European Journal of Agronomy最新文献

{"title":"Yield more in the shadow: Mitigating shading-induced yield penalty of maize via optimizing source-sink carbon partitioning","authors":"Xiao-Gui Liang ,&nbsp;Hui-Min Chen ,&nbsp;Yu-Qiang Pan ,&nbsp;Zhi-Wei Wang ,&nbsp;Cheng Huang ,&nbsp;Zhen-Yuan Chen ,&nbsp;Wang Tang ,&nbsp;Xian-Min Chen ,&nbsp;Si Shen ,&nbsp;Shun-Li Zhou","doi":"10.1016/j.eja.2024.127421","DOIUrl":"10.1016/j.eja.2024.127421","url":null,"abstract":"<div><div>Global solar radiation has been decreasing, posing a great threat to food security by reducing photo-assimilation and disrupting carbon (C) partitioning in crops like maize. However, practical countermeasures to cope with source-sink balance in periodic shading stress are lacking. Here, we first simulated shading stresses with different degrees and occurring periods on field maize for two years. Results verified that shading-induced yield penalties are most severe around silking and are closely associated with biomass allocation, implying a significant imbalance of source: sink C partitioning during silking. To mitigate yield losses from shading, detasseling (Det) and synchronous pollination (SP), targeting the two sink tissues (tassel and ear, respectively), were applied to 70 % shading at the silking stage in two seasons. Both practices conferred benefits to grain number and yield production, with final yield increases ranging from 4.0 % to 31.3 % under shading. Through ¹³C labeling, sugar metabolism assay and global analysis, we proved that Det improved the source-sink balance via increasing light irradiance within the canopy and eliminating apical dominance to stimulate C assimilates partitioning into the ear. SP promoted C partitioning into the ear by increasing reproductive sink strength and optimizing assimilates allocation among grain siblings. Intriguingly, Det and SP also provided marginal yield increase under normal light conditions. Our findings underscore the potential of source-sink coordination and C partitioning in mitigating maize yield penalty under environmental stresses like shading. The research also provides new avenues for developing agronomic practices and breeding strategies via tasseling and silking regulation, aiming to improve maize crop production and stress resilience and ensure food security in the face of climate change.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127421"},"PeriodicalIF":4.5,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655955","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":"Using UAV-based multispectral and RGB imagery to monitor above-ground biomass of oat-based diversified cropping","authors":"Pengpeng Zhang ,&nbsp;Bing Lu ,&nbsp;Junyong Ge ,&nbsp;Xingyu Wang ,&nbsp;Yadong Yang ,&nbsp;Jiali Shang ,&nbsp;Zhu La ,&nbsp;Huadong Zang ,&nbsp;Zhaohai Zeng","doi":"10.1016/j.eja.2024.127422","DOIUrl":"10.1016/j.eja.2024.127422","url":null,"abstract":"<div><div>Timely access to crop above-ground biomass (AGB) information is crucial for estimating crop yields and managing water and fertilizer efficiently. Unmanned aerial vehicle (UAV) imagery offers promising avenues for AGB estimation due to its high efficiency and flexibility. However, the accuracy of these estimations can be influenced by various factors, including crop growth stages, the spectral resolution of UAV sensors, and flight altitudes. These factors need thorough investigation, especially in diversified cropping systems where crop diversity and growth stages interplay complexly, challenging the accuracy of AGB estimation. This study aims to estimate AGB of oats planted under different agricultural regimes—monoculture, crop rotation, and intercropping—at various growth stages (jointing, flowering, and grain-filling) and across all stages combined, using multispectral and RGB UAV images collected at different flight altitudes (25 m, 50 m, and 100 m). Three feature selection methods—maximal information coefficient (MIC), least absolute shrinkage and selection operator (LAS), and recursive feature elimination (RFE)—were tested. Four machine learning models—ridge regression (RR), multilayer perceptron (MLP), light gradient boosting machine (LGBM), and extreme gradient boosting (XGBoost)—were used for estimating AGB. Each feature selection method was combined with each machine learning model (e.g., MIC-RR, MIC-MLP, MIC-LGBM, MIC-XGBoost, LAS-RR) to evaluate their performance. Results revealed that the highest accuracy in AGB estimation was achieved with images acquired at a flight altitude of 25 m. The RFE-MLP model demonstrated superior results during the jointing stage (R² = 0.84, root mean squared error (RMSE) = 217.45 kg/ha, root mean squared logarithmic error (RMSLE) = 0.16, mean absolute percentage error (MAPE) = 4.15 %), the LAS-RR model excelled in the flowering stage (R² = 0.85, RMSE = 263.03 kg/ha, RMSLE = 0.05, MAPE = 14.44 %), and the RFE-XGBoost model was most effective during the grain-filling stage (R² = 0.68, RMSE = 865.03 kg/ha, RMSLE = 0.12, MAPE = 8.88 %). For cross-stage modelling, the RFE-MLP achieved remarkable results (R² = 0.93, RMSE = 680.44 kg/ha, RMSLE = 0.16, MAPE = 12.12 %). This study demonstrates the efficacy of combining feature selection methods with machine learning algorithms to enhance the accuracy of oat AGB estimations. The involvement of multiple cropping patterns enhances the generalizability of our findings, facilitating real-time and rapid monitoring of crop growth in future diversified cropping systems.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127422"},"PeriodicalIF":4.5,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655954","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":"Demonstrating almost half of cotton fiber quality variation is attributed to climate change using a hybrid machine learning-enabled approach","authors":"Xin Li ,&nbsp;Zhenggui Zhang ,&nbsp;Zhanlei Pan ,&nbsp;Guilan Sun ,&nbsp;Pengcheng Li ,&nbsp;Jing Chen ,&nbsp;Lizhi Wang ,&nbsp;Kunfeng Wang ,&nbsp;Ao Li ,&nbsp;Junhong Li ,&nbsp;Yaopeng Zhang ,&nbsp;Menghua Zhai ,&nbsp;Wenqi Zhao ,&nbsp;Jian Wang ,&nbsp;Zhanbiao Wang","doi":"10.1016/j.eja.2024.127426","DOIUrl":"10.1016/j.eja.2024.127426","url":null,"abstract":"<div><div>Understanding the effects of climate change on cotton fiber quality will reduce the risks to production caused by global warming. Machine learning algorithms are effective for forecasting climate impacts on crops. However, the impact of climate change on cotton fiber quality is unclear. Hence, a hybrid machine learning-enabled approach, the Bayesian model average (BMA) method with multiple machine learning algorithms (linear regressor, SVR, RFR, GBDT, LightGBM, and XGBoost) and bootstrap resampling, was developed to explore the impact and screen the important climatic factors affecting various traits of fiber quality. On the basis of fiber quality data from 1033 test stations across Xinjiang, China, from 2016 to 2022, the explained variance for climate change in the hybrid machine learning model was as follows: 44.72 %–50.55 % for white cotton grade, 44.06 %–53.95 % for length, 51.72 %–56.81 % for micronaire, 32.70 %–49.50 % for length uniformity, and 45.66 %–53.09 % for strength in the 1000 bootstrapping samples. In addition, recursive feature elimination with cross-validation (RFECV) was used to select the optimal feature set and calculate the contribution of each feature. The variability in micronaire in the hybrid model was affected primarily by climate factors, such as the daily minimum temperature, rainfall, and wind speed, whereas the other quality traits were affected mainly by radiation-related climatic indicators. The climate during the harvest stage in October had a significant effect on cotton quality, explaining 33.0 % of the variance in white cotton grade, 32.1 % in length, and 48.3 % in fiber strength. Conversely, the climate during the boll opening and early harvest stages in September had a greater influence on micronaire and length uniformity, accounting for 21.4 % and 37.2 % of the variance, respectively<em>.</em> This study highlights that climate change explains nearly 50 % of the variation in fiber quality, with the influence being notably more considerable during the later stages of the cotton growth period. These findings clarify the uncertainty in the impact of climate change on cotton fiber quality considering the uncertainty of the single machine model and model errors. Equally important, this information can be valuable for farmers and growers seeking to improve fiber quality under climate change.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127426"},"PeriodicalIF":4.5,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655953","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":"Citrus pose estimation under complex orchard environment for robotic harvesting","authors":"Guanming Zhang ,&nbsp;Li Li ,&nbsp;Yunfeng Zhang ,&nbsp;Jiyuan Liang ,&nbsp;Changpin Chun","doi":"10.1016/j.eja.2024.127418","DOIUrl":"10.1016/j.eja.2024.127418","url":null,"abstract":"<div><div>The growth poses of citrus on trees are diverse. To ensure minimal loss during citrus harvesting, accurately estimating the pose of citrus is particularly important. To solve this problem, this research developed a real-time citrus pose estimation system based on neural networks and point cloud processing algorithms. Specifically, this method uses neural networks to identify citrus. After constructing the citrus point cloud, it is input into the Random Sample Consensus with Levenberg-Marquardt (RANSAC-LM) point cloud processing algorithm to obtain the citrus coordinates. Combined with citrus growth information, the pose is output. By analyzing the distribution of citrus poses, citrus poses convenient for end- effector harvesting are defined. To enhance the camera's ability to obtain information about citrus, a camera observation model is constructed to dynamically adjust the camera position. Through experiments, the appropriate deep learning target detection framework YOLO V5 is selected for citrus object detection. The precision (P), recall rate (R), and mean average precision (mAP) are 92.3 %, 79.1 %, and 88.5 % respectively. This network can handle detection tasks in real orchard environments. The original Random Sample Consensus (RANSAC) is improved by using the Levenberg-Marquardt (LM) nonlinear optimization method. Experimental results show that RANSAC-LM reduces the citrus center coordinate precision error from (0.2, 0.2, 2.3) mm to (0.1, 0.2, 1.4) mm, reduces the accuracy Spherical Error Probable (SEP) from 2.77 to 1.61, and finally reduces the citrus pose error from 5.72° to 2.43°. The efficiency of the proposed citrus pose estimation algorithm is 0.24 s. Deployed on a citrus picking robot, it verifies the feasibility of the algorithm and provides a new solution for the pose estimation problem of citrus harvesting robots.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127418"},"PeriodicalIF":4.5,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578733","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":"Shallow drains and straw mulch alleviate multiple constraints to increase sunflower yield on a clay-textured saline soil I. Effects of decreased soil salinity, waterlogging and end-of-season drought","authors":"Mohammad Nazrul Islam ,&nbsp;Richard W. Bell ,&nbsp;Edward G. Barrett-Lennard ,&nbsp;Mohammad Maniruzzaman","doi":"10.1016/j.eja.2024.127416","DOIUrl":"10.1016/j.eja.2024.127416","url":null,"abstract":"<div><div>A well-designed drainage system can alleviate soil salinity and waterlogging, leading to increased crop yield if the drainage does not cause a water shortage late in the growing season. We conducted three field experiments with sunflower across two dry seasons (Experiment I in 2019–20, and II and III in 2020–21) in a tropical landscape to examine the effectiveness of shallow drains and mulch in overcoming these constraints. In Experiment I, four surface drains of 0.1 or 0.2 m depth spaced 1.2 or 1.8 m apart were tested along with an undrained treatment. In Experiment II, the same four drainage treatments and an undrained treatment in the main plots were split into mulch (-M and +M) sub-plots. Experiment III had four main treatments, undrained, surface drains (SD; 0.1 m deep, 1.8 m apart), subsoil drains (SSD; 0.5 m deep, 4.5 m apart) and SSD+SD each split for mulch (-M and +M) sub-plots. At vegetative emergence and at the 8-leaf stage, all plots were inundated (3–5 cm depth; EC_w: 1.5–2.5 dS m^–1) for 24 h before opening the drains. Drainage treatments without mulch reduced SEW₃₀ (waterlogging index, sum of excess water within 30 cm soil depth) and soil EC_1:5 at 0–15 cm, while increasing sunflower yield by 15–100 % compared to the undrained no-mulch treatment. Relative to the undrained no-mulch treatment, drains with straw mulch conserved soil water, reduced EC_1:5 at 0–15 cm and increased yield in Experiments II and III by 40–47 and 76–143 %, respectively. There were no yield differences among the combinations of shallow drains. Although combined drains (SSD+SD) added 25–30 % extra yield relative to surface drains, these have higher installation costs. Shallow surface drains at 1.2–1.8 m spacing coupled with mulch are effective options for smallholder farmers to reduce salinity, waterlogging and drought stresses, and increase yield on saline, clay soils.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127416"},"PeriodicalIF":4.5,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578734","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":"Estimating the temperature sensitivity of rice (Oryza sativa L.) yield and its components in China using the CERES-Rice model","authors":"Zeyu Zhou ,&nbsp;Jiming Jin ,&nbsp;Fei Li ,&nbsp;Jian Liu","doi":"10.1016/j.eja.2024.127419","DOIUrl":"10.1016/j.eja.2024.127419","url":null,"abstract":"<div><div>The effects of temperature changes on rice (<em>Oryza</em> sativa L.) yield and its components have been widely documented. However, most existing studies are based on small-scale, short-term field experiments, with few assessing these effects on a large scale or over long periods. Here, the calibrated Crop Environment Resource Synthesis (CERES)-Rice model was used for numerical simulations over six climate regions in the major rice cultivation areas of China for the period of 1989–2018. The simulated results were used to estimate the temperature sensitivity of rice yield with a panel model in each climate region, and the yield sensitivity was then decomposed into the temperature sensitivity of three components: panicle number per unit area (Pan_no), filled grain number per panicle (Grain_no), and grain weight (Grainwt). Results indicated that rice yield exhibited negative temperature sensitivity across all climate regions, driven primarily by the temperature sensitivity of Grain_no in most regions. Additionally, Grainwt did not vary with temperature in all regions. Further analysis suggested that yield, Pan_no, and Grain_no were more sensitive to high temperature degree days (HDD) than to growing degree days (GDD). Under the warmer scenarios, HDD increase played a dominant role in the reduction of Grain_no, while the joint effect of GDD and HDD resulted in an increased Pan_no in most regions. However, the negative effect of temperature on Grain_no outweighed its positive effect on Pan_no, leading to a decline in yield. This study provides insight for understanding the temperature response of rice yield and its components and will be beneficial for developing targeted adaptations to ensure rice sustainable production under global warming.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127419"},"PeriodicalIF":4.5,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578732","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":"Understanding increased grain yield and water use efficiency by plastic mulch from water input to harvest index for dryland maize in China’s Loess Plateau","authors":"Naijiang Wang ,&nbsp;Xiaosheng Chu ,&nbsp;Jinchao Li ,&nbsp;Xiaoqi Luo ,&nbsp;Dianyuan Ding ,&nbsp;Kadambot H.M. Siddique ,&nbsp;Hao Feng","doi":"10.1016/j.eja.2024.127402","DOIUrl":"10.1016/j.eja.2024.127402","url":null,"abstract":"<div><div>In China’s Loess Plateau, plastic mulch (PM) is an effective agronomic practice for dryland maize (<em>Zea mays</em> L.) to increase grain yield (GY) and water use efficiency (WUE) under water-limited conditions. However, there is dearth of quantitative data on how PM affects field water use step by step, subsequently increasing GY and WUE. The study aimed to identify which changes in the field water use pathway generated the positive effects of PM on GY and WUE. During the early vegetative stage (EVS), late vegetative stage (LVS), reproductive stage (RS), and entire growing season (GS), the field water use pathway was divided into five sequential steps: total water input (TWI), evapotranspiration to TWI ratio (ET/TWI), transpiration to ET ratio (T/ET), transpiration efficiency (TE), and harvest index (HI). A seven-year field experiment demonstrated that although TWI_GS exhibited no change, TWI_LVS and TWI_RS increased by 6.7 % and 5.4 %, respectively, on average following PM application. This highlighted the PM’s ability to increase water input into fields. Overall, PM negatively, neutrally, and positively affected ET/TWI_EVS (−29.8 %), ET/TWI_LVS, and ET/TWI_RS (+23.9 %), respectively, and thereby made unchanged ET/TWI_GS. There were average increases of 83.3 %, 29.8 %, 26.1 %, and 33.9 % by PM for T/ET_EVS, T/ET_LVS, T/ET_RS, and T/ET_GS respectively. Therefore, increased diversion of inputted water to T occurred in fields with PM. TE positively responded to PM during the LVS and RS. PM increased TE_LVS by 20.9 % and TE_RS by 44.1 % on average, signifying increased aboveground biomass produced per unit T under PM. The proportion of aboveground biomass partitioned to grains remained unaffected by PM as indicated by the neutral response of HI to PM. Increased water input into fields, diversion of inputted water to T, and aboveground biomass produced per unit T contributed to increased GY (+19.9 %) and WUE (+20.0 %) after applying PM. The study enhances our understanding of improved field water use pathway to produce more grains using limited water supplies in PM-based drylands in China’s Loess Plateau and similar regions worldwide.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127402"},"PeriodicalIF":4.5,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571465","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":"Growth conditions but not the variety, affect the yield, seed oil and meal protein of camelina under Mediterranean conditions","authors":"N. Codina-Pascual ,&nbsp;C. Cantero-Martínez ,&nbsp;M.P. Romero-Fabregat ,&nbsp;G. De la Fuente ,&nbsp;A. Royo-Esnal","doi":"10.1016/j.eja.2024.127424","DOIUrl":"10.1016/j.eja.2024.127424","url":null,"abstract":"<div><div>European agriculture policies emphasize the importance of agricultural sustainability, focusing on increase of biodiversity through crop diversification. In Mediterranean dryland cropping systems, the introduction of crops in rotation with cereals is challenged by scarce precipitation and high evapotranspiration. In this scenario, camelina (<em>Camelina sativa</em> (L.) Crantz), a low-input annual oleaginous crop with a high morphological plasticity, short life cycle, and interesting oil and meal composition, could be an option to be included in rotation with winter cereals. The aim of this experiment was to study the agronomic performance, and seed oil and meal protein contents of camelina in two different climatic conditions, with a sowing delay in one of them. Several trials were conducted in Montargull (Mediterranean semihumid) and in Lleida (Mediterranean semiarid) in two seasons (2020–21 and 2021–22). In Montargull, two sowing dates (November, SD1 and January, SD2) were established. In each growing condition, three spring camelina varieties were sown (<em>Calena, CO46</em> and <em>GP204</em>). Camelina was harvested between May and July, and yield and harvest index were measured. After cold pressing the seeds, seed oil and meal protein contents were analysed. Camelina yield and quality was not related to the variety, but to two climatic scenarios: 1) a favourable rainfall distribution without important drought periods (2020–21); 2) significant rainfalls in November and April, but with a drought period in between (2021–22). In the first situation, camelina production ranged from 1533 to 2187 kg ha⁻¹, with high seed oil (40.4–41.4 %) and meal protein (41.0–44.8 %) contents. In the second situation, the yield decreased to 242–661 kg ha⁻¹, seed oil content to 31.0–34.7 %, and meal protein content to 37.6–40.4 %. Despite these seasonal differences, SD1 in Montargull obtained higher average yields and protein content than in Lleida and in SD2. In contrast, in Lleida and in SD2 in Montargull camelina produced higher oil content. The implementation of camelina into Mediterranean dryland crop rotation systems is feasible. Considering the importance of moisture in these climatic conditions, the use of no-till practices is recommended in dryland fields to avoid excessive water loss, while the use of camelina in irrigated fields could be explored. However, more long-term agronomic and industrial research is still needed.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127424"},"PeriodicalIF":4.5,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571466","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":"Wheat growth stage identification method based on multimodal data","authors":"Yong Li ,&nbsp;Yinchao Che ,&nbsp;Handan Zhang ,&nbsp;Shiyu Zhang ,&nbsp;Liang Zheng ,&nbsp;Xinming Ma ,&nbsp;Lei Xi ,&nbsp;Shuping Xiong","doi":"10.1016/j.eja.2024.127423","DOIUrl":"10.1016/j.eja.2024.127423","url":null,"abstract":"<div><div>Accurate identification of crop growth stages is a crucial basis for implementing effective cultivation management. With the development of deep learning techniques in image understanding, research on intelligent real-time recognition of crop growth stages based on RGB images has garnered significant attention. However, the small differences and high similarity in crop morphological characteristics during the transition between adjacent growth stages pose challenges for accurate identification. To address this issue, this study proposes a multi-scale convolutional neural network model, termed MultiScalNet-Wheat (MSN-W), which enhances the algorithm's ability to learn complex features by utilizing multi-scale convolution and attention mechanisms. This model extracts key information from redundant data to identify winter wheat growth stages in complex field environments. Experimental results show that the MSN-W model achieves a recognition accuracy of 97.6 %, outperforming typical convolutional neural network models such as VGG19, ResNet50, MobileNetV3, and DenseNet. To further address the difficulty in recognizing growth stages during transition periods, where canopy morphological features are highly similar and show small differences, this paper introduces an innovative approach by incorporating sequential environmental data related to wheat growth stages. By extracting these features and performing multi-modal collaborative inference, a multi-modal feature-based wheat growth stage recognition model, termed MultiModalNet-Wheat (MMN-W), is constructed on the basis of the MSN-W model. Experimental results indicate that the MMN-W model achieves a recognition accuracy of 98.5 %, improving by 0.9 % over the MSN-W model. Both the MSN-W and MMN-W models provide accurate methods for observing wheat growth stages, thereby supporting the scientific management of winter wheat at different growth stages.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127423"},"PeriodicalIF":4.5,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571467","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":"Combination with moderate irrigation water temperature and nitrogen application rate enhances nitrogen utilization and seed cotton yield","authors":"Zhanli Ma ,&nbsp;Jing He ,&nbsp;Jinzhu Zhang ,&nbsp;Wenhao Li ,&nbsp;Feihu Yin ,&nbsp;Yue Wen ,&nbsp;Yonghui Liang ,&nbsp;Hanchun Ye ,&nbsp;Jian Liu ,&nbsp;Zhenhua Wang","doi":"10.1016/j.eja.2024.127417","DOIUrl":"10.1016/j.eja.2024.127417","url":null,"abstract":"<div><div>To promote the efficient utilization of groundwater and improve nitrogen fertilizer effectiveness, a reasonable range of nitrogen application rates and irrigation water temperature was investigated. A field experiment was conducted in Xinjiang, China, in 2022 and 2023, involving four irrigation water temperature levels (T0: 15 °C, T1: 20 °C, T2: 25 °C, and T3: 30 °C) and three nitrogen application rates (F1: 250 kg ha⁻¹, F2: 300 kg ha⁻¹, and F3: 350 kg ha⁻¹). The results indicated that soil nitrogen content, cotton dry matter weight, cotton nitrogen content, seed cotton yield, and nitrogen partial factor productivity (NPFP) increased with higher nitrogen application rates. However, as irrigation water temperature increased, soil nitrogen content decreased, whereas cotton dry matter weight, cotton nitrogen content, seed cotton yield, and NPFP initially increased before declining. Notably, the maximum yield and NPFP among all treatments were observed in T2F2 (25 °C, 300 kg ha⁻¹), yielding 6652 kg ha^–1 and 6941 kg ha^–1, and in T2F1 (25 °C, 250 kg ha^–1), with 24.20 kg kg^–1 and 25.20 kg kg^–1 in 2022 and 2023, respectively. Furthermore, the optimal range of irrigation water temperature of 23.82–27.41 °C and nitrogen application rate of 276.43–289.23 kg ha^–1 were identified to achieve over 80 % of the highest seed cotton yield and NPFP using multiple regression and spatial analysis methods. This study offers valuable guidance for optimizing irrigation and fertilization strategies to enhance resource efficiency and promote sustainable cotton production in arid regions.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"162 ","pages":"Article 127417"},"PeriodicalIF":4.5,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142560673","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}