{"title":"Artificial intelligence for early detection and management of Tuta absoluta-induced tomato leaf diseases: A systematic review","authors":"Harisu Abdullahi Shehu , Aniebietabasi Ackley , Marvellous Mark , Ofem Ebriba Eteng","doi":"10.1016/j.eja.2025.127669","DOIUrl":"10.1016/j.eja.2025.127669","url":null,"abstract":"<div><div>Food security is a critical challenge of the 21st century, increasingly exacerbated by climate change, which facilitates the spread of pests on farms. The South American tomato pinworm, Tuta absoluta (Meyrick), represents a significant global threat to tomato crops. Rising infestations have led to the extensive use of insecticides, raising concerns about pesticide resistance, human health risks, and environmental contamination. Meanwhile, artificial intelligence (AI) provides real-time, scalable, and cost-effective alternatives to traditional pest detection methods, which are labour-intensive and prone to human error. As a result, this study comprehensively assesses the potential of AI in the early detection and mitigation of Tuta absoluta-induced tomato leaf diseases. A systematic literature review was conducted across four major academic databases: ScienceDirect, Scopus, ACM, and IEEE. After a rigorous screening process, 115 studies were selected from an initial pool of 178 papers based on the relevance of their methodologies. This paper synthesises current research on AI methodologies, pest detection technologies, and their agricultural applications for the early detection, identification, and management of Tuta absoluta-induced tomato leaf diseases. Beyond tomato crops, the findings offer broader implications for managing similar pests affecting other economically significant crops. The study concludes with actionable recommendations for integrating AI-driven pest detection into precision agriculture, with the goal of enhancing food security and promoting sustainable farming practices worldwide.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"170 ","pages":"Article 127669"},"PeriodicalIF":4.5,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147286","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}
Fabo Liu , Xiaoge Shen , Xiaopeng Gao , Fen Zhang , Xu Luo , Yang Liu , Yunfei Yang , Wenkang Yang , Tao Liang , Chunli Wang , Xiaozhong Wang , Xinping Chen
{"title":"An innovative integrated management strategy drives sustainable vegetable production in southwest China: Higher yield with reduced net GHG emissions","authors":"Fabo Liu , Xiaoge Shen , Xiaopeng Gao , Fen Zhang , Xu Luo , Yang Liu , Yunfei Yang , Wenkang Yang , Tao Liang , Chunli Wang , Xiaozhong Wang , Xinping Chen","doi":"10.1016/j.eja.2025.127703","DOIUrl":"10.1016/j.eja.2025.127703","url":null,"abstract":"<div><div>Intensive vegetable production in Southwest China is characterized by excessive fertilizer inputs, low nutrient use efficiency and high environmental costs. Thus, effective management strategies for sustainable vegetable production need to be explored. A two-year field experiment (2023–2024) was conducted to comprehensively evaluate the effects of different nutrient management strategies on vegetable yield and quality, net greenhouse gas (GHG) emissions, soil carbon (C) sequestration, and net ecosystem economic benefits (NEEB) from an open-field pepper (<em>Capsicum annuum L.</em>) production system in Southwest China. The six treatments included a control without fertilizer (CK), farmers’ conventional practice (FP), three optimized nutrient management strategies (optimized NPK fertilizer, OPT; single-dose application of controlled release urea, CRU; and high-efficiency water-soluble fertilizer with nitrification inhibitor, WSF+NI), and an innovative integrated knowledge and product strategy (IKPS, which integrates optimized nutrient management, soil health and improved crop management). Compared with the FP treatment, the optimized nutrient management strategy decreased the fertilizer inputs by 43–62 %, increased the average pepper yield by 2.1–9.6 % and the nutrient use efficiency by 1.7–3.3 times. Compared with these optimized strategies, IKPS further significantly increased the vegetable yield, nutrient uptake and nutrient use efficiency by 12.4–20.8 %, 10.3–62.2 % and 31.9–83.9 %, respectively. Additionally, compared with those under FP, the three optimized nutrient management practices and IKPS significantly decreased the nitrite content in pepper fruits by 13.9–42.4 % and increased the vitamin C content by 60.5–77.6 %. These results indicated a comprehensive improvement in vegetable quality. Moreover, the net GHG emissions in the OPT, CRU, and WSF + NI treatments were reduced by 56.7 %, 72.1 % and 82.7 %, respectively, relative to those in the FP treatment, primarily because of the reduced fertilizer inputs. Compared with the three optimized nutrient management practices, the IKPS further improved soil C sequestration by 29.1–43.0 %, further reduced net GHG emissions by 47.2–78.9 %, and increased the NEEB by 33.2–47.2 %. The highest comprehensive evaluation index (CEI) was achieved with IKPS. These results confirmed its great potential as an innovative integrated management strategy to increase yields, improve economic and environmental benefits, and ultimately achieve sustainability in vegetable production. This study provides a template for sustainable vegetable production practices in subtropical regions, highlighting the importance of the IKPS for achieving carbon neutrality.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"169 ","pages":"Article 127703"},"PeriodicalIF":4.5,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144139617","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":"Simulation of soil mineral nitrogen dynamics in banana cover-cropping systems on andosol with the BANANA-N model","authors":"Marie Ruillé , Elodie Dorey , Marc Dorel","doi":"10.1016/j.eja.2025.127670","DOIUrl":"10.1016/j.eja.2025.127670","url":null,"abstract":"<div><div>The use of organic nitrogen (N) fertilizer and cover crops offer a potential alternative to the synthetic N fertilization in banana cropping systems. However, these changes in cultural practices alter the availability of mineral N and could result in a loss in yield in these agrosystems. Our objective was to develop a model based on existing models specific to banana cultivation to simulate soil mineral N in agroecological banana agrosystems on andosol. BANANA-N integrated several modifications: the simulation of atmospheric N fixation by legume cover crops, simulation at mat scale to take account of stand heterogeneity, and subdivision of the soil into two layers to better match the functioning of andosols. Then, the model was evaluated by comparing observed and simulated soil mineral N dynamics in banana cropping systems with contrasting N fertilization management. Although model formalisms imply simplifying assumptions, BANANA-N performs well in predicting above ground banana biomass with contrasting N fertilization management (0.27 ≤RRMSE≤0.42 and 0.7 ≤NSE≤0.86). The soil mineral nitrogen dynamics were fairly well predicted in sole cropping or intercropping with a grass plant (0.33 ≤RRMSE≤0.46), while it was poorly predicted when banana is grown in association with a leguminous plant (RRMSE≥0.53). This study presents the first calibration of the BANANA-N model, capable of assessing the impact of different fertilization strategies on banana productivity, and their potential contribution to maximize internal N recycling and minimize N losses to the environment.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"169 ","pages":"Article 127670"},"PeriodicalIF":4.5,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144139692","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":"Integrated weed management in olive orchard: The effect of spontaneous grass cover crops on weed community, olive production and soil fertility","authors":"Veronica Pedraza, Jose L. Gonzalez-Andujar","doi":"10.1016/j.eja.2025.127706","DOIUrl":"10.1016/j.eja.2025.127706","url":null,"abstract":"<div><div>Olive groves are vital to the Mediterranean Basin's economy, agro-ecology, and culture. Effective weed management is critical for their long-term sustainability and productivity. This study evaluated the effects of spontaneous grass cover crops on weed community structure, olive production, and soil fertility, comparing them with conventional tillage practices. Over three years in southern Spain, two management strategies were tested: a Grass Cover Crop (GCC) system—combining no-tillage with chemical control, pruning wood residues in intra-row spaces, and spontaneous grass cover crops in inter-row spaces and a Tillage (TL) system, which included tillage operations and pruning wood residues in both intra- and inter-row spaces. Weed community and olive crop impacts were assessed by examining richness, abundance, diversity (Shannon index), and equity (Pielou evenness index) at two time points, alongside evaluations of olive yield, quality, and soil fertility. Before herbicide application, the GCC system exhibited greater weed richness, abundance, and diversity in intra-rows and higher richness and diversity in inter-rows compared to TL. Post-herbicide, richness and abundance remained higher in GCC, with increased diversity in inter-rows, and low weed biomass was maintained. While olive yield and quality were unaffected, soil fertility improved under GCC. These results highlight that integrating soil cover methods, such as spontaneous grass cover crops, can balance crop productivity with beneficial weed diversity, fostering a sustainable agricultural system.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"169 ","pages":"Article 127706"},"PeriodicalIF":4.5,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144139616","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}
Heguang Sun , Huanming Mai , Yanzhi Mao , Qingquan Li , Mei Guo , Yongshun Liu , Ziheng Feng , Haikuan Feng , Wei Guo , Guijun Yang , Xiaoling Deng , XiaoYu Song
{"title":"Multi-variety monitoring of potato late blight severity using UAV data with improved SMOTE-CS for small sample modeling and deep feature learning","authors":"Heguang Sun , Huanming Mai , Yanzhi Mao , Qingquan Li , Mei Guo , Yongshun Liu , Ziheng Feng , Haikuan Feng , Wei Guo , Guijun Yang , Xiaoling Deng , XiaoYu Song","doi":"10.1016/j.eja.2025.127702","DOIUrl":"10.1016/j.eja.2025.127702","url":null,"abstract":"<div><div>Accurate and non-destructive monitoring of potato late blight (PLB) using unmanned aerial vehicle (UAV) remote sensing data is of great significance for field management. However, during disease outbreaks, there is a lack of universally applicable rapid monitoring models. On the one hand, different varieties exhibit varying levels of resistance and disease monitoring progression, which can be attributed to genetic and environmental factors. On the other hand, the heterogeneity, imbalance, and noise in spectral and textural data across regions pose significant challenges for disease monitoring. To address these issues, this study first improves upon the noise problem in Synthetic Minority Over-sampling Technique (SMOTE) by employing an enhanced feature selection algorithm based on the Feature Selection with Compactness and Separability (FS-CS) principle. Subsequently, the feature ranking is then used with the Importance-Ordered Weighted Averaging (IOWA) operator to calculate the induced Minkowski OWA distance (IMOWAD), replacing the nearest neighbor distance used in SMOTE. This refinement emphasizes the boundaries of synthetic sample regions and mitigates noise-related issues. This improved method is referred to as SMOTE-CS. Secondly, nine models were constructed to evaluate the effectiveness of FS-CS in feature selection when integrating multiple datasets. Compared to mRmR and ReliefF, FS-CS achieved higher accuracy with a smaller number of features. Finally, to address varietal and environmental differences, modeling was conducted using a shallow transfer learning 1D-CNN model and a deep DRSN model incorporating nonlinear soft thresholding processing, respectively. The results indicate that the 1D-CNN model achieved overall accuracies (OA) of 0.99 and 0.93 on the two datasets, respectively. However, its performance was affected by the poor interpretability of the boundary between the synthetic source and target domain samples. The integration of nonlinear soft-thresholding into the DRSN model enhanced its feature extraction capability and noise suppression. It demonstrated strong performance on the two datasets, achieving an OA of 0.91 and a Kappa coefficient of 0.86. Compared to the original SMOTE version, the proposed approach exhibited superior generalization ability. The results of this study provide new insights into the problems of small sample imbalance, noise, and technical support for multi-species PLB monitoring in different regions.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"169 ","pages":"Article 127702"},"PeriodicalIF":4.5,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144134896","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}
Diego Soto-Gómez , Silvia Martínez-Martínez , Jose A. Acosta , Juan A. Fernández , Josefina Contreras , María Almagro , María Martínez-Mena , Carolina Boix-Fayos , Elvira Díaz-Pereira , Abdelmalek Temnani , Pablo Berrios , Alejandro Pérez-Pastor , Virginia Sánchez-Navarro
{"title":"Changes in the chemical fertility of a Mediterranean soil after the implementation of alley crops rotation in a mandarin orchard under regulated deficit irrigation","authors":"Diego Soto-Gómez , Silvia Martínez-Martínez , Jose A. Acosta , Juan A. Fernández , Josefina Contreras , María Almagro , María Martínez-Mena , Carolina Boix-Fayos , Elvira Díaz-Pereira , Abdelmalek Temnani , Pablo Berrios , Alejandro Pérez-Pastor , Virginia Sánchez-Navarro","doi":"10.1016/j.eja.2025.127705","DOIUrl":"10.1016/j.eja.2025.127705","url":null,"abstract":"<div><div>Intensive orchard monocultures in the Mediterranean region lead to environmental issues as soil erosion, soil organic matter loss and nutrient leaching. Alley cropping could serve as suitable strategy to improve soil fertility while increasing land productivity. This study aimed to assess the effect of different alley crop rotations on soil fertility and their effect on counteracting the effects of water stress on mandarin production. For this, three types of alley cropping with two different irrigation intensities were applied: i) a mandarin monoculture with bare alley soil, under both control irrigation (MM) and regulated deficit irrigation, RDI, (MMDI); ii) a multiple cropping of barley/vetch and fava bean, under both control irrigation (AC1) and RDI (AC1DI); and iii) a rotation of fava bean, purslane, and cowpea, under both control irrigation (AC2) and RDI (AC2DI). Soil samples were collected from two depths (0–10 cm and 10–30 cm) within the alleys, and different soil nutrients and cation exchange capacity (CEC) were measured. Chemical fertility in the MM treatment is relatively stable over time with time. A slight increase in the CEC was observed in AC1DI. In contrast, the AC2DI plots showed increases in B, P, and total nitrogen concentrations in subsurface samples. In terms of yield, this was significantly higher during the first year in MM, compared to AC1. Changes in production were similar in the three treatments. Average fruit size remained almost constant in MM but increased in AC1 and AC2. Regarding the productivity of the land, it decreased in MM and AC2 during the last year.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"169 ","pages":"Article 127705"},"PeriodicalIF":4.5,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144124228","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}
Insa Kühling , Klaus Sieling , Thomas Räbiger , Mirjam Helfrich , Heinz Flessa , Michaela Schlathölter , Dennis Grunwald , Heinz-Josef Koch , Lisa Essich , Reiner Ruser , Henning Kage
{"title":"Different utilisation of residual N from oil radish cover crop by maize or sugar beet, and subsequent winter wheat","authors":"Insa Kühling , Klaus Sieling , Thomas Räbiger , Mirjam Helfrich , Heinz Flessa , Michaela Schlathölter , Dennis Grunwald , Heinz-Josef Koch , Lisa Essich , Reiner Ruser , Henning Kage","doi":"10.1016/j.eja.2025.127700","DOIUrl":"10.1016/j.eja.2025.127700","url":null,"abstract":"<div><div>Cover crops (CC) may take up substantial amounts of nitrogen and thereby reduce the soil nitrate pool in autumn and thus, the risk of nitrogen (N) leaching losses during winter. The dynamics of the remineralisation of this organic N into plant-available N pools affects the fertiliser N needs of subsequent crops and their economic optimal N rate (EONR). In a series of eight field trials (two years x four sites) across Germany, the effects of oil radish (OR) as CC on above-ground dry matter (DM) accumulation and N uptake of silage maize (SM) and sugar beets (SB) as first subsequent crops, and winter wheat (WW) as second subsequent crop were investigated in combination with four fertiliser N levels. Across all site-years, the N amount in pre-winter OR biomass clearly enhanced SM growth, while SB showed no or, in the unfertilized control, a negative response, indicating the occurrence of pre-emptive competition. The same pattern was observed for parameters derived from N response curves (DM yield and N uptake) without N fertilisation and at EONR. Net soil N mineralisation was stronger affected by soil type than by the first succeeding main crop with negative correlation of OR N uptake on sand and positive correlation on loess soils. In the second year, OR biomass N showed small effects on WW yield and N uptake without N fertilisation (positive after SM, negative after SB), but optimal N supply superimposed all OR effects. Residual N from OR did not significantly reduce EONR either in the first or the second succeeding main crop. For an economically beneficial effect in SM, OR N uptake must be at least 71 kg N ha<sup>−1</sup>, while in SB typical N uptake from CC would not reach the break-even point.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"169 ","pages":"Article 127700"},"PeriodicalIF":4.5,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144124227","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}
Andrea Burato , Giovanna Marta Fusco , Alfonso Pentangelo , Domenico Ronga , Petronia Carillo , Pasquale Campi , Mario Parisi
{"title":"Balancing yield, water productivity, and fruit quality of processing tomatoes through the combined use of biodegradable mulch film and regulated deficit irrigation","authors":"Andrea Burato , Giovanna Marta Fusco , Alfonso Pentangelo , Domenico Ronga , Petronia Carillo , Pasquale Campi , Mario Parisi","doi":"10.1016/j.eja.2025.127695","DOIUrl":"10.1016/j.eja.2025.127695","url":null,"abstract":"<div><div>Italy is the third largest producer of processing tomatoes (<em>Solanum lycopersicum</em> L.) worldwide. Tomato production is projected to be considerably affected by climate change, especially in drought-prone regions where maximizing water use efficiency is essential. A two-year on-farm experiment was conducted to compare full irrigation (T1) with two water-saving irrigation strategies: T2 (regulated deficit irrigation, RDI) and T3 (RDI combined with soil-biodegradable mulch film). The experiment was conducted at two representative sites in southern Italy, where yield performance, sustainability, and fruit quality were assessed. T2 resulted in 31 % water savings and maintained comparable yields, increasing irrigation (+44 %) and economic (+56 %) water productivities with respect to T1. Nevertheless, the accelerated crop cycle observed in T2 reduced the leaf coverage of fruit, leading to a higher number of sun-scalded fruits and decreased lycopene content at harvest. The negative effects of RDI were partially mitigated by combining it with soil-biodegradable mulch film (T3), which improved the soluble solid content (+4 %), marketable (+23 %) and Brix (+28 %) yields, and irrigation (+71 %) and economic (+78 %) water productivities compared with T1. Metabolic profiling further highlighted that T3 increased key stress-related metabolites, including alanine (+50 %), glycine (+31 %), and proline (+44 %), indicating enhanced metabolic adaptation to water stress. The increase in proline, a crucial osmolyte and antioxidant, suggests improved nitrogen use efficiency and overall metabolic resilience under water-deficient conditions. Based on these findings, T3 is recommended as a valuable practice for improving yield and sustainability, while maintaining fruit quality in drought-prone areas.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"169 ","pages":"Article 127695"},"PeriodicalIF":4.5,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144124226","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}
Ying Song , Zhijie Li , Jiayu Sun , Hanwen Chen , Jinxia Fu , Xiaoling He , Asim Biswas , Fenli Zheng , Zhi Li
{"title":"Soil thinning dominates crop yield reduction among various degradation types in the typical black soil region of Northeast China","authors":"Ying Song , Zhijie Li , Jiayu Sun , Hanwen Chen , Jinxia Fu , Xiaoling He , Asim Biswas , Fenli Zheng , Zhi Li","doi":"10.1016/j.eja.2025.127694","DOIUrl":"10.1016/j.eja.2025.127694","url":null,"abstract":"<div><div>The degradation of black soil poses a substantial threat to the sustainability of agriculture in Northeast China. Although numerous studies have investigated the impact of soil degradation on crop yield, including soil thinning, nutrient depletion, and structural degradation, the primary form of degradation contributing to regional crop yield reduction remains unclear. We synthesized 488 paired observations from 32 studies to identify the predominant type of soil degradation in the typical black soil region of Northeast China. Subsequently, we examined the effects of environmental factors on crop yield occurring under the dominant degradation type. Our findings indicated that the yield reduction is the greater under soil thinning (effect size: −27 %), followed by nutrient depletion (effect size: −20 %) and soil structure degradation (effect size: −6 %). Focusing on the soil thinning, we identified 5 cm reduction in topsoil depth as the threshold, below which crop yields are not significantly affected. The impacts of soil thinning on yield followed a non-linear pattern, with severe yield losses for greater reduction in topsoil thickness, and a greater reduction in soybean yield compared to maize. The depth of topsoil removal was the primary factor causing crop yield reduction, followed by soil organic matter (SOM) and total soil nitrogen (STN). The structural equation model further indicated that topsoil removal depth, experimental duration, and fertilizer types not only directly affected the changes in crop yield, but also indirectly impacted yield by altering soil physical and chemical properties. Overall, our findings highlight the critical role of soil thinning in driving crop yield reductions in Northeast China, and emphasize that soil properties are key determinants in the recovery of crop yields in agricultural systems affected by soil thinning.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"169 ","pages":"Article 127694"},"PeriodicalIF":4.5,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144124225","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}
Wei Zhu , Runchen Ma , Jianshuo An , Wenbin Li , Xiaopeng Bai , Daochun Xu
{"title":"Three-dimensional reconstruction and parameters extraction of walnut (Juglans regia L.) branches based on Neural Radiation Fields","authors":"Wei Zhu , Runchen Ma , Jianshuo An , Wenbin Li , Xiaopeng Bai , Daochun Xu","doi":"10.1016/j.eja.2025.127693","DOIUrl":"10.1016/j.eja.2025.127693","url":null,"abstract":"<div><div>Three-dimensional (3D) reconstruction is important for obtaining morphological information and making intelligent management decisions for fruit trees. Thus, a method for the 3D reconstruction and parameters extraction of branches based on Neural Radiation Fields (NeRF) was proposed for walnut (Juglans regia L.) trees. This approach combined Structure from Motion (SfM) with NeRF and used multi-view images to reconstruct branches. First, a dataset of multi-view images of walnut trees was built and camera poses were obtained using SfM. Second, WalnutNeRF was optimized by incorporating hash encoding, piecewise sampler and appearance embedding features to address challenges associated with complex outdoor environments and accurately reconstruct branches. A scale recovery method using calibration objects was employed to extract branch parameters. The effectiveness of WalnutNeRF was evaluated by analyzing rendering performance, reconstruction efficiency, point cloud quality, and the accuracy of extracted branch parameters. WalnutNeRF outperformed existing methods in terms of the quality of rendered images and the accuracy of estimated depth, as determined using PSNR, SSIM, LPIPS, and other metrics. WalnutNeRF resulted in a branch reconstruction accuracy of 90.94 %, with a training time that was 9-time faster than that of SfM-MVS. Compared with SfM-MVS, WalnutNeRF decreased reconstruction errors for the main branches, lateral branches, and watershoots by 72 %, 67 %, and 57 %, respectively, and decreased the errors in length by 7.09 %, 4.33 %, and 65.07 %, respectively. Accordingly, WalnutNeRF decreased the reconstruction time, while increasing accuracy, providing robust support for the development of intelligent management applications (e.g., intelligent pruning) for walnut trees.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"169 ","pages":"Article 127693"},"PeriodicalIF":4.5,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144099715","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}