European Journal of Agronomy最新文献

{"title":"Spectral data driven machine learning classification models for real time leaf spot disease detection in brinjal crops","authors":"Rohit Anand ,&nbsp;Roaf Ahmad Parray ,&nbsp;Indra Mani ,&nbsp;Tapan Kumar Khura ,&nbsp;Harilal Kushwaha ,&nbsp;Brij Bihari Sharma ,&nbsp;Susheel Sarkar ,&nbsp;Samarth Godara","doi":"10.1016/j.eja.2024.127384","DOIUrl":"10.1016/j.eja.2024.127384","url":null,"abstract":"<div><div>This study presents the development and evaluation of machine learning models for detecting leaf spot disease in brinjal crops using spectral sensor data. The spectral reflectance of diseased and healthy tissues was recorded across nine wavelength bands (F1: 415 nm, F2: 445 nm, F3: 480 nm, F4: 515 nm, F5: 555 nm, F6: 590 nm, F7: 630 nm, F8: 680 nm, and F9: NIR-750 nm). The data revealed distinct spectral signatures, particularly between F5 (555 nm) and F9 (NIR), where diseased tissues consistently showed lower reflectance compared to healthy tissues. Two machine learning algorithms, Decision Tree (DT) and Support Vector Machine (SVM), were employed to classify the spectral data. The DT model achieved a maximum testing accuracy of 88.2 %, with a Gini index and a depth of 4 as optimal hyperparameters. The confusion matrix indicated that the DT model correctly identified 883 diseased instances and 667 healthy cases, while misclassifying 213 healthy tissues as diseased and 25 diseased tissues as healthy. The SVM model, configured with a cost parameter of 10.0 and a tolerance of 0.01, outperformed the DT model, achieving a testing accuracy of 92.4 %. The SVM model correctly classified 99.3 % of diseased instances and 94.1 % of healthy cases. The results demonstrate the potential of spectral sensor data combined with ML algorithms for precise disease detection, facilitating targeted pesticide application, and reducing input costs. The high accuracy of the SVM model underscores its utility in agricultural disease management, enabling early intervention and enhancing crop health monitoring. Future research may explore integrating multiple sensors and advanced feature extraction methods to further improve the efficiency and accuracy of these systems.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127384"},"PeriodicalIF":4.5,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419327","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":"Climate, altitude, yield, and varieties drive lodging in sugarcane: A random forest approach to predict risk levels on a tropical island","authors":"Mathias Christina ,&nbsp;Benjamin Heuclin ,&nbsp;Raphaël Pilloni ,&nbsp;Mathilde Mellin ,&nbsp;Laurent Barau ,&nbsp;Jean-Yves Hoarau ,&nbsp;Thomas Dumont","doi":"10.1016/j.eja.2024.127381","DOIUrl":"10.1016/j.eja.2024.127381","url":null,"abstract":"<div><div>Lodging is a critical factor in reducing sugarcane yields worldwide, mainly due to the selection of highly productive varieties. Understanding the response of yield and lodging to the combined effects of climate, sugarcane traits, and varieties has become a priority under climate change. The aim of this study was to better understand the influence of plant characteristics, climate, and soil conditions on the trade-off between sugarcane yield and lodging on the tropical Reunion Island. Data from a 14-year experimental network run by the eRcane breeding institute were used to build random-forest models to predict sugarcane yield and lodging classes, i.e. &lt;10 %, 10–50 %, &gt;50 % of lodging. Yield and lodging probability were then predicted across the island using climate change projections from 2015 to 2035. Both yield and lodging were highly influenced by the variety and characteristics (height and tillering) and climatic conditions. Areas on the island at high altitudes were subject to high probability of lodging (&gt;50 %), while in areas with high wind speed, the risk of moderate lodging (10–50 %) increased. Overall, conditions or plant characteristics that favor higher yields increased lodging probability. Nevertheless, the correlation between yield and lodging probability varied considerably depending on the variety, highlighting the importance of sugarcane characteristics in resistance to lodging. This study highlights the fact that promoting more productive varieties in recent decades has led to an increase in lodging and identified critical environments on the island prone to increased risk of lodging.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127381"},"PeriodicalIF":4.5,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419234","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":"A comparative study of yield components and their trade-off in oilseed crops (Brassica napus L. and Brassica carinata A. Braun)","authors":"Maximiliano Verocai ,&nbsp;Pablo González-Barrios ,&nbsp;Sebastián R. Mazzilli","doi":"10.1016/j.eja.2024.127377","DOIUrl":"10.1016/j.eja.2024.127377","url":null,"abstract":"<div><div>Canola (<em>Brassica napus</em> L.) and carinata (<em>Brassica carinata A.</em> Braun) are two oilseed crops that have seen a surge in demand in recent years. However, current yields achieved by farmers are inconsistent and significantly lower than those achieved in research experiments. Therefore, a better understanding of the trade-off between yield components is crucial to help breeders develop new high-yielding cultivars and for farmers to manage their crops more effectively. Unfortunately, scientific literature focused on trade-offs between yield components in rapeseed is scarce for canola and lacking for carinata. To address this issue, we conducted field experiments in Uruguay over three consecutive seasons (2016–2018) using the cultivars “Rivette” and “Avanza 641” for canola and carinata, respectively. Our goal was to study yield compensation and determine the comparative performance of canola and carinata across a wide range of sowing dates. Our results showed that carinata yields ranged from 854 kg ha⁻¹ to 7283 kg ha⁻¹, while canola yields ranged from 1152 kg ha⁻¹ to 4489 kg ha⁻¹. Higher biomass production was linked to increased yields in carinata, while an increase in biomass did not necessarily result in higher yields in canola due to a harvest index reduction. Carinata yield was positively correlated with grain number, silique number, and grains per silique. In canola, moderate to large yield changes were primarily influenced by grain number and grain weight, as silique number had a negative trade-off with yield, while grains per silique had a neutral relationship with yield. Our study revealed a distinct yield building process in canola and carinata, despite the general belief that they share physiological similarities and can be managed alike. These findings enhance our understanding of crop knowledge and management, potentially leading to increased crop productivity, and generate more effective breeding programs. Enhancing the yield performance of canola and carinata will position them as economically profitable crops, allowing for greater crop diversification and meeting the growing global demand for biofuels.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127377"},"PeriodicalIF":4.5,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419273","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":"Changes in end-use quality parameters of two bread wheat cultivars under water stress and heatwave conditions","authors":"David Soba ,&nbsp;Jon González-Torralba ,&nbsp;María Ancín ,&nbsp;Sergio Menéndez ,&nbsp;Iker Aranjuelo","doi":"10.1016/j.eja.2024.127385","DOIUrl":"10.1016/j.eja.2024.127385","url":null,"abstract":"<div><div>The baking industry requires a high level of uniformity in flour quality to meet its demands. Cereal production and nutritional traits are tightly conditioned by genotype and environmental factors. In the current study, the impact of temperature and rainfall on yield and end-use quality of two bread wheat (<em>Triticum aestivum</em> L.) cultivars (Camargo and Marcopolo) was analysed under field conditions. To do that a 2-year experiment (2018–2019) was carried out in three contrasting agro-climatic environments in Navarra (northern Spain). The results revealed that year (Y) (linked with temperature and precipitation) was the main factor controlling most crop agronomic performance parameters. Further, genotype (G), G x E, G x Y and the triple interaction had significant effects in the studied grain quality parameters, suggesting a well-differentiated response to different environments between both cultivars. More specifically, Marcopolo was more affected by drought, decreasing grain yield and starch but increasing quality parameters (protein, gluten and N content and dough extensibility (alveograph L) and dough baking strength (alveograph W). On the other hand, only heatwave affected protein and N and gluten content in the Camargo cultivar. Nitrogen content in grain was selected as a potential small-scale rapid parameter to predict quality traits due to its high correlation with protein and gluten content and alveograph W with correlations higher than r = 0.85. Finally, the C isotopic discrimination (Δ¹³C) and N isotope composition (δ¹⁵N) determinations showed that while Δ¹³C was the best trait predicting grain yield, δ¹⁵N was significantly correlated with some important end-use quality parameters. In summary, the current study underscores the fact that alongside a direct impact on crop yield, heat and water stress are target factors conditioning wheat grain quality traits.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127385"},"PeriodicalIF":4.5,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419236","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":"Dissecting durum wheat time to anthesis into physiological traits using a QTL-based model","authors":"Pierre Martre ,&nbsp;Rosella Motzo ,&nbsp;Anna Maria Mastrangelo ,&nbsp;Daniela Marone ,&nbsp;Pasquale De Vita ,&nbsp;Francesco Giunta","doi":"10.1016/j.eja.2024.127379","DOIUrl":"10.1016/j.eja.2024.127379","url":null,"abstract":"<div><div>Fine tuning crop development is a major breeding avenue to increase crop yield and for adaptation to climate change. We used an ecophysiological model that integrates our current understanding of the physiology of wheat phenology to predict the development and anthesis date of 91 recombinant inbreed lines (RILs) of durum wheat with genotypic parameters controlling vernalization requirement, photoperiod sensitivity, and earliness <em>per se</em> estimated using leaf stage, final leaf number, anthesis date data from a pot experiment with vernalized and nonvernalized treatments combined with short- and long-day length. Predictions of final leaf number and anthesis date of the QTL-based model was evaluated for the whole population of RILs in a set of independent field trials and for the two parents, which were not used to estimate the parameter values. Our novel approach reduces the number of environments and the time required to obtain the required data sets to develop a QTL-based prediction of model parameters. Moreover, the use of a physiologically based model of phenology gives new insight into genotype-phenology relations for wheat. We discuss the approach we used to estimate the parameters of the model and their association with QTL and major phenology genes that collocate at QTL.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127379"},"PeriodicalIF":4.5,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419237","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":"Enhancement of soil humic acid hydrophobicity by 5 consecutive years of full-amount straw shallow-mixed field return","authors":"Bo-Yan Zhang,&nbsp;Sen Dou,&nbsp;Song Guan","doi":"10.1016/j.eja.2024.127378","DOIUrl":"10.1016/j.eja.2024.127378","url":null,"abstract":"<div><div>Crop yield is directly influenced by the storage and stabilisation of soil organic carbon (SOC), which is determined by the hydrophobicity of soil humic acid (HA). Changes in soil HA hydrophobicity, humic substances, SOC and crop yield were compared after the application of different amounts of straw returns in the field, and the contribution of straw application in enhancing HA hydrophobicity was examined. The treatments included no straw application and soil stirring, no straw application with soil stirring, application of half-amount straw shallow-mixed field return, application of full-amount straw shallow-mixed field return and application of double-amount straw shallow-mixed field return. Using elemental analysis, infrared spectroscopy and fluorescence spectroscopy, the structural hydrophobicity of soil HA was exhaustively characterised. The results showed that the hydrogen to carbon ratio of HA increased by 11.46 %, the ratio of hydrophobic to hydrophilic intensity increased by 21.02 %, and the ratio of peak B to peak A fluorescence intensity decreased by 32.21 % after 5 years of full amount straw shallow-mixing field return compared to no straw application and soil stirring. The observed results indicate that the augmentation in hydrophobicity stimulates the formation of HA, enhances soil humification, elevates SOC content by 9.78 % and potentially contributes to the ultimate crop yield increase by 22.98 %. Compared with stirring the soil, the contribution rate of applying full amount of straw to increase HA hydrophobicity was 49.57–62.05 %, and the contribution rate to increase SOC and yield were 54.59 % and 76.37 %, respectively. While stirring the soil contributed to increasing hydrophobicity, straw application persisted as the primary factor in enhancing hydrophobicity. The findings of this study have significant implications for understanding the mechanism by which straw improves HA hydrophobicity, thereby facilitating carbon sequestration and increasing crop yield.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127378"},"PeriodicalIF":4.5,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419272","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":"Arbuscular mycorrhizal fungus activates wheat physiology for higher reproductive allocation under drought stress in primitive and modern wheat","authors":"Hai-Xia Duan ,&nbsp;Chong-Liang Luo ,&nbsp;Ying Zhu ,&nbsp;Ling Zhao ,&nbsp;Jing Wang ,&nbsp;Wei Wang ,&nbsp;You-Cai Xiong","doi":"10.1016/j.eja.2024.127376","DOIUrl":"10.1016/j.eja.2024.127376","url":null,"abstract":"<div><div>Arbuscular mycorrhizal fungus (AMF) can mediate physiological adaptation of higher plants to drought stress, including wheat. Yet, it is unclear how AMF affects reproductive output via mediating crop physiological vitality at the evolutionary scale. To clarify this issue, a growth environment-controlled experiment was conducted using four primitive wheat genotypes and four modern ones with or without AMF (<em>Funneliformis mosseae</em>) inoculation. Two water regimes (80 % and 40 % field water capacity, FWC80 (well-watered) and FWC40 (drought stress)) were included. The data indicated that AMF inoculation significantly improved leaf area, photosynthetic rate, stomatal conductance and water use efficiency under drought stress, compared to the non-AMF group (CK). Regardless of soil moisture, the relationship between reproductive biomass vs. vegetative biomass (R-V), and between leaf biomass vs. shoot biomass, all fell into a typical allometric pattern (α&gt;1, <em>P</em>&lt;0.001) in primitive wheat. In contrast, in modern wheat, the R-V relationship tended to an isometric pattern (α≈1, <em>P</em>&lt;0.001), showing lower α values in all treatments relative to primitive ones. Furthermore, AMF inoculation significantly promoted the maintenance rate of yield and biomass under drought stress, suggesting greater drought tolerance as induced by AMF in modern wheat compared to primitive ones. These findings illuminated a key evolutionary strategy to enhance reproductive allocation via activating physiological activities under drought stress from primitive to modern wheat.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127376"},"PeriodicalIF":4.5,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419271","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":"Greenhouse gas emissions and mitigation potential of crop production in Northeast China","authors":"Jin-Sai Chen ,&nbsp;Hao-Ran Li ,&nbsp;Yu-Gang Tian ,&nbsp;Ping-Ping Deng ,&nbsp;Olatunde Pelumi Oladele ,&nbsp;Wei Bai ,&nbsp;Yash Pal Dang ,&nbsp;Xin Zhao ,&nbsp;Hai-Lin Zhang","doi":"10.1016/j.eja.2024.127371","DOIUrl":"10.1016/j.eja.2024.127371","url":null,"abstract":"<div><div>Agricultural management practices that reduce greenhouse gas (GHG) emissions have been identified as effective mitigation strategies. However, research on carbon emissions from major crops in Northeast China focuses on national and provincial data, overlooking city-scale variability and uncertainties, which prevents fine-scale assessment of crop emissions reduction potential. To address this, a life cycle assessment (LCA) combined with the Monte Carlo method was conducted to estimate the carbon footprint of rice, maize, and soybean production for different cities in Northeast China from 1991 to 2020. The results showed that the top one-third of cities with the highest total carbon emissions (TCE) account for approximately 40 % of the region's TCE. Nitrogen losses and production processes related to nitrogen fertilizer application were identified as the primary contributors to TCE from crop production, accounting for 29.6–62.5 % of the total, with a relative importance of 58.5–78.2 %. Scenario analysis indicated that optimizing nitrogen fertilizer management and reducing active nitrogen losses are the most effective strategies for reducing TCE from major crop production, offering a reduction potential of 34.5–60.6 %. Recommended strategies include phased application of nitrogen fertilizer, the addition of nitrification inhibitors, or using slow-release nitrogen fertilizers, combined with appropriate increases in crop planting density, straw return decomposition technologies and water-saving irrigation methods to reduce GHG emissions. These strategies aim to achieve low-carbon sustainable grain production and provide a foundation for exploring the emissions reduction potential of agricultural inputs and optimizing regional crop layouts, offering new insights for developing more effective GHG reduction strategies.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127371"},"PeriodicalIF":4.5,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced seed yield of full-season soybean when rotated with cereals and cover crops as compared to monoculture in a long-term experiment","authors":"F. Salvagiotti ,&nbsp;M.M. Biassoni ,&nbsp;L. Magnano ,&nbsp;S. Bacigaluppo","doi":"10.1016/j.eja.2024.127382","DOIUrl":"10.1016/j.eja.2024.127382","url":null,"abstract":"<div><div>Soybeans are of great importance to the global economy, but the cultivation as monoculture has shown several negative environmental implications in the long-term. Long-term studies demonstrate the cumulative effects of rotations on soil variables, but few studies have considered changes during consecutive years in a time series of soybean as a monoculture. The inclusion of cereals and cover crops in rotation with soybean increases the intensification sequence index (ISI, time with crops actively growing during the year) and increases in soybean yield are expected. In line with this, some studies suggest that only including a winter cover crop will increase ISI and raise production. However, these comparisons have not been made in the long term. The objectives of this work were to: i) compare the evolution of full-season soybean yield and production when sowed as monoculture and in cropping sequences that include cereal crops and cover crops, and ii) quantify a yield gap in full-season soybean due to monoculture by evaluating the long-term residual effect of crop sequences with different land occupation. Soybean yield time series in a 14-years period in rotation or as monoculture were studied in a long-term field experiment under no-tillage established in 2006 in the Northern Pampas region of Argentina. Rotations consisted in sequences that included soybean (S), maize (M) and wheat (W), and also incorporated wheat as a winter cover crop (CC): S-S, CC/S-CC/S, S-W/S-M, CC/S-W/S-M, M-W/S, and CC/M-W/S, with ISI values of 0.39, 0.69, 0.55, 0.64, 0.65 and 0.80, respectively. In 2021/22 season, full-season soybean was planted in all plots as a \"test\" crop, to evaluate the long-term residual effect of sequences with different intensification indexes. Seed yield averaged 3249 kg ha⁻¹ among years. During the 14 years under study, seed yield in S-W/S-M surpassed S-S by 28 % in 6 out of 14 years. The differences between S-S with respect to this sequence were observed consistently from the ninth crop season (i.e. since 2017/18). The inclusion of a cover crop within a soybean monoculture (i.e. CC/S-CC/S) showed similar seed yields as in S-S in 11 out of 14 years. The analysis of the test crop showed yield-gaps when soybeans were grown as monoculture (seed yield in rotations minus seed yield in S-S) of 9, 20, 27, 21 and 31 % for CC/S-CC/S, S-W/S-M, CC/S-W/S-M, M-W/S and CC/M-W/S, respectively. In summary, soybean in rotation with cereals showed an average increase of ca. 346 kg ha⁻¹ and including a cover crop within a soybean monoculture did not increase seed yield at the levels observed when rotated with cereals. Finally, when estimating seed yield-gaps in soybean, it is important to set in which rotation soybean is placed, since a higher maximum yield is expected to happen when soybean follows a more intensified rotation.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127382"},"PeriodicalIF":4.5,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419269","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":"Achieving wheat seedling freezing injury assessment during the seedling stage using Unmanned Ground Vehicle (UGV) and hyperspectral imaging technology","authors":"Zhaosheng Yao ,&nbsp;Ruimin Shao ,&nbsp;Muhammad Zain ,&nbsp;Yuanyuan Zhao ,&nbsp;Ting Tian ,&nbsp;Jianliang Wang ,&nbsp;Dingshun Zhang ,&nbsp;Tao Liu ,&nbsp;Xiaoxin Song ,&nbsp;Chengming Sun","doi":"10.1016/j.eja.2024.127375","DOIUrl":"10.1016/j.eja.2024.127375","url":null,"abstract":"<div><div>Freezing injury may cause irreversible damage to wheat (<em><strong>Triticum aestivum L</strong></em>) tissues and can significantly reduce yield and quality. Therefore, quick and non-destructively estimating the degree of frost damage for formulating anti-freezing protection strategies and preventing frost damage is very crucial. In this study, we obtained hyperspectral images of wheat leaves for accurate identification of frost damage. A remote-controlled Unmanned Ground Vehicle (UGV) equipped with an imaging spectral camera was used to capture the hyperspectral images of frost-damaged wheat leaves. We compared the efficiency of two methods (the one without removal of weeds, and the other is to remove the corresponding area of weeds from the hyperspectral image by Deeplab V3+) for estimation of wheat freezing damage degree by using four different algorithms; Support Vector Machine Classification (SVM), Mahalanobis Distance Classification (MaD), Minimum Distance Classification (MiD), and Maximum Likelihood Classification (ML). We found that, Deeplab V3+ can efficiently identify the weeds from hyperspectral images, as the overall accuracy (OA) values of different algorithms were high in images with weeds removal as compared to the values in weeds containing images. Further, applying ML model after weeds removal have high OA (93.26 %) as compared to the other models. Thus, using Deeplab V3+ and ML can be a potential approach to identify the freezing injury in wheat for sustainable agricultural productivity.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"161 ","pages":"Article 127375"},"PeriodicalIF":4.5,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419268","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}