{"type": "FeatureCollection", "features": [{"id": "10.5281/zenodo.14761001", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-05-30T16:23:49Z", "type": "Software", "title": "PyretoClustR (executable version)", "description": "PyretoClustR (executable version)  Distilling the Pareto Optimal Front into Actionable Insights  ##Highlights:    Open-access tool to cluster and visualize complex multi-dimensional Pareto solutions  Bridging the gap between decision and objective space through intuitive visualizations  Implements k-means and k-medoids clustering without expert knowledge  Uses frequency maps to display hotspot locations for spatial optimization problems  Increasing stakeholder accessibility to Pareto solutions   Program languages: Python, RSoftware availability (source code version): https://github.com/SydneyEWhite/Pareto_ClusteringSoftware availability (executable version, with python and libraries implemented): Zenodo (10.5281/zenodo.14761001)  ## Overview    This framework performs k-means and k-medoids clustering on a set of Pareto optimal solutions derived from a multi-objective optimization algorithm.  (Optional) A correlation matrix of the input variables is returned (the goal is to help users reduce the input variable count).  Before clustering occurs, the data is cast onto principal component axes and extreme solutions are handled (if desired).  The code iterates through different possible inputs for the number of clusters, the number of principal components, and the variables that define 'extreme solutions'.  After these iterations, the best solution, as defined by silhouette score, is visualized in several ways:    Representative solutions are plotted on up to 4 dimensions  Distributions of values within the clusters are plotted in a violin plot  (optional) Maps with the frequency of a trait can be plotted, if locational data (*.shp file) is provided     ## Background: executable version  Unlike the version of PyretoClustR available on GitHub (https://github.com/SydneyEWhite/PyretoClustR), this version on Zenodo represents a standalone version of PyretoClustR not requiring a Python installation. The python_files folder contains three executables and one folder called _internal. The executables can be run by clicking on them. The _internal folder is crucial for the standalone operation of the executables and should not be modified or deleted.  ## Example Data  The data provided in the input folder (pareto_and_scen_solutions.csv and the shapefiles) are part of the BiodivERsA project TALE (\u2018Towards multifunctional agricultural landscapes in Europe\u2019). This project optimized four objectives, Agricultural gross margin (AY), Breeding habitat (BH), Low flow (LF), Nitrate load (NL) and four different land use scenarios (SQ, BAU, EXT, INT) were distinguished in the decision space.\u00a0The config.ini has been adapted to run with this dataset. To run it with your own data please alter the respective input values as outlined in config.ini.  ## Directory Structure  project_root/||\u2500\u2500 README.md||\u2500\u2500 input/|\u00a0 |\u2500\u2500 config.ini|\u00a0 |\u2500\u2500 [your_input_data].csv| \u2514\u2500\u2500 [shape_files]||\u2500\u2500 python_files/|\u00a0 |\u2500\u2500 _internal|\u00a0 |\u2500\u2500 correlation_matrix.exe|\u00a0 |\u2500\u2500 kmeans.exe| \u2514\u2500\u2500 kmedoid.exe||\u2500\u2500 r_files/| \u2514\u2500\u2500 plot_frequency_maps.R|\u2514\u2500\u2500 output/ (populated once code is run)\u00a0\u00a0 |\u2500\u2500 correlation_matrix.csv (if run)\u00a0\u00a0 |\u2500\u2500 kmeans_data_w_clusters_representativesolutions.csv (created with kmeans.exe when Extreme Solutions are not handled)\u00a0\u00a0\u00a0 |\u2500\u2500 kmeans_data_w_clusters_representativesolutions_outliers.csv (created with kmeans.exe when Extreme Solutions are handled)\u00a0\u00a0 |\u2500\u2500 kmedoid_data_w_clusters_representativesolutions.csv (created with kmedoid.exe when Extreme Solutions are not handled)\u00a0\u00a0 |\u2500\u2500 kmedoid_data_w_clusters_representativesolutions_outliers.csv (created with kmedoid.exe when Extreme Solutions are handled)\u00a0 \u2514\u2500\u2500 freq_map_cluster_X.png (if run)", "keywords": ["Multi-objective optimization", "Pareto pruning", "Land management", "Pareto optimal data", "visualization", "clustering"]}, "links": [{"href": "https://doi.org/10.5281/zenodo.14761001"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.14761001", "name": "item", "description": "10.5281/zenodo.14761001", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.14761001"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-01-29T00:00:00Z"}}, {"id": "10.1002/ece3.8676", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:14:28Z", "type": "Journal Article", "created": "2022-03-08", "title": "Effects of operational taxonomic unit inference methods on soil microeukaryote community analysis using long-read metabarcoding", "description": "Abstract<p>Long amplicon metabarcoding has opened the door for phylogenetic analysis of the largely unknown communities of microeukaryotes in soil. Here, we amplified and sequenced the ITS and LSU regions of the rDNA operon (around 1500\uffc2\uffa0bp) from grassland soils using PacBio SMRT sequencing. We tested how three different methods for generation of operational taxonomic units (OTUs) effected estimated richness and identified taxa, and how well large\uffe2\uff80\uff90scale ecological patterns associated with shifting environmental conditions were recovered in data from the three methods. The field site at Kungs\uffc3\uffa4ngen Nature Reserve has drawn frequent visitors since Linnaeus's time, and its species rich vegetation includes the largest population of Fritillaria meleagris in Sweden. To test the effect of different OTU generation methods, we sampled soils across an abrupt moisture transition that divides the meadow community into a Carex acuta dominated plant community with low species richness in the wetter part, which is visually distinct from the mesic\uffe2\uff80\uff90dry part that has a species rich grass\uffe2\uff80\uff90dominated plant community including a high frequency of F.\uffc2\uffa0meleagris. We used the moisture and plant community transition as a framework to investigate how detected belowground microeukaryotic community composition was influenced by OTU generation methods. Soil communities in both moisture regimes were dominated by protists, a large fraction of which were taxonomically assigned to Ciliophora (Alveolata) while 30%\uffe2\uff80\uff9340% of all reads were assigned to kingdom Fungi. Ecological patterns were consistently recovered irrespective of OTU generation method used. However, different methods strongly affect richness estimates and the taxonomic and phylogenetic resolution of the characterized community with implications for how well members of the microeukaryotic communities can be recognized in the data.</p>", "keywords": ["580", "species hypothesis", "Ekologi", "0301 basic medicine", "0303 health sciences", "Ecology", "rDNA", "Biological Systematics", "15. Life on land", "03 medical and health sciences", "14. Life underwater", "ITS", "Research Articles", "clustering"]}, "links": [{"href": "https://pub.epsilon.slu.se/27699/1/eshghi-sahraei-s-et-al-220505.pdf"}, {"href": "https://onlinelibrary.wiley.com/doi/pdf/10.1002/ece3.8676"}, {"href": "https://doi.org/10.1002/ece3.8676"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Ecology%20and%20Evolution", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1002/ece3.8676", "name": "item", "description": "10.1002/ece3.8676", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1002/ece3.8676"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-03-01T00:00:00Z"}}, {"id": "10.1002/eqe.3286", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:14:29Z", "type": "Journal Article", "created": "2020-06-22", "title": "Spatiotemporal seismic hazard and risk assessment of M9.0 megathrust earthquake sequences of wood\u2010frame houses in Victoria, British Columbia, Canada", "description": "Summary<p>Megathrust earthquake sequences, comprising mainshocks and triggered aftershocks along the subduction interface and in the overriding crust, can impact multiple buildings and infrastructure in a city. The time between the mainshocks and aftershocks usually is too short to retrofit the structures; therefore, moderate\uffe2\uff80\uff90size aftershocks can cause additional damage. To have a better understanding of the impact of aftershocks on city\uffe2\uff80\uff90wide seismic risk assessment, a new simulation framework of spatiotemporal seismic hazard and risk assessment of future M9.0 sequences in the Cascadia subduction zone is developed. The simulation framework consists of an epidemic\uffe2\uff80\uff90type aftershock sequence (ETAS) model, ground\uffe2\uff80\uff90motion model, and state\uffe2\uff80\uff90dependent seismic fragility model. The spatiotemporal ETAS model is modified to characterise aftershocks of large and anisotropic M9.0 mainshock ruptures. To account for damage accumulation of wood\uffe2\uff80\uff90frame houses due to aftershocks in Victoria, British Columbia, Canada, state\uffe2\uff80\uff90dependent fragility curves are implemented. The new simulation framework can be used for quasi\uffe2\uff80\uff90real\uffe2\uff80\uff90time aftershock hazard and risk assessments and city\uffe2\uff80\uff90wide post\uffe2\uff80\uff90event risk management.</p>", "keywords": ["Mainshock-aftershock sequences", "550", "seismic risk", "Damage accumulation", "seismic hazard", "Cascadia", "City-wide seismic risk", "02 engineering and technology", "Wood-frame houses", "01 natural sciences", "aftershocks", "0201 civil engineering", "earthquake clustering", "13. Climate action", "Cascadia subduction earthquakes", "Spatiotemporal ETAS seismicity model", "earthquakes", "State-dependent aftershock fragility curves", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/10.1002/eqe.3286"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Earthquake%20Engineering%20%26amp%3B%20Structural%20Dynamics", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1002/eqe.3286", "name": "item", "description": "10.1002/eqe.3286", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1002/eqe.3286"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-06-21T00:00:00Z"}}, {"id": "10.1007/s10994-018-5744-y", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-05-30T16:15:22Z", "type": "Journal Article", "created": "2018-07-11", "title": "Ensembles for multi-target regression with random output selections", "description": "We address the task of multi-target regression, where we generate global models that simultaneously predict multiple continuous variables. We use ensembles of generalized decision trees, called predictive clustering trees (PCTs), in particular bagging and random forests (RF) of PCTs and extremely randomized PCTs (extra PCTs). We add another dimension of randomization to these ensemble methods by learning individual base models that consider random subsets of target variables, while leaving the input space randomizations (in RF PCTs and extra PCTs) intact. Moreover, we propose a new ensemble prediction aggregation function, where the final ensemble prediction for a given target is influenced only by those base models that considered it during learning. An extensive experimental evaluation on a range of benchmark datasets has been conducted, where the extended ensemble methods were compared to the original ensemble methods, individual multi-target regression trees, and ensembles of single-target regression trees in terms of predictive performance, running times and model sizes. The results show that the proposed ensemble extension can yield better predictive performance, reduce learning time or both, without a considerable change in model size. The newly proposed aggregation function gives best results when used with extremely randomized PCTs. We also include a comparison with three competing methods, namely random linear target combinations and two variants of random projections.", "keywords": ["Ensemble methods", "Predictive clustering trees", "0202 electrical engineering", " electronic engineering", " information engineering", "Structured outputs", "02 engineering and technology", "Multi-target regression", "Output space decomposition"]}, "links": [{"href": "https://doi.org/10.1007/s10994-018-5744-y"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Machine%20Learning", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1007/s10994-018-5744-y", "name": "item", "description": "10.1007/s10994-018-5744-y", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1007/s10994-018-5744-y"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2018-07-11T00:00:00Z"}}, {"id": "10.1007/s10994-020-05918-z", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:15:22Z", "type": "Journal Article", "created": "2020-10-28", "title": "Incremental predictive clustering trees for online semi-supervised multi-target regression", "description": "Abstract<p>In many application settings, labeling data examples is a costly endeavor, while unlabeled examples are abundant and cheap to produce. Labeling examples can be particularly problematic in an online setting, where there can be arbitrarily many examples that arrive at high frequencies. It is also problematic when we need to predict complex values (e.g., multiple real values), a task that has started receiving considerable attention, but mostly in the batch setting. In this paper, we propose a method for online semi-supervised multi-target regression. It is based on incremental trees for multi-target regression and the predictive clustering framework. Furthermore, it utilizes unlabeled examples to improve its predictive performance as compared to using just the labeled examples. We compare the proposed iSOUP-PCT method with supervised tree methods, which do not use unlabeled examples, and to an oracle method, which uses unlabeled examples as though they were labeled. Additionally, we compare the proposed method to the available state-of-the-art methods. The method achieves good predictive performance on account of increased consumption of computational resources as compared to its supervised variant. The proposed method also beats the state-of-the-art in the case of very few labeled examples in terms of performance, while achieving comparable performance when the labeled examples are more common.</p", "keywords": ["semi-supervised learning", "multi-target regression", "Classification and discrimination; cluster analysis (statistical aspects)", "Linear regression; mixed models", "predictive clustering", "Artificial Intelligence", "Learning and adaptive systems in artificial intelligence", "0202 electrical engineering", " electronic engineering", " information engineering", "Online algorithms; streaming algorithms", "02 engineering and technology", "Software", "data-stream mining"]}, "links": [{"href": "https://doi.org/10.1007/s10994-020-05918-z"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Machine%20Learning", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1007/s10994-020-05918-z", "name": "item", "description": "10.1007/s10994-020-05918-z", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1007/s10994-020-05918-z"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-10-28T00:00:00Z"}}, {"id": "10.1016/j.geoderma.2024.116962", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:16:57Z", "type": "Journal Article", "created": "2024-07-06", "title": "Disentangling soil-based ecosystem services synergies, trade-offs, multifunctionality, and bundles: A case study at regional scale (NE Italy) to support environmental planning", "description": "The explicit use of ecosystem services (ESs) assessments has been called as a way to guide environmental decision making, yet the promise of the ES approach lies behind its potential. A way to consolidate the approach could be to introduce some aspects into the ESs assessments which might have been neglected so far. Such aspects are mainly: (1) a focus on the complex ESs relations (such as synergies and trade-offs) that can impact the supply of multiple SESs (soil ecosystem services), and (2) focus on potential drivers of SESs relations. We applied bivariate and multivariate approaches to SESs indicators derived from a solid pedological knowledge of the Emilia-Romagna study area in NE Italy. We focused on 7 SES: (1) habitat for soil organisms, (2) filtering and buffering capacity, (3) contribution to microclimate regulation, (4) carbon sequestration, (5) food provision potential, (6) water regulation, and (7) water storage capacity. These SESs were estimated through a combination of point observations, and pedotransfer functions (PTF) estimates spatialised over the area of interest with geostatistical simulation techniques. We found that SESs bivariate spatial relations could be categorised mainly in three types of patterns at regional scale, either: (1) synergistic SESs relations dominating at the region level, (2) trade-offs dominating, or (3) both kind of relations more or less equally frequent. Interestingly, in some cases the dominant regional SESs relation switched at a local level, and such switch was driven by soil properties. For the multivariate case (>2 SESs), two main results are highlighted. First, the combination of properties of some soils is so characteristic that they conform a single SESs bundle, as in the case of the rich SOM soils of alluvial origin in the NE of the region with low agricultural productivity, but high value in regulating SESs. Secondly, some SESs such as potential food provision and water regulation are more important than others to determine locations with high multi-services value at a regional level. This suggests that attention must be paid when ascribing high multi-services value locations as this is not independent of SESs relations. Overall, our results highlight the importance of soils in the potential supply of ESs and show that SESs relations are useful in the implementation of the concept in environmental assessments.", "keywords": ["2. Zero hunger", "Soil multifunctionality index", "Science", "Q", "15. Life on land", "Bivariate local indicators of spatial association", "01 natural sciences", "Soil-based ecosystem services relations", "6. Clean water", "EJPSoil", "WP3", "SERENA project", "Ecosystem services relations\u2019 drivers", "Grant Agreement: 862695", "Pedo-landscapes; Soil multifunctionality index; Soil-based ecosystem services relations; Bivariate local indicators of spatial association; SES k-means clustering; Ecosystem services relations\u2019 drivers", "Ecosystem services relations' drivers", "SES k-means clustering", "bundle", "Pedo-landscapes", "0105 earth and related environmental sciences"], "contacts": [{"organization": "Medina-Roldan, Eduardo, Lorenzetti, Romina, Calzolari, Costanza, UNGARO, FABRIZIO,", "roles": ["creator"]}]}, "links": [{"href": "https://iris.cnr.it/bitstream/20.500.14243/532230/1/1-s2.0-S0016706124001915-main.pdf"}, {"href": "https://doi.org/10.1016/j.geoderma.2024.116962"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Geoderma", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1016/j.geoderma.2024.116962", "name": "item", "description": "10.1016/j.geoderma.2024.116962", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1016/j.geoderma.2024.116962"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-08-01T00:00:00Z"}}, {"id": "10.3168/jds.2019-16575", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:21:33Z", "type": "Journal Article", "created": "2019-08-22", "title": "Using machine learning to estimate herbage production and nutrient uptake on Irish dairy farms", "description": "Nutrient management on grazed grasslands is of critical importance to maintain productivity levels, as grass is the cheapest feed for ruminants and underpins these meat and milk production systems. Many attempts have been made to model the relationships between controllable (crop and soil fertility management) and noncontrollable influencing factors (weather, soil drainage) and nutrient/productivity levels. However, to the best of our knowledge not much research has been performed on modeling the interconnections between the influencing factors on one hand and nutrient uptake/herbage production on the other hand, by using data-driven modeling techniques. Our paper proposes to use predictive clustering trees (PCT) learned for building models on data from dairy farms in the Republic of Ireland. The PCT models show good accuracy in estimating herbage production and nutrient uptake. They are also interpretable and are found to embody knowledge that is in accordance with existing theoretical understanding of the task at hand. Moreover, if we combine more PCT into an ensemble of PCT (random forest of PCT), we can achieve improved accuracy of the estimates. In practical terms, the number of grazings, which is related proportionally with soil drainage class, is one of the most important factors that moderates the herbage production potential and nutrient uptake. Furthermore, we found the nutrient (N, P, and K) uptake and herbage nutrient concentration to be conservative in fields that had medium yield potential (11 t of dry matter per hectare on average), whereas nutrient uptake was more variable and potentially limiting in fields that had higher and lower herbage production. Our models also show that phosphorus is the most limiting nutrient for herbage production across the fields on these Irish dairy farms, followed by nitrogen and potassium.", "keywords": ["2. Zero hunger", "nutrient uptake", "Nutrients", "04 agricultural and veterinary sciences", "15. Life on land", "Poaceae", "Animal Feed", "Diet", "Machine Learning", "herbage production", "Dairying", "Milk", "nutrient uptake", " herbage production", " predictive clustering trees", " random forest", "predictive clustering trees", "Animals", "Lactation", "0401 agriculture", " forestry", " and fisheries", "Cattle", "Female", "Ireland", "random forest"]}, "links": [{"href": "https://doi.org/10.3168/jds.2019-16575"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Dairy%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3168/jds.2019-16575", "name": "item", "description": "10.3168/jds.2019-16575", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3168/jds.2019-16575"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-11-01T00:00:00Z"}}, {"id": "10.1039/d1ra03337a", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:18:28Z", "type": "Journal Article", "created": "2021-09-10", "title": "Exploring the performance of a functionalized CNT-based sensor array for breathomics through clustering and classification algorithms: from gas sensing of selective biomarkers to discrimination of chronic obstructive pulmonary disease", "description": "<p>Extensive application of clustering and classification algorithms shows the potential of a CNT-based sensor array in breathomics.</p>", "keywords": ["electronic nose", "Linear discriminant analysis", "Principal component analysis", "Breath analysis", "02 engineering and technology", "sensors", "Supported Vectror Machine", "01 natural sciences", "nanotubes", "Ammonia; Biomarkers; Carbon nanotubes; Classification (of information); Clustering algorithms; Molecules; Nitrogen oxides; Principal component analysis; Sulfur compounds; Support vector machines", "0104 chemical sciences", "3. Good health", "breathomics", "Chemistry", "SWCNTs", "COPD", "ta318", "e-nose", "0210 nano-technology", "ta215"]}, "links": [{"href": "https://iris.cnr.it/bitstream/20.500.14243/536855/1/RSC%20Adv._2021.pdf"}, {"href": "https://boa.unimib.it/bitstream/10281/517427/2/d1ra03337a.pdf%3b"}, {"href": "https://publicatt.unicatt.it/bitstream/10807/190102/1/d1ra03337a.pdf"}, {"href": "http://pubs.rsc.org/en/content/articlepdf/2021/RA/D1RA03337A"}, {"href": "https://doi.org/10.1039/d1ra03337a"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/RSC%20Advances", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1039/d1ra03337a", "name": "item", "description": "10.1039/d1ra03337a", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1039/d1ra03337a"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-01-01T00:00:00Z"}}, {"id": "10.1109/access.2019.2945084", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-05-30T16:19:12Z", "type": "Journal Article", "created": "2019-10-02", "title": "Data-Driven Structuring of the Output Space Improves the Performance of Multi-Target Regressors", "description": "The task of multi-target regression (MTR) is concerned with learning predictive models capable of predicting multiple target variables simultaneously. MTR has attracted an increasing attention within research community in recent years, yielding a variety of methods. The methods can be divided into two main groups: problem transformation and problem adaptation. The former transform a MTR problem into simpler (typically single target) problems and apply known approaches, while the latter adapt the learning methods to directly handle the multiple target variables and learn better models which simultaneously predict all of the targets. Studies have identified the latter group of methods as having competitive advantage over the former, probably due to the fact that it exploits the interrelations of the multiple targets. In the related task of multi-label classification, it has been recently shown that organizing the multiple labels into a hierarchical structure can improve predictive performance. In this paper, we investigate whether organizing the targets into a hierarchical structure can improve the performance for MTR problems. More precisely, we propose to structure the multiple target variables into a hierarchy of variables, thus translating the task of MTR into a task of hierarchical multi-target regression (HMTR). We use four data-driven methods for devising the hierarchical structure that cluster the real values of the targets or the feature importance scores with respect to the targets. The evaluation of the proposed methodology on 16 benchmark MTR datasets reveals that structuring the multiple target variables into a hierarchy improves the predictive performance of the corresponding MTR models. The results also show that data-driven methods produce hierarchies that can improve the predictive performance even more than expert constructed hierarchies. Finally, the improvement in predictive performance is more pronounced for the datasets with very large numbers (more than hundred) of targets.", "keywords": ["multi-target regression", "clustering", " feature ranking", " hierarchy", " multi-target regression", " target space", "target space", "hierarchy", "Electrical engineering. Electronics. Nuclear engineering", "Clustering", "feature ranking", "clustering", "TK1-9971"]}, "links": [{"href": "https://doi.org/10.1109/access.2019.2945084"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/IEEE%20Access", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1109/access.2019.2945084", "name": "item", "description": "10.1109/access.2019.2945084", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1109/access.2019.2945084"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-01-01T00:00:00Z"}}, {"id": "10.1109/ssci.2017.8280947", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:19:14Z", "type": "Journal Article", "created": "2018-02-07", "title": "Applying design knowledge and machine learning to scada data for classification of wind turbine operating regimes", "description": "Open AccessISBN:978-1-5386-2727-3", "keywords": ["supervised classi\ufb01cation", "data dimensionality reduction", "data clustering", "structural health monitoring", "13. Climate action", "11. Sustainability", "0202 electrical engineering", " electronic engineering", " information engineering", "unsupervised classi\ufb01cation", "02 engineering and technology", "7. Clean energy", "vibration data", "supervised classi\ufb01cation; unsupervised classi\ufb01cation; data clustering; data dimensionality reduction; vibration data; structural health monitoring"]}, "links": [{"href": "http://xplorestaging.ieee.org/ielx7/8267146/8280782/08280947.pdf?arnumber=8280947"}, {"href": "https://doi.org/10.1109/ssci.2017.8280947"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/2017%20IEEE%20Symposium%20Series%20on%20Computational%20Intelligence%20%28SSCI%29", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1109/ssci.2017.8280947", "name": "item", "description": "10.1109/ssci.2017.8280947", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1109/ssci.2017.8280947"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2017-11-01T00:00:00Z"}}, {"id": "10.1785/0120190121", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-05-30T16:20:41Z", "type": "Journal Article", "created": "2020-01-16", "title": "Variability of ETAS Parameters in Global Subduction Zones and Applications to Mainshock\u2013Aftershock Hazard Assessment", "description": "ABSTRACT<p>Megathrust earthquake sequences can impact buildings and infrastructure due to not only the mainshock but also the triggered aftershocks along the subduction interface and in the overriding crust. To give realistic ranges of aftershock simulations in regions with limited data and to provide time-dependent seismic hazard information right after a future giant shock, we assess the variability of the epidemic-type aftershock sequence (ETAS) model parameters in subduction zones that have experienced M\uffe2\uff89\uffa57.5 earthquakes, comparing estimates from long time windows with those from individual sequences. Our results show that the ETAS parameters are more robust if estimated from a long catalog than from individual sequences, given individual sequences have fewer data including missing early aftershocks. Considering known biases of the parameters (due to model formulation, the isotropic spatial aftershock distribution, and finite size effects of catalogs), we conclude that the variability of the ETAS parameters that we observe from robust estimates is not significant, neither across different subduction-zone regions nor as a function of maximum observed magnitudes. We also find that ETAS parameters do not change when multiple M\uffc2\uffa08.0\uffe2\uff80\uff939.0 events are included in a region, mainly because an M\uffc2\uffa09.0 sequence dominates the number of events in the catalog. Based on the ETAS parameter estimates in the long time period window, we propose a set of ETAS parameters for future M\uffc2\uffa09.0 sequences for aftershock hazard assessment (K0=0.04\uffc2\uffb10.02, \uffce\uffb1=2.3, c=0.03\uffc2\uffb10.01, p=1.21\uffc2\uffb10.08, \uffce\uffb3=1.61\uffc2\uffb10.29, d=23.48\uffc2\uffb118.17, and q=1.68\uffc2\uffb10.55). Synthetic catalogs created with the suggested ETAS parameters show good agreement with three observed M\uffc2\uffa09.0 sequences since 1965 (the 2004 M\uffc2\uffa09.1 Aceh\uffe2\uff80\uff93Andaman earthquake, the 2010 M\uffc2\uffa08.8 Maule earthquake, and the 2011 M\uffc2\uffa09.0 Tohoku earthquake).</p>", "keywords": ["earthquake clustering", "550", "13. Climate action", "seismic hazard", "earthquakes", "01 natural sciences", "aftershocks", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://doi.org/10.1785/0120190121"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Bulletin%20of%20the%20Seismological%20Society%20of%20America", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.1785/0120190121", "name": "item", "description": "10.1785/0120190121", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.1785/0120190121"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2020-01-14T00:00:00Z"}}, {"id": "10.3390/s22020645", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:22:01Z", "type": "Journal Article", "created": "2022-01-17", "title": "Clustering and Smoothing Pipeline for Management Zone Delineation Using Proximal and Remote Sensing", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>In precision agriculture (PA) practices, the accurate delineation of management zones (MZs), with each zone having similar characteristics, is essential for map-based variable rate application of farming inputs. However, there is no consensus on an optimal clustering algorithm and the input data format. In this paper, we evaluated the performances of five clustering algorithms including k-means, fuzzy C-means (FCM), hierarchical, mean shift, and density-based spatial clustering of applications with noise (DBSCAN) in different scenarios and assessed the impacts of input data format and feature selection on MZ delineation quality. We used key soil fertility attributes (moisture content (MC), organic carbon (OC), calcium (Ca), cation exchange capacity (CEC), exchangeable potassium (K), magnesium (Mg), sodium (Na), exchangeable phosphorous (P), and pH) collected with an online visible and near-infrared (vis-NIR) spectrometer along with Sentinel2 and yield data of five commercial fields in Belgium. We demonstrated that k-means is the optimal clustering method for MZ delineation, and the input data should be normalized (range normalization). Feature selection was also shown to be positively effective. Furthermore, we proposed an algorithm based on DBSCAN for smoothing the MZs maps to allow smooth actuating during variable rate application by agricultural machinery. Finally, the whole process of MZ delineation was integrated in a clustering and smoothing pipeline (CaSP), which automatically performs the following steps sequentially: (1) range normalization, (2) feature selection based on cross-correlation analysis, (3) k-means clustering, and (4) smoothing. It is recommended to adopt the developed platform for automatic MZ delineation for variable rate applications of farming inputs.</p></article>", "keywords": ["Agriculture and Food Sciences", "2. Zero hunger", "Spatial Analysis", "precision agriculture", "ACCURACY", "Chemical technology", "management zone delineation", "TP1-1185", "04 agricultural and veterinary sciences", "15. Life on land", "Article", "VARIABILITY", "Soil", "YIELD", "FUSION", "feature selection", "ATTRIBUTES", "clustering; feature selection; management zone delineation; precision agriculture", "Remote Sensing Technology", "Cluster Analysis", "0401 agriculture", " forestry", " and fisheries", "FIELD", "SOIL-PHOSPHORUS", "Algorithms", "clustering"]}, "links": [{"href": "http://www.mdpi.com/1424-8220/22/2/645/pdf"}, {"href": "https://www.mdpi.com/1424-8220/22/2/645/pdf"}, {"href": "https://doi.org/10.3390/s22020645"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Sensors", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10.3390/s22020645", "name": "item", "description": "10.3390/s22020645", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.3390/s22020645"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-01-14T00:00:00Z"}}, {"id": "10.5281/zenodo.14761002", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:23:49Z", "type": "Software", "title": "PyretoClustR (executable version)", "description": "PyretoClustR (executable version)  Distilling the Pareto Optimal Front into Actionable Insights  ##Highlights:    Open-access tool to cluster and visualize complex multi-dimensional Pareto solutions  Bridging the gap between decision and objective space through intuitive visualizations  Implements k-means and k-medoids clustering without expert knowledge  Uses frequency maps to display hotspot locations for spatial optimization problems  Increasing stakeholder accessibility to Pareto solutions   Program languages: Python, RSoftware availability (source code version): https://github.com/SydneyEWhite/Pareto_ClusteringSoftware availability (executable version, with python and libraries implemented): Zenodo (10.5281/zenodo.14761001)  ## Overview    This framework performs k-means and k-medoids clustering on a set of Pareto optimal solutions derived from a multi-objective optimization algorithm.  (Optional) A correlation matrix of the input variables is returned (the goal is to help users reduce the input variable count).  Before clustering occurs, the data is cast onto principal component axes and extreme solutions are handled (if desired).  The code iterates through different possible inputs for the number of clusters, the number of principal components, and the variables that define 'extreme solutions'.  After these iterations, the best solution, as defined by silhouette score, is visualized in several ways:    Representative solutions are plotted on up to 4 dimensions  Distributions of values within the clusters are plotted in a violin plot  (optional) Maps with the frequency of a trait can be plotted, if locational data (*.shp file) is provided     ## Background: executable version  Unlike the version of PyretoClustR available on GitHub (https://github.com/SydneyEWhite/PyretoClustR), this version on Zenodo represents a standalone version of PyretoClustR not requiring a Python installation. The python_files folder contains three executables and one folder called _internal. The executables can be run by clicking on them. The _internal folder is crucial for the standalone operation of the executables and should not be modified or deleted.  ## Example Data  The data provided in the input folder (pareto_and_scen_solutions.csv and the shapefiles) are part of the BiodivERsA project TALE (\u2018Towards multifunctional agricultural landscapes in Europe\u2019). This project optimized four objectives, Agricultural gross margin (AY), Breeding habitat (BH), Low flow (LF), Nitrate load (NL) and four different land use scenarios (SQ, BAU, EXT, INT) were distinguished in the decision space.\u00a0The config.ini has been adapted to run with this dataset. To run it with your own data please alter the respective input values as outlined in config.ini.  ## Directory Structure  project_root/||\u2500\u2500 README.md||\u2500\u2500 input/|\u00a0 |\u2500\u2500 config.ini|\u00a0 |\u2500\u2500 [your_input_data].csv| \u2514\u2500\u2500 [shape_files]||\u2500\u2500 python_files/|\u00a0 |\u2500\u2500 _internal|\u00a0 |\u2500\u2500 correlation_matrix.exe|\u00a0 |\u2500\u2500 kmeans.exe| \u2514\u2500\u2500 kmedoid.exe||\u2500\u2500 r_files/| \u2514\u2500\u2500 plot_frequency_maps.R|\u2514\u2500\u2500 output/ (populated once code is run)\u00a0\u00a0 |\u2500\u2500 correlation_matrix.csv (if run)\u00a0\u00a0 |\u2500\u2500 kmeans_data_w_clusters_representativesolutions.csv (created with kmeans.exe when Extreme Solutions are not handled)\u00a0\u00a0\u00a0 |\u2500\u2500 kmeans_data_w_clusters_representativesolutions_outliers.csv (created with kmeans.exe when Extreme Solutions are handled)\u00a0\u00a0 |\u2500\u2500 kmedoid_data_w_clusters_representativesolutions.csv (created with kmedoid.exe when Extreme Solutions are not handled)\u00a0\u00a0 |\u2500\u2500 kmedoid_data_w_clusters_representativesolutions_outliers.csv (created with kmedoid.exe when Extreme Solutions are handled)\u00a0 \u2514\u2500\u2500 freq_map_cluster_X.png (if run)", "keywords": ["Multi-objective optimization", "Pareto pruning", "Land management", "Pareto optimal data", "visualization", "clustering"], "contacts": [{"organization": "White, Sydney E., Witing, Felix, Wittekind, Cordula, Volk, Martin, Strauch, Michael,", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.14761002"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.14761002", "name": "item", "description": "10.5281/zenodo.14761002", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.14761002"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-01-29T00:00:00Z"}}, {"id": "10.5281/zenodo.15043864", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-05-30T16:23:56Z", "type": "Report", "title": "Post-processing & interactive visualisation of optimisation results. Deliverable D5.2 of the EU Horizon 2020 project OPTAIN", "description": "Deliverable report D5.2 of the EU Horizon 2020 Project OPTAIN (Grant agreement No. 862756)  Summary\u00a0Multi-objective optimisation is a powerful approach for generating a set of Pareto optimal design alternatives that decision-makers can evaluate in order to select the most-suitable configuration. In practice, however, selecting from a large number of Pareto optimal solutions can be daunting. The objective of this report is to enable researchers and stakeholders to assess the optimisation outputs produced in OPTAINs previous Task 5.2 in a structured manner, to render the results tangible and understandable, and to maximise their use for the subsequent stakeholder consultation.  This report describes the tool ParetoPick-R, including how to run it, its data input requirements and the processes it employs. ParetoPick-R allows (1) to make the complex optimisation outputs understandable through various intuitive visualisation techniques, including for the links between the objective space and the decision space of Natural/Small Water Retention Measures (NSWRM) implementation plans. (2) It implements a methodology for reducing the high number of solutions from the previous optimisation to a manageable number while reducing information loss, and (3) allows to perform an Analytical Hierarchy Process for stakeholders to assign priorities based on pairwise preferences in a structured manner.  This report is useful for researchers and stakeholders from OPTAIN and beyond working with complex optimisation problems who want to analyse their results in\u00a0a structured and meaningful way and render them actionable.", "keywords": ["CoMOLA", "combination", "SWAT+", "NSWRM", "post-processing", "H2020", "OPTAIN", "interactive visualisation", "stakeholder support", "R tool", "multi-objective optimization", "allocation", "Pareto solutions", "Analytical Hierarchy Process", "pareto pruning", "clustering"]}, "links": [{"href": "https://doi.org/10.5281/zenodo.15043864"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.15043864", "name": "item", "description": "10.5281/zenodo.15043864", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.15043864"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2025-03-18T00:00:00Z"}}, {"id": "1854/LU-8746428", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:26:24Z", "type": "Journal Article", "created": "2022-01-16", "title": "Clustering and Smoothing Pipeline for Management Zone Delineation Using Proximal and Remote Sensing", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>In precision agriculture (PA) practices, the accurate delineation of management zones (MZs), with each zone having similar characteristics, is essential for map-based variable rate application of farming inputs. However, there is no consensus on an optimal clustering algorithm and the input data format. In this paper, we evaluated the performances of five clustering algorithms including k-means, fuzzy C-means (FCM), hierarchical, mean shift, and density-based spatial clustering of applications with noise (DBSCAN) in different scenarios and assessed the impacts of input data format and feature selection on MZ delineation quality. We used key soil fertility attributes (moisture content (MC), organic carbon (OC), calcium (Ca), cation exchange capacity (CEC), exchangeable potassium (K), magnesium (Mg), sodium (Na), exchangeable phosphorous (P), and pH) collected with an online visible and near-infrared (vis-NIR) spectrometer along with Sentinel2 and yield data of five commercial fields in Belgium. We demonstrated that k-means is the optimal clustering method for MZ delineation, and the input data should be normalized (range normalization). Feature selection was also shown to be positively effective. Furthermore, we proposed an algorithm based on DBSCAN for smoothing the MZs maps to allow smooth actuating during variable rate application by agricultural machinery. Finally, the whole process of MZ delineation was integrated in a clustering and smoothing pipeline (CaSP), which automatically performs the following steps sequentially: (1) range normalization, (2) feature selection based on cross-correlation analysis, (3) k-means clustering, and (4) smoothing. It is recommended to adopt the developed platform for automatic MZ delineation for variable rate applications of farming inputs.</p></article>", "keywords": ["Agriculture and Food Sciences", "2. Zero hunger", "Spatial Analysis", "precision agriculture", "ACCURACY", "Chemical technology", "management zone delineation", "TP1-1185", "04 agricultural and veterinary sciences", "15. Life on land", "Article", "VARIABILITY", "Soil", "YIELD", "FUSION", "feature selection", "ATTRIBUTES", "clustering; feature selection; management zone delineation; precision agriculture", "Remote Sensing Technology", "Cluster Analysis", "0401 agriculture", " forestry", " and fisheries", "FIELD", "SOIL-PHOSPHORUS", "Algorithms", "clustering"]}, "links": [{"href": "http://www.mdpi.com/1424-8220/22/2/645/pdf"}, {"href": "https://www.mdpi.com/1424-8220/22/2/645/pdf"}, {"href": "https://doi.org/1854/LU-8746428"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Sensors", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "1854/LU-8746428", "name": "item", "description": "1854/LU-8746428", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/1854/LU-8746428"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2022-01-14T00:00:00Z"}}, {"id": "20.500.14243/532230", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-05-30T16:26:44Z", "type": "Journal Article", "created": "2024-07-06", "title": "Disentangling soil-based ecosystem services synergies, trade-offs, multifunctionality, and bundles: A case study at regional scale (NE Italy) to support environmental planning", "description": "The explicit use of ecosystem services (ESs) assessments has been called as a way to guide environmental decision making, yet the promise of the ES approach lies behind its potential. A way to consolidate the approach could be to introduce some aspects into the ESs assessments which might have been neglected so far. Such aspects are mainly: (1) a focus on the complex ESs relations (such as synergies and trade-offs) that can impact the supply of multiple SESs (soil ecosystem services), and (2) focus on potential drivers of SESs relations. We applied bivariate and multivariate approaches to SESs indicators derived from a solid pedological knowledge of the Emilia-Romagna study area in NE Italy. We focused on 7 SES: (1) habitat for soil organisms, (2) filtering and buffering capacity, (3) contribution to microclimate regulation, (4) carbon sequestration, (5) food provision potential, (6) water regulation, and (7) water storage capacity. These SESs were estimated through a combination of point observations, and pedotransfer functions (PTF) estimates spatialised over the area of interest with geostatistical simulation techniques. We found that SESs bivariate spatial relations could be categorised mainly in three types of patterns at regional scale, either: (1) synergistic SESs relations dominating at the region level, (2) trade-offs dominating, or (3) both kind of relations more or less equally frequent. Interestingly, in some cases the dominant regional SESs relation switched at a local level, and such switch was driven by soil properties. For the multivariate case (>2 SESs), two main results are highlighted. First, the combination of properties of some soils is so characteristic that they conform a single SESs bundle, as in the case of the rich SOM soils of alluvial origin in the NE of the region with low agricultural productivity, but high value in regulating SESs. Secondly, some SESs such as potential food provision and water regulation are more important than others to determine locations with high multi-services value at a regional level. This suggests that attention must be paid when ascribing high multi-services value locations as this is not independent of SESs relations. Overall, our results highlight the importance of soils in the potential supply of ESs and show that SESs relations are useful in the implementation of the concept in environmental assessments.", "keywords": ["2. Zero hunger", "Soil multifunctionality index", "Science", "Q", "15. Life on land", "Bivariate local indicators of spatial association", "01 natural sciences", "Soil-based ecosystem services relations", "6. Clean water", "Ecosystem services relations\u2019 drivers", "Pedo-landscapes; Soil multifunctionality index; Soil-based ecosystem services relations; Bivariate local indicators of spatial association; SES k-means clustering; Ecosystem services relations\u2019 drivers", "SES k-means clustering", "Pedo-landscapes", "0105 earth and related environmental sciences"]}, "links": [{"href": "https://iris.cnr.it/bitstream/20.500.14243/532230/1/1-s2.0-S0016706124001915-main.pdf"}, {"href": "https://doi.org/20.500.14243/532230"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Geoderma", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "20.500.14243/532230", "name": "item", "description": "20.500.14243/532230", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/20.500.14243/532230"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2024-08-01T00:00:00Z"}}, {"id": "10.5281/zenodo.3477551", "type": "Feature", "geometry": null, "properties": {"license": "Open Access", "updated": "2026-05-30T16:24:25Z", "type": "Report", "title": "Unsupervised local cluster-weighted Bagging the output from multiple stochastic simulators", "description": "Unsupervised local cluster-weighted Bagging the output from multiple stochastic simulators. The objective of this research<br> is to derive the local posterior predictive distribution when output from multiple (multi-fidelity) stochastic simulators are available.", "keywords": ["Model aggregation", "Model uncertainty", "Bagging", "Model combination", "multi-fidelity stochastic simulators", "Clustering", "Model Fusion"], "contacts": [{"organization": "Abdallah, Imad", "roles": ["creator"]}]}, "links": [{"href": "https://doi.org/10.5281/zenodo.3477551"}, {"rel": "self", "type": "application/geo+json", "title": "10.5281/zenodo.3477551", "name": "item", "description": "10.5281/zenodo.3477551", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10.5281/zenodo.3477551"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-01-01T00:00:00Z"}}, {"id": "10807/190102", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:26:03Z", "type": "Journal Article", "created": "2021-09-10", "title": "Exploring the performance of a functionalized CNT-based sensor array for breathomics through clustering and classification algorithms: from gas sensing of selective biomarkers to discrimination of chronic obstructive pulmonary disease", "description": "<?xml version='1.0' encoding='UTF-8'?><article><p>Extensive application of clustering and classification algorithms shows the potential of a CNT-based sensor array in breathomics.</p></article>", "keywords": ["electronic nose", "Linear discriminant analysis", "Chemistry", " Multidisciplinary", "Principal component analysis", "02 engineering and technology", "VOLATILE ORGANIC-COMPOUNDS", "sensors", "Supported Vectror Machine", "01 natural sciences", "nanotubes", "E-NOSE", "breathomics", "THIN-FILMS", "SWCNTs", "RANDOM NETWORKS", "COPD", "ta318", "e-nose", "ta215", "WALLED CARBON NANOTUBES", "Science & Technology", "Breath analysis", "SWCNT SENSOR", "34 Chemical sciences", "Ammonia; Biomarkers; Carbon nanotubes; Classification (of information); Clustering algorithms; Molecules; Nitrogen oxides; Principal component analysis; Sulfur compounds; Support vector machines", "0104 chemical sciences", "3. Good health", "Chemistry", "ROOM-TEMPERATURE", "AMMONIA SENSOR", "Physical Sciences", "NO2 DETECTION", "03 Chemical Sciences", "0210 nano-technology", "RESISTIVE SENSORS"]}, "links": [{"href": "https://iris.cnr.it/bitstream/20.500.14243/536855/1/RSC%20Adv._2021.pdf"}, {"href": "https://boa.unimib.it/bitstream/10281/517427/2/d1ra03337a.pdf%3b"}, {"href": "https://publicatt.unicatt.it/bitstream/10807/190102/1/d1ra03337a.pdf"}, {"href": "http://pubs.rsc.org/en/content/articlepdf/2021/RA/D1RA03337A"}, {"href": "https://doi.org/10807/190102"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/RSC%20Advances", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "10807/190102", "name": "item", "description": "10807/190102", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/10807/190102"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2021-01-01T00:00:00Z"}}, {"id": "11019/1960", "type": "Feature", "geometry": null, "properties": {"updated": "2026-05-30T16:26:05Z", "type": "Journal Article", "created": "2019-08-22", "title": "Using machine learning to estimate herbage production and nutrient uptake on Irish dairy farms", "description": "Nutrient management on grazed grasslands is of critical importance to maintain productivity levels, as grass is the cheapest feed for ruminants and underpins these meat and milk production systems. Many attempts have been made to model the relationships between controllable (crop and soil fertility management) and noncontrollable influencing factors (weather, soil drainage) and nutrient/productivity levels. However, to the best of our knowledge not much research has been performed on modeling the interconnections between the influencing factors on one hand and nutrient uptake/herbage production on the other hand, by using data-driven modeling techniques. Our paper proposes to use predictive clustering trees (PCT) learned for building models on data from dairy farms in the Republic of Ireland. The PCT models show good accuracy in estimating herbage production and nutrient uptake. They are also interpretable and are found to embody knowledge that is in accordance with existing theoretical understanding of the task at hand. Moreover, if we combine more PCT into an ensemble of PCT (random forest of PCT), we can achieve improved accuracy of the estimates. In practical terms, the number of grazings, which is related proportionally with soil drainage class, is one of the most important factors that moderates the herbage production potential and nutrient uptake. Furthermore, we found the nutrient (N, P, and K) uptake and herbage nutrient concentration to be conservative in fields that had medium yield potential (11 t of dry matter per hectare on average), whereas nutrient uptake was more variable and potentially limiting in fields that had higher and lower herbage production. Our models also show that phosphorus is the most limiting nutrient for herbage production across the fields on these Irish dairy farms, followed by nitrogen and potassium.", "keywords": ["2. Zero hunger", "nutrient uptake", "Nutrients", "04 agricultural and veterinary sciences", "15. Life on land", "Poaceae", "Animal Feed", "Diet", "Machine Learning", "herbage production", "Dairying", "Milk", "predictive clustering trees", "Animals", "Lactation", "0401 agriculture", " forestry", " and fisheries", "Cattle", "Female", "Ireland", "random forest"]}, "links": [{"href": "https://doi.org/11019/1960"}, {"rel": "related", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/Journal%20of%20Dairy%20Science", "name": "related record", "description": "related record", "type": "application/json"}, {"rel": "self", "type": "application/geo+json", "title": "11019/1960", "name": "item", "description": "11019/1960", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items/11019/1960"}, {"rel": "collection", "type": "application/json", "title": "Collection", "name": "collection", "description": "Collection", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main"}], "time": {"date": "2019-11-01T00:00:00Z"}}], "links": [{"rel": "self", "type": "application/geo+json", "title": "This document as GeoJSON", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=clustering&f=json", "hreflang": "en-US"}, {"rel": "alternate", "type": "text/html", "title": "This document as HTML", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=clustering&f=html", "hreflang": "en-US"}, {"rel": "collection", "type": "application/json", "title": "Collection URL", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main", "hreflang": "en-US"}, {"type": "application/geo+json", "rel": "first", "title": "items (first)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=clustering&", "hreflang": "en-US"}, {"rel": "last", "type": "application/geo+json", "title": "items (last)", "href": "https://repository.soilwise-he.eu/cat/collections/metadata:main/items?keywords=clustering&offset=19", "hreflang": "en-US"}], "numberMatched": 19, "numberReturned": 19, "distributedFeatures": [], "timeStamp": "2026-05-30T23:13:59.156496Z"}