Aug 2026· Remote Sensing· Vol 18, pp. 2669· 0 citations· 41 references
Abstract
Geotechnical hazards such as landslides, subsidence, slope instability, and infrastructure deformation threaten rapidly urbanising and environmentally stressed regions worldwide, intensifying the need for scalable and intelligent monitoring systems capable of continuously observing complex Earth surface dynamics. Although multisensor remote sensing fusion has substantially expanded the observational capabilities of modern geotechnical monitoring through the integration of Synthetic Aperture Radar (SAR), optical imagery, Light Detection and Ranging (LiDAR), and environmental data, existing fusion pipelines remain subject to several well-documented constraints, including weak semantic alignment, limited temporal reasoning, and poor transferability across heterogeneous environmental conditions. This review synthesises the emerging transition from conventional sensor-centric fusion toward intelligent geospatial monitoring architectures centred on deep multimodal representation learning, transformer-based temporal reasoning, self-supervised learning, and geospatial foundation models. Particular emphasis is placed on how recent architectures are designed to better preserve coherent spatial, temporal, and contextual environmental relationships within unified latent representation spaces rather than through downstream handcrafted integration. The review further examines the growing role of multimodal transformers, masked autoencoders, contrastive learning, and large-scale geospatial foundation models in enabling scalable environmental reasoning, adaptive multimodal learning, and transferable geospatial intelligence across sensing modalities and geographic domains. Finally, remaining challenges involving uncertainty, explainability, computational scalability, and environmental generalisation are discussed alongside future research directions involving continual learning, physics-aware artificial intelligence, and autonomous geotechnical monitoring systems. Together, the reviewed literature suggests that multimodal Earth observation is evolving from passive environmental sensing toward adaptive geospatial intelligence systems capable of scalable hazard reasoning and autonomous environmental understanding.
Artificial intelligence (AI) increasingly supports subsurface characterization by integrating heterogeneous geophysical, geochemical, and spatial data. However, existing studies remain fragmented across disciplines and often leave unresolved questions about cross-modal physical coupling, fusion design, uncertainty propagation, validation integrity, and decision relevance. This review synthesizes AI-based multimodal fusion methods for mineral exploration, geothermal systems, geological CO₂ storage, and radioactive-waste disposal. It organizes the field along orthogonal dimensions: the representation stage of fusion; the mechanism and strength of physical coupling; the training signal and model objective; the integration of prior knowledge; the output type; and the intended scope of generalization. The review critically examines scale and support mismatch, spatial autocorrelation, modality dominance, uncertain rock-physics and geochemical relationships, topological and conservation constraints in generative models, and validation leakage. It also distinguishes aleatoric, epistemic, methodological, and ontological uncertainty and considers how these uncertainties propagate through multimodal workflows. Emerging priorities include cross-modally coupled physics-informed learning, constrained generative simulation, foundation-model representations, and risk-aware monitoring. By clarifying conceptual distinctions and evidence limitations, the review provides a rigorous roadmap for developing interpretable, uncertainty-aware, and decision-relevant multimodal subsurface AI.
H. Namazi, M. F. Sulaima, Ondrej Krejcar et al.· Environmental Earth Sciences· 0 citations
The global wildfire crisis requires comprehensive early detection strategies to reduce environmental, economic, and societal impacts. This review systematically evaluates remote sensing (RS) technologies employed in early wildfire detection, classifying them into satellite systems, aerial platforms, and ground‐based sensors. Subsequently, it critically examines detection methodologies, which include image classification, object detection, semantic segmentation, and emergent approaches utilizing large language models (LLMs). Analysis reveals that deep learning (DL) significantly improves detection accuracy; however, its effectiveness is limited by resolution constraints, especially in the context of detecting smaller fires. As an advanced extension of the DL paradigm, LLMs built upon transformer‐based architectures complement conventional DL methods by enabling contextual reasoning over multimodal inputs, thereby bridging the gap between raw visual feature extraction and high‐level semantic interpretation. In this regard, LLMs demonstrate considerable potential in synthesizing complex, heterogeneous datasets, thereby enhancing the integration of diverse remote sensing data. Despite these advancements, substantial challenges remain, including limitations in spatial and temporal resolution, environmental interference, and complexities associated with data processing. To mitigate these obstacles, prospective research endeavors should prioritize strengthening algorithmic robustness, refining data fusion methodologies, and establishing real‐time monitoring systems. By integrating existing methodologies and outlining key challenges, this study aims to guide future academic inquiry in enhancing wildfire risk mitigation strategies and improving early detection frameworks.
This article is categorized under:
Fundamental Concepts of Data and Knowledge > Big Data Mining
Technologies > Machine Learning
Technologies > Artificial Intelligence
Muneeb Raza, Xu-Cheng Yin, Touqeer Abbas et al.· WIREs Data Mining and Knowle...· 0 citations
Monitoring mining infrastructure is essential for ensuring operational safety and minimizing environmental risks associated with subsidence and structural instability. However, existing approaches often rely on single-source data, limiting their ability to capture complex and dynamic deformation processes. This study proposes an integrated multi-source monitoring framework that combines satellite-based Interferometric Synthetic Aperture Radar (InSAR), unmanned aerial vehicle (UAV) observations, ground-based measurements, and advanced digital analysis techniques. The methodology integrates multi-temporal InSAR time-series analysis with high-resolution UAV-derived data within a unified geospatial environment, supported by machine learning models for pattern recognition and prediction. The results reveal clear spatial and temporal deformation patterns in mining areas, with subsidence rates up to −50 mm/year in active extraction zones. Time-series analysis shows that deformation evolves nonlinearly, underscoring the importance of continuous monitoring for early risk detection. Validation against ground-based measurements confirms the reliability of the proposed approach, with root-mean-square error (RMSE) values in the range of 1–2 mm. The integration of multi-source data significantly improves monitoring accuracy and enables detailed analysis across different spatial scales. Furthermore, the application of machine learning techniques enhances predictive capability, allowing identification of potential instability zones before critical failure occurs.
Nurbek Abdixamidov, Maksuda Juraeva, Nafosat Meyliyeva et al.· Geotechnology, Mining and Ra...· 0 citations
The increasing unpredictability of weather patterns due to climate change necessitates robust, real-time flood monitoring systems for high-risk disaster-prone cities. Existing monitoring approaches primarily utilize satellite-based remote sensing, in-situ telemetry such as ultrasonic level detection and precipitation gauges, or convolutional neural networks trained on heterogeneous, crowd-sourced internet imagery. However, the effectiveness of these systems is limited by Severe Inundation Visual Paucity (SIVP), which refers to the scarcity of historical visual data depicting extreme, high-stage inundation events required for training deep learning classifiers. To address this data gap, this study presents Semantically-Guided Hydro-Synthesis (SGHS), a novel generative framework that employs latent diffusion models to synthesize photorealistic, weather-variant inundation overlays on fixed CCTV perspectives. Unlike prior generative flood-data approaches that operate from satellite or aerial perspectives, produce numerical depth grids, or rely on site-agnostic image priors, SGHS is uniquely conditioned on a site-specific UAV-reconstructed 3D digital twin, employs prompt-driven domain randomization across six atmospheric parameters, and is governed by a formalized ten-level anthropometric severity taxonomy that enables graduated, decision-relevant severity estimation rather than binary flood/no-flood inference. By using SGHS to generate a balanced dataset encompassing escalating flood severities and diverse meteorological conditions, the SIVP constraint is directly mitigated, thereby enriching the training distribution with essential high-stage instances absent from historical records. Empirical results are reported across three evaluation tiers with disaggregated test-set provenance and across ten random seeds with mean and standard deviation. On the Tier-1 sim-to-real holdout at Levels 0 through 3, the raw-data baseline achieves Accuracy <inline-formula> <tex-math notation="LaTeX">$=0.1990~\pm ~0.0146$ </tex-math></inline-formula> and F<inline-formula> <tex-math notation="LaTeX">$1=0.2170~\pm ~0.0160$ </tex-math></inline-formula>, while the SGHS-augmented curated classifier achieves Accuracy <inline-formula> <tex-math notation="LaTeX">$=0.7700~\pm ~0.0099$ </tex-math></inline-formula> and F<inline-formula> <tex-math notation="LaTeX">$1=0.7825~\pm ~0.0108$ </tex-math></inline-formula> (Wilcoxon signed-rank, p < 0.002). Matched-augmentation controls applying focal loss, balanced sampling, and standard photometric augmentation to the raw partition reach only F<inline-formula> <tex-math notation="LaTeX">$1=0.3120~\pm ~0.0211$ </tex-math></inline-formula>, isolating the contribution of generative augmentation. Tier-3 results at Levels 6 through 9 (F<inline-formula> <tex-math notation="LaTeX">$1=0.6685$ </tex-math></inline-formula>–0.7135) are explicitly reframed as evidence of internal consistency within the simulation domain rather than as a claim of sim-to-real operational transfer, since extreme-severity ground truth remains structurally absent from the observational record. These results indicate that site-specific, semantically-guided generative augmentation provides a measurable and statistically significant improvement over both raw-data and algorithmic class-imbalance baselines, addressing hydrological data scarcity for vision-based disaster response systems.
Rocelle Andrea S. Belandres, Miguel Antonio M. Sumulong, John Anthony C. Jose· IEEE Access· 0 citations
Effective flood monitoring is critical for minimizing the impacts of flood disasters on populations and infrastructure. Yet reliable remote sensing across extensive and environmentally diverse regions remains challenging, as most segmentation algorithms lack the generalisation capacity required for large-scale application, while annotated flood data are scarce and unevenly distributed. This study presents an end-to-end multimodal framework for Russian Federation territories sustainable flood monitoring and damage assessment based on synthetic aperture radar data, multispectral imagery, and digital elevation models with their derivatives, forming a 21-channel input. Using a self-collected multimodal dataset covering seven Russian regions, two strategies for water surface detection under limited data conditions were compared: a supervised U-Net++ model and the self-supervised AnySat architecture pre-trained and fine-tuned for the segmentation task. Under the data conditions of this study, supervised learning proved more effective, while the AnySat-based approach offered greater stability and retains advantages for settings where larger unlabelled data or missing modalities at inference are expected. The best flood area predictions were used to estimate flood impact in urban areas in terms of the area affected, material damage, casualties, and ecological and agricultural impact. The estimations were conducted following the official methodology of the Russian Ministry of Emergency Situations. Applied to the 2019 Tulun flood, the obtained results closely matched official assessments, except for material damage, due to the open-source databases usage. The results demonstrate the potential of deep learning and multimodal satellite data integration for scalable, reliable flood monitoring across diverse environmental and data-limited conditions.
I. Novikov, S. Illarionova, Ruslan B. Dzharkinov et al.· arXiv.org· 0 citations
Flooding remains one of the most damaging climate‐related hazards globally, yet flood remote sensing has historically developed largely along sensor‐specific pathways. This review addresses the need for a systematic and decision‐oriented synthesis of how space‐borne remote sensing has evolved toward integrated flood monitoring and disaster risk reduction frameworks. Moving beyond conventional sensor inventories, the study examines sensor integration pathways, temporal evolution, and decision relevance. Four research questions guide the analysis: (RQ1) how space‐borne sensors have been applied and advanced in flood studies, (RQ2) how multi‐sensor fusion architectures have evolved, (RQ3) what limitations persist, and (RQ4) what future directions are emerging. Following PRISMA guidelines, 176 peer‐reviewed studies published between 2001 and 2024 were systematically analysed. Quantitative synthesis indicates a marked post‐2018 increase in multi‐sensor approaches, alongside a growing share of studies adopting fusion frameworks. Synthetic Aperture Radar (SAR)‐centred integration systems represent a dominant share of recent applications; most commonly combined with precipitation products and digital elevation models. Analytical synthesis further indicates that SAR plays a central role in flood detection, while precipitation and topographic data provide key hydrological drivers and terrain constraints. These findings indicate a transition from static flood mapping toward process‐aware, multi‐sensor, and algorithm‐driven flood intelligence systems. The review also highlights the growing role of artificial intelligence and cloud‐based platforms in enabling scalable, near‐real‐time flood analysis. It concludes that future flood resilience increasingly depends on the coordinated integration of space‐borne observations, advanced analytics, and operational decision‐support architectures. This synthesis provides a unifying framework to guide next‐generation flood monitoring and disaster risk reduction under accelerating climate change.
R. Kemarau, Nurfashareena Muhamad, Aida Soraya Shamsuddin et al.· Journal of Flood Risk Manage...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
