Pub Date : 2025-12-06DOI: 10.1016/j.eja.2025.127947
Armand Román , Pablo González-Altozano , Pau Martí , Luis Bonet , María Amparo Martínez-Gimeno , Eduardo Badal
This study assessed the effects of spring-regulated deficit irrigation (RDI) strategies on the physiological and agronomic performance of a ‘Rojo Brillante’ persimmon (Diospyros kaki) orchard grafted onto Diospyros lotus and D. virginiana rootstocks. The trial was conducted from 2016 to 2019 in a commercial orchard located in Llíria (Valencia, Spain), under Mediterranean climate conditions. RDI was applied during late spring at increasing water restriction levels, while control treatments received non-limited irrigation. Results showed that RDI did not reduce yield per tree, even under severe water deficits, and consistently improved irrigation water productivity by up to 21 % in D. lotus and 31 % in D. virginiana compared to fully irrigated controls. The reduction in fruit drop observed in RDI treatments led to a 30 % increase in harvested fruits in D. lotus and 42 % in D. virginiana. On average, fruit drop-to-flowering ratios were lower under RDI (36.5 % in D. lotus, 68.6 % in D. virginiana) than in fully irrigated controls (49.9 % and 81.6 %, respectively). D. lotus trees showed more stable yields and a favourable vegetative-reproductive balance, while D. virginiana exhibited a different water stress response pattern in the seasonal dynamics of stem water potential, which is used to characterise differences in plant water status rather than intrinsic drought tolerance. Still, D. virginiana trees produced lower and more variable yields under both irrigation regimes, likely due to higher fruit drop and a potential biennial bearing pattern. Overall, the findings support spring RDI as a viable strategy to enhance irrigation water productivity in persimmon orchards.
{"title":"Agronomic and physiological responses of mature ‘Rojo Brillante’ persimmon grafted onto Diospyros lotus and Diospyros virginiana under spring-regulated deficit irrigation in Mediterranean conditions","authors":"Armand Román , Pablo González-Altozano , Pau Martí , Luis Bonet , María Amparo Martínez-Gimeno , Eduardo Badal","doi":"10.1016/j.eja.2025.127947","DOIUrl":"10.1016/j.eja.2025.127947","url":null,"abstract":"<div><div>This study assessed the effects of spring-regulated deficit irrigation (RDI) strategies on the physiological and agronomic performance of a ‘Rojo Brillante’ persimmon (<em>Diospyros kaki</em>) orchard grafted onto <em>Diospyros lotus</em> and <em>D. virginiana</em> rootstocks. The trial was conducted from 2016 to 2019 in a commercial orchard located in Llíria (Valencia, Spain), under Mediterranean climate conditions. RDI was applied during late spring at increasing water restriction levels, while control treatments received non-limited irrigation. Results showed that RDI did not reduce yield per tree, even under severe water deficits, and consistently improved irrigation water productivity by up to 21 % in <em>D. lotus</em> and 31 % in <em>D. virginiana</em> compared to fully irrigated controls. The reduction in fruit drop observed in RDI treatments led to a 30 % increase in harvested fruits in <em>D. lotus</em> and 42 % in <em>D. virginiana</em>. On average, fruit drop-to-flowering ratios were lower under RDI (36.5 % in <em>D. lotus</em>, 68.6 % in <em>D. virginiana</em>) than in fully irrigated controls (49.9 % and 81.6 %, respectively). <em>D. lotus</em> trees showed more stable yields and a favourable vegetative-reproductive balance, while <em>D. virginiana</em> exhibited a different water stress response pattern in the seasonal dynamics of stem water potential, which is used to characterise differences in plant water status rather than intrinsic drought tolerance. Still, <em>D. virginiana</em> trees produced lower and more variable yields under both irrigation regimes, likely due to higher fruit drop and a potential biennial bearing pattern. Overall, the findings support spring RDI as a viable strategy to enhance irrigation water productivity in persimmon orchards.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127947"},"PeriodicalIF":5.5,"publicationDate":"2025-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145689963","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 : 2025-12-02DOI: 10.1016/j.eja.2025.127948
Onusha Sharmita , Abu Bakar Siddique , Ke Liu , Sergey Shabala , Matthew Tom Harrison , Meixue Zhou , Chenchen Zhao
Soil waterlogging can result from excessive rainfall, poor soil drainage, high groundwater tables and inadequate drainage, leading to hypoxic or anoxic environments in crop rhizophores. Oxygen-deprived conditions negatively impact root growth and, in severe cases, lead to root senescence due to detrimental soil physiochemical properties, such as lack of nutrient availability and accumulation of toxic elements (elemental toxicity). As the primary plant tissue affected by waterlogging, plant roots have evolved several adaptive strategies to restore oxygen supply, optimize nutrient acquisition, and mitigate elemental toxicity. Previous research has been primarily focussed on ‘oxygen-to-roots’ traits, such as development of adventitious and lateral roots, formation of aerenchyma (air-filled cavities) and the radial oxygen loss barriers. However, underlying phytohormones regulatory networks in response to waterlogging have often been overlooked. This review synthesizes contemporary research on hormonal regulation of root adaptations under waterlogging, aiming to fill key knowledge gaps by linking hormone signalling to root-based waterlogging and soil toxicity tolerance. We highlight roles of ethylene, ABA, and auxin in regulating aerenchyma formation and development of barrier to reduce radial oxygen loss and show that auxin and cytokinin are vital for lateral and adventitious root development and regulating cellular anatomical adaptations. We propose that ethylene, gibberellins (GAs), and brassinosteroids (BRs) are all crucial hormones that play roles in nodule development for nitrogen supply under waterlogging. Importantly, for the first time, we reviewed crucial roles of phytohormones on regulating elemental toxicity underlying waterlogging tolerance. This review also highlights the mitigating roles of emerging hormones, such as melatonin and strigolactones, in enhancing root-associated adaptation. Our review comprehensively elucidates phytohormones derived waterlogging tolerance mechanisms including linking phytohormones signalling to root-associated traits and provides valuable insights for oriented breeding strategies, aiming to improve crop resilience and ensure sustainable crop production.
{"title":"Boosting crop resilience to waterlogging through hormone-regulated root traits","authors":"Onusha Sharmita , Abu Bakar Siddique , Ke Liu , Sergey Shabala , Matthew Tom Harrison , Meixue Zhou , Chenchen Zhao","doi":"10.1016/j.eja.2025.127948","DOIUrl":"10.1016/j.eja.2025.127948","url":null,"abstract":"<div><div>Soil waterlogging can result from excessive rainfall, poor soil drainage, high groundwater tables and inadequate drainage, leading to hypoxic or anoxic environments in crop rhizophores. Oxygen-deprived conditions negatively impact root growth and, in severe cases, lead to root senescence due to detrimental soil physiochemical properties, such as lack of nutrient availability and accumulation of toxic elements (elemental toxicity). As the primary plant tissue affected by waterlogging, plant roots have evolved several adaptive strategies to restore oxygen supply, optimize nutrient acquisition, and mitigate elemental toxicity. Previous research has been primarily focussed on ‘oxygen-to-roots’ traits, such as development of adventitious and lateral roots, formation of aerenchyma (air-filled cavities) and the radial oxygen loss barriers. However, underlying phytohormones regulatory networks in response to waterlogging have often been overlooked. This review synthesizes contemporary research on hormonal regulation of root adaptations under waterlogging, aiming to fill key knowledge gaps by linking hormone signalling to root-based waterlogging and soil toxicity tolerance. We highlight roles of ethylene, ABA, and auxin in regulating aerenchyma formation and development of barrier to reduce radial oxygen loss and show that auxin and cytokinin are vital for lateral and adventitious root development and regulating cellular anatomical adaptations. We propose that ethylene, gibberellins (GAs), and brassinosteroids (BRs) are all crucial hormones that play roles in nodule development for nitrogen supply under waterlogging. Importantly, for the first time, we reviewed crucial roles of phytohormones on regulating elemental toxicity underlying waterlogging tolerance. This review also highlights the mitigating roles of emerging hormones, such as melatonin and strigolactones, in enhancing root-associated adaptation. Our review comprehensively elucidates phytohormones derived waterlogging tolerance mechanisms including linking phytohormones signalling to root-associated traits and provides valuable insights for oriented breeding strategies, aiming to improve crop resilience and ensure sustainable crop production.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127948"},"PeriodicalIF":5.5,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145657299","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 : 2025-12-01DOI: 10.1016/j.eja.2025.127942
Wei Wang , Bao-Zhong Wang , Wei Zhang , Meng-Ying Li , Jian-Ming Li , Sheng-Jun Ji , Muhammad Abrar , Muhammad Maqsood Ur Rehman , Wasim Khan , Hong-Yan Tao , Mohamed S. Sheteiwy , Wen-Ying Wang , You-Cai Xiong
Cereal-legume intercropping is widely recognized for enhancing crop productivity in semiarid rainfed systems. However, the mechanisms underlying its yield advantages and stability under variable rainfall conditions remain unclear, limiting its adoption as a climate-resilient strategy. This study evaluated the stability of crop yield and economic benefits across inter-annual rainfall fluctuations (418 mm in 2019, 362 mm in 2020, and 253 mm in 2021) in a three-year field experiment. We assessed yield–economic performance of maize-soybean and wheat-soybean intercropping systems and their impacts on key soil functional parameters to elucidate the mechanisms underlying climate resilience. Both maize-soybean and wheat-soybean intercropping were observed to harvest 17–26 % higher yields (per plant) and 1.04–1.26 land equivalent ratios, therefore enhancing land-use efficiency. Economically, maize-based systems were the most profitable, while wheat-soybean intercropping turned to improve net returns by 1654 USD ha⁻¹ . Climate-resilience analysis showed that intercropping reduced yield volatility by 10–61 % when precipitation declined (418–253 mm), highlighting its role in stabilizing agroecosystem productivity and economic benefits. Also, intercropping systems were found to significantly improve total nitrogen (13.7 %–20.6 %) and phosphorus (16.3 %–19.8 %). Mechanistically, the above indicators were resulted from improving soil microbial biomass (20.8 %–23.0 %), enhancing extracellular enzyme activities (9.3 %–15.8 % for C- and P-hydrolases) and promoting soil moisture retention (11.0 %–12.9 %). The data confirmed that intercropping can greatly enhance soil multifunctionality and thus contribute to yield and economic stability. Therefore, cereal-legume intercropping can act as a scalable strategy to enhance productivity, soil quality, and climate resilience in semiarid rainfed environment. The findings offer policymakers and smallholders a sustainable solution to balance land-use efficiency and climate adaptation.
{"title":"Cereal-legume intercropping stabilizes yield and economic advantages under variable rainfall in semiarid rainfed environment","authors":"Wei Wang , Bao-Zhong Wang , Wei Zhang , Meng-Ying Li , Jian-Ming Li , Sheng-Jun Ji , Muhammad Abrar , Muhammad Maqsood Ur Rehman , Wasim Khan , Hong-Yan Tao , Mohamed S. Sheteiwy , Wen-Ying Wang , You-Cai Xiong","doi":"10.1016/j.eja.2025.127942","DOIUrl":"10.1016/j.eja.2025.127942","url":null,"abstract":"<div><div>Cereal-legume intercropping is widely recognized for enhancing crop productivity in semiarid rainfed systems. However, the mechanisms underlying its yield advantages and stability under variable rainfall conditions remain unclear, limiting its adoption as a climate-resilient strategy. This study evaluated the stability of crop yield and economic benefits across inter-annual rainfall fluctuations (418 mm in 2019, 362 mm in 2020, and 253 mm in 2021) in a three-year field experiment. We assessed yield–economic performance of maize-soybean and wheat-soybean intercropping systems and their impacts on key soil functional parameters to elucidate the mechanisms underlying climate resilience. Both maize-soybean and wheat-soybean intercropping were observed to harvest 17–26 % higher yields (per plant) and 1.04–1.26 land equivalent ratios, therefore enhancing land-use efficiency. Economically, maize-based systems were the most profitable, while wheat-soybean intercropping turned to improve net returns by 1654 USD ha⁻¹ . Climate-resilience analysis showed that intercropping reduced yield volatility by 10–61 % when precipitation declined (418–253 mm), highlighting its role in stabilizing agroecosystem productivity and economic benefits. Also, intercropping systems were found to significantly improve total nitrogen (13.7 %–20.6 %) and phosphorus (16.3 %–19.8 %). Mechanistically, the above indicators were resulted from improving soil microbial biomass (20.8 %–23.0 %), enhancing extracellular enzyme activities (9.3 %–15.8 % for C- and P-hydrolases) and promoting soil moisture retention (11.0 %–12.9 %). The data confirmed that intercropping can greatly enhance soil multifunctionality and thus contribute to yield and economic stability. Therefore, cereal-legume intercropping can act as a scalable strategy to enhance productivity, soil quality, and climate resilience in semiarid rainfed environment. The findings offer policymakers and smallholders a sustainable solution to balance land-use efficiency and climate adaptation.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127942"},"PeriodicalIF":5.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145650848","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}
Unmanned aerial vehicles (UAVs) offer potential for precise, sustainable herbicide application in wheat, but their efficacy under variable field conditions requires robust evaluation. This study aims to rectify these research gaps and introduces a novel multi-parameter field evaluation of UAV-based herbicide applications for sustainable wheat weed management, explicitly evaluating the critical impact of real-time meteorological variability and application parameters. Field experiments over two growing seasons (2021/2022 and 2022/2023) compared UAV applications (30 L ha−1, fine-to-medium droplets) at 1.5 m and 2.5 m altitudes with conventional spraying (200 L ha−1, medium-coarse droplets), using constant doses of two commercial herbicide formulations (1. tritosulfuron + florasulam; 2. iodosulfuron-methyl-sodium + amidosulfuron + mefenpyr-diethyl). Efficacy was measured via species-specific weed density and fresh mass reduction. UAV treatments achieved significantly higher or equivalent suppression of Capsella bursa-pastoris, Lactuca serriola, Sinapis arvensis, and Veronica persica compared to conventional spraying. Despite more challenging conditions (high temperature, lower humidity, stronger wind) in the second season, overall efficacy increased, attributed to using a more effective herbicide formulation, underscoring the critical role of herbicide selection for UAV systems. Lamium purpureum exhibited significant weather sensitivity, with lower flight altitude enhancing fresh mass reduction. Correlation analysis suggested temperature positively (r = 0.586, p = 0.045) and wind velocity negatively (r = ̵ 0.588, p = 0.045) influenced treatment efficacy. UAV applications achieved up to 90 % efficacy in the second year by 31 DAHA (i.e., herbicide application) while using 85 % less water. This research provides the first multi-parameter field validation of UAV herbicide application under variable environmental conditions, demonstrating its viability and significant water-saving potential. The findings offer crucial, actionable inferences for optimizing UAV parameters (altitude, droplet size) with herbicide selection and real-time weather data, benefiting global precision agriculture efforts towards resource-efficient and environmentally responsible weed management.
无人机（uav）提供了在小麦上精确、可持续施用除草剂的潜力，但其在可变田间条件下的有效性需要可靠的评估。本研究旨在弥补这些研究空白，并引入一种新的多参数田间评估方法，明确评估实时气象变率和应用参数对小麦杂草可持续管理的关键影响。在两个生长季节（2021/2022和2022/2023）的现场实验中，比较了无人机在1.5 m和2.5 m海拔的应用（30 L ha−1，细至中等滴）与传统喷洒（200 L ha−1，中至粗滴），使用恒定剂量的两种商业除草剂配方(1。三磺隆+ florasulam；2. 碘磺隆-甲基钠+氨基磺隆+甲芬吡酯-二乙基)。通过种特异性杂草密度和新鲜质量减少来衡量效果。与常规喷洒相比，无人机处理对法氏囊荠菜、serriola、Sinapis arvensis和Veronica persica的抑制效果明显更高或相当。尽管第二季的条件更具挑战性（高温、低湿度、强风），但由于使用了更有效的除草剂配方，总体效果有所提高，这强调了除草剂选择对无人机系统的关键作用。紫叶Lamium purpureum表现出显著的天气敏感性，较低的飞行高度增强了鲜质量的减少。相关分析表明，温度对治疗效果有正影响（r = 0.586, p = 0.045），风速对治疗效果有负影响（r = 0.588, p = 0.045）。无人机应用在第二年通过31 DAHA（即除草剂应用）达到高达90% %的效率，同时使用85% %的水。本研究首次对不同环境条件下的无人机除草剂应用进行了多参数现场验证，证明了其可行性和显著的节水潜力。该研究结果为优化无人机参数（高度、液滴大小）、除草剂选择和实时天气数据提供了关键的、可操作的推断，有利于全球精准农业努力实现资源高效和对环境负责的杂草管理。
{"title":"Optimizing UAV-based herbicide applications for sustainable wheat weed management by a novel multi-parameter field evaluation under variable environmental conditions","authors":"Biljana Boskovic , Dragana Bozic , Milan Drazic , Kosta Gligorevic , Velibor Spalevic , Shuraik Kader , Milos Pajic","doi":"10.1016/j.eja.2025.127945","DOIUrl":"10.1016/j.eja.2025.127945","url":null,"abstract":"<div><div>Unmanned aerial vehicles (UAVs) offer potential for precise, sustainable herbicide application in wheat, but their efficacy under variable field conditions requires robust evaluation. This study aims to rectify these research gaps and introduces a novel multi-parameter field evaluation of UAV-based herbicide applications for sustainable wheat weed management, explicitly evaluating the critical impact of real-time meteorological variability and application parameters. Field experiments over two growing seasons (2021/2022 and 2022/2023) compared UAV applications (30 L ha<sup>−1</sup>, fine-to-medium droplets) at 1.5 m and 2.5 m altitudes with conventional spraying (200 L ha<sup>−1</sup>, medium-coarse droplets), using constant doses of two commercial herbicide formulations (1. <em>tritosulfuron</em> + <em>florasulam</em>; 2. <em>iodosulfuron-methyl-sodium</em> + <em>amidosulfuron</em> + <em>mefenpyr-diethyl</em>). Efficacy was measured via species-specific weed density and fresh mass reduction. UAV treatments achieved significantly higher or equivalent suppression of <em>Capsella bursa-pastoris</em>, <em>Lactuca serriola</em>, <em>Sinapis arvensis</em>, and <em>Veronica persica</em> compared to conventional spraying. Despite more challenging conditions (high temperature, lower humidity, stronger wind) in the second season, overall efficacy increased, attributed to using a more effective herbicide formulation, underscoring the critical role of herbicide selection for UAV systems. <em>Lamium purpureum</em> exhibited significant weather sensitivity, with lower flight altitude enhancing fresh mass reduction. Correlation analysis suggested temperature positively (r = 0.586, p = 0.045) and wind velocity negatively (r = ̵ 0.588, p = 0.045) influenced treatment efficacy. UAV applications achieved up to 90 % efficacy in the second year by 31 DAHA (i.e., herbicide application) while using 85 % less water. This research provides the first multi-parameter field validation of UAV herbicide application under variable environmental conditions, demonstrating its viability and significant water-saving potential. The findings offer crucial, actionable inferences for optimizing UAV parameters (altitude, droplet size) with herbicide selection and real-time weather data, benefiting global precision agriculture efforts towards resource-efficient and environmentally responsible weed management.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127945"},"PeriodicalIF":5.5,"publicationDate":"2025-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145619438","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 : 2025-11-29DOI: 10.1016/j.eja.2025.127931
Zixi Shi , Shuo Shi , Jia Sun , Wei Gong , Lu Xu , Binhui Wang , Chenxi Liu
Accurate retrieval of plant functional traits is critical for monitoring crop growth and improving agronomic management. Canopy structural parameters, such as leaf area index (LAI) and leaf inclination distribution function (LIDFa), strongly influence inversion accuracy. Quantifying canopy structural uncertainties and developing strategies to improve retrieval accuracy are crucial. In this study, we developed an inversion framework based on the Soil Canopy Observation of Photosynthesis and Energy fluxes (SCOPE) model, integrating reflectance and solar-induced fluorescence (SIF) data. Using both simulation modelling and field measurements in NEON STER crop field, we introduced multi-level prior noise and evaluated how uncertainties in LAI and LIDFa propagate into the retrieval of chlorophyll content (Cab), maximum carboxylation rate (Vcmax), and fluorescence quantum efficiency (fqe). To assess the influence of canopy structure and improve retrieval accuracy, three inversion strategies—Prior-Matched (PM), Regularized (RI), and No-Prior (NP)—were designed and tested for their accuracy and robustness. The results showed that second-order Sobol’ indices (S2) captured interactions among canopy structural parameters and functional traits, particularly between Cab-LAI, Cab-LIDFa and fqe-LAI, with sensitive spectral ranges at 680–740 nm (fluorescence) and 600–720 nm (reflectance). Error amplification analysis under six noise levels showed that structural uncertainties significant amplified reflectance and fluorescence variations, with red-edge shifts () and 740 nm fluorescence changes () being most sensitive. Incorporating prior canopy structure information improved inversion accuracy by up to 7.93 % in R² and reduced RMSE by 21.25 %, although this advantage diminished under high noise levels. LAI uncertainty had a greater impact than LIDFa, and additive noise introduced more uncertainty than multiplicative noise. Comparison of the inversion strategies revealed that the RI strategy achieved higher accuracy (simulated data: R2=0.954; measured data: R2=0.799) and greater robustness to noise than the PM strategy. These findings demonstrate the value of integrating canopy structure into computational inversion models to enhance the reliability of remote sensing trait retrieval, supporting precision agriculture and sustainable crop production.
{"title":"Integrating canopy structure into remote sensing inversion strategies: Optimizing plant functional trait retrieval","authors":"Zixi Shi , Shuo Shi , Jia Sun , Wei Gong , Lu Xu , Binhui Wang , Chenxi Liu","doi":"10.1016/j.eja.2025.127931","DOIUrl":"10.1016/j.eja.2025.127931","url":null,"abstract":"<div><div>Accurate retrieval of plant functional traits is critical for monitoring crop growth and improving agronomic management. Canopy structural parameters, such as leaf area index (LAI) and leaf inclination distribution function (LIDFa), strongly influence inversion accuracy. Quantifying canopy structural uncertainties and developing strategies to improve retrieval accuracy are crucial. In this study, we developed an inversion framework based on the Soil Canopy Observation of Photosynthesis and Energy fluxes (SCOPE) model, integrating reflectance and solar-induced fluorescence (SIF) data. Using both simulation modelling and field measurements in NEON STER crop field, we introduced multi-level prior noise and evaluated how uncertainties in LAI and LIDFa propagate into the retrieval of chlorophyll content (Cab), maximum carboxylation rate (Vcmax), and fluorescence quantum efficiency (fqe). To assess the influence of canopy structure and improve retrieval accuracy, three inversion strategies—Prior-Matched (PM), Regularized (RI), and No-Prior (NP)—were designed and tested for their accuracy and robustness. The results showed that second-order Sobol’ indices (S2) captured interactions among canopy structural parameters and functional traits, particularly between Cab-LAI, Cab-LIDFa and fqe-LAI, with sensitive spectral ranges at 680–740 nm (fluorescence) and 600–720 nm (reflectance). Error amplification analysis under six noise levels showed that structural uncertainties significant amplified reflectance and fluorescence variations, with red-edge shifts (<span><math><mrow><mi>Δ</mi><mi>RE</mi></mrow></math></span>) and 740 nm fluorescence changes (<span><math><mrow><mi>Δ</mi><msub><mrow><mi>F</mi></mrow><mrow><mn>740</mn></mrow></msub></mrow></math></span>) being most sensitive. Incorporating prior canopy structure information improved inversion accuracy by up to 7.93 % in R² and reduced RMSE by 21.25 %, although this advantage diminished under high noise levels. LAI uncertainty had a greater impact than LIDFa, and additive noise introduced more uncertainty than multiplicative noise. Comparison of the inversion strategies revealed that the RI strategy achieved higher accuracy (simulated data: R<sup>2</sup>=0.954; measured data: R<sup>2</sup>=0.799) and greater robustness to noise than the PM strategy. These findings demonstrate the value of integrating canopy structure into computational inversion models to enhance the reliability of remote sensing trait retrieval, supporting precision agriculture and sustainable crop production.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127931"},"PeriodicalIF":5.5,"publicationDate":"2025-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145614019","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 : 2025-11-29DOI: 10.1016/j.eja.2025.127946
Mona Schatke , Johanna Bensch , Lena Ulber , Bärbel Gerowitt , Christoph von Redwitz
Four decision concepts were tested for ex-ante chemical weed control decisions to be integrated into site-specific weed management (SSWM). Two concepts assess the economic profitability of a weed control treatment: one considers the abundance of weed taxonomic groups, and the other takes into account individual weed species. The third and fourth concepts utilize weed functional traits to quantify a species’ ability to provide ecosystem services (service potential) and its competitive ability (disservice potential), thereby informing management decisions. Based on grid-based manual weed assessments in five winter cereal fields in Germany, species-specific weed distribution maps were created using an interpolation approach. For each square meter of the fields, a weed control recommendation was generated using each of the four decision concepts, followed by the creation of weed control maps. Control recommendations by the two economic decision concepts showed the highest similarity across all fields, recommending weed control for 23 %–100 % (weed groups) and 6 %–100 % (species-specific) of the total field area. The concepts based on functional weed traits recommended weed control for 2 %–50 % of the area. Both economic decision concepts recommended a weed control treatment in areas recommended to be left untreated when functional traits are considered. The analysis revealed strengths and weaknesses in all concepts and recommends combining functional weed traits and economic profitability.
{"title":"Trait-based weed control decisions compared to economic thresholds for site-specific weed management","authors":"Mona Schatke , Johanna Bensch , Lena Ulber , Bärbel Gerowitt , Christoph von Redwitz","doi":"10.1016/j.eja.2025.127946","DOIUrl":"10.1016/j.eja.2025.127946","url":null,"abstract":"<div><div>Four decision concepts were tested for ex-ante chemical weed control decisions to be integrated into site-specific weed management (SSWM). Two concepts assess the economic profitability of a weed control treatment: one considers the abundance of weed taxonomic groups, and the other takes into account individual weed species. The third and fourth concepts utilize weed functional traits to quantify a species’ ability to provide ecosystem services (service potential) and its competitive ability (disservice potential), thereby informing management decisions. Based on grid-based manual weed assessments in five winter cereal fields in Germany, species-specific weed distribution maps were created using an interpolation approach. For each square meter of the fields, a weed control recommendation was generated using each of the four decision concepts, followed by the creation of weed control maps. Control recommendations by the two economic decision concepts showed the highest similarity across all fields, recommending weed control for 23 %–100 % (weed groups) and 6 %–100 % (species-specific) of the total field area. The concepts based on functional weed traits recommended weed control for 2 %–50 % of the area. Both economic decision concepts recommended a weed control treatment in areas recommended to be left untreated when functional traits are considered. The analysis revealed strengths and weaknesses in all concepts and recommends combining functional weed traits and economic profitability.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127946"},"PeriodicalIF":5.5,"publicationDate":"2025-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145614020","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}
Pest and disease control is critical for agricultural productivity, as infestations reduce crop yields, compromise quality, and threaten food security. Although chemical control remains prevalent, pesticide overuse causes ecological disruption. Physical plant protection technologies offer sustainable alternatives by leveraging acoustic, optical, electrical, and thermal energy to disrupt pest physiology. This review systematically analyzes these technologies including steam, flame, microwave, laser, and acoustic treatments detailing their mechanisms, efficiencies, and limitations. While effective for pesticide-free production in protected crops, challenges include high equipment costs, operational complexity, and ecological trade-offs. We compare 16 physical control mXethods and identify unresolved issues in weed management, soil disinfection, and ecological regulation, concluding with recommendations for future research.
{"title":"The application and challenges of physical technology in modern agricultural plant protection","authors":"Shaobo Li, Qingyang Feng, Shaomeng Yu, Qianfeng Liu, Yang Cao, Guangzhao Tian, Yunfu Chen, Wei Qiu","doi":"10.1016/j.eja.2025.127944","DOIUrl":"10.1016/j.eja.2025.127944","url":null,"abstract":"<div><div>Pest and disease control is critical for agricultural productivity, as infestations reduce crop yields, compromise quality, and threaten food security. Although chemical control remains prevalent, pesticide overuse causes ecological disruption. Physical plant protection technologies offer sustainable alternatives by leveraging acoustic, optical, electrical, and thermal energy to disrupt pest physiology. This review systematically analyzes these technologies including steam, flame, microwave, laser, and acoustic treatments detailing their mechanisms, efficiencies, and limitations. While effective for pesticide-free production in protected crops, challenges include high equipment costs, operational complexity, and ecological trade-offs. We compare 16 physical control mXethods and identify unresolved issues in weed management, soil disinfection, and ecological regulation, concluding with recommendations for future research.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127944"},"PeriodicalIF":5.5,"publicationDate":"2025-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145611862","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 : 2025-11-27DOI: 10.1016/j.eja.2025.127925
Eric Asamoah , Gerard B.M. Heuvelink , Vincent Logah , Johan G.B. Leenaars , Prem S. Bindraban
Efficient fertilizer application is vital for enhancing maize production and profitability in Sub-Saharan Africa, where soil fertility varies widely across regions. This study aimed to develop a machine learning approach for generating site-specific fertilizer recommendations for maize production in Ghana and to evaluate its performance against conventional and semi-mechanistic approaches. A random forest machine learning model was trained on 482 maize yield experiments, consisting of 3136 yield observations collected from 1991 to 2020, to predict maize yield response to different fertilizer rates. The model incorporated multiple explanatory variables, including soil properties, climate conditions, and management practices, to generate fertilizer response curves from which fertilizer recommendations were derived for 14 sites across three agro-ecological zones in Ghana where field validation experiments were conducted. On these sites, the recommendations were compared with recommendations derived from the Quantitative Evaluation of the Fertility of Tropical Soils (QUEFTS), Conventional Fertilizer Dose Response (CFDR), and Updated Conventional Fertilizer Dose Response (UCFDR) approaches and validated through field experiments. The machine learning approach generally recommended lower rates of phosphorus and potassium than the other approaches, while nitrogen recommendations were comparable. In the Guinea Savanna zone, the recommendations from the machine learning approach outperformed those from the other approaches, producing higher mean yields for three out of the four sites in the zone. In the Forest-Savanna Transition (FST) zone, the machine learning model recommendations led to higher mean yields at four sites, while the approaches based on QUEFTS and UCFDR performed best at two other sites. In the Semi-deciduous Forest zone, the recommendations of the QUEFTS approach resulted in the highest mean yields at three sites, and CFDR at one site. Despite high input prices during the period of experimentation, the machine learning approach-based recommendations demonstrated higher net profit margins in the FST zone, suggesting cost-effectiveness in this zone. These findings indicate that site-specific fertilizer recommendations are more efficient than blanket recommendations and that machine learning approaches offer a promising and innovative approach for generating cost-effective, site-specific fertilizer recommendations in tropical climates.
{"title":"Fertilizer recommendations for maize production in Ghana: Comparison of machine learning, semi-mechanistic and conventional approaches","authors":"Eric Asamoah , Gerard B.M. Heuvelink , Vincent Logah , Johan G.B. Leenaars , Prem S. Bindraban","doi":"10.1016/j.eja.2025.127925","DOIUrl":"10.1016/j.eja.2025.127925","url":null,"abstract":"<div><div>Efficient fertilizer application is vital for enhancing maize production and profitability in Sub-Saharan Africa, where soil fertility varies widely across regions. This study aimed to develop a machine learning approach for generating site-specific fertilizer recommendations for maize production in Ghana and to evaluate its performance against conventional and semi-mechanistic approaches. A random forest machine learning model was trained on 482 maize yield experiments, consisting of 3136 yield observations collected from 1991 to 2020, to predict maize yield response to different fertilizer rates. The model incorporated multiple explanatory variables, including soil properties, climate conditions, and management practices, to generate fertilizer response curves from which fertilizer recommendations were derived for 14 sites across three agro-ecological zones in Ghana where field validation experiments were conducted. On these sites, the recommendations were compared with recommendations derived from the Quantitative Evaluation of the Fertility of Tropical Soils (QUEFTS), Conventional Fertilizer Dose Response (CFDR), and Updated Conventional Fertilizer Dose Response (UCFDR) approaches and validated through field experiments. The machine learning approach generally recommended lower rates of phosphorus and potassium than the other approaches, while nitrogen recommendations were comparable. In the Guinea Savanna zone, the recommendations from the machine learning approach outperformed those from the other approaches, producing higher mean yields for three out of the four sites in the zone. In the Forest-Savanna Transition (FST) zone, the machine learning model recommendations led to higher mean yields at four sites, while the approaches based on QUEFTS and UCFDR performed best at two other sites. In the Semi-deciduous Forest zone, the recommendations of the QUEFTS approach resulted in the highest mean yields at three sites, and CFDR at one site. Despite high input prices during the period of experimentation, the machine learning approach-based recommendations demonstrated higher net profit margins in the FST zone, suggesting cost-effectiveness in this zone. These findings indicate that site-specific fertilizer recommendations are more efficient than blanket recommendations and that machine learning approaches offer a promising and innovative approach for generating cost-effective, site-specific fertilizer recommendations in tropical climates.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127925"},"PeriodicalIF":5.5,"publicationDate":"2025-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145611856","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 : 2025-11-27DOI: 10.1016/j.eja.2025.127878
Sibylle Lustenberger , Bassirou Bonfoh , Bognan Valentin Koné , Johan Six , Günther Fink
<div><h3>Context</h3><div>In Côte d’Ivoire, cocoa is primarily produced on small-scale monoculture plantations as the main source of income for much of the rural population. Fertilization of cocoa farms remains uncommon, and long-term production without fertilization contributes to soil degradation. The ongoing decrease in productivity on small-scale cocoa farms undermines producers’ livelihoods and aggravates poverty. Poultry litter compost from the emerging poultry industry bares potential as a sustainable alternative to mineral fertilizers, but its effectiveness and profitability for cocoa production remain unknown.</div></div><div><h3>Objective</h3><div>Our study aimed to compare productivity and profitability effects of mineral-, compost-, and mixed fertilizers on a representative sample of established small-scale, age-diverse cocoa fields.</div></div><div><h3>Methods</h3><div>Our randomized controlled on-farm experiment included 120 farmers’ cocoa fields in central Côte d’Ivoire to assess productivity and profitability of three fertilizer options over one production cycle: Organic- (composted poultry litter, 71 kg N ha<sup>−1</sup>y<sup>−1</sup>), mineral- (marketed NPK+, 15 kg N ha<sup>−1</sup>y<sup>−1</sup>), and 50:50 combined organic and mineral fertilization (43 kg N ha<sup>−1</sup>y<sup>−1</sup>). Experimental plots comprised three cocoa trees per treatment and trees were fertilized twice before trees’ main harvest yields were measured. We estimated bean dry weights, annual yields and financial incomes per hectare. Treatment differences in yield and market value per hectare were tested using linear mixed-effects models, and report value-to-cost ratio (VCR = additional cocoa market value divided by total fertilization cost) of treatments’ projected annual harvests. We predicted compost fertilization VCR under both low-end and high-end price scenarios to account for regional variation in commercialization of poultry litter sale and resulting price variance.</div></div><div><h3>Results and conclusions</h3><div>Organic fertilization led to the highest increase of main harvest productivity (+ 190 kg dryweight per ha (dw), 38 %) followed by mixed fertilization (+ 145 kg ha<sup>−1</sup> dw, 31 %) and mineral fertilization (+ 118 kg ha<sup>−1</sup> dw, 22 %). Organic fertilization showed a high positive return on investment (VCR<sub>l</sub> = 3.08, CI = 1.94, 4.22) in the low cost scenario of USD 104 ha<sup>−1</sup> y<sup>−1</sup>, but not when high costs were assumed (VCR<sub>h</sub> = 0.94, CI = 0.59, 1.29, USD 342 ha<sup>−1</sup> y<sup>−1</sup>). The value-to-cost ratio was below one for both the mixed (VCR<sub>l</sub> = 0.88, CI = 0.47, 1.29, USD 290 and VCR<sub>h</sub> = 0.62, CI = 0.33, 0.91, USD 409 ha<sup>−1</sup> y<sup>−1</sup>) and the mineral fertilizer (VCR = 0.26, CI = 0.01, 0.51, USD 460 ha<sup>−1</sup> y<sup>−1</sup>).</div></div><div><h3>Significance</h3><div>This study provides first experimental evidence of the effectiveness
在Côte科特迪瓦，可可主要由小规模单一种植种植园生产，是大部分农村人口的主要收入来源。可可农场很少施肥，长期不施肥的生产会导致土壤退化。小规模可可农场的生产力持续下降，破坏了生产者的生计，加剧了贫困。新兴家禽业的家禽垃圾堆肥具有作为矿物肥料的可持续替代品的潜力，但其对可可生产的有效性和盈利能力尚不清楚。我们的研究旨在比较矿物肥料、堆肥肥料和混合肥料对已建立的小规模、年龄不同的可可田的代表性样本的生产力和盈利能力的影响。方法采用随机对照的农场试验方法，在Côte科特迪瓦中部120个农户的可可田进行试验，以评估三种肥料方案在一个生产周期内的生产力和盈利能力：有机肥料（堆肥家禽粪便，71 kg N ha−1y−1）、矿物肥料（市场销售的氮磷钾+，15 kg N ha−1y−1）和50:50有机和矿物联合施肥（43 kg N ha−1y−1）。试验田每处理三棵可可树，在测量树的主要收获产量之前，对树进行两次施肥。我们估计了每公顷豆子的干重、年产量和财政收入。使用线性混合效应模型测试了每公顷产量和市场价值的处理差异，并报告了处理的预计年收成的价值成本比（VCR =额外的可可市场价值除以总施肥成本）。我们预测了低端和高端价格情景下的堆肥施肥VCR，以解释家禽产仔销售商业化的区域差异和由此产生的价格差异。结果与结论有机肥对主要收获生产力的提高最大（+ 190 kg / hw, 38 %），其次是混肥（+ 145 kg ha−1 dw, 31 %）和矿肥（+ 118 kg ha−1 dw, 22 %）。在104美元 ha−1 y−1的低成本情况下，有机肥显示出较高的正投资回报率（VCRh = 3.08, CI = 1.94, 4.22），但在高成本情况下则不是这样（VCRh = 0.94, CI = 0.59, 1.29, 342美元 ha−1 y−1）。混合肥料（VCR = 0.88, CI = 0.47, 1.29, USD 290, VCRh = 0.62, CI = 0.33, 0.91, USD 409 ha−1 y−1）和矿物肥（VCR = 0.26, CI = 0.01, 0.51, USD 460 ha−1 y−1）的价值成本比均低于1。本研究首次为小规模可可种植中禽畜堆肥有机施肥的有效性和效益提供了实验证据。虽然施肥对提高生产力和收入至关重要，但普遍较低的VCR突出表明，可可豆的农场价格不足，这阻碍了大多数经过试验的施肥策略的有利可图的采用。关键的政策建议包括确保适当的农场收购价，为投入成本和物流提供有针对性的补贴，以及促进推广服务，鼓励农民在田间试用肥料。需要进一步的研究，包括长期的农场试验和对农民认为采用肥料的障碍的定性研究，为支持可可农业生态系统的肥力和恢复力的有效政策提供信息。
{"title":"On-farm fertilization experiment on small-scale cocoa farms in Côte d′Ivoire: Evaluation of poultry litter compost for sustainable yield and profitability","authors":"Sibylle Lustenberger , Bassirou Bonfoh , Bognan Valentin Koné , Johan Six , Günther Fink","doi":"10.1016/j.eja.2025.127878","DOIUrl":"10.1016/j.eja.2025.127878","url":null,"abstract":"<div><h3>Context</h3><div>In Côte d’Ivoire, cocoa is primarily produced on small-scale monoculture plantations as the main source of income for much of the rural population. Fertilization of cocoa farms remains uncommon, and long-term production without fertilization contributes to soil degradation. The ongoing decrease in productivity on small-scale cocoa farms undermines producers’ livelihoods and aggravates poverty. Poultry litter compost from the emerging poultry industry bares potential as a sustainable alternative to mineral fertilizers, but its effectiveness and profitability for cocoa production remain unknown.</div></div><div><h3>Objective</h3><div>Our study aimed to compare productivity and profitability effects of mineral-, compost-, and mixed fertilizers on a representative sample of established small-scale, age-diverse cocoa fields.</div></div><div><h3>Methods</h3><div>Our randomized controlled on-farm experiment included 120 farmers’ cocoa fields in central Côte d’Ivoire to assess productivity and profitability of three fertilizer options over one production cycle: Organic- (composted poultry litter, 71 kg N ha<sup>−1</sup>y<sup>−1</sup>), mineral- (marketed NPK+, 15 kg N ha<sup>−1</sup>y<sup>−1</sup>), and 50:50 combined organic and mineral fertilization (43 kg N ha<sup>−1</sup>y<sup>−1</sup>). Experimental plots comprised three cocoa trees per treatment and trees were fertilized twice before trees’ main harvest yields were measured. We estimated bean dry weights, annual yields and financial incomes per hectare. Treatment differences in yield and market value per hectare were tested using linear mixed-effects models, and report value-to-cost ratio (VCR = additional cocoa market value divided by total fertilization cost) of treatments’ projected annual harvests. We predicted compost fertilization VCR under both low-end and high-end price scenarios to account for regional variation in commercialization of poultry litter sale and resulting price variance.</div></div><div><h3>Results and conclusions</h3><div>Organic fertilization led to the highest increase of main harvest productivity (+ 190 kg dryweight per ha (dw), 38 %) followed by mixed fertilization (+ 145 kg ha<sup>−1</sup> dw, 31 %) and mineral fertilization (+ 118 kg ha<sup>−1</sup> dw, 22 %). Organic fertilization showed a high positive return on investment (VCR<sub>l</sub> = 3.08, CI = 1.94, 4.22) in the low cost scenario of USD 104 ha<sup>−1</sup> y<sup>−1</sup>, but not when high costs were assumed (VCR<sub>h</sub> = 0.94, CI = 0.59, 1.29, USD 342 ha<sup>−1</sup> y<sup>−1</sup>). The value-to-cost ratio was below one for both the mixed (VCR<sub>l</sub> = 0.88, CI = 0.47, 1.29, USD 290 and VCR<sub>h</sub> = 0.62, CI = 0.33, 0.91, USD 409 ha<sup>−1</sup> y<sup>−1</sup>) and the mineral fertilizer (VCR = 0.26, CI = 0.01, 0.51, USD 460 ha<sup>−1</sup> y<sup>−1</sup>).</div></div><div><h3>Significance</h3><div>This study provides first experimental evidence of the effectiveness","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127878"},"PeriodicalIF":5.5,"publicationDate":"2025-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145609497","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 : 2025-11-26DOI: 10.1016/j.eja.2025.127929
S. ABARNA , D. KESAVARAJA
Paddy yield prediction plays a crucial role in agriculture, enabling farmers to make informed decisions. This work proposes an innovative approach combining Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for accurate paddy yield forecasting. The hybrid model harnesses the spatial understanding capabilities of CNNs and the sequential learning ability of RNNs to capture both local and temporal dependencies in agricultural data. A key enhancement introduced in this method is the incorporation of a dynamic parameter calibration technique. Traditional regularization methods often rely on static values, which may not adapt effectively to varying complexities in the dataset. The proposed approach dynamically adjusts the regularization strength parameters during training, allowing the model to better converge to different patterns and fluctuations in paddy growth parameters. The dataset utilized for training and evaluation comprises comprehensive agricultural variables, including soil composition, climate conditions, and historical yield data. Experiments demonstrate the effectiveness of the hybrid CNN-RNN architecture with dynamic parameter calibration which improves prediction accuracy over conventional models. This research contributes to the advancement of precision agriculture by providing a more robust and adaptable framework for paddy yield prediction. The integration of spatial and temporal features, along with dynamic parameter calibration, showcases the potential for optimizing agricultural decision-making processes and mitigating the impact of unpredictable factors on paddy production.
{"title":"Dynamic parameter calibration based deep network for paddy yield prediction","authors":"S. ABARNA , D. KESAVARAJA","doi":"10.1016/j.eja.2025.127929","DOIUrl":"10.1016/j.eja.2025.127929","url":null,"abstract":"<div><div>Paddy yield prediction plays a crucial role in agriculture, enabling farmers to make informed decisions. This work proposes an innovative approach combining Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for accurate paddy yield forecasting. The hybrid model harnesses the spatial understanding capabilities of CNNs and the sequential learning ability of RNNs to capture both local and temporal dependencies in agricultural data. A key enhancement introduced in this method is the incorporation of a dynamic parameter calibration technique. Traditional regularization methods often rely on static values, which may not adapt effectively to varying complexities in the dataset. The proposed approach dynamically adjusts the regularization strength parameters during training, allowing the model to better converge to different patterns and fluctuations in paddy growth parameters. The dataset utilized for training and evaluation comprises comprehensive agricultural variables, including soil composition, climate conditions, and historical yield data. Experiments demonstrate the effectiveness of the hybrid CNN-RNN architecture with dynamic parameter calibration which improves prediction accuracy over conventional models. This research contributes to the advancement of precision agriculture by providing a more robust and adaptable framework for paddy yield prediction. The integration of spatial and temporal features, along with dynamic parameter calibration, showcases the potential for optimizing agricultural decision-making processes and mitigating the impact of unpredictable factors on paddy production.</div></div>","PeriodicalId":51045,"journal":{"name":"European Journal of Agronomy","volume":"174 ","pages":"Article 127929"},"PeriodicalIF":5.5,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145599014","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号