European Journal of Agronomy最新文献

{"title":"Performance of different corn hybrids and their corresponding water consumption analysis under various water management practices: Insights from experiments conducted under rain-shelters based on the TOPSIS method","authors":"Lei Wang ,&nbsp;Jing Chen ,&nbsp;Zhenyu Chu,&nbsp;Baizhao Ren,&nbsp;Bin Zhao,&nbsp;Peng Liu,&nbsp;Shuting Dong,&nbsp;Jiwang Zhang","doi":"10.1016/j.eja.2025.127587","DOIUrl":"10.1016/j.eja.2025.127587","url":null,"abstract":"<div><div>Hybrid selection and water management practices are crucial for sustaining corn productivity. The adoption of short-season hybrid (SS) represents the viable strategy to facilitate corn production in the North China Plain. However, there is limited information available regarding grain yield (GY) and water consumption characteristics for SS in this region. The three-year experiment was carried out under the rain-shelters with SS and full-season hybrid (FS). Corn plants were grown under three irrigation amounts (target relative soil moisture content was at 60% (WL), 75 % (WM), and 90% (WH) of field capacity). The results showed the GY for FS was 6.7 % higher than that for SS, SS obtained comparable or even higher water use efficiency (WUE) than FS. Soil evaporation (E) and crop evapotranspiration (ET) for SS were decreased by 7.2 % and 9.5%, compared with those for FS. The higher irrigation level resulted on the higher the intensity of daily water consumption during three growing seasons. The relationship between GY and ET was fitted to the quadratic function. A logarithmic relationship was observed between the ratio of soil E to ET and the leaf area index. The soil E and ET of summer corn demonstrated an increase with the augmentation of applied irrigation water. WM had statistically similar (<em>p</em> &gt; 0.05) yield and N fertilizer partial factor productivity (NPFP) compared to WH. The TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method showed the FSWM treatment ranked first, followed by SSWM treatment. WM was the appropriate irrigation level for both hybrids to maintain yields, improve efficiency and optimize water consumption characteristics. This study provided scientific insights into corn yield and water consumption characteristics in relation to hybrid maturity and water management practices.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127587"},"PeriodicalIF":4.5,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143684804","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":"Enhanced ammonia volatilization prediction with EPIC: Model description and testing of different fertilizers","authors":"Andrea Gozio ,&nbsp;Matteo Longo ,&nbsp;Miguel L. Cabrera ,&nbsp;Roberto César Izaurralde ,&nbsp;David E. Kissel ,&nbsp;Barbara Lazzaro ,&nbsp;Nicola Dal Ferro ,&nbsp;Francesco Morari","doi":"10.1016/j.eja.2025.127616","DOIUrl":"10.1016/j.eja.2025.127616","url":null,"abstract":"<div><div>Biogeochemical models are promising cost-effective tools to evaluate ammonia (NH₃) volatilization reduction strategies at large spatial scales provided they capture all the relevant processes that regulate universally the nitrogen (N) cycle in agroecosystems. This work aims to enhance the Environmental Policy Integrated Climate (EPIC) model to improve its ability to simulate NH₃ volatilization from both organic and mineral N fertilizers in agricultural fields. Extant algorithms of NH₃ volatilization in EPIC were replaced with a mechanistic submodel that, operating at hourly steps, effectively simulated NH₃ volatilization by capturing processes of ammonium (NH₄⁺) adsorption, urea hydrolysis, soil pH-based partitioning of total ammoniacal N into NH₃ and NH₄⁺, and mass transfer. The new EPIC submodel was calibrated and validated using data from two different locations (Legnaro, NE Italy; Eatonton, Georgia, USA), including several combinations of fertilizer types and application methods in different pedo-climatic conditions. Results showed that the new submodel provided more accurate estimates of cumulative NH₃ loss than the original one (validated R² = 0.79 vs. 0.50, validated RMSE = 10.6 vs 17.8 kg N ha⁻¹). Furthermore, the implementation now enables more accurate simulation of fertilizer types and management, incorporating the effect of fertilizer pH, depth and method of application, and infiltration of the liquid fraction. In conclusion, the updated EPIC reported here becomes an effective tool to evaluate and select best agricultural practices capable of reducing NH₃ volatilization.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127616"},"PeriodicalIF":4.5,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143684798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On-farm insights in the South American Gran Chaco reveal the importance of soil organic matter and crop management decisions for boosting maize yields","authors":"Andrés Madias ,&nbsp;Carlos G. Simón ,&nbsp;Nicolás I. Stahringer ,&nbsp;Lucas Borrás ,&nbsp;Gerardo Rubio ,&nbsp;Brenda L. Gambin","doi":"10.1016/j.eja.2025.127612","DOIUrl":"10.1016/j.eja.2025.127612","url":null,"abstract":"<div><div>Soybean monoculture is widespread across recently deforested areas in South America, leading to a decline in soil organic matter (SOM) and compromising the sustainability of the cropping system. Introducing cereals like maize into the crop rotation is necessary, but proper management knowledge to maximize its yield and profitability is needed. Our objectives were to quantify the impact of management and environmental variables influencing maize yield and estimate the potential to increase attainable yields in recently deforested fields of South American Gran Chaco. The analysis included a total of 62 on-farm trials across multiple environments, each including 9–28 hybrids. The mean site yields ranged from 2235 to 11141 kg ha⁻¹. Using linear mixed models, we identified and tested a model with key management and environmental variables explaining yield variation. We used this model to estimate attainable yields across the region. Nitrogen availability, sowing date, and hybrid type (temperate or sub-tropical) were the most important management variables to predict yield (relative importance ≥ 0.80). Soil organic matter and soil water availability at sowing were the most important environmental yield predictors (relative importance of 0.71 and 0.66, respectively). The best model, tested against an independent dataset (n = 34 trials; RMSE=1722 kg ha⁻¹; RRMSE=21 %) confirmed the influence of defined predictors. Our findings demonstrate that simple management adjustments can boost yields by ∼20 % (∼1500 kg ha⁻¹). In this recently deforested region, the decline in SOM and its negative impact on yields highlight the importance of crop management strategies and policies aimed at improving current cropping systems.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127612"},"PeriodicalIF":4.5,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143684797","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":"Maize yield estimation based on UAV multispectral monitoring of canopy LAI and WOFOST data assimilation","authors":"Guodong Fu ,&nbsp;Chao Li ,&nbsp;Wenrong Liu ,&nbsp;Kun Pan ,&nbsp;Jizhong He ,&nbsp;Wenfeng Li","doi":"10.1016/j.eja.2025.127614","DOIUrl":"10.1016/j.eja.2025.127614","url":null,"abstract":"<div><div>The estimation accuracy of crop model is influenced by model parameters, model inputs, and model structure. Data assimilation was frequently employed to enhance model performance. To evaluate the feasibility of data assimilation by UAV remote sensing and WOFOST in improving maize yield prediction, a set of field experiments was conducted in Mangshi, Yunnan Province, from 2023 to 2024. Based on the canopy remote sensing data collected by UAV, five inversion models of leaf area index (LAI) were developed using machine learning methods, i.e. Random Forest (RF), Partial Least Squares (PLS), Ridge Regression (RR), k-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGBoost), the best-performing inversion model was selected for data assimilation. Field trials data were used to calibrate the WOFOST model, and the ensemble Kalman filter (ENKF) was applied to assimilate inverted LAI. The results showed that the RF-based inversion model provided the highest accuracy in estimating LAI, with R² of 0.82 and NRMSE of 18 %. For the calibrated model, the NRMSE of yield and LAI were 12 % and 34 %, respectively. After assimilation, the NRMSE for yield and LAI decreased to 4 % and 15 %, respectively, and the average yield error was reduced by 808 kg/ha. Multiple rounds of assimilation reduced both the error range and bias caused by parameters uncertainty. This study demonstrates that assimilating UAV-inverted LAI with RF into the WOFOST model effectively enhances its ability to simulate dynamic crop growth and reduces uncertainty. The effect of data assimilation on the interaction of various uncertainties in the model needs further research. This research offers valuable insights into applying UAV remote sensing and data assimilation technologies for precision maize management.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127614"},"PeriodicalIF":4.5,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143684796","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":"Organic management and local genotypes for elevating yield and seed quality to confront climate change challenges","authors":"Arantza del-Canto ,&nbsp;Nuria De Diego ,&nbsp;Álvaro Sanz-Sáez ,&nbsp;Nikola Štefelová ,&nbsp;Usue Pérez-López ,&nbsp;Amaia Mena-Petite ,&nbsp;Maite Lacuesta","doi":"10.1016/j.eja.2025.127613","DOIUrl":"10.1016/j.eja.2025.127613","url":null,"abstract":"<div><div>Drought, exacerbated by climate change, is a challenge in agricultural production, especially in connection with nutrient-rich legumes like common beans, essential for sustainable food security. Selecting drought-adapted genotypes across various agricultural managements is a viable strategy to mitigate the impact of drought. This study aimed to evaluate different common bean genotypes, locally adapted and commercial ones, under different environmental factors, management practices, and water regimes to understand how the various growth conditions impact their performance and seed biochemical composition. We conducted a pioneering three-year field experiment with twelve genotypes grown under irrigated and rainfed conditions within conventional and organic farming systems. Physiological responses, seed yield, and quality parameters were evaluated and correlated to identify possible biomarkers that can be used for identifying resilient genotypes. The research found that drought and farming practices significantly affect bean yield and quality, with extreme temperatures being a key factor. Organic farming was as productive as conventional under irrigation and improved seed quality in rainfed conditions. The landrace Arrocina de Álava stood out for its tolerance and high-quality seeds under rainfed conditions, underlining the importance of locally adapted genotypes for climate resilience. The study confirmed the seed carbon isotope discrimination (Δ¹³C) as a reliable marker for selecting stress-tolerant genotypes and highlighted the impact of extreme temperatures on seed fat and energy content. It underscores the need for climate-adapted agriculture, highlighting organic farming as a sustainable method and the importance of incorporating climate resilience in crop breeding and management<strong>.</strong></div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127613"},"PeriodicalIF":4.5,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143643752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving the transferability of potato nitrogen concentration estimation models based on hybrid feature selection and Gaussian process regression","authors":"Hang Yin ,&nbsp;Haibo Yang ,&nbsp;Yuncai Hu ,&nbsp;Fei Li ,&nbsp;Kang Yu","doi":"10.1016/j.eja.2025.127611","DOIUrl":"10.1016/j.eja.2025.127611","url":null,"abstract":"<div><div>Feature selection methods are widely used to improve the performance of plant nitrogen concentration (PNC) estimation models. However, the performance of individual feature selection methods can vary across different environments due to various uncertainties. This study aimed to propose a hybrid feature selection method to accurately identify the sensitive bands for the PNC estimation. Field experiments with different potato cultivars and N treatments were carried out in the Inner Mongolia during 2018, 2019, and 2021. The results showed that the hybrid feature selection method can effectively identify the sensitive bands for PNC. When combined with variational heteroscedastic Gaussian process regression (VHGPR), the hybrid method significantly improves the prediction accuracy of potato PNC. Validation using an independent dataset demonstrated that the hybrid feature selection method achieved the highest prediction accuracy compared to traditional feature selection methods, with the mean coefficient of determination (R²) increasing by 16.27 %. Additionally, the performance of VHGPR was benchmarked against partial least squares regression (PLSR). The results indicated that the VHGPR model outperforms the PLSR model across various data types, with a mean R² improvement of 8.92 %. In conclusion, combining the hybrid feature selection method with VHGPR can facilitate real-time PNC estimation in the field, thereby assisting farmers in accurately applying nitrogen fertilization strategies.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127611"},"PeriodicalIF":4.5,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642691","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":"Integrating machine learning with agroecosystem modelling: Current state and future challenges","authors":"Meshach Ojo Aderele ,&nbsp;Amit Kumar Srivastava ,&nbsp;Klaus Butterbach-Bahl ,&nbsp;Jaber Rahimi","doi":"10.1016/j.eja.2025.127610","DOIUrl":"10.1016/j.eja.2025.127610","url":null,"abstract":"<div><div>Machine learning (ML), especially deep learning (DL), is gaining popularity in the agroecosystem modelling community due to its ability to improve the efficiency of computationally intensive tasks. By reviewing previous modelling studies using the PRISMA technique, we present several examples of ML applications in this domain. The potential of using such models is highligthed. The different types of integration and model-building methods are categorized into process-based modelling (PBMs) and data-driven modelling (DDMs), which simulate different aspects of agroecosystem dynamics. While PBMs excel at capturing complex biophysical and biogeochemical processes, they are computationally intensive and may not always be solvable using analytical methods. To address these challenges, machine learning (ML) techniques, including deep learning (DL), are increasingly being integrated into agroecosystem modelling. This integration involves replacing PBMs with data-driven models, using hybrid models that combine PBMs and ML, or constructing simplified versions of PBMs through meta-modelling. ML-based meta-models offer computational efficiency and can capture intricate patterns and non-linear relationships in complex agricultural systems. However, challenges such as interpretability and data requirements remain. This review highlights the importance of addressing gaps and challenges to fully realize the potential of ML to identify the most promising ways of field management in promoting sustainable agricultural systems. It also highlights specific considerations such as data requirements, interpretability, model validation, and scalability for the successful integration of ML with PBMs in agriculture and the transformative potential of combining ML with PBMs, particularly in extending simulations from field to global scales and streamlining data collection processes through advanced sensor technologies based on their applications.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127610"},"PeriodicalIF":4.5,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combined application of nitrogen and phosphorus fertilizers increases soil organic carbon storage in cropland soils","authors":"Jianyu Tao,&nbsp;Xiaoyuan Liu","doi":"10.1016/j.eja.2025.127607","DOIUrl":"10.1016/j.eja.2025.127607","url":null,"abstract":"<div><div>Inorganic fertilization is indispensable in modern agriculture, yet its effects on soil organic carbon (SOC) storage and the underlying driving factors remain uncertain due to natural and anthropogenic interferences. In this study, bootstrap and random forest algorithms were employed to examine the effects of various inorganic fertilization regimes on SOC and crop yield, using a comprehensive dataset derived from 332 peer-reviewed publications. Moreover, the responses of SOC storage to agricultural management practices, climatic conditions, and initial soil properties under combined nitrogen (N) and phosphorus (P) fertilization were analyzed. Results indicated that inorganic fertilization generally increased crop yield and enhanced SOC sequestration. The increases in SOC and crop yield were significantly higher under combined N and P fertilization (i.e., NP and NPK fertilization) than under N fertilization alone. Straw return was the only agricultural management practice that significantly enhanced the annual SOC change rates. However, combined N and P fertilization increased SOC storage even without straw return, probably due to the enhanced plant-derived C inputs. Additionally, soil nutrient conditions, particularly soil P availability, were the key regulators of SOC turnover and storage under combined N and P fertilization. Microbial P limitation constrains the magnitude of SOC sequestration in cropland soils. In conclusion, our findings highlight the pivotal role of soil P availability in promoting SOC sequestration under combined N and P fertilization. Therefore, further efforts are required to determine the optimal amounts and ratios of N and P fertilizers to achieve higher soil C sequestration while sustaining crop yield.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127607"},"PeriodicalIF":4.5,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Co-implementation of deficit irrigation and nutrient management strategies to strengthen soil-plant-seed nexus, water use efficiency, and yield sustainability in fodder corn","authors":"Hanamant M. Halli ,&nbsp;B.G. Shivakumar ,&nbsp;V.K. Wasnik ,&nbsp;Prabhu Govindasamy ,&nbsp;V.K. Yadav ,&nbsp;Sunil Swami ,&nbsp;Vinod Kumar ,&nbsp;E. Senthamil ,&nbsp;Vinay M. Gangana Gowdra ,&nbsp;P.S. Basavaraj ,&nbsp;K.M. Boraiah ,&nbsp;C.B. Harisha","doi":"10.1016/j.eja.2025.127609","DOIUrl":"10.1016/j.eja.2025.127609","url":null,"abstract":"<div><div>Water scarcity-induced nutrient deficiency, low feed quality, and unsustainable fodder yields are important challenges for livestock production in tropical and subtropical countries, jeopardizing sustainable development goal-2: zero hunger. In this context, optimizing the co-benefits of deficit irrigation and fertilizer rates is crucial for strengthening the soil–plant–seed nexus, yield sustainability, water use efficiency (WUE), and the viability of progeny seed. Field experiments were carried for three years (2018–2021) in a split-plot design on a sandy loam soil of central India. Results revealed that moderate irrigation (I2) favored fodder corn root surface architecture (improved root length; 26.85–32.2 %, root weight; 24.5–31.45 %, and surface density; 24.51–32.87 %) and nutrients uptake (N, P, and K) due to increased nutrient accessibility. Likewise, balanced application of N, P, K, and Zn (N4; 120:60:40:20 kg ha⁻¹) had improved the corn roots and nutrient uptake (N; 93.56 kg ha⁻¹, P; 40.33 kg ha⁻¹, and K; 101.5 kg ha⁻¹). As a result, the integration of I2 × N4 had greater leaf area, seed (4.86 t ha⁻¹) and stover (9.62 t ha⁻¹) yields, WUE, and sustainable yield index (0.90). Furthermore, I2 × N4 enhanced the relative feed value and relative feed quality of corn seed and stover. Thus, maintained the vigor of progeny seedling (29.76 %). Therefore, the co-implementation of moderate deficit irrigation and balanced nutrition (I2 × N4) could optimize functional associations, minimize yield variations while improving WUE (by 28.6 %), root activity, optimize nutritional quality of corn feed (seed + stover), and increase the vigor of progeny seeds by strengthening soil–plant–seed nexus in limited conditions. By examining the interactions between soil, plant, and seed health, the research provides valuable insights into how irrigation and fertilization can work together to improve overall crop and feed quality.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127609"},"PeriodicalIF":4.5,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621090","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":"LVR: A language and vision fusion method for rice diseases segmentation under complex environment","authors":"Tianrui Zhao,&nbsp;Honglin Zhou,&nbsp;Miying Yan,&nbsp;Guoxiong Zhou,&nbsp;Chaoying He,&nbsp;Yang Hu,&nbsp;Xiaoyangdi Yan,&nbsp;Meixi Pan,&nbsp;Yunlong Yu,&nbsp;Yiting Liu","doi":"10.1016/j.eja.2025.127599","DOIUrl":"10.1016/j.eja.2025.127599","url":null,"abstract":"<div><div>Accurate identification of rice diseases depends on high-quality disease segmentation. However, challenges such as the complexity of the rice field environment, interference from redundant information, and slow model convergence can hinder effective segmentation. To address these issues, we propose A Language and Vision Fusion Method for Rice Diseases Segmentation under complex environment (LVR), which combines CNN and Transformer architectures. First, we present the Efficient Wavelet-based Multi-scale Attention (EWWL) module, designed to enhance the model’s ability to capture fine details of disease regions in complex environments. Next, to mitigate information redundancy, we design the KAN-segmentation (KAN-seg) module for efficient feature extraction. Additionally, we propose a Self-Adaptive Gradient Enhancement (SAGE) algorithm that dynamically adjusts the network’s learning rate, thereby accelerating convergence. Experimental results demonstrate that the LVR method achieves exceptional accuracy and robustness in rice disease segmentation, even under challenging field conditions. This provides substantial technical support for intelligent agricultural disease management and offers promising applications, particularly in the realm of smart agricultural disease monitoring and management.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"168 ","pages":"Article 127599"},"PeriodicalIF":4.5,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610788","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}