Vasileios Linardos

Machine learning approaches to wildfire spread prediction are constrained by the lack of standardized, multi-source, spatiotemporal datasets that fuse terrain, weather, and fire-state information into a single ML-ready format. We present WildfireCube, a reproducible event-centric pipeline and methodology for constructing dense fourth-order spatiotemporal tensors of shape (T, C, H, W) at 30 m spatial and 3 h temporal resolution. Following the analysis-ready data convention established in the Earth Observation community, the pipeline fuses four open data sources: the Copernicus GLO-30 Digital Elevation Model for static terrain derivatives, ERA5-Land reanalysis for hourly weather forcing, Sentinel-2 Level-2A imagery for spectral vegetation and burn-severity indices, and NASA FIRMS active-fire hotspot detections for fire-state reconstruction via ordinary kriging. The resulting 13-channel normalized tensor separates causal drivers into three physically motivated groups: static landscape controls (elevation, slope, aspect, fuel load), dynamic atmospheric forcings (wind components, temperature, precipitation), and evolving fire state (fire-front mask, burn severity, fractional burn, observation confidence). A physics-informed normalization framework maps all channels to bounded ranges using fixed physical constants rather than sample statistics, ensuring cross-event comparability and exact invertibility. We demonstrate the pipeline on 13 wildfire events across the United States, Canada, and Greece (2017–2023), producing a processed catalog exceeding 300 GB compressed and spanning a 14-fold range in burned area, a 27 °C range in mean temperature, and different fire regimes. Event tensors are stored in chunked Zarr archives with Zstandard compression, achieving a 2.58× compression ratio. As future work, the pipeline will be applied to a 40-event target catalog projected to exceed 2 TB of raw data, providing the multi-regime diversity and scale required for training robust deep learning models for spatiotemporal wildfire prediction.

Wildfire events pose significant threats to global ecosystems, with Greece experiencing substantial economic losses exceeding EUR 1.7 billion in 2023 alone, generating immediate financial burdens while contributing to atmospheric carbon dioxide emissions and accelerating climate change effects. This study presents a group of classification models for Greece wildfires utilizing historical datasets spanning 2017 to 2021, incorporating satellite-derived remote sensing data, topographical characteristics, and meteorological observations through a multimodal methodology that integrates satellite imagery processing with traditional numerical data analysis techniques. The framework encompasses multiple deep learning architectures, specifically implementing four standalone models comprising two convolutional neural networks optimized for spatial image processing and long short-term memory networks designed for temporal pattern recognition, extending classification approaches by incorporating visual satellite data alongside established numerical datasets to enable the system to leverage both spatial visual patterns and temporal numerical trends. The implementation employs an ensemble methodology that combines individual model classifications through systematic voting mechanisms, harnessing the complementary strengths of each architectural approach to deliver enhanced predictive capabilities and demonstrate the substantial benefits achieved through multimodal data integration for comprehensive wildfire risk assessment applications.

In this research, we explore the use of Large Language Models (LLMs) and clustering techniques to automate the structuring and labeling of disaster-related social media content. With a gathered dataset comprising millions of tweets related to various disasters, our approach aims to transform unstructured and unlabeled data into a structured and labeled format that can be readily used for training machine learning algorithms and enhancing disaster response efforts. We leverage LLMs to preprocess and understand the semantic content of the tweets, applying several semantic properties to the data. Subsequently, we apply clustering techniques to identify emerging themes and patterns that may not be captured by predefined categories, with these patterns surfaced through topic extraction of the clusters. We proceed with manual labeling and evaluation of 10,000 examples to evaluate the LLMs’ ability to understand tweet features. Our methodology is applied to real-world data for disaster events, with results directly applicable to actual crisis situations.

In this research, we explore the use of Large Language Models (LLMs) and clustering techniques to automate the structuring and labeling of disaster-related social media con-tent. With a gathered dataset comprising millions of tweets related to various disasters, our approach aims to transform unstructured and unlabeled data into a structured and labeled format that can be readily used for training machine learning algorithms and en-hancing disaster response efforts. We leverage LLMs to preprocess and understand the semantic content of the tweets, applying several semantic properties to the data, followed by the application of clustering techniques to identify emerging themes and patterns that may not be captured by predefined categories and are surfaced through topic extraction of the clusters. We proceed with manual labeling and evaluation of 10,000 examples to evaluate the LLMs' ability to understand tweet features. Our methodology is applied to re-al-world data for disaster events, with results directly applicable to actual crisis situations.

Recent years include the world’s hottest year, while they have been marked mainly, besides the COVID-19 pandemic, by climate-related disasters, based on data collected by the Emergency Events Database (EM-DAT). Besides the human losses, disasters cause significant and often catastrophic socioeconomic impacts, including economic losses. Recent developments in artificial intelligence (AI) and especially in machine learning (ML) and deep learning (DL) have been used to better cope with the severe and often catastrophic impacts of disasters. This paper aims to provide an overview of the research studies, presented since 2017, focusing on ML and DL developed methods for disaster management. In particular, focus has been given on studies in the areas of disaster and hazard prediction, risk and vulnerability assessment, disaster detection, early warning systems, disaster monitoring, damage assessment and post-disaster response as well as cases studies. Furthermore, some recently developed ML and DL applications for disaster management have been analyzed. A discussion of the findings is provided as well as directions for further research.

Purpose: Developments in Industry 4.0 technologies and Artificial Intelligence (AI) have enabled data-driven manufacturing. Predictive maintenance (PdM) has therefore become the prominent approach for fault detection and diagnosis (FD/D) of induction motors (IMs). The maintenance and early FD/D of IMs are critical processes, considering that they constitute the main power source in the industrial production environment. Machine learning (ML) methods have enhanced the performance and reliability of PdM. Various deep learning (DL) based FD/D methods have emerged in recent years, providing automatic feature engineering and learning and thereby alleviating drawbacks of traditional ML based methods. This paper presents a comprehensive survey of ML and DL based FD/D methods of IMs that have emerged since 2015. An overview of the main DL architectures used for this purpose is also presented. A discussion of the recent trends is given as well as future directions for research.Design/methodology/approach: A comprehensive survey has been carried out through all available publication databases using related keywords. Classification of the reviewed works has been done according to the main ML and DL techniques and algorithmsFindings: DL based PdM methods have been mainly introduced and implemented for IM fault diagnosis in recent years. Novel DL FD/D methods are based on single DL techniques as well as hybrid techniques. DL methods have also been used for signal preprocessing and moreover, have been combined with traditional ML algorithms to enhance the FD/D performance in feature engineering. Publicly available datasets have been mostly used to test the performance of the developed methods, however industrial datasets should become available as well. Multi-agent system (MAS) based PdM employing ML classifiers has been explored. Several methods have investigated multiple IM faults, however, the presence of multiple faults occurring simultaneously has rarely been investigated.Originality/value: The paper presents a comprehensive review of the recent advances in PdM of IMs based on ML and DL methods that have emerged since 2015.