Signe Marie Jensen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Signe Marie Jensen has a total of 198 co-authors. Here are the top co-authors by number of shared publications:
- Christian Ritz
National Institute of Public Health, University of Southern Denmark, Copenhagen, Denmark
17 shared publications - Christian Mølgaard
Department of Nutrition, Exercise and Sports, Faculty of Science University of Copenhagen Copenhagen Denmark
10 shared publications - Christian Andreasen
Department of Plant and Environmental Sciences, University of Copenhagen, Højbakkegaard Allé 13, 2630 Taastrup, Denmark
5 shared publications - Felix M. Kluxen
BASF SE, Limburgerhof, Germany
5 shared publications - Hans Bisgaard
COPSAC, Copenhagen Prospective Studies on Asthma in Childhood, Herlev and Gentofte Hospital, University of Copenhagen, Copenhagen, Denmark
5 shared publications - Kim Fleischerm Michaelsen
Department of Nutrition, Exercise and Sports, University of Copenhagen, DK 1958 Frederiksberg, Denmark
5 shared publications
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on AgriFood Electronics
- Vol. 4 (2) , 1-10
LeafCast: A Lightweight Edge-Deployable Network for Temporal Plant Growth Prediction
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on AgriFood Electronics
- Vol. 4 (2) , 1-10
LeafCast: A Lightweight Edge-Deployable Network for Temporal Plant Growth Prediction
- 14 November 2025
- Published by Oxford University Press (OUP) in Integrated Environmental Assessment and Management
- Vol. 22 (3) , 741-754
Hybrid method benchmark dose estimation with a heterogeneous variance structure
For several decades, the benchmark dose (BMD) methodology has been recommended for estimating safe exposure levels to toxic substances. When the response variable is continuous, the BMD and its lower confidence limit (BMDL) are often estimated using the hybrid method, which assumes a normal distribution to model the probability of an adverse response. Typically, this approach relies on a dose-response model with the assumption of constant SD across all doses. However, when this assumption is violated, it can lead to biased estimates, and current implementations of the hybrid method do not account for this. In this article, we introduce an extended class of dose-response models that allows for variation in the SD across doses and adapt the hybrid method accordingly. We illustrate the proposed method using two datasets with two types of heteroscedasticity and show, through simulation, that addressing variance heterogeneity reduces bias and results in BMDL estimates with coverage closer to the nominal level.
- 14 November 2025
- Published by Oxford University Press (OUP) in Integrated Environmental Assessment and Management
- Vol. 22 (3) , 741-754
Hybrid method benchmark dose estimation with a heterogeneous variance structure
For several decades, the benchmark dose (BMD) methodology has been recommended for estimating safe exposure levels to toxic substances. When the response variable is continuous, the BMD and its lower confidence limit (BMDL) are often estimated using the hybrid method, which assumes a normal distribution to model the probability of an adverse response. Typically, this approach relies on a dose-response model with the assumption of constant SD across all doses. However, when this assumption is violated, it can lead to biased estimates, and current implementations of the hybrid method do not account for this. In this article, we introduce an extended class of dose-response models that allows for variation in the SD across doses and adapt the hybrid method accordingly. We illustrate the proposed method using two datasets with two types of heteroscedasticity and show, through simulation, that addressing variance heterogeneity reduces bias and results in BMDL estimates with coverage closer to the nominal level.
- Open Access
- 3 September 2025
- Published by Springer Nature in Euphytica
- Vol. 221 (10) , 1-16
Can knowledge of the spatial field trend improve phenotypic prediction accuracy through informed choice of experimental design?
Environmental variation is an important factor in crop yield variability, especially in large agricultural experiments such as breeding trials. This study explores whether prior knowledge of the spatial field trends can enhance phenotypic prediction accuracy by choice of experimental design and statistical analysis. Using data from three breeding trials and a simulation study with eight field trends, we compared five experimental designs and six statistical models. The results showed that combining field trend knowledge with an appropriate analysis strategy can improve predictive performance. There was no universally optimal design; but among the designs considered, the row-column design performed best for most field trends with a high degree of spatial variation. Statistical models correcting for spatial variation consistently reduced bias and increased correlation between predicted and true yield. This work emphasizes the need to integrate spatial information in the decision of both the design and analysis of breeding trials to boost prediction accuracy.
- 3 September 2025
- Published by Springer Nature in Euphytica
- Vol. 221 (10) , 1-16
Open AccessCan knowledge of the spatial field trend improve phenotypic prediction accuracy through informed choice of experimental design?
Environmental variation is an important factor in crop yield variability, especially in large agricultural experiments such as breeding trials. This study explores whether prior knowledge of the spatial field trends can enhance phenotypic prediction accuracy by choice of experimental design and statistical analysis. Using data from three breeding trials and a simulation study with eight field trends, we compared five experimental designs and six statistical models. The results showed that combining field trend knowledge with an appropriate analysis strategy can improve predictive performance. There was no universally optimal design; but among the designs considered, the row-column design performed best for most field trends with a high degree of spatial variation. Statistical models correcting for spatial variation consistently reduced bias and increased correlation between predicted and true yield. This work emphasizes the need to integrate spatial information in the decision of both the design and analysis of breeding trials to boost prediction accuracy.
- Open Access
- 21 February 2025
- Published by Elsevier in Smart Agricultural Technology
- Vol. 11
The PhenoLab – an automated, high-throughput phenotyping platform for analyzing development, abiotic stress responses and pathogen infection in model and crop plants
- 21 February 2025
- Published by Elsevier in Smart Agricultural Technology
- Vol. 11
Open AccessThe PhenoLab – an automated, high-throughput phenotyping platform for analyzing development, abiotic stress responses and pathogen infection in model and crop plants
- Top Cited PapersOpen Access
- 17 January 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (2) , 196
LEAF-Net: A Unified Framework for Leaf Extraction and Analysis in Multi-Crop Phenotyping Using YOLOv11
Accurate leaf segmentation and counting are critical for advancing crop phenotyping and improving breeding programs in agriculture. This study evaluates YOLOv11-based models for automated leaf detection and segmentation across spring barley, spring wheat, winter wheat, winter rye, and winter triticale. The key focus is assessing whether a unified model trained on a combined multi-crop dataset can outperform crop-specific models. Results show that the unified model achieves superior performance in bounding box tasks, with mAP@50 exceeding 0.85 for spring crops and 0.7 for winter crops. Segmentation tasks, however, reveal mixed results, with individual models occasionally excelling in recall for winter crops. These findings highlight the benefits of dataset diversity in improving generalization, while emphasizing the need for larger annotated datasets to address variability in real-world conditions. While the combined dataset improves generalization, the unique characteristics of individual crops may still benefit from specialized training.
- 17 January 2025
- Published by MDPI AG in Agriculture
- Vol. 15 (2) , 196
Top Cited PapersOpen AccessLEAF-Net: A Unified Framework for Leaf Extraction and Analysis in Multi-Crop Phenotyping Using YOLOv11
Accurate leaf segmentation and counting are critical for advancing crop phenotyping and improving breeding programs in agriculture. This study evaluates YOLOv11-based models for automated leaf detection and segmentation across spring barley, spring wheat, winter wheat, winter rye, and winter triticale. The key focus is assessing whether a unified model trained on a combined multi-crop dataset can outperform crop-specific models. Results show that the unified model achieves superior performance in bounding box tasks, with mAP@50 exceeding 0.85 for spring crops and 0.7 for winter crops. Segmentation tasks, however, reveal mixed results, with individual models occasionally excelling in recall for winter crops. These findings highlight the benefits of dataset diversity in improving generalization, while emphasizing the need for larger annotated datasets to address variability in real-world conditions. While the combined dataset improves generalization, the unique characteristics of individual crops may still benefit from specialized training.
- Open Access
- 6 December 2024
- Published by Springer Nature in Research Square
LEAF-Net: A Unified Framework for Leaf Extraction and Analysis in Multi-Crop Phenotyping Using YOLOv11
Accurate leaf segmentation and counting are critical for advancing crop phenotyping and improving breeding programs in agriculture. This study evaluates YOLOv11-based models for automated leaf detection and segmentation across spring barley, spring wheat, winter wheat, winter rye, and winter triticale. The key focus is assessing whether a unified model trained on a combined multi-crop dataset can outperform crop-specific models. Results show that the unified model achieves superior performance in bounding box tasks, with mAP@50 exceeding 0.85 for spring crops and above 0.7 for winter crops. Segmentation tasks, however, reveal mixed results, with individual models occasionally excelling in recall for winter crops. These findings highlight the benefits of dataset diversity in improving generalization, while emphasizing the need for larger annotated datasets to address variability in real-world conditions. This highlights that while the combined dataset improves generalization, the unique characteristics of individual crops may still benefit from specialized training. This work demonstrates the potential of AI-driven models to advance automated phenotyping for large-scale precision agriculture.
- 6 December 2024
- Published by Springer Nature in Research Square
Open AccessLEAF-Net: A Unified Framework for Leaf Extraction and Analysis in Multi-Crop Phenotyping Using YOLOv11
Accurate leaf segmentation and counting are critical for advancing crop phenotyping and improving breeding programs in agriculture. This study evaluates YOLOv11-based models for automated leaf detection and segmentation across spring barley, spring wheat, winter wheat, winter rye, and winter triticale. The key focus is assessing whether a unified model trained on a combined multi-crop dataset can outperform crop-specific models. Results show that the unified model achieves superior performance in bounding box tasks, with mAP@50 exceeding 0.85 for spring crops and above 0.7 for winter crops. Segmentation tasks, however, reveal mixed results, with individual models occasionally excelling in recall for winter crops. These findings highlight the benefits of dataset diversity in improving generalization, while emphasizing the need for larger annotated datasets to address variability in real-world conditions. This highlights that while the combined dataset improves generalization, the unique characteristics of individual crops may still benefit from specialized training. This work demonstrates the potential of AI-driven models to advance automated phenotyping for large-scale precision agriculture.
- Open Access
- 21 August 2024
- Published by Springer Nature in Research Square
Innovative Leaf Disease Mapping: Unsupervised Anomaly Detection for Precise Area Estimation
Detecting and quantifying the diseased regions in a leaf is an important task in plant breeding in order to select plants based on disease resistance. Ratings done by eye and hand are not accurate, can be highly subjective and take a lot of work hours. Using machine learning, it is possible to generate faster more accurate data. By combining modern anomaly detection algorithms with masking algorithms a robust method capable of estimating the infected leaf area was developed, resulting in a novel method with superior results. Using unsupervised models both for the masking and for the detection, the method can easily be used for different kinds of detection tasks.
- 21 August 2024
- Published by Springer Nature in Research Square
Open AccessInnovative Leaf Disease Mapping: Unsupervised Anomaly Detection for Precise Area Estimation
Detecting and quantifying the diseased regions in a leaf is an important task in plant breeding in order to select plants based on disease resistance. Ratings done by eye and hand are not accurate, can be highly subjective and take a lot of work hours. Using machine learning, it is possible to generate faster more accurate data. By combining modern anomaly detection algorithms with masking algorithms a robust method capable of estimating the infected leaf area was developed, resulting in a novel method with superior results. Using unsupervised models both for the masking and for the detection, the method can easily be used for different kinds of detection tasks.
- Open Access
- 8 December 2023
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 14, 1308528
Plant disease detection model for edge computing devices
In this paper, we address the question of achieving high accuracy in deep learning models for agricultural applications through edge computing devices while considering the associated resource constraints. Traditional and state-of-the-art models have demonstrated good accuracy, but their practicality as end-user available solutions remains uncertain due to current resource limitations. One agricultural application for deep learning models is the detection and classification of plant diseases through image-based crop monitoring. We used the publicly available PlantVillage dataset containing images of healthy and diseased leaves for 14 crop species and 6 groups of diseases as example data. The MobileNetV3-small model succeeds in classifying the leaves with a test accuracy of around 99.50%. Post-training optimization using quantization reduced the number of model parameters from approximately 1.5 million to 0.93 million while maintaining the accuracy of 99.50%. The final model is in ONNX format, enabling deployment across various platforms, including mobile devices. These findings offer a cost-effective solution for deploying accurate deep-learning models in agricultural applications.
- 8 December 2023
- Published by Frontiers Media SA in Frontiers in Plant Science
- Vol. 14, 1308528
Open AccessPlant disease detection model for edge computing devices
In this paper, we address the question of achieving high accuracy in deep learning models for agricultural applications through edge computing devices while considering the associated resource constraints. Traditional and state-of-the-art models have demonstrated good accuracy, but their practicality as end-user available solutions remains uncertain due to current resource limitations. One agricultural application for deep learning models is the detection and classification of plant diseases through image-based crop monitoring. We used the publicly available PlantVillage dataset containing images of healthy and diseased leaves for 14 crop species and 6 groups of diseases as example data. The MobileNetV3-small model succeeds in classifying the leaves with a test accuracy of around 99.50%. Post-training optimization using quantization reduced the number of model parameters from approximately 1.5 million to 0.93 million while maintaining the accuracy of 99.50%. The final model is in ONNX format, enabling deployment across various platforms, including mobile devices. These findings offer a cost-effective solution for deploying accurate deep-learning models in agricultural applications.
- Open Access
Unravelling the Complexities of Genotype-Soil-Management Interaction for Precision Agriculture
The knowledge of interactions among crop genotypes, soil types, and crop management is essential for precision agriculture. This paper explores these interactions through the analysis of 27 years of winter wheat trials, with 276 unique varieties tested across seven distinct soil types and more than 8000 plots. The study investigates how different winter wheat crop varieties respond to varying soil types and preceding crops. The findings revealed a significant interaction between variety, soil type, and preceding crop. With only a few exceptions, the highest-yielding varieties were predominantly the most recently developed. The ranking of the varieties exhibited inconsistency across the various soil types, implying that a variety yields differently when cultivated in different soil types. Furthermore, the influence of preceding crops on yield varied with soil type. This suggests that taking field-specific soil variation and the preceding crop into account during variety selection may improve the yield potential. Furthermore, the study highlights consistent yield increases due to advancements in breeding programs, with yearly increases ranging from 0.05 to 0.1 t/ha per year across all soil types. Integration of insights from genetics, soil attributes, and management practices demonstrates how farmers can increase productivity.
Open AccessUnravelling the Complexities of Genotype-Soil-Management Interaction for Precision Agriculture
The knowledge of interactions among crop genotypes, soil types, and crop management is essential for precision agriculture. This paper explores these interactions through the analysis of 27 years of winter wheat trials, with 276 unique varieties tested across seven distinct soil types and more than 8000 plots. The study investigates how different winter wheat crop varieties respond to varying soil types and preceding crops. The findings revealed a significant interaction between variety, soil type, and preceding crop. With only a few exceptions, the highest-yielding varieties were predominantly the most recently developed. The ranking of the varieties exhibited inconsistency across the various soil types, implying that a variety yields differently when cultivated in different soil types. Furthermore, the influence of preceding crops on yield varied with soil type. This suggests that taking field-specific soil variation and the preceding crop into account during variety selection may improve the yield potential. Furthermore, the study highlights consistent yield increases due to advancements in breeding programs, with yearly increases ranging from 0.05 to 0.1 t/ha per year across all soil types. Integration of insights from genetics, soil attributes, and management practices demonstrates how farmers can increase productivity.
- Open Access
- 10 August 2023
- Published by Wiley in Pest Management Science
- Vol. 80 (5) , 2362-2370
Parasitoids of the cabbage seed weevil deliver high and consistent parasitism in variable landscapes: A showcase of conservation biocontrol
BACKGROUND: Insect pest resistance to insecticides and societal pressure to reduce pesticide load has increased oilseed rape (OSR) farmers' motivation to protect and exploit parasitoids for pest control. However, parasitoid presence and parasitism must be made visible to influence farmers' spraying decisions. Parasitism of cabbage seed weevil (CSW) (Ceutorhynchus obstrictus (Marsham)) reduces damage to OSR immediately, making them a good case for demonstrating conservation biocontrol to farmers. We assessed the occurrence and activity of CSW parasitoids in 84 OSR fields over 2 years and identified the impact of associated local landscape factors.RESULTS: Mean cabbage seed weevil infestation rates were 11% and 10% in 2020 and 2021, and parasitism rates were high in both years (75% and 74%, respectively). Temporal and spatial dynamics of OSR in the landscape surrounding the focal fields were important for both CSW and parasitoid numbers, suggesting a dilution effect for increasing OSR area since the previous year. A multimodel inference analysis showed that OSR‐related factors were important predictors for both the infestation rate of CSW and the number of parasitoids. For parasitoids, protected nature areas and hedgerows were important. Parasitism rates were high and largely unaffected by landscape factors.CONCLUSION: CSW and its parasitoids respond similarly to interannual changes in the OSR resource; in addition, parasitoids benefit from uncropped areas in the surrounding landscape. The complexity of the pest and parasitoid response to landscape factors limits the prospect of designing landscapes for improved pest control by the parasitoids. Parasitoids of CSW may be present as local populations in agricultural landscapes with the potential for consistent and substantial parasitism. © 2023 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.
- 10 August 2023
- Published by Wiley in Pest Management Science
- Vol. 80 (5) , 2362-2370
Open AccessParasitoids of the cabbage seed weevil deliver high and consistent parasitism in variable landscapes: A showcase of conservation biocontrol
BACKGROUND: Insect pest resistance to insecticides and societal pressure to reduce pesticide load has increased oilseed rape (OSR) farmers' motivation to protect and exploit parasitoids for pest control. However, parasitoid presence and parasitism must be made visible to influence farmers' spraying decisions. Parasitism of cabbage seed weevil (CSW) (Ceutorhynchus obstrictus (Marsham)) reduces damage to OSR immediately, making them a good case for demonstrating conservation biocontrol to farmers. We assessed the occurrence and activity of CSW parasitoids in 84 OSR fields over 2 years and identified the impact of associated local landscape factors.RESULTS: Mean cabbage seed weevil infestation rates were 11% and 10% in 2020 and 2021, and parasitism rates were high in both years (75% and 74%, respectively). Temporal and spatial dynamics of OSR in the landscape surrounding the focal fields were important for both CSW and parasitoid numbers, suggesting a dilution effect for increasing OSR area since the previous year. A multimodel inference analysis showed that OSR‐related factors were important predictors for both the infestation rate of CSW and the number of parasitoids. For parasitoids, protected nature areas and hedgerows were important. Parasitism rates were high and largely unaffected by landscape factors.CONCLUSION: CSW and its parasitoids respond similarly to interannual changes in the OSR resource; in addition, parasitoids benefit from uncropped areas in the surrounding landscape. The complexity of the pest and parasitoid response to landscape factors limits the prospect of designing landscapes for improved pest control by the parasitoids. Parasitoids of CSW may be present as local populations in agricultural landscapes with the potential for consistent and substantial parasitism. © 2023 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.