Інше (ММАД)

Постійне посилання зібрання

https://ela.kpi.ua/handle/123456789/43460
У зібранні розміщено матеріали, які не належать до зазначених зібрань.

Переглянути

Перегляд Інше (ММАД) за Дата публікації

Перейти на індекс:
Зараз показуємо 1 - 3 з 3
  • Ескіз
    ДокументВідкритий доступ
    Спосіб побудови карт земного покриву великих за площею територій
    (Національний орган інтелектуальної власності. Державне підприємство «Український інститут інтелектуальної власності», 2022) Шелестов, Андрій Юрійович; Куссуль, Наталія Миколаївна; Яйлимов, Богдан Ялкапович; Чирков, Артем Валерійович
  • Ескіз
    ДокументВідкритий доступ
    Спосіб класифікації сільськогосподарських культур із використанням супутникових даних
    (Національний орган інтелектуальної власності. Державне підприємство «Український інститут інтелектуальної власності», 2022) Шелестов, Андрій Юрійович; Куссуль, Наталія Миколаївна; Яйлимов, Богдан Ялкапович; Чирков, Артем Валерійович
  • Ескіз
    ДокументВідкритий доступ
    iMERMAID Project: Integrating Satellite and In-Situ Data for Water Pollution Identification in the Mediterranean Basin
    (2025 Living Planet Symposium, 2025-06) Shelestov, Andrii; Drozd, Sofiia; Yailymov, Bogdan; Henitsoi, Pavlo; Donate, J.; Milián, M.; Rostan, J.; Sedano, R.
    Monitoring and improving water quality in the Mediterranean Sea is critical for preserving its unique biodiversity and addressing environmental challenges caused by anthropogenic activities. The Mediterranean Sea serves as a hotspot of ecological and economic importance, yet it faces significant threats from chemical pollution and overexploitation. As part of the Horizon Europe iMERMAID project, “Innovative Solutions for Mediterranean Ecosystem Remediation via Monitoring and Decontamination from Chemical Pollution”, our research focuses on advancing satellite-based methodologies to monitor key water quality indicators, specifically chlorophyll-a concentration and water turbidity. These indicators are vital for assessing biological productivity, phytoplankton dynamics, and water clarity, providing insights into the health of marine ecosystems. Traditional methods of measuring chlorophyll-a and water turbidity rely on costly and time-intensive laboratory analyses, which are limited in spatial and temporal scope. In contrast, satellite remote sensing offers an efficient and scalable solution for monitoring large and diverse marine areas. Leveraging satellite data from Sentinel-2, Sentinel-3, MODIS, and GCOM-C missions, the iMERMAID project develops integrated methodologies that combine spectral band analysis, in-situ measurements, and advanced machine learning models. Our research prioritizes improving the spatial and temporal resolution of chlorophyll-a and turbidity data to facilitate effective environmental management and pollution remediation strategies. A key innovation in our approach is the use of machine learning models, including Random Forest (RF) and multilayer perceptron (MLP), to analyze the non-linear relationships between spectral satellite data and in-situ chlorophyll-a measurements [1]. For example, regression models applied to GCOM-C and Aqua MODIS data achieved significant accuracy improvements, with RF models yielding an R² of 0.603 (RMSE = 0.008) for GCOM-C and R² of 0.74 (RMSE = 0.006) for Aqua MODIS. By downscaling coarse-resolution data (e.g., MODIS and GCOM-C) and upscaling Sentinel-3 data, we enhanced spatial resolution from 4 km to 300 m, making these models particularly effective for coastal regions where traditional methods often fail due to complex environmental conditions [2-4]. The integration of in-situ measurements allows us to validate and refine model predictions, ensuring consistency and accuracy in highly dynamic environments like the Mediterranean Sea. In addition to chlorophyll-a monitoring, the project addresses water turbidity by quantifying suspended particulate matter using satellite-derived spectral data. This parameter is critical for identifying sediment transport, pollution hotspots, and other ecological disturbances. By combining data-driven insights with high-resolution mapping capabilities, our methodologies enable timely detection of pollution and provide actionable information for marine ecosystem remediation. A crucial component of the project is the integration of maritime traffic density data to establish potential correlations between anthropogenic activity and water pollution. Using data from the EMODnet Map Viewer, historical navigation patterns in the Mediterranean Sea were analyzed, focusing on regions of high, medium, and low traffic densities. Areas of interest include regions with significant maritime activity, such as the southern Italian coast, the Balearic Islands, and northern Libya, alongside relatively lower-traffic zones like eastern Crete. This approach identifies pollution risks linked to shipping routes, oil spills, and port activities, complementing water quality assessments. Findings reveal a significant correlation between high maritime traffic areas, such as near Malta, and increased occurrences of oil spills, underscoring the role of vessel density in environmental contamination. Additionally, PRISMA images were utilized to explore potential links between satellite images and potential pollutants, such as water turbidity, to evaluate the utility of hyperspectral data for monitoring water quality indicators in the Mediterranean basin [5]. The results of the iMERMAID project demonstrate the potential of advanced remote sensing and data analytics to transform water quality monitoring in marine ecosystems. The integration of multiple data sources and machine learning techniques not only enhances monitoring accuracy but also supports sustainable management strategies. These methodologies are applicable to a wide range of use cases, including early warning systems for pollution, biodiversity conservation, and sustainable fisheries management. Acknowledgment This research was carried out within the Horizon Europe iMERMAID project “Innovative Solutions for Mediterranean Ecosystem Remediation via Monitoring and Decontamination from Chemical Pollution” (Grant agreement 101112824). References 1. P. Henitsoi, A. Shelestov, Transfer Learning Model for Chlorophyll-a Estimation Using Satellite Imagery, International Symposium on Applied Geoinformatics 2024 (ISAG2024), Wroclaw, Poland, 2024, p. 54. https://www.kongresistemi.com/panel/UserUploads/Files/ a3fe58047d50fbc.pdf. 2. B. Yailymov, N. Kussul, P. Henitsoi, A. Shelestov, Improving spatial resolution of chlorophyll-a in the Mediterranean Sea based on machine learning, Radioelectronic and Computer Systems 2024 (2024) 52–65. https://doi.org/10.32620/reks.2024.2.05. 3. H. Wu, W. Li, Downscaling land surface temperatures using a random forest regression model with multitype predictor variables, IEEE Access 7 (2019) 21904-21916. https://doi.org/10.1109/ACCESS.2019.2896241. 4. J. Peng, A. Loew, O. Merlin, N.E. Verhoest, A review of spatial downscaling of satellite remotely sensed soil moisture, Reviews of Geophysics 55 (2017) 341-366. https://doi.org/10.1002/2016RG000543 5. Amieva, Juan Francisco, Daniele Oxoli, and Maria Antonia Brovelli. "Machine and Deep Learning Regression of Chlorophyll-a Concentrations in Lakes Using PRISMA Satellite Hyperspectral Imagery." Remote Sensing 15.22 (2023): 5385. https://www.mdpi.com/2072-4292/15/22/5385