. A field experiment was carried out on a commercial farm in Beervelde, Belgium, employing a semi-autonomous soil vertical drilling machine to apply six treatments with varying drilling depths (50 cm and 90 cm) and hole-to-hole spacings (50 cm, 75 cm, and 100 cm) in a completely randomized design with three replicates across two fields representing two cropping scenarios: 1) fodder maize followed by fodder beet rotation and 2) direct fodder beet cultivation. Treatments included T1 (50 cm depth × 50 cm spacing), T2 (50 cm × 75 cm), T3 (50 cm × 100 cm), T4 (90 cm × 50 cm), T5 (90 cm × 75 cm), T6 (90 cm × 100 cm), and a no-drilling control (T0). Soil bulk density (BD), penetration resistance (PR), and moisture content (MC) were measured at 40 cm and 70 cm depths, alongside fodder beet yield. Results showed that in the maize-beet rotation system, T4 significantly reduced BD by 4.27 % and PR by 20.02 % at 70 cm, increased MC by 15.28 % at 40 cm, and boosted yield by 26.28 % compared to T0. Conversely, direct beet cultivation showed negligible BD reductions, variable PR changes, and yield reductions in most treatments (up to 31 % in T5), with only T6 yielding a 19.8 % increase. In both cropping systems, yield was negatively correlated with BD and PR. These correlations were stronger in the maize-beet rotation system (<em>r</em> = –0.94 for BD, <em>r</em> = –0.86 for PR at 70 cm) than in direct beet cultivation (<em>r</em> = –0.76 for BD, <em>r</em> = –0.61 for PR at 70 cm), highlighting the role of improved soil structure in enhancing productivity. These results demonstrate that maize–beet rotation combined with vertical soil drilling outperforms direct beet cultivation in mitigating subsoil compaction and increasing fodder beet yield. In particular, subsoil drilling at 90 cm depth with 50 cm spacing (T4) showed the most pronounced effects. These findings underscore the value of integrating crop diversification with targeted drilling applications for sustainable soil management in compacted sandy soils.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"175 ","pages":"Article 128005"},"PeriodicalIF":5.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond pesticide reduction: Exploring synergies between contrasted territorial scenarios","authors":"Myrto Parmantier ,&nbsp;Marc Moraine ,&nbsp;Rémy Ballot ,&nbsp;Lorène Prost","doi":"10.1016/j.eja.2026.128009","DOIUrl":"10.1016/j.eja.2026.128009","url":null,"abstract":"<div><div>Pesticide use creates significant environmental, health and socioeconomic challenges and its reduction is hindered by sociotechnical lock-ins. The territorial level, combined with systemic approaches, is promising to overcome these systemic challenges. This research proposes an original methodological approach which, instead of aiming at creating consensus, explores contrasted pesticide reduction scenarios with local stakeholders based on existing initiatives in order to identify pathways for collective action. The study was conducted in the Western Plain of Montpellier, in Southern France, and involved a diversity of stakeholders from the territory and outside of the territory in 5 steps, using the Co-Click’Eau tool and workshops. The scenarios explored the potential of diversification for food production, biodiversity conservation and crop-livestock integration to meet pesticide reduction challenges. In addition to an important pesticide use reduction, each scenario proposed significant land-use and farming practices transformations. The analysis revealed that the approach was able to create spaces for dialogue through the formulation of synergies between these strategies by participants, especially on land-use management, technical levers, linking production to consumers and highlighted complementary contributions of biodiversity and livestock to the territory. Beyond its agronomic dimensions, the process opens the pathway to better coordination with the identification of synergies and tensions between different visions, helping to identify coherent strategies including agricultural production, biodiversity, and food objectives. By doing so, our approach contributes to embedding pesticide reduction into a broader, systemic reconfiguration of agroecosystems and territorial governance.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"175 ","pages":"Article 128009"},"PeriodicalIF":5.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146072111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Innovative integrated management achieves high productivity and profitability of sugarcane in China with low environmental costs","authors":"Huayang Wang ,&nbsp;Yinghe Yao ,&nbsp;Hui Wang ,&nbsp;Jiaxing Chen ,&nbsp;Xiao Tang ,&nbsp;Prakash Lakshmanan ,&nbsp;Xinping Chen ,&nbsp;Yan Deng ,&nbsp;Fusuo Zhang","doi":"10.1016/j.eja.2026.127985","DOIUrl":"10.1016/j.eja.2026.127985","url":null,"abstract":"<div><div>Sugarcane (<em>Saccharum officinarum</em> L.) production in China faces challenges of high input costs, substantial emissions, and low efficiency. While individual sustainable practices such as fertilizer reduction, enhanced-efficiency nitrogen fertilizers, organic amendments, and straw return offer partial benefits, they lack integrated effectiveness. We hypothesize that systematically combining these practices could enhance productivity, reduce emissions, and improve soil health through synergistic nutrient cycling and carbon sequestration. However, empirical evidence and systematic evaluations of such integrated practices in Chinese sugarcane systems remain limited. To address this, a two-year field study was conducted at two representative sugarcane plantations in Guangxi under straw return conditions to evaluate the effects of five regimes on yield, nutrient use efficiency, soil organic carbon (SOC) sequestration, greenhouse gas (GHG) emissions, and net ecosystem economic benefit (NEEB). The treatments included CK (no fertilizer), FP (farmer practice), OPT (optimized NPK), IKPS1 (based on OPT, integrating further optimized nutrient inputs with controlled-release urea), and IKPS2 (based on IKPS1, substituting 30 % of N with organic fertilizer). Compared with FP, both IKPS1 and IKPS2 reduced total NPK inputs by 47 %, while increasing cane yield by 4.6–5.8 % (up to 109.3 t ha⁻¹) and sugar yield by 6.2–9.0 %. Additionally, compared to FP, nutrient use efficiency for N, P, and K under IKPS1 and IKPS2 improved significantly by 81.2–82.0 %, 148.1–255.8 %, and 76.4–101.6 %, respectively. Environmentally, IKPS1 and IKPS2 markedly reduced Nr losses by 57.7–68.7 % and GHG emissions by 40.7–43.8 % relative to FP. Notably, IKPS2 achieved carbon neutrality (-151.9 kg CO₂-eq ha⁻¹), primarily attributed to enhanced SOC sequestration. Economically, both systems increased NEEB over FP, with gains of 114.5 % under IKPS1 and 61.2 % under IKPS2. Comprehensive evaluation indices further confirmed their superiority (0.59 for IKPS1, 0.81 for IKPS2). A stepwise strategy is proposed to prioritize cost-effective practices of IKPS1, while advancing toward carbon neutrality by IKPS2. Overall, this study provides an evidence-based framework to advance sustainable sugarcane production and support the green transformation of tropical agriculture.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"175 ","pages":"Article 127985"},"PeriodicalIF":5.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Forecasting crop yield through a data-driven framework of remote sensing and biophysical knowledge: A case study for wheat and maize in the Guanzhong Plain, China","authors":"Zhikai Cheng,&nbsp;Xiaobo Gu,&nbsp;Yuanling Zhang,&nbsp;Tongtong Zhao,&nbsp;Shikun Sun,&nbsp;Yadan Du,&nbsp;Huanjie Cai","doi":"10.1016/j.eja.2026.128038","DOIUrl":"10.1016/j.eja.2026.128038","url":null,"abstract":"<div><div>Accurate early yield forecasts are essential for maximizing benefits and ensuring food security in the Guanzhong Plain, China. Process-based crop models are often constrained by uncertain input data, which limits their ability to forecast yield at the regional grid level (e.g., 1 km × 1 km). Statistical models, ignore the biophysical mechanisms underlying crop growth and development, and their performance is limited by the quantity and quality of available training data. Therefore, there is an urgent need for a more comprehensive and robust grid-level wheat and maize yield forecasting approach for the Guanzhong Plain. In this study, an interpretable data-driven framework was developed to forecast wheat and maize yields by combining remote sensing (solar-induced chlorophyll fluorescence, SIF; spectral indices, SIs) and biophysical knowledge (APSIM outputs and extreme climatic events) data. A Bayesian integration model (BIM) was trained on high-quality synthetic datasets (obtained by the synthetic minority oversampling technique for regression, SMOTER) to achieve accurate harvest-time yield forecasts at specific time windows. The results showed that the integration of multi-source data reduced the yield prediction error, with the overall normalized root mean square error (NRMSE) decreasing by 0.6 %–39.0 % compared to the single-source models. The data-driven model trained on the SMOTER -based synthetic dataset achieved the highest yield forecasting accuracy (wheat: NRMSE = 16.2 %; maize: NRMSE = 20.7 %). The SIF made the largest contribution to yield forecasts and showed strong interactions and synergies with other feature variables (e.g., aboveground biomass, drought, and low temperature stress), further enhancing model performance. Overall, the proposed data-driven framework demonstrates a promising way for improving grid-level yield forecasting and provides useful insights for the sustainable development of agricultural systems.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"175 ","pages":"Article 128038"},"PeriodicalIF":5.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146160808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancements in weed mapping: A systematic review","authors":"Mohammad Jahanbakht ,&nbsp;Alex Olsen ,&nbsp;Ross Marchant ,&nbsp;Emilie Fillols ,&nbsp;Mostafa Rahimi Azghadi","doi":"10.1016/j.eja.2026.127992","DOIUrl":"10.1016/j.eja.2026.127992","url":null,"abstract":"<div><div>Weed mapping plays a critical role in precision management by providing accurate and timely data on weed distribution, enabling targeted control and reduced herbicide use. This minimizes environmental impacts, supports sustainable land management, and improves outcomes across agricultural and natural environments. Recent advances in weed mapping leverage ground-vehicle Red Green Blue (RGB) cameras, satellite and drone-based remote sensing combined with sensors such as spectral, Near Infra-Red (NIR), and thermal cameras. The resulting data are processed using advanced techniques including big data analytics and machine learning, significantly improving the spatial and temporal resolution of weed maps and enabling site-specific management decisions. Despite a growing body of research in this domain, there is a lack of comprehensive literature reviews specifically focused on weed mapping. In particular, the absence of a structured analysis spanning the entire mapping pipeline, from data acquisition to processing techniques and mapping tools, limits progress in the field. This review addresses these gaps by systematically examining state-of-the-art methods in data acquisition (sensor and platform technologies), data processing (including annotation and modelling), and mapping techniques (such as spatiotemporal analysis and decision support tools). In the data processing stage, weed detection was identified as a critical enabling component of the mapping pipeline; accordingly, dedicated sections were included to systematically review state-of-the-art methods. Following PRISMA guidelines, we critically evaluate and synthesize key findings from the literature to provide a holistic understanding of the weed mapping landscape. This review serves as a foundational reference to guide future research and support the development of efficient, scalable, and sustainable weed management systems.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"175 ","pages":"Article 127992"},"PeriodicalIF":5.5,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}