Tomato is an important commercial product which is perishable by nature and highly susceptible to fungal incidence once it is harvested. Not all tomatoes are equally vulnerable to pathogenic fungi, and an early detection of the vulnerable ones can help in taking timely preventive actions, ranging from isolating tomato batches to adjusting storage conditions, but also in making right business decisions like dynamic pricing based on quality or better shelf life estimate. More importantly, early detection of vulnerable produce can help in taking timely actions to minimize potential post-harvest losses. This paper investigates Near-infrared (NIR) hyperspectral imaging (1000\uffe2\uff80\uff931700\uffc2\uffa0nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections. Hyperspectral images of newly harvested tomatoes (cultivar Brioso) from 5 different growers were acquired before the onset of any visible fungal infection. After imaging, the tomatoes were placed under controlled conditions suited for fungal germination and growth for a 4-day period, and then imaged using normal color cameras. All sepals in the color images were ranked for fungal severity using crowdsourcing, and the final severity of each sepal was fused using principal component analysis. A novel hyperspectral data processing pipeline is presented which was used to automatically segment the tomato sepals from spectral images with multiple tomatoes connected via a truss. The key modelling question addressed in this research is whether there is a correlation between the hyperspectral data captured at harvest and the fungal infection observed 4 days later. Using 10-fold and group k-fold cross-validation, XG-Boost and Random Forest based regression models were trained on the features derived from the hyperspectral data corresponding to each sepal in the training set and tested on hold out test set. The best model found a Pearson correlation of 0.837, showing that there is strong linear correlation between the NIR spectra and the future fungal severity of the sepal. The sepal specific predictions were aggregated to predict the susceptibility of individual tomatoes, and a correlation of 0.92 was found. Besides modelling, focus is also on model interpretation, particularly to understand which spectral features are most relevant to model prediction. Two approaches to model interpretation were explored, feature importance and SHAP (SHapley Additive exPlanations), resulting in similar conclusions that the NIR range between 1390\uffe2\uff80\uff931420\uffc2\uffa0nm contributes most to the model\uffe2\uff80\uff99s final decision.The necessity of sustainable development for landscapes has emerged as an important theme in recent decades. Current methods take a holistic approach to landscape heritage and promote an interdisciplinary dialogue to facilitate complementary landscape management strategies. With the socio-economic values of the \u201cnatural\u201d and \u201ccultural\u201d landscape heritage increasingly recognised worldwide, remote sensing tools are being used more and more to facilitate the recording and management of landscape heritage. The advent of freeware cloud computing services has enabled significant improvements in landscape research allowing the rapid exploration and processing of satellite imagery such as the Landsat and Copernicus Sentinel datasets. This research represents one of the first applications of the Google Earth Engine (GEE) \u00a0Python application programming interface (API) in studies of historic landscapes. The complete free and open-source software (FOSS) cloud protocol proposed here consists of a Python code script developed in Google Colab, which could be adapted and replicated in different areas of the world. A multi-temporal approach has been adopted to investigate the potential of Sentinel-2 satellite imagery to detect buried hydrological and anthropogenic features along with spectral index and spectral decomposition analysis. The protocol's effectiveness in identifying palaeo-riverscape features has been tested in the Po Plain (N Italy).", "keywords": ["FOS: Computer and information sciences", "Landscape Archaeology", "Computer Vision and Pattern Recognition (cs.CV)", "Computer Science - Computer Vision and Pattern Recognition", "0211 other engineering and technologies", "Articles", "02 engineering and technology", "15. Life on land", "01 natural sciences", "Fluvial and Alluvial Archaeology", "12. Responsible consumption", "Multispectral analysis", "Computer Science - Computers and Society", "Buried features", "Multispectral analysis;Sentinel-2;Spectral decomposition;Python;Riverscape;Fluvial and Alluvial Archaeology;Landscape Archaeology;Buried features", "13. Climate action", "Computers and Society (cs.CY)", "11. Sustainability", "Spectral decomposition", "Sentinel-2", "Riverscape", "Python", "Research Article", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://air.unimi.it/bitstream/2434/878015/4/Brandolini%2bet%2bal_ORE_2021_compressed%20%282%29.pdf"}, {"href": "https://eprints.ncl.ac.uk/fulltext.aspx?url=272362/A22B27B6-9486-4FBF-91B1-B06594F968F1.pdf&pub_id=272362"}, {"href": "https://doi.org/10.12688/openreseurope.13135.2"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Open%20Research%20Europe", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.12688/openreseurope.13135.2", "name": "item", "description": "10.12688/openreseurope.13135.2", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.12688/openreseurope.13135.2"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-03-24T00:00:00Z"}}, {"id": "10.3389/fenvs.2018.00061", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:20:46Z", "type": "Journal Article", "created": "2018-07-10", "title": "Recognizing Patterns: Spatial Analysis of Observed Microbial Colonization on Root Surfaces", "description": "Root surfaces are major sites of interactions between plants and associated microorganisms. Here, plants and microbes communicate via signaling molecules, compete for nutrients, and release substrates that may have beneficial or harmful effects on each other. Whilst the body of knowledge on the abundance and diversity of microbial communities at root-soil interfaces is now substantial, information on their spatial distribution at the microscale is still scarce. In this study, a standardized method for recognizing and analyzing microbial cell distributions on root surfaces is presented. Fluorescence microscopy was combined with automated image analysis and spatial statistics to explore the distribution of bacterial colonization patterns on rhizoplanes of rice roots. To test and evaluate the presented approach, a gnotobiotic experiment was performed using a potential nitrogen-fixing bacterial strain in combination with roots of wetland rice. The automated analysis procedure resulted in reliable spatial data of bacterial cells colonizing the rhizoplane. Among all replicate roots, the analysis revealed an increasing density of bacterial cells from the root tip to the region of root cell maturation. Moreover, bacterial cells showed significant spatial clustering and tended to be located around plant root cell borders. The quantitative data suggest that the structure of the root surface plays a major role in bacterial colonization patterns. Possible adaptations of the presented approach for future studies are discussed along with potential pitfalls such as inaccurate imaging. Our results demonstrate that standardized recognition and statistical evaluation of microbial colonization on root surfaces holds the potential to increase our understanding of microbial associations with roots and of the underlying ecological interactions.", "keywords": ["[SDE] Environmental Sciences", "0301 basic medicine", "570", "bacterial colonization", "[SDV]Life Sciences [q-bio]", "CATALYZED REPORTER DEPOSITION", "microbial ecology;root surface;bacterial colonization;point process;spatial statistics;image analysis;pattern recognition;wetland rice", "ECOLOGY", "microbial ecology", "Image analysis", "spatial statistics", "Microbial ecology", "03 medical and health sciences", "image analysis", "Pattern recognition", "root surface", "GE1-350", "Point process", "Wetland rice", "point process", "2. Zero hunger", "106022 Mikrobiologie", "0303 health sciences", "Spatial statistics", "IDENTIFICATION", "pattern recognition", "IN-SITU HYBRIDIZATION", "15. Life on land", "Bacterial colonization", "[SDV] Life Sciences [q-bio]", "SOIL", "Environmental sciences", "wetland rice", "Root surface", "[SDE]Environmental Sciences", "BACTERIA", "106022 Microbiology", "POPULATIONS", "COMMUNITIES"]}, "links": [{"href": "https://doi.org/10.3389/fenvs.2018.00061"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Frontiers%20in%20Environmental%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3389/fenvs.2018.00061", "name": "item", "description": "10.3389/fenvs.2018.00061", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3389/fenvs.2018.00061"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2018-07-10T00:00:00Z"}}, {"id": "10.48550/arxiv.2112.03814", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:21:27Z", "type": "Report", "created": "2022-05-16", "title": "A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images", "description": "Open Access12 pages, ICIAP 2021", "keywords": ["FOS: Computer and information sciences", "computer vision", " semantic segmentation", " aerial images", " incremental learning", "Computer Vision and Pattern Recognition (cs.CV)", "Image and Video Processing (eess.IV)", "Computer Science - Computer Vision and Pattern Recognition", "FOS: Electrical engineering", " electronic engineering", " information engineering", "0211 other engineering and technologies", "0202 electrical engineering", " electronic engineering", " information engineering", "02 engineering and technology", "Electrical Engineering and Systems Science - Image and Video Processing"]}, "links": [{"href": "https://iris.polito.it/bitstream/11583/2962571/1/ICIAP_2021_arnaudo_contrastive_distillation_camera_ready.pdf"}, {"href": "https://iris.polito.it/bitstream/11583/2962571/3/978-3-031-06430-2_62.pdf"}, {"href": "https://link.springer.com/content/pdf/10.1007/978-3-031-06430-2"}, {"href": "https://link.springer.com/content/pdf/10.1007/978-3-031-06430-2_62"}, {"href": "https://doi.org/10.48550/arxiv.2112.03814"}, {"rel": "self", "type": "application/geo+json", "title": "10.48550/arxiv.2112.03814", "name": "item", "description": "10.48550/arxiv.2112.03814", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.48550/arxiv.2112.03814"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-01-01T00:00:00Z"}}, {"id": "10.48550/arxiv.2303.15919", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-07-25T16:21:27Z", "type": "Journal Article", "title": "Fully Hyperbolic Convolutional Neural Networks for Computer Vision", "description": "Real-world visual data exhibit intrinsic hierarchical structures that can be represented effectively in hyperbolic spaces. Hyperbolic neural networks (HNNs) are a promising approach for learning feature representations in such spaces. However, current HNNs in computer vision rely on Euclidean backbones and only project features to the hyperbolic space in the task heads, limiting their ability to fully leverage the benefits of hyperbolic geometry. To address this, we present HCNN, a fully hyperbolic convolutional neural network (CNN) designed for computer vision tasks. Based on the Lorentz model, we generalize fundamental components of CNNs and propose novel formulations of the convolutional layer, batch normalization, and multinomial logistic regression. {Experiments on standard vision tasks demonstrate the promising performance of our HCNN framework in both hybrid and fully hyperbolic settings.} Overall, we believe our contributions provide a foundation for developing more powerful HNNs that can better represent complex structures found in image data. Our code is publicly available at https://github.com/kschwethelm/HyperbolicCV.", "keywords": ["FOS: Computer and information sciences", "Computer Vision and Pattern Recognition (cs.CV)", "Machine Learning (cs.LG)"], "contacts": [{"organization": "Bdeir, Ahmad, Schwethelm, Kristian, Landwehr, Niels,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.48550/arxiv.2303.15919"}, {"rel": "self", "type": "application/geo+json", "title": "10.48550/arxiv.2303.15919", "name": "item", "description": "10.48550/arxiv.2303.15919", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.48550/arxiv.2303.15919"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2023-01-01T00:00:00Z"}}, {"id": "2434/878015", "type": "Feature", "geometry": null, "properties": {"updated": "2026-07-25T16:25:49Z", "type": "Journal Article", "created": "2021-09-06", "title": "A Google Earth Engine-enabled Python approach for the identification of anthropogenic palaeo-landscape features", "description": "
Tomato is an important commercial product which is perishable by nature and highly susceptible to fungal incidence once it is harvested. Not all tomatoes are equally vulnerable to pathogenic fungi, and an early detection of the vulnerable ones can help in taking timely preventive actions, ranging from isolating tomato batches to adjusting storage conditions, but also in making right business decisions like dynamic pricing based on quality or better shelf life estimate. More importantly, early detection of vulnerable produce can help in taking timely actions to minimize potential post-harvest losses. This paper investigates Near-infrared (NIR) hyperspectral imaging (1000\uffe2\uff80\uff931700\uffc2\uffa0nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections. Hyperspectral images of newly harvested tomatoes (cultivar Brioso) from 5 different growers were acquired before the onset of any visible fungal infection. After imaging, the tomatoes were placed under controlled conditions suited for fungal germination and growth for a 4-day period, and then imaged using normal color cameras. All sepals in the color images were ranked for fungal severity using crowdsourcing, and the final severity of each sepal was fused using principal component analysis. A novel hyperspectral data processing pipeline is presented which was used to automatically segment the tomato sepals from spectral images with multiple tomatoes connected via a truss. The key modelling question addressed in this research is whether there is a correlation between the hyperspectral data captured at harvest and the fungal infection observed 4 days later. Using 10-fold and group k-fold cross-validation, XG-Boost and Random Forest based regression models were trained on the features derived from the hyperspectral data corresponding to each sepal in the training set and tested on hold out test set. The best model found a Pearson correlation of 0.837, showing that there is strong linear correlation between the NIR spectra and the future fungal severity of the sepal. The sepal specific predictions were aggregated to predict the susceptibility of individual tomatoes, and a correlation of 0.92 was found. Besides modelling, focus is also on model interpretation, particularly to understand which spectral features are most relevant to model prediction. Two approaches to model interpretation were explored, feature importance and SHAP (SHapley Additive exPlanations), resulting in similar conclusions that the NIR range between 1390\uffe2\uff80\uff931420\uffc2\uffa0nm contributes most to the model\uffe2\uff80\uff99s final decision.Tomato is an important commercial product which is perishable by nature and highly susceptible to fungal incidence once it is harvested. Not all tomatoes are equally vulnerable to pathogenic fungi, and an early detection of the vulnerable ones can help in taking timely preventive actions, ranging from isolating tomato batches to adjusting storage conditions, but also in making right business decisions like dynamic pricing based on quality or better shelf life estimate. More importantly, early detection of vulnerable produce can help in taking timely actions to minimize potential post-harvest losses. This paper investigates Near-infrared (NIR) hyperspectral imaging (1000\uffe2\uff80\uff931700\uffc2\uffa0nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections. Hyperspectral images of newly harvested tomatoes (cultivar Brioso) from 5 different growers were acquired before the onset of any visible fungal infection. After imaging, the tomatoes were placed under controlled conditions suited for fungal germination and growth for a 4-day period, and then imaged using normal color cameras. All sepals in the color images were ranked for fungal severity using crowdsourcing, and the final severity of each sepal was fused using principal component analysis. A novel hyperspectral data processing pipeline is presented which was used to automatically segment the tomato sepals from spectral images with multiple tomatoes connected via a truss. The key modelling question addressed in this research is whether there is a correlation between the hyperspectral data captured at harvest and the fungal infection observed 4 days later. Using 10-fold and group k-fold cross-validation, XG-Boost and Random Forest based regression models were trained on the features derived from the hyperspectral data corresponding to each sepal in the training set and tested on hold out test set. The best model found a Pearson correlation of 0.837, showing that there is strong linear correlation between the NIR spectra and the future fungal severity of the sepal. The sepal specific predictions were aggregated to predict the susceptibility of individual tomatoes, and a correlation of 0.92 was found. Besides modelling, focus is also on model interpretation, particularly to understand which spectral features are most relevant to model prediction. Two approaches to model interpretation were explored, feature importance and SHAP (SHapley Additive exPlanations), resulting in similar conclusions that the NIR range between 1390\uffe2\uff80\uff931420\uffc2\uffa0nm contributes most to the model\uffe2\uff80\uff99s final decision.