Cyanobacterial Harmful Algal Blooms (cyanoHABs) represent significant threats to human health and environmental sustainability. These blooms, characterized by the rapid proliferation of toxic species, can release harmful toxins into aquatic environments, with severe consequences for ecosystems and human populations. Traditional research on cyanoHABs faces several limitations, including the lack of standardized detection methods, environmental variability, and low awareness of the associated risks. Most studies rely on conventional laboratory techniques, which are often resource-intensive and not widely accessible. Additionally, the complex dynamics of cyanoHABs, influenced by factors such as temperature, nutrients, and bloom evolution, make it difficult to establish consistent regulatory and monitoring frameworks. This paper presents a new integrated strategy that combines advanced technologies (remote sensing, in-situ multispectral analysis, mass spectrometry) with bio-monitoring and bio-tracking. This interdisciplinary approach improves the monitoring of cyanoHAB spread, tracks bioaccumulation in the food chain, and provides timely warnings for public health protection. The case study focuses on the Campi Flegrei area, an active volcanic region in Southern Italy, where Lake Avernus, a volcanic lake, has experienced periodic cyanobacterial blooms. This region also hosts mussel aquaculture and recreational activities. Remote sensing allowed the tracking of the 2022 bloom from the lake to the sea, reaching a mussel farm along the coast. Rapid detection and quantification of anabaenopeptins in bivalves enabled timely alerts to local authorities, prompting an assessment of contamination risks. The study demonstrates how the integration of remote sensing and molecular analysis enhances environmental monitoring by providing real-time, high-resolution data. This approach supports a better understanding of bloom dynamics, bioaccumulation, and impacts on the food chain, informing risk management and regulatory strategies. The research highlights the value of combining advanced technologies to improve the management of cyanoHAB-related risks, protecting both human health and ecosystem sustainability.

Persistent environmental contaminants pose a substantial threat to agricultural ecosystems, necessitating robust methodologies for evaluation and mitigation of their effects. This study establishes a direct correlation between environmental impact assessment and sustainable agricultural management, showing the feasibility of using multi-scale bioindication and remote sensing technology to effectively monitor the impact of soil pollution in agricultural ecosystems. The key values of this research lie in the ability of the described approach to integrate advanced proximal/remote sensing and in situ analyses to assess the effects of soil contamination on bioindicators, providing a comprehensive framework for evaluating environmental stressors. The proposed methodology was tested on maize (Zea mays L.) and employs unmanned aerial vehicle-based multi/hyperspectral and thermal imaging to detect vegetation stress indicators such as normalized difference vegetation index and thermal anomalies. The interdisciplinary approach adopted in this research significantly enhances the value of the study by not only focusing on isolated results but also validating the entire methodological workflow. This cross-disciplinary integration ensures that the workflow retains its relevance across various environmental scenarios, enriching the results’ applicability and providing a robust framework for ongoing studies. The research objective of this work was achieved through experimental tests on soils contaminated with heavy metals and organic pollutants exceeding regulatory thresholds that revealed distinct spectral and thermal signatures, demonstrating the efficacy of integrated sensing for detailed environmental assessment. The findings underscore the role of bioindicators as pivotal tools for bridging environmental monitoring and sustainability by providing actionable insights into pollutant impacts and their cascading effects on ecosystems and human health. By equipping stakeholders with precise contamination detection tools, this study aims to provide a methodological approach to expand environmental impact assessment frameworks, supporting sustainable decision-making and risk management. These methodologies contribute to aligning agricultural practices with broader sustainability objectives, ensuring resilient food systems and ecosystem health.

Environmental monitoring systems require robust uncertainty quantification for effective decision-making in complex ecological processes. Harmful algal blooms represent a critical challenge where prediction uncertainty directly impacts resource allocation and response timing, yet current remote sensing-based prediction systems provide only deterministic classifications without confidence measures. This gap between algorithmic predictions and actionable risk assessment limits operational utility for stakeholders managing water quality under varying risk tolerances. This study developed a transferable probabilistic forecasting framework integrating Sentinel-2 multispectral imagery with quantile regression and ensemble machine learning to generate continuous confidence indicators for cyanobacteria density prediction, demonstrated through its application to Lake Okeechobee, Florida. The methodology combines spectral indices extracted from Sentinel-2 data with XGBoost for quantile regression at 0.05, 0.50, and 0.95 probability levels, and LightGBM for multi-horizon temporal forecasting. Sentinel-2’s 13 spectral bands spanning visible to shortwave infrared wavelengths, combined with its 5-day revisit frequency provide a spectrally rich and temporally dense input space that is well-suited to gradient boosting methods such as XGBoost, which can exploit complex nonlinear interactions among spectral features to distinguish cyanobacterial signatures from background water constituents. LightGBM achieved mean absolute percentage errors of 2.9% for 10-day forecasts and 5.7% for 20-day forecasts, outperforming conventional regression models. The framework generates 90% prediction intervals that enable reliable risk classifications for operational bloom management. This approach bridges the gap between satellite-based algal bloom detection and actionable decision-making by quantifying predictive uncertainty, representing a shift from binary classifications to probability-based environmental monitoring systems that accommodate varying stakeholder risk tolerances in water quality management applications.

Environmental monitoring of freshwater ecosystems faces significant challenges in detecting illicit wastewater discharges, which often remain unrecognized due to their intermittent nature and limited spatial footprint. This study presents a novel integrated strategy combining satellite remote sensing, Unmanned Aerial Vehicle (UAV)-based proximal sensing, and in situ measurements to enhance pollution detection in vulnerable aquatic environments. The methodology was applied to Lake Avernus (Italy), a volcanic lake historically affected by eutrophication and toxic cyanobacterial blooms. Landsat 8–9 thermal analysis revealed no detectable anomalies, reflecting the limitations of its coarse spatial resolution. Sentinel-2 multispectral imagery was then analyzed through spectral indices, band ratios, and reflectance signatures, revealing localized variations in surface reflectance and spatial heterogeneity in water optical properties. These satellite-derived anomalies guided targeted high-resolution UAV surveys. UAV-based thermal imaging revealed an elevated-temperature zone along the adjacent shoreline. In situ field screening flagged a candidate chemical anomaly at this location. The hierarchical framework demonstrates that satellite screening effectively identifies areas of concern, while UAV thermal imaging enables high-resolution localization of features invisible to satellite sensors, and in situ measurements provide essential ground-truth validation. This replicable, low-cost methodology offers a powerful tool for early warning, surveillance, and sustainable management of sensitive freshwater ecosystems.

Cyanobacterial harmful algal blooms threaten freshwater quality, ecosystem stability, and public health, creating a need for spatially extensive monitoring tools that complement in situ observations. This study evaluates whether Sentinel-2 multispectral imagery can be used to identify a recurrent spectral pattern associated with Planktothrix rubescens blooms in two volcanic lakes in Central Italy (Albano and Vico). Sentinel-2 Level-1C data were processed with C2RCC to retrieve water-leaving reflectance and compared with microscopy-based observations across 13 acquisition dates (eight bloom and five no-bloom events). At the event level, bloom and no-bloom conditions were spectrally distinguishable. Six of eight bloom spectra showed a green-band peak at 560 nm and a pronounced increase from blue (443–490 nm) to green wavelengths. The B3/B1 ratio was 3.04 under bloom conditions versus 1.12 under no-bloom conditions, while B3/B2 was 1.77 versus 0.76 (both p < 0.05). Within bloom events, the blue-to-green ratio was not significantly correlated with cell density, indicating that the pattern is more suitable for bloom detection than abundance estimation. The recurrent pattern was formalized as a simple Type A criterion and further assessed using cosine similarity. These results support Sentinel-2 as a proof-of-concept screening tool for P. rubescens-dominated blooms, pending broader validation.