Pub Date : 2025-01-02DOI: 10.1016/j.eja.2024.127495
Qianyu Fan, Jiancheng Xie, Jintao Du, Huanyu Ge, Cuilan Wei, Hao Qian, Hai Liang, Jun Nie, Feng Hu, Songjuan Gao, Weidong Cao
The co-incorporation of milk vetch (MV) and rice straw (RS) in paddy field can promote nitrogen (N) uptake of rice, but the mechanisms of increased N utilization and contributions of milk vetch N (NMV) or rice straw N (NRS) to rice N uptake are still unclear. Two long-term field experiments and a 15N dual-label pot experiment were established to explore the effects of co-incorporation of milk vetch and rice straw on the fate and utilization of milk vetch N and rice straw N in the rice cropping system. Results of the field experiments showed that co-incorporation of MV and RS increased the rice N uptake by 45.0 % at two sites on average, compared to single RS return. The 15N dual-label pot experiment indicated that compared to single RS, co-incorporation of MV and RS increased the NRS uptake and NRS recovery of rice by 53.2 % and 53.4 %, respectively, and the NRS recovery in soil was increased by 55.4 %. This study concluded that co-incorporation of MV and RS facilitated the efficient utilization of NRS by increasing NRS uptake of rice and recovery in soil.
{"title":"Rice straw nitrogen can be utilized by rice more efficiently when co-incorporating with milk vetch","authors":"Qianyu Fan, Jiancheng Xie, Jintao Du, Huanyu Ge, Cuilan Wei, Hao Qian, Hai Liang, Jun Nie, Feng Hu, Songjuan Gao, Weidong Cao","doi":"10.1016/j.eja.2024.127495","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127495","url":null,"abstract":"The co-incorporation of milk vetch (MV) and rice straw (RS) in paddy field can promote nitrogen (N) uptake of rice, but the mechanisms of increased N utilization and contributions of milk vetch N (N<ce:inf loc=\"post\">MV</ce:inf>) or rice straw N (N<ce:inf loc=\"post\">RS</ce:inf>) to rice N uptake are still unclear. Two long-term field experiments and a <ce:sup loc=\"post\">15</ce:sup>N dual-label pot experiment were established to explore the effects of co-incorporation of milk vetch and rice straw on the fate and utilization of milk vetch N and rice straw N in the rice cropping system. Results of the field experiments showed that co-incorporation of MV and RS increased the rice N uptake by 45.0 % at two sites on average, compared to single RS return. The <ce:sup loc=\"post\">15</ce:sup>N dual-label pot experiment indicated that compared to single RS, co-incorporation of MV and RS increased the N<ce:inf loc=\"post\">RS</ce:inf> uptake and N<ce:inf loc=\"post\">RS</ce:inf> recovery of rice by 53.2 % and 53.4 %, respectively, and the N<ce:inf loc=\"post\">RS</ce:inf> recovery in soil was increased by 55.4 %. This study concluded that co-incorporation of MV and RS facilitated the efficient utilization of N<ce:inf loc=\"post\">RS</ce:inf> by increasing N<ce:inf loc=\"post\">RS</ce:inf> uptake of rice and recovery in soil.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"20 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142935464","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}
Pub Date : 2024-12-31DOI: 10.1016/j.eja.2024.127502
Carolina Fabbri, Antonio Delgado, Lorenzo Guerrini, Marco Napoli
Durum wheat, one of the most important staple crops, faces increasing use of fertilizers, particularly nitrogen (N), to meet growing food demand. However, inefficient nitrogen management to meet crop demand can contribute to harms ecosystems. This study focuses on the application of precision fertilization technologies, particularly through variable-rate fertilization based on satellite imagery, to enhance N use efficiency in durum wheat cultivation. To this end, an experiment was conducted during four consecutive growing seasons, from October 2018 to July 2022, in Asciano, Siena, Italy. A total of four N fertilization approaches were evaluated: a uniform N rate, calculated conventionally, and three variable rates based on Sentinel-2 L2A spectral bands. These variable rate approaches include one using the Nitrogen Nutrition Index (NNI), a proportional NDVI-based estimate (NDVIH), and a compensative NDVI-based estimate (NDVIL). Results indicate that the NNI approach, based on satellite imagery, lead to significant N savings without compromising grain yield or quality. This approach also optimizes protein partitioning and dough technical properties, essential factors in various end-use applications. The NNI approach consistently outperforms the other approaches in terms of N fertilizer use efficiency (NfUE). Furthermore, the NNI approach proves to be economically advantageous, with lower social costs and higher rates of return compared to other N fertilization approaches. This emphasizes the economic and environmental sustainability of precision fertilization techniques, specifically NNI, in durum wheat cultivation. This research provides valuable insights for the practical implementation of satellite-based N fertilization strategies, in particular NNI, which offer long-term benefits for sustainable agriculture.
{"title":"Precision nitrogen fertilization strategies for durum wheat: a sustainability evaluation of NNI and NDVI map-based approaches","authors":"Carolina Fabbri, Antonio Delgado, Lorenzo Guerrini, Marco Napoli","doi":"10.1016/j.eja.2024.127502","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127502","url":null,"abstract":"Durum wheat, one of the most important staple crops, faces increasing use of fertilizers, particularly nitrogen (N), to meet growing food demand. However, inefficient nitrogen management to meet crop demand can contribute to harms ecosystems. This study focuses on the application of precision fertilization technologies, particularly through variable-rate fertilization based on satellite imagery, to enhance N use efficiency in durum wheat cultivation. To this end, an experiment was conducted during four consecutive growing seasons, from October 2018 to July 2022, in Asciano, Siena, Italy. A total of four N fertilization approaches were evaluated: a uniform N rate, calculated conventionally, and three variable rates based on Sentinel-2 L2A spectral bands. These variable rate approaches include one using the Nitrogen Nutrition Index (NNI), a proportional NDVI-based estimate (NDVIH), and a compensative NDVI-based estimate (NDVIL). Results indicate that the NNI approach, based on satellite imagery, lead to significant N savings without compromising grain yield or quality. This approach also optimizes protein partitioning and dough technical properties, essential factors in various end-use applications. The NNI approach consistently outperforms the other approaches in terms of N fertilizer use efficiency (NfUE). Furthermore, the NNI approach proves to be economically advantageous, with lower social costs and higher rates of return compared to other N fertilization approaches. This emphasizes the economic and environmental sustainability of precision fertilization techniques, specifically NNI, in durum wheat cultivation. This research provides valuable insights for the practical implementation of satellite-based N fertilization strategies, in particular NNI, which offer long-term benefits for sustainable agriculture.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"183 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905653","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}
The rising demand for maize and increasing labor costs necessitate the selection of appropriate varieties to enhance maize production. This study evaluated the performance of three maize varieties—SD650, ZD958, and SD8806—at four planting densities: low (4.5 ×104 plants/hm2), regular (6 ×104 plants/hm2), medium (7.5 ×104 plants/hm2), and high (9 ×104 plants/hm2) over two years (2020 and 2021). The results demonstrated that SD650 consistently outperformed the other varieties, offering higher yield, superior lodging resistance, and better adaptation to high-density planting. These advantages were attributed to SD650’s optimized plant architecture and ability to maintain a higher kernel number per ear under dense planting conditions. Moreover, SD650 had a faster kernel dehydration rate during late growth stages and lower kernel water content at maturity, making it more suitable for mechanical harvesting. In conclusion, maize varieties like SD650, characterized by shorter growth periods, high-density tolerance, high yields, and compatibility with mechanized harvesting, are ideal for cultivation in summer-sown regions.
{"title":"Optimizing maize production in the Guanzhong Region: An evaluation of density tolerance, yield, and mechanical harvesting characteristics in different maize varieties","authors":"Xiaoyue Wang, Xiaopeng Wu, Yongzhi Hua, Yuqing Li, Liangchuan Ma, Yihuang Gong, Wanchao Zhu, Shutu Xu, Jiquan Xue, Xiaoliang Qin, Kadambot H.M. Siddique","doi":"10.1016/j.eja.2024.127500","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127500","url":null,"abstract":"The rising demand for maize and increasing labor costs necessitate the selection of appropriate varieties to enhance maize production. This study evaluated the performance of three maize varieties—SD650, ZD958, and SD8806—at four planting densities: low (4.5 ×10<ce:sup loc=\"post\">4</ce:sup> plants/hm<ce:sup loc=\"post\">2</ce:sup>), regular (6 ×10<ce:sup loc=\"post\">4</ce:sup> plants/hm<ce:sup loc=\"post\">2</ce:sup>), medium (7.5 ×10<ce:sup loc=\"post\">4</ce:sup> plants/hm<ce:sup loc=\"post\">2</ce:sup>), and high (9 ×10<ce:sup loc=\"post\">4</ce:sup> plants/hm<ce:sup loc=\"post\">2</ce:sup>) over two years (2020 and 2021). The results demonstrated that SD650 consistently outperformed the other varieties, offering higher yield, superior lodging resistance, and better adaptation to high-density planting. These advantages were attributed to SD650’s optimized plant architecture and ability to maintain a higher kernel number per ear under dense planting conditions. Moreover, SD650 had a faster kernel dehydration rate during late growth stages and lower kernel water content at maturity, making it more suitable for mechanical harvesting. In conclusion, maize varieties like SD650, characterized by shorter growth periods, high-density tolerance, high yields, and compatibility with mechanized harvesting, are ideal for cultivation in summer-sown regions.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"93 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905648","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}
Pub Date : 2024-12-26DOI: 10.1016/j.eja.2024.127493
Michaela Pia Laumer, Adolf Kellermann, Franz-Xaver Maidl, Kurt-Jürgen Hülsbergen, Thomas Ebertseder
Farmers and French fry producers have stated that each year, various factors impact the frying quality of potato tubers. As a result, a trial was designed to study the frying color development of the cultivar Innovator grown under different conditions (location, nitrogen fertilization, and harvest date) and stored at 6.5°C and 7.5°C. The samples were evaluated monthly from December to March. A multiple regression model was created using all the samples from the two trial years, explaining > 85 % of the differences in frying color. Additionally, models for both the years and every sampling month were calculated. These multiple regression models helped measure the impact of the variables and their consistency. The results revealed a significant impact of the climatic water balance in the latter part of June, which explained differences between years and locations. Other factors determining frying color were the harvest date, storage duration, and storage temperature. No effect of the location or the tested nitrogen fertilization rates could be found.
{"title":"Influence of agronomic parameters and storage parameters on the frying color of French fry potatoes (Solanum tuberosum L.)","authors":"Michaela Pia Laumer, Adolf Kellermann, Franz-Xaver Maidl, Kurt-Jürgen Hülsbergen, Thomas Ebertseder","doi":"10.1016/j.eja.2024.127493","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127493","url":null,"abstract":"Farmers and French fry producers have stated that each year, various factors impact the frying quality of potato tubers. As a result, a trial was designed to study the frying color development of the cultivar Innovator grown under different conditions (location, nitrogen fertilization, and harvest date) and stored at 6.5°C and 7.5°C. The samples were evaluated monthly from December to March. A multiple regression model was created using all the samples from the two trial years, explaining > 85 % of the differences in frying color. Additionally, models for both the years and every sampling month were calculated. These multiple regression models helped measure the impact of the variables and their consistency. The results revealed a significant impact of the climatic water balance in the latter part of June, which explained differences between years and locations. Other factors determining frying color were the harvest date, storage duration, and storage temperature. No effect of the location or the tested nitrogen fertilization rates could be found.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"1 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905649","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}
Sensitivity analysis is crucial for identifying key crop model parameters to improve parameterization efficiency, but climate conditions can affect sensitivity, leading to inaccurate calibration if different climate conditions are not considered. This study uses the extended Fourier amplitude sensitivity test to identify sensitive cultivar parameters in the Agricultural Production System Simulator (APSIM-Maize), focusing on maize yield in a semiarid region. Regression analysis shows that rainfall and maximum temperature significantly impact the sensitivity of maize yield to the transpiration efficiency coefficient (transp_eff_cf) (r = -0.66 and 0.63, p = 0.001 and 0.003, respectively) and grain growth rate (grin_gth_rate) (r = 0.74 and −0.70, p = 0.0002 and 0.0005, respectively). The sensitivity of maize yield to the thermal time from emergency to the end of juvenile (tt_emerg_to_endjuv) shows varying sensitivity across years (STi = 0.03–0.26), influenced by maximum temperature. Our results demonstrated that transp_eff_cf and grain_gth_rate should be adjusted cautiously, especially in drier or warmer conditions. The implications of our study extend to providing valuable support for the calibration of APSIM-Maize cultivar parameters in response to climate variability.
{"title":"Rainfall and maximum temperature are dominant climatic factors influencing APSIM-Maize cultivar parameters sensitivity in semiarid regions","authors":"Xuening Yang, Xuanze Zhang, Zhigan Zhao, Ning Ma, Jing Tian, Zhenwu Xu, Junmei Zhang, Yongqiang Zhang","doi":"10.1016/j.eja.2024.127494","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127494","url":null,"abstract":"Sensitivity analysis is crucial for identifying key crop model parameters to improve parameterization efficiency, but climate conditions can affect sensitivity, leading to inaccurate calibration if different climate conditions are not considered. This study uses the extended Fourier amplitude sensitivity test to identify sensitive cultivar parameters in the Agricultural Production System Simulator (APSIM-Maize), focusing on maize yield in a semiarid region. Regression analysis shows that rainfall and maximum temperature significantly impact the sensitivity of maize yield to the transpiration efficiency coefficient (<ce:italic>transp_eff_cf</ce:italic>) (r = -0.66 and 0.63, p = 0.001 and 0.003, respectively) and grain growth rate (<ce:italic>grin_gth_rate</ce:italic>) (r = 0.74 and −0.70, p = 0.0002 and 0.0005, respectively). The sensitivity of maize yield to the thermal time from emergency to the end of juvenile (<ce:italic>tt_emerg_to_endjuv</ce:italic>) shows varying sensitivity across years (<ce:italic>ST</ce:italic><ce:inf loc=\"post\"><ce:italic>i</ce:italic></ce:inf> = 0.03–0.26), influenced by maximum temperature. Our results demonstrated that <ce:italic>transp_eff_cf</ce:italic> and <ce:italic>grain_gth_rate</ce:italic> should be adjusted cautiously, especially in drier or warmer conditions. The implications of our study extend to providing valuable support for the calibration of APSIM-Maize cultivar parameters in response to climate variability.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"93 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905677","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}
Pub Date : 2024-12-20DOI: 10.1016/j.eja.2024.127475
Mounir Seghouani, Matthieu N. Bravin, Patrice Lecharpentier, Alain Mollier
Soil-crop models are pertinent tools to study and manage phosphorus (P) in agroecosystems. However, P modeling is suffering a delay as compared to nitrogen and carbon. In this study, we extended the STICS model to simulate the P uptake and P feed-back by coupling it with a soil-plant P model. The paper aims at describing the P model and present the results showing the ability of the model to simulate contrasting P uptake and growth response pattern of maize submitted to different level of P inputs. in temperate area. The model simulates the soil P availability and the crop P demand, uptake, and partitioning. A major originality of this work is that it relies on soil solution P concentration and P sorption curves to simulate soil P availability, and critical P dilution curves to simulate crop P demand. We evaluated the model against a dataset coming from four field fertilization trials located at different site in mainland France. The trials consisted of fertilizing maize with a mineral fertilizer at three application rates (P0, P1, P2) which induced contrasted crop responses to P shortage. The model has shown great ability in predicting P uptake both dynamically and at the end of the cropping season for the entire dataset (EF >0.75). The model has satisfactory predictions of crop biomass accumulation (EF >0.5) and leaf area index. Considering each fertilization level separately, the evaluation has shown that the model had predicted the final P uptake of P1 and P2 treatments better than that of P0 treatment (EF of 0.74, 0.73 and 0.62 for P2, P1, and P0, respectively). The predictions made for the P0 treatment remained nonetheless satisfactory for both P uptake and plant growth. The good performance of the model is promising as it shows that the model is sufficiently robust to simulate maize P uptake across a range of soil P availability and P fertilization under contrasting temperate climatic conditions. Further validation on other crop species and soil and climatic conditions is discussed.
{"title":"Simulating phosphorus dynamics between the soil and the crop with the STICS model: Formalization and multi-site evaluation on maize in temperate area","authors":"Mounir Seghouani, Matthieu N. Bravin, Patrice Lecharpentier, Alain Mollier","doi":"10.1016/j.eja.2024.127475","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127475","url":null,"abstract":"Soil-crop models are pertinent tools to study and manage phosphorus (P) in agroecosystems. However, P modeling is suffering a delay as compared to nitrogen and carbon. In this study, we extended the STICS model to simulate the P uptake and P feed-back by coupling it with a soil-plant P model. The paper aims at describing the P model and present the results showing the ability of the model to simulate contrasting P uptake and growth response pattern of maize submitted to different level of P inputs. in temperate area. The model simulates the soil P availability and the crop P demand, uptake, and partitioning. A major originality of this work is that it relies on soil solution P concentration and P sorption curves to simulate soil P availability, and critical P dilution curves to simulate crop P demand. We evaluated the model against a dataset coming from four field fertilization trials located at different site in mainland France. The trials consisted of fertilizing maize with a mineral fertilizer at three application rates (P0, P1, P2) which induced contrasted crop responses to P shortage. The model has shown great ability in predicting P uptake both dynamically and at the end of the cropping season for the entire dataset (EF >0.75). The model has satisfactory predictions of crop biomass accumulation (EF >0.5) and leaf area index. Considering each fertilization level separately, the evaluation has shown that the model had predicted the final P uptake of P1 and P2 treatments better than that of P0 treatment (EF of 0.74, 0.73 and 0.62 for P2, P1, and P0, respectively). The predictions made for the P0 treatment remained nonetheless satisfactory for both P uptake and plant growth. The good performance of the model is promising as it shows that the model is sufficiently robust to simulate maize P uptake across a range of soil P availability and P fertilization under contrasting temperate climatic conditions. Further validation on other crop species and soil and climatic conditions is discussed.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"202 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142884209","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}
There are various types of corn diseases, many of which affect the leaves. However, the specific details such as shape, size, color, and texture of these diseases in images can present challenges for accurate recognition by deep neural networks (DNNs). Furthermore, images of corn leaf diseases captured in the field often contain noise, which can reduce the robustness and effectiveness of the trained model. Addressing these challenges and acknowledging the limitations of current DNNs models in capturing intricate high-frequency details when identifying corn leaf disease images in complex backgrounds, this study proposes a novel corn leaf disease recognition model that incorporates high-frequency information from images. The proposed model enhances the network's fitting capability by integrating high-frequency detailed features from images into the final three layers of the lightweight MobileNetV3-Large architecture. To effectively represent high-frequency information, a high-frequency feature extraction block (HFFE) is devised, and the adaptive ACON-C activation function is employed to enhance the nonlinear expression capacity of high-frequency details. The end-to-end recognition approach yields a 2.1 % increase in average recognition accuracy compared to the baseline MobileNetV3-Large model, indicating that the inclusion of high-frequency information features enhances model performance. Furthermore, experiments introducing varying levels of noise to the test data illustrate the model's superior anti-interference capabilities and robustness. Consequently, our model exhibits significant value and practical utility for real-world applications.
{"title":"Integrating high-frequency detail information for enhanced corn leaf disease recognition: A model utilizing fusion imagery","authors":"Haidong Li, Chao Ruan, Jinling Zhao, Linsheng Huang, Yingying Dong, Wenjiang Huang, Dong Liang","doi":"10.1016/j.eja.2024.127489","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127489","url":null,"abstract":"There are various types of corn diseases, many of which affect the leaves. However, the specific details such as shape, size, color, and texture of these diseases in images can present challenges for accurate recognition by deep neural networks (DNNs). Furthermore, images of corn leaf diseases captured in the field often contain noise, which can reduce the robustness and effectiveness of the trained model. Addressing these challenges and acknowledging the limitations of current DNNs models in capturing intricate high-frequency details when identifying corn leaf disease images in complex backgrounds, this study proposes a novel corn leaf disease recognition model that incorporates high-frequency information from images. The proposed model enhances the network's fitting capability by integrating high-frequency detailed features from images into the final three layers of the lightweight MobileNetV3-Large architecture. To effectively represent high-frequency information, a high-frequency feature extraction block (HFFE) is devised, and the adaptive ACON-C activation function is employed to enhance the nonlinear expression capacity of high-frequency details. The end-to-end recognition approach yields a 2.1 % increase in average recognition accuracy compared to the baseline MobileNetV3-Large model, indicating that the inclusion of high-frequency information features enhances model performance. Furthermore, experiments introducing varying levels of noise to the test data illustrate the model's superior anti-interference capabilities and robustness. Consequently, our model exhibits significant value and practical utility for real-world applications.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"46 4 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142884169","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}
Pub Date : 2024-12-17DOI: 10.1016/j.eja.2024.127477
Dashuai Wang, Minghu Zhao, Zhuolin Li, Sheng Xu, Xiaohu Wu, Xuan Ma, Xiaoguang Liu
In the wake of significant advances in agronomy, biology, informatics, agricultural robots (Agri-robots), and artificial intelligence, modern agriculture is transforming from labor-intensive to data-driven mode. Precision agriculture (PA) is one of the most practical solutions for bridging the crop yield gap by performing the right treatments in the right place and at the right time. As a rising star among Agri-robots, unmanned aerial vehicles (UAVs) equipped with high-resolution onboard sensors and dedicated application systems are playing an increasingly vital role in collecting multi-scale agricultural information and implementing site-specific treatment. In this process, a large number of images are produced. However, considerable effort is required to extract high-value information from the explosively growing number of images. Over the past decade, deep learning (DL) has demonstrated unparalleled advantages in agricultural analytics, such as crop/weed classification, biotic/abiotic stress detection, crop growth monitoring, yield prediction, natural disaster assessment, etc. The combination of UAVs and DL is of great significance for agricultural information acquisition, processing, analysis, decision-making, and deployment. With the rapid development of UAVs, DL, and PA, this work firstly introduces the key components of PA, UAVs, and DL, respectively, and summarizes their major research progress. Subsequently, we focus on the successful applications of UAVs and DL in PA. Furthermore, based on our extensive literature survey, their current challenges and future development trends are sorted out. Ultimately, we hope this survey can draw more attention to the novel applications of UAVs and DL in PA among multidisciplinary scientists around the world and inspire more exciting and practical studies.
随着农艺学、生物学、信息学、农业机器人（Agri-robots）和人工智能的长足发展，现代农业正在从劳动密集型向数据驱动型转变。精准农业（PA）是缩小作物产量差距的最实用解决方案之一，它能在正确的时间和正确的地点进行正确的处理。作为农业机器人中的后起之秀，配备高分辨率机载传感器和专用应用系统的无人机（UAV）在收集多尺度农业信息和实施特定地点处理方面发挥着越来越重要的作用。在此过程中，会产生大量图像。然而，要从爆炸式增长的图像中提取高价值信息，需要付出大量努力。在过去十年中，深度学习（DL）在农业分析领域展现出了无与伦比的优势，例如作物/杂草分类、生物/非生物胁迫检测、作物生长监测、产量预测、自然灾害评估等。无人机与 DL 的结合对于农业信息的获取、处理、分析、决策和部署具有重要意义。随着无人机、DL 和 PA 的快速发展，本文首先分别介绍了 PA、无人机和 DL 的关键组成部分，并总结了它们的主要研究进展。随后，我们重点介绍了无人机和 DL 在 PA 中的成功应用。此外，我们还基于广泛的文献调查，梳理了它们当前面临的挑战和未来的发展趋势。最终，我们希望这份调查报告能引起全球多学科科学家对无人机和 DL 在 PA 中的新型应用的更多关注，并激发更多激动人心的实用研究。
{"title":"A survey of unmanned aerial vehicles and deep learning in precision agriculture","authors":"Dashuai Wang, Minghu Zhao, Zhuolin Li, Sheng Xu, Xiaohu Wu, Xuan Ma, Xiaoguang Liu","doi":"10.1016/j.eja.2024.127477","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127477","url":null,"abstract":"In the wake of significant advances in agronomy, biology, informatics, agricultural robots (Agri-robots), and artificial intelligence, modern agriculture is transforming from labor-intensive to data-driven mode. Precision agriculture (PA) is one of the most practical solutions for bridging the crop yield gap by performing the right treatments in the right place and at the right time. As a rising star among Agri-robots, unmanned aerial vehicles (UAVs) equipped with high-resolution onboard sensors and dedicated application systems are playing an increasingly vital role in collecting multi-scale agricultural information and implementing site-specific treatment. In this process, a large number of images are produced. However, considerable effort is required to extract high-value information from the explosively growing number of images. Over the past decade, deep learning (DL) has demonstrated unparalleled advantages in agricultural analytics, such as crop/weed classification, biotic/abiotic stress detection, crop growth monitoring, yield prediction, natural disaster assessment, etc. The combination of UAVs and DL is of great significance for agricultural information acquisition, processing, analysis, decision-making, and deployment. With the rapid development of UAVs, DL, and PA, this work firstly introduces the key components of PA, UAVs, and DL, respectively, and summarizes their major research progress. Subsequently, we focus on the successful applications of UAVs and DL in PA. Furthermore, based on our extensive literature survey, their current challenges and future development trends are sorted out. Ultimately, we hope this survey can draw more attention to the novel applications of UAVs and DL in PA among multidisciplinary scientists around the world and inspire more exciting and practical studies.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"195 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142841147","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}
Pub Date : 2024-12-16DOI: 10.1016/j.eja.2024.127482
Binbin Zhang, Sihui Yan, Ji Chen, Jim Rasmussen, Peter Sørensen, Shufang Wu, Jørgen E. Olesen
Nitrate leaching has been widely studied in agricultural cropping systems, whereas there are few studies of dissolved organic nitrogen (DON) leaching. Moreover, the factors determining variation of DON leaching in arable cropping systems remain unclear. Here, we examined variations in DON leaching from two organic crop rotations (Organic with Green Manure (OGM) and Organic with Grain Legume (OGL)) and one conventional rotation (Conventional with Grain Legume (CGL)) with and without the use of cover crops and animal manure application. These treatments were part of long-term experiments conducted at three sites in Denmark with different soil types and precipitation. Measurements were conducted in 2008 at all three sites (Jyndevad, Foulum and Flakkebjerg), and 2015 and 2017 at Foulum. We found that the total annual nitrogen (N) leaching ranged from 6.0 to 113.1 kg ha−1 yr−1 at the three rotations. DON leaching ranged from 1.6 to 11.6 kg ha−1 yr−1 under different crop rotations, accounting for 4.5–37.0 % of the total N leaching. The largest DON leaching (about 10 kg N ha−1 yr−1) was found on coarse sandy soil with high rainfall (Jyndevad) and the lowest DON leaching (about 1 kg N ha−1 yr−1) on sandy loam with low rainfall (Flakkebjerg). In the long-term experiment with loamy sand and medium rainfall (Foulum) in 2015 and 2017, cover crops reduced DON leaching in most cases, while manure had no significant effect on DON leaching. On average across different treatments in 2015 and 2017 at Foulum, grass-clover showed the lowest DON leaching (3.3 kg ha−1 in OGM rotation), whereas faba bean had the highest DON leaching (6.5 kg ha−1 in OGL rotation and 6.2 kg ha−1 in CGL rotation). The results demonstrate that DON leaching should be considered when assessing N leaching losses from agricultural cropping systems, in particular when assessing the effectiveness of N mitigation measures that largely affect nitrate leaching and not the losses of DON.
对农业耕作制度中硝酸盐浸出的研究非常广泛，但对溶解有机氮（DON）浸出的研究却很少。此外，决定耕地种植系统中 DON 沥滤变化的因素仍不清楚。在此，我们研究了两种有机轮作（有机与绿肥轮作（OGM）和有机与谷物豆类轮作（OGL））和一种常规轮作（常规与谷物豆类轮作（CGL））在使用或不使用覆盖作物和动物粪便的情况下 DON 沥滤的变化。这些处理是在丹麦三个具有不同土壤类型和降水量的地点进行的长期实验的一部分。2008 年在所有三个地点（Jyndevad、Foulum 和 Flakkebjerg）进行了测量，2015 年和 2017 年在 Foulum 进行了测量。我们发现，在这三个轮作地，每年的氮素（N）沥滤总量为 6.0 至 113.1 千克/公顷-年。不同轮作模式下的 DON 沥滤量为 1.6 至 11.6 kg ha-1 yr-1，占总氮沥滤量的 4.5-37.0%。在降雨量大的粗砂质土壤（Jyndevad）上，DON 沥滤量最大（约 10 千克氮/公顷-年-1），而在降雨量小的砂质壤土（Flakkebjerg）上，DON 沥滤量最小（约 1 千克氮/公顷-年-1）。2015 年和 2017 年，在降雨量中等的壤质沙地（富勒姆）进行的长期试验中，在大多数情况下，覆盖作物减少了 DON 沥滤，而粪肥对 DON 沥滤没有显著影响。平均而言，2015 年和 2017 年在 Foulum 的不同处理中，禾本科三叶草的 DON 沥滤量最低（在 OGM 轮作中为 3.3 千克/公顷），而蚕豆的 DON 沥滤量最高（在 OGL 轮作中为 6.5 千克/公顷，在 CGL 轮作中为 6.2 千克/公顷）。研究结果表明，在评估农业耕作制度的氮沥滤损失时，尤其是在评估主要影响硝酸盐沥滤而非 DON 损失的氮减缓措施的有效性时，应考虑 DON 沥滤。
{"title":"Leaching of dissolved organic nitrogen in long-term organic and conventional crop rotations in Denmark","authors":"Binbin Zhang, Sihui Yan, Ji Chen, Jim Rasmussen, Peter Sørensen, Shufang Wu, Jørgen E. Olesen","doi":"10.1016/j.eja.2024.127482","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127482","url":null,"abstract":"Nitrate leaching has been widely studied in agricultural cropping systems, whereas there are few studies of dissolved organic nitrogen (DON) leaching. Moreover, the factors determining variation of DON leaching in arable cropping systems remain unclear. Here, we examined variations in DON leaching from two organic crop rotations (Organic with Green Manure (OGM) and Organic with Grain Legume (OGL)) and one conventional rotation (Conventional with Grain Legume (CGL)) with and without the use of cover crops and animal manure application. These treatments were part of long-term experiments conducted at three sites in Denmark with different soil types and precipitation. Measurements were conducted in 2008 at all three sites (Jyndevad, Foulum and Flakkebjerg), and 2015 and 2017 at Foulum. We found that the total annual nitrogen (N) leaching ranged from 6.0 to 113.1 kg ha<ce:sup loc=\"post\">−1</ce:sup> yr<ce:sup loc=\"post\">−1</ce:sup> at the three rotations. DON leaching ranged from 1.6 to 11.6 kg ha<ce:sup loc=\"post\">−1</ce:sup> yr<ce:sup loc=\"post\">−1</ce:sup> under different crop rotations, accounting for 4.5–37.0 % of the total N leaching. The largest DON leaching (about 10 kg N ha<ce:sup loc=\"post\">−1</ce:sup> yr<ce:sup loc=\"post\">−1</ce:sup>) was found on coarse sandy soil with high rainfall (Jyndevad) and the lowest DON leaching (about 1 kg N ha<ce:sup loc=\"post\">−1</ce:sup> yr<ce:sup loc=\"post\">−1</ce:sup>) on sandy loam with low rainfall (Flakkebjerg). In the long-term experiment with loamy sand and medium rainfall (Foulum) in 2015 and 2017, cover crops reduced DON leaching in most cases, while manure had no significant effect on DON leaching. On average across different treatments in 2015 and 2017 at Foulum, grass-clover showed the lowest DON leaching (3.3 kg ha<ce:sup loc=\"post\">−1</ce:sup> in OGM rotation), whereas faba bean had the highest DON leaching (6.5 kg ha<ce:sup loc=\"post\">−1</ce:sup> in OGL rotation and 6.2 kg ha<ce:sup loc=\"post\">−1</ce:sup> in CGL rotation). The results demonstrate that DON leaching should be considered when assessing N leaching losses from agricultural cropping systems, in particular when assessing the effectiveness of N mitigation measures that largely affect nitrate leaching and not the losses of DON.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"90 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142841180","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}
Pub Date : 2024-12-16DOI: 10.1016/j.eja.2024.127483
Seiya Wakahara, Yuxin Miao, Matthew McNearney, Carl J. Rosen
In-season nitrogen (N) management is a promising strategy to achieve high tuber yield/quality and N use efficiency in potato (Solanum tuberosum L.) production. The SPAD-502 chlorophyll meter (SPAD) provides relative readings on plant N status using leaf chlorophyll transmittance and has the potential to replace the traditionally used expensive petiole analysis by estimating petiole nitrate-N (PNN) concentration non-destructively. The objective of this study was to develop a robust machine learning (ML) model for PNN concentration prediction across various genetic, environmental, and management conditions. Plot-scale experiments were conducted on an irrigated loamy sand soil in central Minnesota using a number of varieties and N fertilizer sources, application methods, and rates between 2010 and 2022. In each plot, approximately 20 petiole samples were collected for laboratory analysis, and 20 SPAD readings were collected and averaged. Weather information was collected by a nearby weather station. Three ML models (i.e. Random Forest, Extreme Gradient Boosting, and Support Vector Regression) were trained using Bayesian optimization in a nested 5-fold cross-validation. A near-linear trend was found between PNN concentration and the selected important features. Random Forest and Extreme Gradient Boosting regression models demonstrated that PNN concentrations could be predicted with an R2 of 0.8 using 15 features in a new site-year. When simplified by only using SPAD readings, cultivar information, accumulated growing degree days, accumulated total moisture, and as-applied N rates, these two tree-based models maintained the R2 values and achieved a 75 % diagnostic accuracy, outperforming both simple regression (66 %) and multivariate linear regression (70 %) models. We found that potato N status could be diagnosed accurately through PNN concentration prediction using chlorophyll meter and multi-source data fusion. The results of this study can be used as a baseline for future research on in-season N status diagnosis of potatoes involving different proximal and remote sensing technologies and N stress indicators.
{"title":"Non-destructive potato petiole nitrate-nitrogen prediction using chlorophyll meter and multi-source data fusion with machine learning","authors":"Seiya Wakahara, Yuxin Miao, Matthew McNearney, Carl J. Rosen","doi":"10.1016/j.eja.2024.127483","DOIUrl":"https://doi.org/10.1016/j.eja.2024.127483","url":null,"abstract":"In-season nitrogen (N) management is a promising strategy to achieve high tuber yield/quality and N use efficiency in potato (<ce:italic>Solanum tuberosum</ce:italic> L.) production. The SPAD-502 chlorophyll meter (SPAD) provides relative readings on plant N status using leaf chlorophyll transmittance and has the potential to replace the traditionally used expensive petiole analysis by estimating petiole nitrate-N (PNN) concentration non-destructively. The objective of this study was to develop a robust machine learning (ML) model for PNN concentration prediction across various genetic, environmental, and management conditions. Plot-scale experiments were conducted on an irrigated loamy sand soil in central Minnesota using a number of varieties and N fertilizer sources, application methods, and rates between 2010 and 2022. In each plot, approximately 20 petiole samples were collected for laboratory analysis, and 20 SPAD readings were collected and averaged. Weather information was collected by a nearby weather station. Three ML models (i.e. Random Forest, Extreme Gradient Boosting, and Support Vector Regression) were trained using Bayesian optimization in a nested 5-fold cross-validation. A near-linear trend was found between PNN concentration and the selected important features. Random Forest and Extreme Gradient Boosting regression models demonstrated that PNN concentrations could be predicted with an R<ce:sup loc=\"post\">2</ce:sup> of 0.8 using 15 features in a new site-year. When simplified by only using SPAD readings, cultivar information, accumulated growing degree days, accumulated total moisture, and as-applied N rates, these two tree-based models maintained the R<ce:sup loc=\"post\">2</ce:sup> values and achieved a 75 % diagnostic accuracy, outperforming both simple regression (66 %) and multivariate linear regression (70 %) models. We found that potato N status could be diagnosed accurately through PNN concentration prediction using chlorophyll meter and multi-source data fusion. The results of this study can be used as a baseline for future research on in-season N status diagnosis of potatoes involving different proximal and remote sensing technologies and N stress indicators.","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"38 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142841181","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：