For the purpose of this study, an instance segmentation pipeline based on the YOLOv26 model was used for automated detection, classification, visualization, and quantitative analysis of palynofacies in black shales from the Toarcian Oceanic Anoxic Event (T-OAE). With the help of the dataset which contained 564 microscopic images and 2964 annotations in four classes amorphous organic matter (AOM), phytoclasts, palynomorphs, and background, the model achieved a mean average precision at 0.5 IoU threshold (mAP@0.5) of 94.1% on segmentation masks, with aggregate precision of 93.1% and recall of 92.1%. At the individual class level, the model achieved a mAP of 98.7% for palynomorphs. The mAP of palynomorphs was 98.7%.Beyond object detection, the system automates palynofacies analysis by combining model predictions with a custom built Python based analytical engine. This engine algorithmically extracts Hue, Saturation, and Value (HSV) color features from segmented particles to determine an objective Thermal Alteration Index (TAI) maturity score. Simultaneously, the system calculates the relative surface area percentages of each organic component to generate automated Tyson ternary plot diagrams. This end to end pipeline converts raw optical microscopy images into high-throughput, reproducible quantitative data, significantly accelerating palynological workflow times while eliminating subjective visual estimation bias.
Context. The number of meteor observation networks has expanded rapidly due to declining hardware costs, enabling professional and amateur groups to contribute substantial datasets. An accurate data reduction remains challenging, however, because variations in processing methods can significantly affect the trajectory reconstructions and orbital interpretations. Aims. Our goal is to thoroughly compare four professionally produced meteor data-reduction pipelines (FRIPON, DFN, WMPL, and AMOS) by reprocessing FRIPON Geminid observations. This analysis can be used for a comparison with other data-reduction methods. Methods. We processed a dataset of 5 84 Geminid fireballs observed by FRIPON between 2016 and 2023. The single-station astrometric data were converted into the global fireball exchange (GFE) standard format for uniform processing. We assessed variations in trajectory, velocity, and radiant and orbital element calculations in the pipelines and compared them to previously published Geminid measurements. Results. The radiant and velocity solutions provided by the four data-reduction pipelines are all within the range of previously published values, with some nuances. Particularly, the radiants estimated by WMPL, DFN, and AMOS are nearly identical, but FRIPON reports a systematic shift in right ascension (−0.3°) that is caused by an improper handling of the precession. Additionally, the FRIPON data-reduction pipeline also tends to overestimate the initial velocity (+0.3 km s−1), which is due to the deceleration model used as the velocity solver. The FRIPON velocity method relies on a well-constrained deceleration profile, but for the Geminids, many are low-deceleration events, which leads to an overestimation of the initial velocity. At the other end of the spectrum, the DFN tends to predict lower velocities, in particular, for poorly observed events. This velocity shift vanishes for the DFN when we considered Geminids alone with at least three observations or more, however. The primary difference identified in the analysis concerns the velocity uncertainties. Although all four pipelines achieved similar residuals between their trajectories and observations, their velocity uncertainties varied systematically. WMPL outputs the lowest values, followed by AMOS, FRIPON, and DFN. Conclusions. From this Geminid case study, we find that the default FRIPON data-reduction methods, while adequate for meteoritedropping events, are not optimal for all cases. Specifically, FRIPON tends to overestimate velocities for low-deceleration events because the fit is less strongly constrained, and the nominal radiants are not correctly output in J2000. On the other hand, the other data-reduction pipelines (DFN, WMPL, and AMOS) produce consistent results, provided that the observational data are sufficiently robust, that is, more than ∼50 data points from at least three observers. A key takeaway is that we need to reevaluate how the velocity uncertainties are estimated. Our results show that the uncertainty estimates vary systematically in different pipelines, even though the goodness-of-fit statistics is generally similar. The increasing availability of impact observations from varying sources (radar, video, photo, seismic, infrasound, satellite, telescopic, etc.) calls for greater collaboration and transparency in data-reduction practices.
Tax authorities face growing volumes of filings and payments and must manage procedural non-compliance (e.g., late filing, late payment and the accumulation of tax arrears) with limited administrative capacity. Many existing machine learning (ML) and artificial intelligence (AI) applications in tax administration rely on binary outcomes, which limits severity-based prioritisation and the targeting of low-cost interventions. This study develops a multiclass prediction model for administrative tax compliance severity using Slovakia's public tax reliability index, which classifies companies into three categories based on regulator-defined administrative criteria. Using only financial statement ratios and governance indicators, we evaluate nine classifiers and five resampling techniques for class imbalance. Gradient boosting models (XGBoost and CatBoost) perform best, reaching an OvR AUC-ROC above 96% for 1-year forecasts, with modest declines for 2- and 3-year horizons. SHAP explanations indicate that smaller boards and indicators consistent with liquidity constraints and tax-payment pressure are associated with higher-severity administrative classes. The proposed workflow offers a transferable framework for multiclass, long-horizon compliance risk prediction and can support proactive case management (e.g., targeted reminders and payment facilitation, including payment plans, and debt prioritisation) in advance of the regulator's semi-annual updates; it may also provide researchers with a potential early-warning label of administrative compliance frictions that could be examined in relation to financial distress.
In this work, we evaluated the biological and geological contributions to the formation and preservation of the oxidation zones in & Lcaron;ubietov & aacute;-Podlipa, & Lcaron;ubietov & aacute;-Sv & auml;todu & scaron;n & aacute;, Poniky-Farbi & scaron;te and & Scaron;pania Dolina-Piesky. This case study highlights the importance of the biological contribution to weathering processes of ore deposits. It may be extended to other similar sites in order to assess the magnitude of biological input. Using U-Pb dating, secondary minerals from Podlipa were dated to 22 +/- 6 and 19 +/- 4 Ma (Lower Miocene). At this time, this region experienced deep weathering under a humid and warm climate and tectonic quiescence. The isotopic (O, H) composition of the secondary minerals shows that they formed from Lower Miocene meteoric water under surface temperatures. The delta C-13(PDB) values in malachite (-19 to -17 parts per thousand) document a biological source of C, from soil CO2. The delta O-18(VSMOW) values of the PO4 groups in the accessory fluorapatite in the host rocks (1.8 +/- 1.7 parts per thousand, 1 sigma) and pseudomalachite in the oxidation zone (12.1 +/- 2.9 parts per thousand, 1 sigma) show substantial biological P input into the oxidation zone. A biogenic source of both C and P agrees well with the palaeoclimatic constraints based on the radiometric dating. The oxidation zones at Podlipa, Sv & auml;todu & scaron;n & aacute; and Farbi & scaron;te are contemporaneous with kaolin crusts in the same area; they were all preserved only where they were covered by young (14-12 Ma) volcanic rocks and exposed recently by erosion. The other oxidation zones in the Tatric and Veporic units, if they existed, were destroyed by the Pliocene uplift of these units. The oxidation zone at Piesky is younger, dated to 2.5 Ma (Early Pleistocene) when the global temperatures in interglacials were similar to the present, decreasing in glacials by similar to 4 degrees C. The different climate at this time is manifested by scattered delta C-13 values, reflecting surface temperature and vegetation fluctuations at this time.
Ninety-two localities from the Daroca-Calamocha area (central Spain), spanning seven million years, have yielded a high diversity of Miocene erinaceids, comprising six species of Galericinae (Galerix remmerti, Galerix symeonidisi, Galerix exilis, Parasorex sp. Parasorex voesendorfensis, Lantanotherium sp.) and four species of Erinaceinae ('Amphechinus' baudeloti, Atelerix cf. depereti, 'Mioechinus' sp. Erinaceinae gen. et sp. indet). We identify the transition from Galerix remmerti to G. exilis during Local Zone C (MN4) and discuss the differences between G. exilis and G. symeonidisi in Spain. Detailed comparisons of the intraspecific variability of Galerix species lead to a new phylogeny of the genus that supports a strong basal dichotomy and two distinct dispersal events into Europe during the Early Miocene. The record of Parasorex sp. and Lantanotherium sp. in the Iberian Peninsula is constrained to the middle-late Aragonian transition and is correlated with unstable climatic conditions. The latest Aragonian and Vallesian material from Nombrevilla 2, Carrilanga 1, and Pedregueras 2A, previously identified as Parasorex socialis, is reattributed to Parasorex voesendorfensis.
