Pub Date : 2026-09-04DOI: 10.1007/s11119-026-10445-3
Shafi Md. Istiak, Mohammad Aftabi Talami, James Y. Kim, Sulaymon Eshkabilov
Context Weeds significantly reduce crop productivity and profitability, particularly in sugar beet production where losses exceed $1.25 billion annually in the United States. Limitations of herbicide-based control and drawbacks of conventional tillage highlight the need for efficient, sustainable alternatives. Aims To develop and evaluate an autonomous site-specific mechanical weeding (SSMW) system with adaptive control for precise inter-row weed removal under field conditions. Methods An SSMW system was designed by integrating an inter-row tillage mechanism with a robotic platform using RTK-GPS for navigation and site-specific actuation. Site-specific weeding was performed in the field test and a strain-based feedback control system was implemented in computer simulation to enable ASIC tillage under uneven terrain. Simulation studies based on field data were conducted to validate control performance, followed by field experiments to assess system effectiveness. Key Results The SSMW system’s efficacy was found to be 96.5% by tillage length. Conclusion The SSMW system achieved precise site-specific weeding using GPS-based control of individual sweeps, with a weeding efficacy of 96.5% based on tillage length. The ASIC framework with sensor feedback simulation showed the feasibility of improved adaptability to uneven terrain, with future work focusing on enhanced sensing and faster actuation for improved field performance. Implications and Impacts This study contributes to precision agriculture by enabling targeted weed management through intelligent sensing and control, reducing energy use and soil disruption. The system offers a sustainable alternative for organic farming, improving operational efficiency and environmental stewardship.
{"title":"Site-specific mechanical weeding robot with automatic self-adjustable individually controlled cultivator","authors":"Shafi Md. Istiak, Mohammad Aftabi Talami, James Y. Kim, Sulaymon Eshkabilov","doi":"10.1007/s11119-026-10445-3","DOIUrl":"https://doi.org/10.1007/s11119-026-10445-3","url":null,"abstract":"Context Weeds significantly reduce crop productivity and profitability, particularly in sugar beet production where losses exceed $1.25 billion annually in the United States. Limitations of herbicide-based control and drawbacks of conventional tillage highlight the need for efficient, sustainable alternatives. Aims To develop and evaluate an autonomous site-specific mechanical weeding (SSMW) system with adaptive control for precise inter-row weed removal under field conditions. Methods An SSMW system was designed by integrating an inter-row tillage mechanism with a robotic platform using RTK-GPS for navigation and site-specific actuation. Site-specific weeding was performed in the field test and a strain-based feedback control system was implemented in computer simulation to enable ASIC tillage under uneven terrain. Simulation studies based on field data were conducted to validate control performance, followed by field experiments to assess system effectiveness. Key Results The SSMW system’s efficacy was found to be 96.5% by tillage length. Conclusion The SSMW system achieved precise site-specific weeding using GPS-based control of individual sweeps, with a weeding efficacy of 96.5% based on tillage length. The ASIC framework with sensor feedback simulation showed the feasibility of improved adaptability to uneven terrain, with future work focusing on enhanced sensing and faster actuation for improved field performance. Implications and Impacts This study contributes to precision agriculture by enabling targeted weed management through intelligent sensing and control, reducing energy use and soil disruption. The system offers a sustainable alternative for organic farming, improving operational efficiency and environmental stewardship.","PeriodicalId":20423,"journal":{"name":"Precision Agriculture","volume":"43 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148883801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-09-04DOI: 10.1007/s11119-026-10446-2
Younghoo Cho, Ziwen Yu, Yiannis Ampatzidis, Ju-Seok Nam
{"title":"Facilitating a future agricultural data ecosystem: a cross-sectoral review of blockchain application in data sharing","authors":"Younghoo Cho, Ziwen Yu, Yiannis Ampatzidis, Ju-Seok Nam","doi":"10.1007/s11119-026-10446-2","DOIUrl":"https://doi.org/10.1007/s11119-026-10446-2","url":null,"abstract":"","PeriodicalId":20423,"journal":{"name":"Precision Agriculture","volume":"174 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148883802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-09-04DOI: 10.1007/s11119-026-10447-1
Amrinder Jakhar, Gonzalo J. Scarpin, Lorena N. Lacerda, Brenda V. Ortiz, Miguel L. Cabrera, George Vellidis, Leonardo M. Bastos
Purpose In-season optical sensor-based variable-rate nitrogen application (VRA) is designed to optimize nitrogen (N) management in maize (Zea mays L.) by aligning N inputs with real-time crop demand, yet reports on its performance are inconsistent. This study quantified the effects of VRA relative to fixed-rate management on N inputs, yield, N use efficiency, and profit; assessed VRA’s economic response to market volatility; identified key moderators; tested hierarchical interactions among moderators; and characterized economic and N-efficiency trade-offs. Methods A systematic review through February 2026 yielded 25 studies and 235 paired comparisons. The log response ratio was calculated for total N rate, grain yield, partial factor productivity of N (PFPN), and partial profit. Weighted linear mixed-effects models estimated overall effects, single-moderator analyses identified drivers, and conditional inference trees identified hierarchical interactions. Results VRA reduced total N rate by 18%, increased PFPN by 22%, and produced a 6% profit gain without affecting grain yield. Profitability was significant across all six market scenarios and scaled with the N: Maize price ratio. Agronomic outcomes were governed primarily by pre-plant N strategy, with the greatest benefits when pre-plant N was absent or minimal (≤ 12 kg N ha⁻¹). Economic outcomes were driven by algorithm design and application timing. A quadrant analysis showed simultaneous improvements in profit and PFPN in 57% of comparisons. Conclusion Relative to the uniform-rate treatments reported in the included studies, VRA reduced N inputs and improved efficiency while maintaining yield. Success depends on conservative pre-plant N strategies, appropriate algorithm selection, and early to mid-season timing.
基于季节光学传感器的可变速率施氮（VRA）旨在通过调整氮素投入与作物实时需求来优化玉米（Zea mays L.）的氮素管理，但有关其性能的报告并不一致。本研究量化了相对于固定费率管理的VRA对氮素投入、产量、氮素利用效率和利润的影响；评估VRA对市场波动的经济反应；确定了关键的主持人；测试了版主之间的层级互动；并描述了经济和氮效率的权衡。方法截至2026年2月的系统综述共纳入25项研究和235项配对比较。计算全氮用量、粮食产量、部分氮素要素生产率和部分利润的对数响应比。加权线性混合效应模型估计总体效应，单一调节因子分析确定驱动因素，条件推理树确定层次相互作用。结果VRA在不影响粮食产量的情况下，使总施氮量降低18%，使PFPN提高22%，并产生6%的利润增益。盈利能力在所有六种市场情景中都很显著，并与玉米价格比成比例。农艺结果主要由种植前N策略决定，当种植前N缺失或最小（≤12 kg N ha⁻¹）时，效益最大。经济结果由算法设计和应用时机驱动。象限分析显示，57%的比较中利润和PFPN同时改善。结论与纳入的研究中报道的均匀速率处理相比，VRA在保持产量的同时减少了氮素投入，提高了效率。成功取决于保守的种植前N策略，适当的算法选择，以及早到中期的季节时机。
{"title":"In-season optical sensor-based variable-rate nitrogen management in maize production: a meta-analysis","authors":"Amrinder Jakhar, Gonzalo J. Scarpin, Lorena N. Lacerda, Brenda V. Ortiz, Miguel L. Cabrera, George Vellidis, Leonardo M. Bastos","doi":"10.1007/s11119-026-10447-1","DOIUrl":"https://doi.org/10.1007/s11119-026-10447-1","url":null,"abstract":"Purpose In-season optical sensor-based variable-rate nitrogen application (VRA) is designed to optimize nitrogen (N) management in maize (Zea mays L.) by aligning N inputs with real-time crop demand, yet reports on its performance are inconsistent. This study quantified the effects of VRA relative to fixed-rate management on N inputs, yield, N use efficiency, and profit; assessed VRA’s economic response to market volatility; identified key moderators; tested hierarchical interactions among moderators; and characterized economic and N-efficiency trade-offs. Methods A systematic review through February 2026 yielded 25 studies and 235 paired comparisons. The log response ratio was calculated for total N rate, grain yield, partial factor productivity of N (PFPN), and partial profit. Weighted linear mixed-effects models estimated overall effects, single-moderator analyses identified drivers, and conditional inference trees identified hierarchical interactions. Results VRA reduced total N rate by 18%, increased PFPN by 22%, and produced a 6% profit gain without affecting grain yield. Profitability was significant across all six market scenarios and scaled with the N: Maize price ratio. Agronomic outcomes were governed primarily by pre-plant N strategy, with the greatest benefits when pre-plant N was absent or minimal (≤ 12 kg N ha⁻¹). Economic outcomes were driven by algorithm design and application timing. A quadrant analysis showed simultaneous improvements in profit and PFPN in 57% of comparisons. Conclusion Relative to the uniform-rate treatments reported in the included studies, VRA reduced N inputs and improved efficiency while maintaining yield. Success depends on conservative pre-plant N strategies, appropriate algorithm selection, and early to mid-season timing.","PeriodicalId":20423,"journal":{"name":"Precision Agriculture","volume":"494 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148883834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-08-29DOI: 10.1007/s11119-026-10441-7
François Stevens, Jeroen Degerickx, Stephanie Delalieux, Kristof Govaerts, Erik De Bruyne, Vincent Baeten, Philippe Vermeulen
{"title":"Powdery mildew detection in sugar beet breeding trials using spectral sensing techniques","authors":"François Stevens, Jeroen Degerickx, Stephanie Delalieux, Kristof Govaerts, Erik De Bruyne, Vincent Baeten, Philippe Vermeulen","doi":"10.1007/s11119-026-10441-7","DOIUrl":"https://doi.org/10.1007/s11119-026-10441-7","url":null,"abstract":"","PeriodicalId":20423,"journal":{"name":"Precision Agriculture","volume":"18 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-08-29DOI: 10.1007/s11119-026-10430-w
Nathan Sprague, John Evans, Michael Mardikes
Purpose Accurate measurement of corn stalk diameter is important for assessing plant robustness, lodging resistance, and harvest performance, but automated measurement across changing crop conditions remains challenging. This study evaluated whether a ground-based stereo-vision system could reliably estimate stalk diameter throughout the growing season, from mid-summer through senescence. Methods A stereo-vision pipeline using dual AR0234 global-shutter cameras was deployed on an autonomous ground robot. YOLOv8 provided stalk localization and pose correction, BoT-SORT enabled multi-frame tracking, and U-Net segmentation with an edge-mask strategy extracted stalk boundaries under partial occlusion. Repeated per-frame width estimates were filtered and converted to physical dimensions using disparity-based calibration. Vision estimates were compared with perpendicular caliper measurements. Results Under mid-summer conditions with minimal leaf interference, the system achieved a mean absolute error (MAE) of 1.1–1.5 mm and r² of 0.90. During late-season senescence, leaf-sheath expansion and occlusion caused systematic diameter overestimation and reduced accuracy. Applying a seasonally derived offset of approximately 3.8 mm reduced MAE to approximately 1.3 mm, although correlation remained modest (r² ≈ 0.41). Independent human measurements also exhibited variability, with inter-rater r² ≈ 0.77 and mean disagreement of approximately 1.0 mm. Conclusion Stereo vision can provide accurate, non-contact corn stalk diameter measurements under favorable canopy conditions and remains viable across the crop lifecycle. However, robust late-season phenotyping will require improved modeling of leaf sheaths and occlusions together with more reliable ground-truth measurement procedures.
{"title":"Corn stalk diameter estimation using deep learning","authors":"Nathan Sprague, John Evans, Michael Mardikes","doi":"10.1007/s11119-026-10430-w","DOIUrl":"https://doi.org/10.1007/s11119-026-10430-w","url":null,"abstract":"Purpose Accurate measurement of corn stalk diameter is important for assessing plant robustness, lodging resistance, and harvest performance, but automated measurement across changing crop conditions remains challenging. This study evaluated whether a ground-based stereo-vision system could reliably estimate stalk diameter throughout the growing season, from mid-summer through senescence. Methods A stereo-vision pipeline using dual AR0234 global-shutter cameras was deployed on an autonomous ground robot. YOLOv8 provided stalk localization and pose correction, BoT-SORT enabled multi-frame tracking, and U-Net segmentation with an edge-mask strategy extracted stalk boundaries under partial occlusion. Repeated per-frame width estimates were filtered and converted to physical dimensions using disparity-based calibration. Vision estimates were compared with perpendicular caliper measurements. Results Under mid-summer conditions with minimal leaf interference, the system achieved a mean absolute error (MAE) of 1.1–1.5 mm and r² of 0.90. During late-season senescence, leaf-sheath expansion and occlusion caused systematic diameter overestimation and reduced accuracy. Applying a seasonally derived offset of approximately 3.8 mm reduced MAE to approximately 1.3 mm, although correlation remained modest (r² ≈ 0.41). Independent human measurements also exhibited variability, with inter-rater r² ≈ 0.77 and mean disagreement of approximately 1.0 mm. Conclusion Stereo vision can provide accurate, non-contact corn stalk diameter measurements under favorable canopy conditions and remains viable across the crop lifecycle. However, robust late-season phenotyping will require improved modeling of leaf sheaths and occlusions together with more reliable ground-truth measurement procedures.","PeriodicalId":20423,"journal":{"name":"Precision Agriculture","volume":"17 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-08-29DOI: 10.1007/s11119-026-10432-8
Fàtima Della-Bellver, Belen Franch, Javier Tarin-Mestre, Cesar José Guerrero-Benavent, Concha Domingo, Mar Català Forner, Karen Marti-Jerez, Luis Marqués
Background Rice ( Oryza sativa L.) is a staple crop that accounts for 8% of the global primary crop production. This sector faces an environmental challenge driven by climate change, rising water scarcity, and the need for more resilient and adaptive production systems. Although Remote Sensing (RS) offers solutions for optimizing inputs, most current models are calibrated for specific varieties, limiting their application across diverse cultivars. This study evaluates the transferability of RS models for monitoring nitrogen (N) fertilization status and predicting yield across a highly heterogeneous dataset of rice genotypes, locations and seasons. Materials and methods Six field trials were conducted across three locations in Spain (Valencia and Tarragona) during seasons 2022 and 2023. The study analysed over 170 cultivars, including commercial Japonica and Indica varieties, and a selection of 170 non-commercialized-under development varieties, both subjected to low (100 kg N/ha) and high (200 kg N/ha) fertilization regimes. Multispectral UAV imagery (MAIA S2) was normalized using Accumulated Growing Degree Days (GDD) to align phenological stages across sites. Random Forest (RF) classifiers were employed to analyse the capacity of RS to identify whether rice paddies are under- or over-fertilized. The transferability of N models between rice genotypes was also assessed. Furthermore, the previously established MS3 + yield regression model, originally developed for the JSendra variety, was evaluated against a multi-variety dataset. Results Random Forest classifiers effectively discriminated between nitrogen application rates across diverse genotypes, with several sites exceeding an 85% validation accuracy. A consistent trend emerges when analysing spectral importance: visible (VIS) bands take importance during the early season stages, whereas near-infrared (NIR) and red-edge (RE) reflectance provide critical diagnostic information throughout the entire crop cycle. Notably, 82% of the evaluated varieties demonstrated a high compatibility with the global model. Conversely, the yield model showed limited transferability between varieties. While it performed poorly on the global dataset, it successfully predicted yields for 48.8% of commercial varieties (residues within ± 1 tons per hectare), specifically those with genetic and structural similarities to the training variety. Conclusion The study concludes that N-status monitoring via RS classifiers is robust across varying rice genetics, whereas yield prediction models exhibit strong genotype dependency.
{"title":"Assessing rice genotype dependency in remote sensing: challenges in nitrogen discrimination and yield forecasting","authors":"Fàtima Della-Bellver, Belen Franch, Javier Tarin-Mestre, Cesar José Guerrero-Benavent, Concha Domingo, Mar Català Forner, Karen Marti-Jerez, Luis Marqués","doi":"10.1007/s11119-026-10432-8","DOIUrl":"https://doi.org/10.1007/s11119-026-10432-8","url":null,"abstract":"Background Rice ( <jats:italic>Oryza sativa</jats:italic> L.) is a staple crop that accounts for 8% of the global primary crop production. This sector faces an environmental challenge driven by climate change, rising water scarcity, and the need for more resilient and adaptive production systems. Although Remote Sensing (RS) offers solutions for optimizing inputs, most current models are calibrated for specific varieties, limiting their application across diverse cultivars. This study evaluates the transferability of RS models for monitoring nitrogen (N) fertilization status and predicting yield across a highly heterogeneous dataset of rice genotypes, locations and seasons. Materials and methods Six field trials were conducted across three locations in Spain (Valencia and Tarragona) during seasons 2022 and 2023. The study analysed over 170 cultivars, including commercial <jats:italic>Japonica</jats:italic> and <jats:italic>Indica</jats:italic> varieties, and a selection of 170 non-commercialized-under development varieties, both subjected to low (100 kg N/ha) and high (200 kg N/ha) fertilization regimes. Multispectral UAV imagery (MAIA S2) was normalized using Accumulated Growing Degree Days (GDD) to align phenological stages across sites. Random Forest (RF) classifiers were employed to analyse the capacity of RS to identify whether rice paddies are under- or over-fertilized. The transferability of N models between rice genotypes was also assessed. Furthermore, the previously established MS3 + yield regression model, originally developed for the <jats:italic>JSendra</jats:italic> variety, was evaluated against a multi-variety dataset. Results Random Forest classifiers effectively discriminated between nitrogen application rates across diverse genotypes, with several sites exceeding an 85% validation accuracy. A consistent trend emerges when analysing spectral importance: visible (VIS) bands take importance during the early season stages, whereas near-infrared (NIR) and red-edge (RE) reflectance provide critical diagnostic information throughout the entire crop cycle. Notably, 82% of the evaluated varieties demonstrated a high compatibility with the global model. Conversely, the yield model showed limited transferability between varieties. While it performed poorly on the global dataset, it successfully predicted yields for 48.8% of commercial varieties (residues within ± 1 tons per hectare), specifically those with genetic and structural similarities to the training variety. Conclusion The study concludes that N-status monitoring via RS classifiers is robust across varying rice genetics, whereas yield prediction models exhibit strong genotype dependency.","PeriodicalId":20423,"journal":{"name":"Precision Agriculture","volume":"35 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-08-29DOI: 10.1007/s11119-026-10436-4
Kurt Wedegaertner, Brent Black, Anderson Safre, Alfonso Torres-Rua, Grant Cardon, Matt Yost
Purpose Evaluate how soil and canopy sensing can map within-block variability in tart cherry orchards and identify indicators robust enough for repeatable management decisions. Methods Soil apparent electrical conductivity (ECa) was mapped in spring 2022 across four commercial tart cherry blocks (8.5–10.5 ha; approximately 3,500 trees per block), followed by canopy sensing in 2023–2024. Canopy structure was measured using unmanned aerial vehicle (UAV) photogrammetry and mobile terrestrial laser scanning (MTLS) using light detection and ranging (LiDAR), and canopy density using mobile ceptometry. Spatial layers were aligned to per-tree grid cells. An August 2025 campaign compared UAV- and LiDAR-derived tree height with ground-truthed height. Results Soil-to-canopy relationships were weak to moderate but consistent within blocks ( r = 0.10–0.40), with strength and direction varying by site conditions. Canopy density was more strongly associated with UAV-derived volume than height. UAV-derived 90th-percentile height best predicted ground-truthed height ( R ² = 0.89; RMSE = 0.34 m), whereas LiDAR showed a weaker relationship and greater error ( R ² = 0.70; RMSE = 0.52 m). Cross-sensor agreement was moderate to strong ( r = 0.41–0.65). Per-tree rankings were stable between years for UAV height and volume. Conclusion Whole-block sensing revealed persistent spatial patterns that could support management-zone delineation. UAV photogrammetry provided accurate canopy metrics, MTLS offered measurements suited to routine orchard operations, ceptometry added seasonal canopy-density information, and ECa provided soil context. Occasional ECa mapping combined with strategically timed UAV surveys and other sensors as needed could reduce redundant sensing while supporting fertilizer evaluation, pruning, and labor allocation.
{"title":"Integrating soil and canopy sensing to map and relate variability in tart cherry orchards","authors":"Kurt Wedegaertner, Brent Black, Anderson Safre, Alfonso Torres-Rua, Grant Cardon, Matt Yost","doi":"10.1007/s11119-026-10436-4","DOIUrl":"https://doi.org/10.1007/s11119-026-10436-4","url":null,"abstract":"Purpose Evaluate how soil and canopy sensing can map within-block variability in tart cherry orchards and identify indicators robust enough for repeatable management decisions. Methods Soil apparent electrical conductivity (ECa) was mapped in spring 2022 across four commercial tart cherry blocks (8.5–10.5 ha; approximately 3,500 trees per block), followed by canopy sensing in 2023–2024. Canopy structure was measured using unmanned aerial vehicle (UAV) photogrammetry and mobile terrestrial laser scanning (MTLS) using light detection and ranging (LiDAR), and canopy density using mobile ceptometry. Spatial layers were aligned to per-tree grid cells. An August 2025 campaign compared UAV- and LiDAR-derived tree height with ground-truthed height. Results Soil-to-canopy relationships were weak to moderate but consistent within blocks ( <jats:italic>r</jats:italic> = 0.10–0.40), with strength and direction varying by site conditions. Canopy density was more strongly associated with UAV-derived volume than height. UAV-derived 90th-percentile height best predicted ground-truthed height ( <jats:italic>R</jats:italic> ² = 0.89; RMSE = 0.34 m), whereas LiDAR showed a weaker relationship and greater error ( <jats:italic>R</jats:italic> ² = 0.70; RMSE = 0.52 m). Cross-sensor agreement was moderate to strong ( <jats:italic>r</jats:italic> = 0.41–0.65). Per-tree rankings were stable between years for UAV height and volume. Conclusion Whole-block sensing revealed persistent spatial patterns that could support management-zone delineation. UAV photogrammetry provided accurate canopy metrics, MTLS offered measurements suited to routine orchard operations, ceptometry added seasonal canopy-density information, and ECa provided soil context. Occasional ECa mapping combined with strategically timed UAV surveys and other sensors as needed could reduce redundant sensing while supporting fertilizer evaluation, pruning, and labor allocation.","PeriodicalId":20423,"journal":{"name":"Precision Agriculture","volume":"26 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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 : 2026-08-24DOI: 10.1007/s11119-026-10405-x
Martin Mittermayer, Joseph Donauer, Felix Klein, Frank Leßke, Ludwig Hagn, Johannes Schuster, Kurt-Jürgen Hülsbergen
Purpose This study developed and validated an integrated framework to identify critical nitrate loss zones at sub-field scale in a drinking water protection area. The key question was whether satellite-based estimation of grain N uptake, combined with site-specific N balancing and soil–water–nitrate modeling, can reliably capture spatial patterns of nitrate leaching under practical farming conditions. Methods A satellite-based algorithm was developed to estimate winter wheat N uptake using data from georeferenced plots in southern Germany. Multiple linear regression and Random Forest models were applied based on Sentinel-2 vegetation indices, as well as soil, topographic, and climatic variables. Results and Discussion The Random Forest model performed slightly better (R 2 = 0.74, RMSE = 14.8 kg ha⁻ 1 , MAE = 11.2 kg ha⁻ 1 ) than the linear regression model (R 2 = 0.70, RMSE = 16.0 kg ha⁻ 1 , MAE = 12.5 kg ha⁻ 1 ). Predicted N uptake was combined with field-specific fertilization data to calculate site-specific N balances, which were integrated into a soil–water–nitrate leaching model. Low-yield zones showed lower N uptake but higher N surplus, modeled nitrate leaching, and measured nitrate–N stocks in deeper soil layers compared to high-yield zones. During validation (Field A), low-yield zones showed N surpluses of 98 kg ha⁻ 1 and modeled nitrate concentrations of 120 mg L⁻ 1 in seepage water, compared to 33 kg ha⁻ 1 and 49 mg L⁻ 1 in high-yield zones. Modeled nitrate concentrations correlated with measured nitrate–N stocks (R 2 = 0.68). The approach shows strong potential for identifying nitrate-prone areas and enabling targeted measures for drinking water protection.
本研究开发并验证了一个综合框架，以确定饮用水保护区在分田尺度上的临界硝酸盐损失区。关键问题是，基于卫星的谷物氮吸收估算，结合特定地点的氮平衡和土壤-水-硝酸盐模型，能否可靠地捕捉到实际农业条件下硝酸盐淋失的空间格局。方法利用德国南部地理参考地块的数据，开发了一种基于卫星的算法来估计冬小麦对氮的吸收。基于Sentinel-2植被指数以及土壤、地形和气候变量，应用多元线性回归和随机森林模型。结果和讨论随机森林模型（r2 = 0.74, RMSE = 14.8 kg ha - 1, MAE = 11.2 kg ha - 1）比线性回归模型（r2 = 0.70, RMSE = 16.0 kg ha - 1, MAE = 12.5 kg ha - 1）稍好。将预测的氮素吸收与田间特定施肥数据相结合，计算场地特定氮素平衡，并将其整合到土壤-水-硝酸盐淋溶模型中。与高产区相比，低产区表现出较低的氮素吸收量，但较高的氮素剩余量，模拟的硝酸盐淋失和测量的深层氮素储量。在验证过程中（田A），低产区显示出98 kg ha - 1的氮过剩，并模拟了渗漏水中120 mg L - 1的硝酸盐浓度，而高产区为33 kg ha - 1和49 mg L - 1。模拟的硝酸盐浓度与测量的硝酸盐- n储量相关（r2 = 0.68）。该方法显示出在确定硝酸盐易发地区和采取有针对性的饮用水保护措施方面的巨大潜力。
{"title":"Determination of critical nitrogen loss zones and high-resolution nitrate leaching modeling in drinking water protection areas with satellite-based algorithms","authors":"Martin Mittermayer, Joseph Donauer, Felix Klein, Frank Leßke, Ludwig Hagn, Johannes Schuster, Kurt-Jürgen Hülsbergen","doi":"10.1007/s11119-026-10405-x","DOIUrl":"https://doi.org/10.1007/s11119-026-10405-x","url":null,"abstract":"Purpose This study developed and validated an integrated framework to identify critical nitrate loss zones at sub-field scale in a drinking water protection area. The key question was whether satellite-based estimation of grain N uptake, combined with site-specific N balancing and soil–water–nitrate modeling, can reliably capture spatial patterns of nitrate leaching under practical farming conditions. Methods A satellite-based algorithm was developed to estimate winter wheat N uptake using data from georeferenced plots in southern Germany. Multiple linear regression and Random Forest models were applied based on Sentinel-2 vegetation indices, as well as soil, topographic, and climatic variables. Results and Discussion The Random Forest model performed slightly better (R <jats:sup>2</jats:sup> = 0.74, RMSE = 14.8 kg ha⁻ <jats:sup>1</jats:sup> , MAE = 11.2 kg ha⁻ <jats:sup>1</jats:sup> ) than the linear regression model (R <jats:sup>2</jats:sup> = 0.70, RMSE = 16.0 kg ha⁻ <jats:sup>1</jats:sup> , MAE = 12.5 kg ha⁻ <jats:sup>1</jats:sup> ). Predicted N uptake was combined with field-specific fertilization data to calculate site-specific N balances, which were integrated into a soil–water–nitrate leaching model. Low-yield zones showed lower N uptake but higher N surplus, modeled nitrate leaching, and measured nitrate–N stocks in deeper soil layers compared to high-yield zones. During validation (Field A), low-yield zones showed N surpluses of 98 kg ha⁻ <jats:sup>1</jats:sup> and modeled nitrate concentrations of 120 mg L⁻ <jats:sup>1</jats:sup> in seepage water, compared to 33 kg ha⁻ <jats:sup>1</jats:sup> and 49 mg L⁻ <jats:sup>1</jats:sup> in high-yield zones. Modeled nitrate concentrations correlated with measured nitrate–N stocks (R <jats:sup>2</jats:sup> = 0.68). The approach shows strong potential for identifying nitrate-prone areas and enabling targeted measures for drinking water protection.","PeriodicalId":20423,"journal":{"name":"Precision Agriculture","volume":"16 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148842941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：