Autonomous robots operating under forest canopies need robust perception of trees and surrounding vegetation across varying seasonal conditions. Existing forestry datasets provide lidar or camera data with per-tree annotations, but none include co-registered 4D imaging radar – a modality of growing interest for its resilience to visual degradation, surface contamination, and vegetation occlusion. We introduce a multi-sensor forest dataset collected by a mobile robot equipped with a high-resolution FMCW imaging radar, lidar, RGB camera, IMU, and RTK-GNSS. The site was recorded in two sessions under contrasting vegetation states, and 3D cuboid annotations – including per-tree diameter estimates – provide shared semantic labels across all three perception modalities. Furthermore, we provide baseline results for semantic segmentation of the radar and lidar point clouds using MinkowskiUNet. Radar achieves IoU scores competitive with lidar for dominant classes (ground 91

Titanium dioxide nanoparticles (TiO₂NPs) are widely produced engineered nanomaterials with ongoing human exposure through consumer and occupational uses. Conventional in vitro assays often focus on cytotoxicity and may therefore overlook early or sublethal cellular perturbations. Here, we applied Cell Painting-based phenomics to resolve size-dependent sub-lethal phenotypic signatures of TiO2NP exposure in human HepG2 hepatocytes. Two TiO2NPs (<25 nm and <100 nm) were characterized by field emission scanning electron microscopy and evaluated following 24-hour exposure at five concentrations: 6.25, 12.5, 25, 50, and 100 µg/mL. Cell viability was assessed using the alamarBlue assay, and high-dimensional phenotypic profiles were generated using Cell Painting-based phenomics, including automated high-content imaging and CellProfiler-based feature extraction. TiO2NP exposure induced modest reductions in viability at the highest concentration, indicating limited acute cytotoxicity. In contrast, phenomic profiling revealed clear, concentration-dependent phenotypic perturbations for both size fractions, with markedly stronger and more consistent effects for the < 100 nm TiO2NPs. At 100 µg/mL, the < 100 nm TiO2NPs altered 50.9% of the measured phenotypic features, compared with 28.9% for the < 25 nm particles, with prominent contributions from endoplasmic reticulum-, actin/Golgi/plasma membrane-, mitochondria-, and RNA-associated features. Dimensionality reduction and correlation analyses confirmed reproducible, concentration-dependent phenotypic trajectories. Importantly, the TiO2NP-induced phenotypes were distinct from those induced by the reference chemical CA-074Me, which produced broad perturbations and served as a reference chemical to verify assay sensitivity and dynamic range. Overall, Cell Painting phenomics sensitively captures size-dependent, sublethal cellular phenotypes induced by TiO2NPs, supporting its value as a New Approach Methodology for nanosafety assessment beyond conventional viability endpoints.

Understanding how environmental chemicals and their mixtures perturb biological systems remains a central challenge in ecotoxicology, particularly when translating complex in vitro responses into interpretable mechanistic insight. Here, we establish an integrated multi-omics framework combining Cell Painting-based phenomics with comprehensive metabolomics to resolve complementary layers of cellular perturbation in fish liver cell models. Using well-characterized and environmentally ubiquitous legacy compounds as reference perturbagens under non-cytotoxic conditions, we systematically captured structural (phenotypic) and functional (metabolic) responses to single- and mixture-exposure conditions. Across exposure scenarios, phenomic and metabolomic profiles revealed partial non-convergence, including species-specific response and layer-specific sensitivity. Importantly, integrative analysis uncovered direct pathway-to-phenotype associations, a key advance in the functional interpretation of high-content phenotypic signatures. Coordinated shifts in carbohydrate, amino acid, lipid, and nucleotide metabolism were directly associated with defined subcellular phenotypes, including altered mitochondrial organization and nuclear texture. In mixture exposures, integrated signatures further allowed the resolution of overlapping and dominant response patterns, demonstrating how multi-layered profiling improves the interpretability of complex chemical interactions beyond single-omics approaches. Together, this systems-level approach advances the mechanistic interpretation of high-content phenotypic data and establishes a scalable framework for integrating phenomics and metabolomics in New Approach Methodologies (NAMs), supporting mechanism-based, animal-free assessment of chemicals.

Nanoplastics have recently been detected in human liver tissue, raising concerns about their potential impact on liver function. However, early hepatocyte responses associated with nanoplastics exposure remain poorly understood. Here, we combined high-throughput Cell Painting-based phenomics, untargeted metabolomics, and Seahorse mitochondrial functional assay to investigate the effects of 100 nm polystyrene nanoplastics on human HepaRG hepatocytes, a surrogate for primary human hepatocytes. At the tested concentrations (6.25-100 µg/mL), exposure did not induce overt cytotoxicity, enabling assessment of early sublethal cellular responses. Phenomics revealed widespread subcellular perturbations, with 16.4% of the measured phenotypic features significantly altered. Mitochondria-associated features represented the dominant altered phenotypic signature, showing pronounced changes in granularity, texture, and radial distribution, alongside alterations in endoplasmic reticulum- and cytoskeleton-associated features. Untargeted metabolomics of intracellular metabolites and the extracellular secretome revealed metabolic alterations, characterized by changes consistent with altered β-oxidation, lipid handling, membrane stress, and central carbon metabolism, including changes in the tricarboxylic acid (TCA) cycle and amino acid catabolism. Pathway analysis identified the TCA cycle as one of the most significantly affected pathways (FDR = 0.028). Integrated phenomic-metabolomic analysis revealed strong correlations between mitochondrial phenotypic features and metabolites involved in lipid and energy metabolism, indicating a coordinated structural-metabolic response to polystyrene nanoplastics exposure. Functional assessment using Seahorse assay showed reduced basal and maximal respiration and decreased ATP-linked O2 consumption. Together, these findings provide evidence that 100 nm polystyrene nanoplastics elicit early mitochondria-associated phenotypic, metabolic, and functional responses prior to overt cytotoxicity under the tested conditions. They also highlight the value of phenomic-metabolomic-functional integration for profiling sublethal nanotoxicological responses and guiding future targeted mechanistic studies.

Effective early warning systems for aquatic contamination require monitoring strategies capable of detecting subtle, long-term shifts in mixture-driven biological activity. Suspended particulate matter (SPM) serves as a carrier and reservoir for complex contaminant mixtures, facilitating their transport and persistence in aquatic systems, yet systematic toxicological time series for archived SPM remain scarce. Regulatory monitoring predominantly targets Priority Substances and River Basin Specific Pollutants, leaving the temporal trends of particle-associated mixture toxicity largely unresolved. Leveraging 18 years (2005-2022) of cryogenically archived annual SPM composites from the Rhine River, we conducted a spatiotemporal effect-based assessment integrating receptor-mediated effects, oxidative stress analysis and untargeted Cell Painting phenomics. This integrated toolbox enabled evaluation of pathway-specific responses and multi-compartment cellular perturbations associated with particle-bound contaminant mixtures. Polar SPM-associated chemicals elicited oxidative stress response and caused endocrine disruption through estrogen receptor α (ERα) activation and androgen receptor inhibition (anti-AR). Trend analysis showed spatiotemporal variation along the river, with statistically increasing trends of oxidative stress and anti-AR activity over time at Koblenz, driven by polar chemicals. Both polar and non-polar SPM extracts activated the aryl hydrocarbon receptor (AhR), indicating presence of compounds capable of triggering xenobiotic response pathways. Several subcellular compartments were affected, with mitochondrial features being among the most affected. These findings demonstrate that SPM-associated chemicals elicit diverse toxicological effects by acting on several receptors and impacting diverse cellular structures. Combining targeted and phenomics-based effect approaches provided comprehensive mechanistic insights and valuable information to support the early warning systems for chemical contamination in aquatic environments.

Metal additive manufacturing (AM) relies on alloy feedstock powders that may come into contact with the workers' skin during handling, yet skin-relevant data on metal release and biological reactivity remain limited. Here, we assessed the cutaneous bioactivity of the fine particle fraction of four gas-atomized Fe-based AM powders (316L stainless steel, Fe-powder A, and tooling steels B and C). Powders were sieved to <10 μm and characterized by scanning electron microscopy and X-ray photoelectron spectroscopy before and after incubation in artificial sweat (ASW). Metal biodissolution was quantified in ASW and keratinocyte culture medium using atomic absorption spectrophotometry. Cellular responses were evaluated in HaCaT keratinocytes using Cell Painting-based phenomics and multiplex cytokine/chemokine profiling and in an ex vivo full-thickness human skin explant model, including superficial barrier disruption, IL-8/CXCL8 quantification, and histological assessment. ASW exposure induced marked shifts in the outermost surface composition across powders, indicating sweat-driven surface transformation. Biodissolution was low and medium-dependent, with Fe dominating the release in ASW, and with an overall metal release remaining limited in cell culture medium. In HaCaT cells, MCP-1/CCL2, IL-6, and IL-8/CXCL8 were quantifiable but showed no significant changes following powder exposure. Cell Painting revealed subtle, shared phenotypic signatures, primarily involving mitochondrial-associated features, without evidence of broad cellular stress. In the ex vivo skin model, AM powders did not increase IL-8/CXCL8 secretion, the particles remained localized to the skin surface without detectable penetration, and coexposure with Staphylococcus epidermidis did not enhance bacterial colonization or induce inflammation. To the best of our knowledge, this is the first study that applies a human skin explant model to evaluate dermal responses to metal AM powders. Overall, the tested AM powders showed low short-term cutaneous reactivity under skin-relevant conditions, providing human-relevant evidence to inform occupational risk assessment in AM environments.

Per- and polyfluoroalkyl substances and nanoplastics frequently co-occur in environmental matrices, yet the effects of co-exposure on cellular responses upon ingestion are poorly understood. Here, we exposed human intestinal Caco-2 cells to perfluorooctanesulfonic acid, nanoplastics, and their combination. Cell painting-based phenomics was used to map phenotypic alterations across subcellular structures, and untargeted metabolomics using ultra-high-performance liquid chromatography coupled to quadrupole time-of-flight mass spectrometry was employed to assess metabolic changes. Results show that perfluorooctanesulfonic acid predominantly affected the actin cytoskeleton, Golgi apparatus, and plasma membrane, while nanoplastics primarily targeted mitochondria. Combined exposure disrupted the endoplasmic reticulum, RNA, and mitochondria. Perfluorooctanesulfonic acid reduced levels of carnitines, free fatty acids, nucleotides, and sugars, whereas nanoplastics inhibited ceramides, triglycerides, sphingomyelins, and additional free fatty acids. Combined exposure produced a metabolic profile resembling that of nanoplastics, with specific differences attributed to perfluorooctanesulfonic acid. Overall, nanoplastics appear as the main drivers of the co-exposure effects.

As the volume of plastic waste from electrical and electronic equipment (WEEE) continues to rise, a significant portion is disposed of in the environment, with only a small fraction being recycled. Both disposal and recycling pose unknown health risks that require immediate attention. Existing knowledge of WEEE plastic toxicity is limited and mostly relies on epidemiological data and association studies, with few insights into the underlying toxicity mechanisms. Therefore, this study aimed to perform comprehensive chemical screening and mechanistic toxicological assessment of WEEE plastic-associated chemicals. Chemical analysis, utilizing suspect screening based on high-resolution mass spectrometry, along with quantitative target chemical analysis, unveiled numerous hazardous compounds including polyaromatic compounds, organophosphate flame retardants, phthalates, benzotriazoles, etc. Toxicity endpoints included perturbation of morphological phenotypes using the Cell Painting assay, inflammatory response, oxidative stress, and endocrine disruption. Results demonstrated that WEEE plastic chemicals altered the phenotypes of the cytoskeleton, endoplasmic reticulum, and mitochondria in a dose-dependent manner. In addition, WEEE chemicals induced inflammatory responses in resting macrophages and altered inflammatory responses in lipopolysaccharide-primed macrophages. Furthermore, WEEE chemicals activated the nuclear factor erythroid 2-related factor 2 (Nrf2) pathway, indicating oxidative stress, and the aryl hydrocarbon receptor (AhR). Endocrine disruption was also observed through the activation of estrogenic receptor-α (ER-α) and the induction of anti-androgenic activity. The findings show that WEEE plastic-associated chemicals exert effects in multiple subcellular sites, via different receptors and mechanisms. Thus, an integrated approach employing both chemical and toxicological methods is essential for comprehensive assessment of the toxicity mechanisms and cumulative chemical burden of WEEE plastic-associated chemicals.

Existing research has proven difficult to understand the interplay between upstream signaling events during NLRP3 inflammasome activation. Additionally, events downstream of inflammasome complex formation such as cytokine release and pyroptosis can exhibit variation, further complicating matters. Cell Painting has emerged as a prominent tool for unbiased evaluation of the effect of perturbations on cell morphological phenotypes. Using this technique, phenotypic fingerprints can be generated that reveal connections between phenotypes and possible modes of action. To the best of our knowledge, this was the first study that utilized Cell Painting on human THP-1 macrophages to generate phenotypic fingerprints in response to different endogenous and exogenous NLRP3 inflammasome triggers and to identify phenotypic features specific to NLRP3 inflammasome complex formation. Our results demonstrated that not only can Cell Painting generate morphological fingerprints that are NLRP3 trigger-specific but it can also identify cellular fingerprints associated with NLRP3 inflammasome activation.

PFAS are ubiquitous industrial chemicals with known adverse health effects, particularly on the liver. The liver, being a vital metabolic organ, is susceptible to PFAS-induced metabolic dysregulation, leading to conditions such as hepatotoxicity and metabolic disturbances. In this study, we investigated the phenotypic and metabolic responses of PFAS exposure using two hepatocyte models, HepG2 (male cell line) and HepaRG (female cell line), aiming to define phenotypic alterations, and metabolic disturbances at the metabolite and pathway levels. The PFAS mixture composition was selected based on epidemiological data, covering a broad concentration spectrum observed in diverse human populations. Phenotypic profiling by Cell Painting assay disclosed predominant effects of PFAS exposure on mitochondrial structure and function in both cell models as well as effects on F-actin, Golgi apparatus, and plasma membrane-associated measures. We employed comprehensive metabolic characterization using liquid chromatography combined with high-resolution mass spectrometry (LC-HRMS). We observed dose-dependent changes in the metabolic profiles, particularly in lipid, steroid, amino acid and sugar and carbohydrate metabolism in both cells as well as in cell media, with HepaRG cell line showing a stronger metabolic response. In cells, most of the bile acids, acylcarnitines and free fatty acids showed downregulation, while medium-chain fatty acids and carnosine were upregulated, while the cell media showed different response especially in relation to the bile acids in HepaRG cell media. Importantly, we observed also nonmonotonic response for several phenotypic features and metabolites. On the pathway level, PFAS exposure was also associated with pathways indicating oxidative stress and inflammatory responses. Taken together, our findings on PFAS-induced phenotypic and metabolic disruptions in hepatocytes shed light on potential mechanisms contributing to the broader comprehension of PFAS-related health risks.

Object detection is crucial in diverse autonomous systems like surveillance, autonomous driving, and driver assistance, ensuring safety by recognizing pedestrians, vehicles, traffic lights, and signs. However, adverse weather conditions such as snow, fog, and rain pose a challenge, affecting detection accuracy and risking accidents and damage. This clearly demonstrates the need for robust object detection solutions that work in all weather conditions. We employed three strategies to enhance deep learning-based object detection in adverse weather: training on real-world all-weather images, training on images with synthetic augmented weather noise, and integrating object detection with adverse weather image denoising. The synthetic weather noise is generated using analytical methods, GAN networks, and style-transfer networks. We compared the performance of these strategies by training object detection models using real-world all-weather images from the BDD100K dataset and for assessment employed unseen real-world adverse weather images. Adverse weather denoising methods were evaluated by denoising real-world adverse weather images and the results of object detection on denoised and original noisy images were compared. We found that the model trained using all-weather real-world images performed best, while the strategy of doing object detection on denoised images performed worst.

Gas Distribution Mapping (GDM) is a valuable tool for monitoring the distribution of gases in a wide range of applications, including environmental monitoring, emergency response, and industrial safety. While GDM is actively researched in the scope of gas-sensitive mobile robots (Mobile Robot Olfaction), there is a potential for broader applications utilizing sensor networks. This study aims to address the lack of deep learning approaches in GDM and explore their potential for improved mapping of gas distributions. In this paper, we introduce Gas Distribution Decoder (GDD), a learning-based GDM method. GDD is a deep neural network for spatial interpolation between sparsely distributed sensor measurements that was trained on an extensive data set of realistic-shaped synthetic gas plumes based on actual airflow measurements. As access to ground truth representations of gas distributions remains a challenge in GDM research, we make our data sets, along with our models, publicly available. We test and compare GDD with state-of-the-art models on synthetic and real-world data. Our findings demonstrate that GDD significantly outperforms existing models, demonstrating a 35% improvement in accuracy on synthetic data when measured using the Root Mean Squared Error over the entire distribution map. Notably, GDD appears to have superior capabilities in reconstructing the edges and characteristic shapes of gas plumes compared to traditional models. These potentials offer new possibilities for more accurate and efficient environmental monitoring, and we hope to inspire other researchers to explore learning-based GDM.

Adverse weather (rain, snow, and fog) can negatively impact computer vision tasks by introducing noise in sensor data; therefore, it is essential to recognize weather conditions for building safe and robust autonomous systems in the agricultural and autonomous driving/drone sectors. The performance degradation in computer vision tasks due to adverse weather depends on the type of weather and the intensity, which influences the amount of noise in sensor data. However, existing weather recognition datasets often lack intensity labels, limiting their effectiveness. To address this limitation, we present VARG, a novel video-based weather recognition dataset with weather intensity labels. The dataset comprises a diverse set of short video sequences collected from various social media platforms and videos recorded by the authors, processed into usable clips, and categorized into three major weather categories, rain, fog, and snow, with three intensity classes: absent/no, moderate, and high. The dataset contains 6742 annotated clips from 1079 videos, with the training set containing 5159 clips and the test set containing 1583 clips. Two sets of annotations are provided for training, the first set to train the models as a multi-label weather intensity classifier and the second set to train the models as a multi-class classifier for three weather scenarios. This paper describes the dataset characteristics and presents an evaluation study using several deep learning-based video recognition approaches for weather intensity prediction.

Tire wear particles (TWP) stand out as a major contributor to microplastic pollution, yet their environmental impact remains inadequately understood. This study delves into the cocktail effects of TWP leachates, employing molecular, cellular, and organismal assessments on diverse biological models. Extracted in artificial seawater and analyzed for metals and organic compounds, TWP leachates revealed the presence of polyaromatic hydrocarbons and 4-tert-octylphenol. Exposure to TWP leachates (1.5 to 1000 mg peq L-1) inhibited algae growth and induced zebrafish embryotoxicity, pigment alterations, and behavioral changes. Cell painting uncovered pro-apoptotic changes, while mechanism-specific gene-reporter assays highlighted endocrine-disrupting potential, particularly antiandrogenic effects. Although heavy metals like zinc have been suggested as major players in TWP leachate toxicity, this study emphasizes water-leachable organic compounds as the primary causative agents of observed acute toxicity. The findings underscore the need to reduce TWP pollution in aquatic systems and enhance regulations governing highly toxic tire additives.

Additive manufacturing (AM) or industrial 3D printing uses cutting-edge technologies and materials to produce a variety of complex products. However, the effects of the unintentionally emitted AM (nano)particles (AMPs) on human cells following inhalation, require further investigations. The physicochemical characterization of the AMPs, extracted from the filter of a Laser Powder Bed Fusion (L-PBF) 3D printer of iron-based materials, disclosed their complexity, in terms of size, shape, and chemistry. Cell Painting, a high-content screening (HCS) assay, was used to detect the subtle morphological changes elicited by the AMPs at the single cell resolution. The profiling of the cell morphological phenotypes, disclosed prominent concentration-dependent effects on the cytoskeleton, mitochondria, and the membranous structures of the cell. Furthermore, lipidomics confirmed that the AMPs induced the extensive membrane remodeling in the lung epithelial and macrophage co-culture cell model. To further elucidate the biological mechanisms of action, the targeted metabolomics unveiled several inflammation-related metabolites regulating the cell response to the AMP exposure. Overall, the AMP exposure led to the internalization, oxidative stress, cytoskeleton disruption, mitochondrial activation, membrane remodeling, and metabolic reprogramming of the lung epithelial cells and macrophages. We propose the approach of integrating Cell Painting with metabolomics and lipidomics, as an advanced nanosafety methodology, increasing the ability to capture the cellular and molecular phenotypes and the relevant biological mechanisms to the (nano)particle exposure.

Due to their exceptional properties and cost effectiveness, polyamides or nylons have emerged as widely used materials, revolutionizing diverse industries, including industrial 3D printing or additive manufacturing (AM). Powder-based AM technologies employ tonnes of polyamide microplastics to produce complex components every year. However, the lack of comprehensive toxicity assessment of particulate polyamides and polyamide-associated chemicals, especially in the light of the global microplastics crisis, calls for urgent action. This study investigated the physicochemical properties of polyamide-12 microplastics used in AM, and assessed a number of toxicity endpoints focusing on inflammation, immunometabolism, genotoxicity, aryl hydrocarbon receptor (AhR) activation, endocrine disruption, and cell morphology. Specifically, microplastics examination by means of field emission scanning electron microscopy revealed that work flow reuse of material created a fraction of smaller particles with an average size of 1-5 µm, a size range readily available for uptake by human cells. Moreover, chemical analysis by means of gas chromatography high-resolution mass spectrometry detected several polyamide-associated chemicals including starting material, plasticizer, thermal stabilizer/antioxidant, and migrating slip additive. Even if polyamide particles and chemicals did not induce an acute inflammatory response, repeated and prolonged exposure of human primary macrophages disclosed a steady increase in the levels of proinflammatory chemokine Interleukin-8 (IL-8/CXCL-8). Moreover, targeted metabolomics disclosed that polyamide particles modulated the kynurenine pathway and some of its key metabolites. The p53-responsive luciferase reporter gene assay showed that particles per se were able to activate p53, being indicative of a genotoxic stress. Polyamide-associated chemicals triggered moderate activation of AhR and elicited anti-androgenic activity. Finally, a high-throughput and non-targeted morphological profiling by Cell Painting assay outlined major sites of bioactivity of polyamide-associated chemicals and indicated putative mechanisms of toxicity in the cells. These findings reveal that the increasing use of polyamide microplastics may pose a potential health risk for the exposed individuals, and it merits more attention.

To better understand the dynamics in hazardous environments, gas distribution mapping aims to map the gas concentration levels of a specified area precisely. Sampling is typically carried out in a spatially sparse manner, either with a mobile robot or a sensor network and concentration values between known data points have to be interpolated. In this paper, we investigate sequential deep learning models that are able to map the gas distribution based on a multiple time step input from a sensor network. We propose a novel hybrid convolutional LSTM - transpose convolutional structure that we train with synthetic gas distribution data. Our results show that learning the spatial and temporal correlation of gas plume patterns outperforms a non-sequential neural network model.

We evaluate improvement in the performance of the optical transmission systems operating with the continuous nonlinear Fourier spectrum by the artificial neural network equalisers installed at the receiver end. We propose here a novel equaliser designs based on bidirectional long short-term memory (BLSTM) gated recurrent neural network and compare their performance with the equaliser based on several fully connected layers. The proposed approach accounts for the correlations between different nonlinear spectral components. The application of BLSTM equaliser leads to a 16x improvement in terms of bit-error rate (BER) compared to the non-equalised case. The proposed equaliser makes it possible to reach the data rate of 170 Gbit/s for one polarisation conventional nonlinear Fourier transform (NFT) based system at 1000 km distance. We show that our new BLSTM equalisers significantly outperform the previously proposed scheme based on a feed-forward fully connected neural network. Moreover, we demonstrate that by adding a 1D convolutional layer for the data pre-processing before BLSTM recurrent layers, we can further enhance the performance of the BLSTM equaliser, reaching 23x BER improvement for the 170 Gbit/s system over 1000 km, staying below the 7% forward error correction hard decision threshold (HD-FEC).