Матеріали конференцій, семінарів і т.п. (ММАД)

Постійне посилання зібрання

https://ela.kpi.ua/handle/123456789/43453

У зібранні розміщено матеріали, опубліковані у збірниках, що видані за результатами конференцій, семінарів, конгресів, круглих столів тощо.

Переглянути

Зараз показуємо 1 - 20 з 45

Відкритий доступ
Assessing Ukraine`s solar power potential: a comprehensive analysis using satellite data and fuzzy logic
(Assembled by Conference Management Services, Inc., 2024) Drozd, Sofiia; Kussul, Nataliia
This study evaluates the land suitability for the placement of solar power stations in Ukraine, utilizing satellite data on climate factors (Global Horizontal Irradiance, temperature, precipitation, wind speed), topography (elevation, slope), and land use. Fuzzy logic, pairwise comparisons, and weighted linear combination methods were utilized to develop a high-resolution (100 m) land suitability map for the installation of solar power plants. The results show that more than half (54.5%) of Ukraine’s territory has a high suitability score (exceeding 0.65) for solar power stations, particularly in the southern and eastern regions, such as Odessa, Kherson, Mykolaiv, Zaporizhia, Donetsk, and Crimea. Only 10.68% of the land has a suitability score less than 0.6, and 18.18% is deemed absolutely unsuitable (with a score of 0, due to land cover), primarily located in the western and northern parts of the country. This indicates that Ukraine has significant potential for green energy production. The study provides an effective and useful tool for decision-making on the optimal location of solar power facilities in Ukraine.
Відкритий доступ
Flooded areas monitoring below the Kakhovka Dam based on machine learning and satellite data
(Assembled by Conference Management Services, Inc., 2024) Yailymov, Bohdan; Yailymova, Hanna; Kussul, Nataliia; Shelestov, Andrii
This study analyzed the flooding under the Kakhovka Dam in Ukraine using satellite remote sensing data after the dam was destroyed on June 6, 2023. Maps of the water bodies were created before and after the flooding disaster using Sentinel-1, Sentinel-2, and Landsat-9 imagery. A random forest classifier was used to map the flooded areas. As of June 9, 2023, the total flooded area below the Kakhovka Dam was 47,330 hectares, impacting agricultural lands, forests, grasslands and human settlements. The flooding also affected areas along the Ingulets River, leading to inundation of croplands located close to the river banks which could impact water quality. The disappearance of water canals that were used for irrigation of croplands is also analyzed, showing the far-reaching agricultural impacts of this flooding event. This study demonstrates the utility of satellite remote sensing for rapid monitoring and quantification of the impacts from dam failure flooding disasters.
Відкритий доступ
A multimodal dataset for forest damage detection and machine learning
(Assembled by Conference Management Services, Inc., 2024) Yailymova, Hanna; Yailymov, Bohdan; Salii, Yevhenii; Kuzin, Volodymyr; Shelestov, Andrii; Kussul, Nataliia
Accurately recognizing areas of forest damage is crucial for planning, monitoring recovery processes, and evaluating environmental impact following catastrophic events. The widespread accessibility of satellite data, coupled with the ongoing advancement of machine and deep learning techniques, as well as computer vision methods, renders the implementation of these approaches in the automatic detection of damaged forest areas highly difficult. Nevertheless, a significant challenge in this regard is the scarcity of labeled data. The purpose of this article is to provide a useful and reliable dataset for territory of Ukraine for scientists, conservationists, foresters and other stakeholders involved in monitoring forest damage and its consequences for forest ecosystems and their services. The created dataset contains 18 locations with a time series of satellite images with a resolution of up to 10 m per pixel across Ukraine, as well as weather information. The data was collected from the Copernicus Sentinel-1,2 satellite missions as well as based on ERA-5 weather information.
Відкритий доступ
Features’ Selection for Forest State Classification Using Machine Learning on Satellite Data
(Assembled by Conference Management Services, Inc., 2024) Salii, Yevhenii; Kuzin, Volodymyr; Lavreniuk, Alla; Kussul, Nataliia; Shelestov, Andrii
This paper discusses the use of advanced computer vision and artificial intelligence techniques for analysing remote sensing data, specifically focusing on the semantic segmentation of forest areas. The goal is to identify forest damage caused by insect pests using multispectral images from Sentinel-2 satellites. The proposed approach involves using genetic algorithms to automatically select informative features based on vegetation indices. A new fitness function is introduced to assess the quality of the selected feature sets. The neural network is then trained and tested using real data. The results of the study show the effectiveness of proposed approach and highlight its advantages over traditional methods. The developed technique allowed to obtain highly informative set of features with minimized redundancy within huge feature space with moderate amount of computation.
Відкритий доступ
Single-Polarized SAR Image Preprocessing in Scope of Transfer Learning for Oil Spill Detection
(IEEE IM/CS/SMC, 2024) Kussul, Nataliia; Kuzin, Volodymyr; Salii, Yevhenii; Yailymov, Bohdan; Shelestov, Andrii
This study proposes a novel preprocessing approach for improving oil spill detection from Synthetic Aperture Radar (SAR) satellite imagery using deep learning models. A transfer learning approach with the LinkNet segmentation architecture pre-trained on ImageNet is employed. The model is trained on Sentinel-1 SAR data from 2018–2023 using a designed preprocessing pipeline that converts the single-channel SAR input to a 3-channel RGB image. The proposed preprocessing involves transforming the original SAR intensity values to a normal distribution, extracting nonlinear features, and encoding them into the RGB channels. Quantitative results on a test set show the preprocessed model achieves an improvement of 0.038 in F1-score and 0.054 in Intersection over Union compared to the original dB-scale preprocessing approach. Qualitative evaluation on independent SAR scenes from the Mediterranean Sea also demonstrates the model's ability to generalize to new geographic areas after training on data from other regions. The proposed preprocessing technique shows promising performance gains for automatic oil spill segmentation from SAR imagery and potential for integration with other preprocessing methods and task-specific neural network architectures.
Відкритий доступ
Detection of War-Caused Agricultural Field Damages Using Sentinel-2 Satellite Data with Machine Learning and Anomaly Detection
(ACM Special Interested Group on Applied Computing (SIGAPP), 2024) Drozd, Sofiia
This research aims to detect war-caused damages on agricultural fields in Ukraine using Sentinel-2 satellite data. To achieve this, a Random Forest-based classification and an anomaly detection method deployed in the GEE cloud environment are applied. Two spectral bands - blue (B2) and green (B3) and two vegetation indices - NDVI and GCI - were used as input parameters. According to the results, the f1-score of classification reach 0.9. Using the developed methodology, more than 1.5 millions ha of fields were identified as damaged during the period of 2022--2023.
Відкритий доступ
Semi-supervised European forest types mapping using high-fidelity satellite data
(CEUR Workshop Proceedings (CEUR-WS.org), 2024-09) Yailymov, Bohdan; Yailymova, Hanna; Kussul, Nataliia; Shelestov, Andrii
Accurate and up-to-date forest type maps are crucial for effective monitoring and management of forest ecosystems across Europe. However, the availability of up to date high-resolution forest type maps has been limited. This study introduces an innovative semi-supervised approach for mapping European forest types by harnessing the power of high-resolution Sentinel-1 and Sentinel-2 satellite data from the Copernicus program. The novelty of the approach lies in the integration of various data sources for training dataset creation and the utilization of the Random Forest classifier on the Google Earth Engine cloud computing platform. This innovative combination enables efficient processing and classification of vast amounts of satellite imagery for large-scale forest type mapping. In particular, the LUCAS Copernicus 2018 and 2022 datasets were employed for training and validation, ensuring the robustness of the classification model. The resulting forest type map for 2022 has a fine spatial resolution of 10 meters and distinguishes between three key classes: broadleaved, coniferous, and mixed forests. Accuracy assessment using independent validation data demonstrated the reliability of the proposed approach, yielding an impressive overall accuracy of 93%. Comparative analysis with existing forest products revealed both consistencies and differences, underscoring the dynamic nature of forest ecosystems. The generated map fills a gap in up to date geospatial information on European forest types, empowering informed decision-making in forest management, conservation efforts, and environmental impact assessment. This study demonstrates the potential of synergizing cutting-edge remote sensing, cloud computing, and machine learning technologies to tackle complex environmental challenges at a continental scale, paving the way for future advancements in forest monitoring and management.
Відкритий доступ
Geospatial Analysis of Life Quality in Ukrainian Rural Areas
(IEEE, 2023) Yailymova, Hanna; Yailymov, Bohdan; Kussul, Nataliia; Shelestov, Andrii
In this work, the authors developed an initial algorithm for assessing the quality of life in rural areas of Ukraine using the aggregation of heterogeneous geospatial information. The approach consists in a comprehensive assessment of the remoteness of the village from vital infrastructure facilities (hospitals, educational institutions, banks, libraries, shops, roads, power lines, etc.), to natural ecosystems (water bodies, forests or parks), as well as to occupied territories. The obtained results show that the largest number of villages with a depressed quality of life are located in the eastern and southern territories of the country, and with a positive quality - mainly in the west and central Ukraine. This, of course, is partly related to active hostilities, but considering that the proposed algorithm works based on the analysis of distances to various objects, it can be concluded that the war only worsened the condition of life in the villages.
Відкритий доступ
Fusion of very high and moderate spatial resolution satellite data for detection and mapping of damages in agricultural fields
(IEEE, 2023) Kussul, Natallia; Drozd, Sofiia; Skakun, Sergii; Duncan, Erik; Becker-Reshef, Inbal
The war in Ukraine has resulted in significant losses in the agricultural sector due to damages to farmlands posing a threat to global food security. To restore the prosperity of the agricultural sector it is essential to detect and assess damages in agricultural fields and monitor their evolution. Commercial satellite data at very high spatial resolution $(\lt3 \mathrm{m})$ such as sub-meter imagery acquired by Maxar’s WorldView and Planet Labs’ SkySat platforms allow detection and mapping of artillery craters at fine scale. However, the frequency of acquisition and geographical coverage of this type of data is limited and may be quite low, e.g., 1-2 scenes per agriculture season. With the aim to continuously monitor the state of the fields over large areas in Ukraine we must compliment the analysis with satellite data at lower spatial resolution, e.g., daily PlanetScope at $\sim 3-\mathrm{m}$ and 10-m Sentinel-2/MSI. Here, we propose a data fusion approach to monitor artillery craters in agricultural fields using combination of satellite images acquired at different spatial and temporal resolution. Specifically, we use a single-date SkySat image at 0.5-m resolution with crater detection using previously developed deep learning approach along with multi-temporal data acquired by PlanetScope and Sentinel-2 images. For the latter, we detect anomalies of refelecant signal in the blue and green spectral bands and the Normalized Difference Water Index (NDWI). This approach is applied to a test area of 8,800 ha in Donetsk oblast. We found that with PlanetScope images at 3-m we were able to identify 202 ha of craters, or 63% of those in SkySat imagery; with Sentinel-2 at 10-m we detected 165 ha (or 51%) of craters. Craters with an area smaller than $100 \mathrm{m}{2}$ were poorly detected. By analyzing anomalies in multi-temporal PlanetScope and Sentinel-2 images, we were able to identify craters that were not detected in SkySat data highlighting the importance of temporal component in the data. Furthermore, with daily PlanetScope data combined with Sentinel-2 data (3-5 days), we were able to estimate the dates of crater appearances and analyze the dynamics of craters and their evolution.
Відкритий доступ
Assessing Ukrainian Territory Suitability for Solar Power Station Placement Using Satellite Data on Climate and Topography
(IEEE, 2023) Kussul, Nataliia; Drozd, Sofiia
This research aims to assess the suitability of Ukrainian territories for the placement of solar power stations using satellite data on climate and topographic characteristics. The suitability of the territories was determined using a weighted sum method, incorporating input parameters from climate maps sourced from ERA5- Land dataset, which included data on annual global horizontal solar irradiation (GHI), accumulated annual temperature above 25°C, average annual wind speed, and maps of accumulated annual precipitation. Additionally, topographic maps from the SRTM dataset were utilized, providing information on elevations, slopes, and terrain shading. Furthermore, data from Wikimapia on the locations of existing major solar power stations in Ukraine were used to verify the placement optimization. The results of the study revealed that the largest portion of the country (over 48%) exhibits moderate suitability scores (0.3-0.4). Favorable territories (suitability score above 0.3) outweigh unsuitable ones for solar power stations. The southern regions and the Crimean Peninsula offer the most favorable conditions for the placement of solar farms. Overall, all analyzed major solar power stations in Ukraine were located in optimal territories. Furthermore, it was found that certain regions such as Odessa, Poltava, Kharkiv, Zaporizhia, Dnipropetrovsk, Donetsk, and Luhansk demonstrate good suitability scores (0.3-0.4), yet they are not fully exploited. These regions hold significant potential for the future construction of powerful and productive solar power stations.
Відкритий доступ
Monitoring of Fires Caused by War in Ukraine Based on Satellite Data
(IEEE, 2023) Yailymov, Bohdan; Yailymova, Hanna; Shelestov, Andrii; Shumilo, Leonid
The focus of this paper is on fire monitoring studies which utilize a variety of satellite data. The study examines various data sources that are used to automatically detect fires at a national level in Ukraine. Existing fire monitoring systems have low spatial resolution, which makes it difficult to detect fires. Therefore, the authors propose an approach that uses both low- and high-resolution satellite data for fire monitoring. The study found that MODIS, Landsat-8,9 and Sentinel-2 satellite data provide reliable information for fire monitoring in Ukraine. These data sources offer a variety of benefits, including high spatial resolution, frequent revisit times, and wide spectral coverage. In order to understand how favourable weather conditions are for the occurrence of fire, the authors used the Fire Potential Index (FPI). The methodology developed in this study provides a promising approach to monitoring fires and understanding the causes of fires, particularly those caused by the war in Ukraine. The authors implemented the fire detection methodology and FPI index assessment in the Google Earth Engine cloud platform, which allowed for efficient processing and analysis of large volumes of data. In conclusion, the paper highlights the importance of using a combination of low- and high-resolution satellite data for fire monitoring.
Відкритий доступ
Geospatial monitoring of sustainable and degraded agricultural land
(2023-07) Yailymova, Hanna; Yailymov, Bohdan; Kussul, Nataliia; Shelestov, Andrii; Shumilo, Leonid
In this study, the assessment of sustainable development goal (SDG) indicator 2.4.1 for Ukraine and Germany is conducted using geospatial and satellite data. The traditional methodology for the SDG indicator 2.4.1 calculation cannot be directly applied to the Ukrainian territory due to the lack of systematic data collection of the essential indicators. Therefore, the authors have developed an integrated approach to estimate land degradation, that uses different schemes for various land cover and crop types at the national scale, utilizing satellite data and employing the WOFOST model for crop growing simulation. The research describes the information sources used for creation crop type classification maps and the necessary data for modeling leaf area index (LAI) based on the WOFOST model. The calculated indicators are determined for each Ukrainian region from 2018 to 2022. Observations in 2022 show a decline in the indicator 2.4.1 across nearly all regions of Ukraine, directly attributed to the military conflicts within the Ukraine. To assess the possibility of applying the developed technology to a large area, the indicator was calculated for a European country (Germany).
Відкритий доступ
Autoregressive models for air quality investigation
(2023-08) Zalieska, Olena; Yailymova, Hanna
The aim of the work is to build a forecast of air quality in Kyiv for some period of time. For this purpose we preprocessed and analized data, selected and fitted a model.
Відкритий доступ
Generative Adversarial Networks for the Satellite Data Super Resolution Based on the Transformers with Attention
(2023) Lavreniuk, Mykola; Shumilo, Leonid; Lavreniuk, Alla
In recent years, free access to high and medium resolution data has become available, providing researchers with the opportunity to work with low resolution satellite images on a global scale. Sentinel-1 and Sentinel-2 are popular sources of information due to their high spectral and spatial resolution. To obtain a final product with a resolution of 10 meters, we have to use bands with a resolution of 10 meters. Other satellite data with lower resolution, such as Landsat-8 and Landsat-9, can improve the results of land monitoring, but their harmonization requires a process known as super-resolution. In this study, we propose a method for improving the resolution of low-resolution images using advanced deep learning techniques called Generative Adversarial Networks (GANs). The state-of-the-art neural networks, namely transformers, with the combination of channel attention and self-attention blocks were employed at the base of the GANs. Our experiments showed that this approach can effectively increase the resolution of Landsat satellite images and could be used for creating high resolution products.
Відкритий доступ
Machine learning models and technology for classification of forest on satellite data
(2023) Salii, Yevhenii; Kuzin, Volodymyr; Hohol, Anton; Kussul, Nataliia; Yailymova, Hanna
The paper deals with the problem of semantic segmentation of satellite imagery to deliver forest type map with high resolution. To solve the problem, we propose 4 machine learning models. Two of them are based on Random Forest (RF) and other two - on Convolutional Neural Network (CNN) - U-Net. As an input we use 2 images of Sentinel-2 (one for summer and one for winter, 4 spectral bands from each). As an output (labels) we use the Copernicus Forest Type dataset for 2018 year. Our models showed promising results on validation data. Of all models the one based on U-Net ended up being the most efficient in forest classification with overall accuracy 91.7%. At the same time the best RF model scored with 86.5%. After comparing the results, in order to check our model transferability we created and compared forest map of northern part of Kyiv region of 2018 and 2022. The experiment confirmed the robustness of the model and it's scalability. The developed models have been implemented in the cloud platform specialized on satellite data - CREODIAS. The developed map can provide valuable data for foresters, biologists, or other researchers to make decisions about forest management and conservation, as well as to ensure that Europe's forests are managed in an ecologically sustainable way.
Відкритий доступ
Air Quality as Proxy for Assesment of Economic Activity
(2023) Yailymova, Hanna; Kolotii, Andrii; Kussul, Nataliia; Shelestov, Andrii
In Ukraine most of citizens and economic activity are concentrated over urban city centers and city functional areas. Thus, Air Quality and, in particular, levels of fine particulate matter (e.g., PM2.5 and PM 10 ) over cities can be a proxy for assessment of economic activity and density of city populations. Since the russia invasion to Ukraine started on 24 of February 2022 according to UNHCR (the UN Refugee Agency) 8 million refugees from Ukraine have now been registered across the Europe. Almost 7 million more are displaced within the country. On the other hand, there is no official statistics from national statistical service showing current influence of invasion on city economic activity or inhabitants amount. Thus, such a proxy can be used to see current situation by analyzing of particulate matter time series. In this work we compare averaged annual cumulated PM2.5 for 2018–2021 years with values for 2022 and estimate the correlation them with publicly available statistics on migration to see some relations. Global Sustainable Development Goal (SDG) indicator 11.6.2, “Annual mean levels of fine particulate in cities (population weighted)” is being extended for 2022 and compared with previous years.
Відкритий доступ
Forecast of Yield of Major Crops in Ukraine in War Conditions 2022 based on MODIS and Sentinel-2 Satellite Data
(2023) Kussul, Nataliia; Drozd, Sophia; Yailymova, Hanna
Ukraine was one of the main exporters of plant products. However, as a result of the aggression, the country's agriculture has suffered greatly, export volumes are decreasing, which may provoke a shortage of agricultural products on world markets. It is impossible to assess crop yield and forecast the harvest volume locally, as the collection of information has become difficult due to the active conduct of hostilities and the occupation of a large part of the territories. Therefore, it is necessary to use land remote sensing data to assess crop yield. In this research, we will build regression models based on a random forest for each region of Ukraine to estimate crop yield based on 16-day composites of the NDVI time series during the summer vegetation period from Sentinel-2 (10m) and MODIS (500m) satellites, involving in the calculation NDVI crop maps. The official yield of maize, sunflower, soybean, rapeseed, and wheat for the years 2016-2021 was used as training data. According to the results of the analysis, models based on NDVI from the MODIS satellite showed better accuracy (relative error within 8-18%), but models based on NDVI data from Sentinel-2 better described the variance of the predicted yield. During the research, we found a sharp drop in land productivity indicators compared to the productivity of 2021 for the territories of central, southern and eastern Ukraine. According to our estimates based on MODIS data, the average yield at the country level is expected to be 40.98 t/ha for wheat, 57.66 t/ha for maize, 23.57 t/ha for sunflower, 21.06 t/ha for soybeans, 21.15 t/ha for rapeseed. Estimates based on Sentinel-2 data: 43.22 t/ha for wheat, 71.93 t/ha for maize, 26.86 t/ha for sunflower, 22.94 t/ha for soybeans, 28.23 t/ha for rapeseed.
Відкритий доступ
War Damage Detection Based on Satellite Data
(2023) Shelestov, Andrii; Drozd, Sophia; Mikava, Polina; Barabash, Illia; Yailymova, Hanna
As a result of the resolution of the armed military conflict on the territory of Ukraine on February 24, 2022, the agricultural infrastructure of the latter was marked by large-scale destruction. Thousands of hectares of fields, the harvest from which previously provided both domestic and world needs, were mined, destroyed, damaged by artillery shelling, explosions and movements of military equipment. To restore the affected areas to ensure food security of Ukraine and the world, the state government, with the support of international organizations, must correctly distribute financial resources between affected landowners and farmers. For this, there is a need for accurate identification of war-affected territories. This task can be effectively performed using remote sensing data. In this work, damage to agricultural fields due to military operations is searched for by calculating the relative difference of the vegetation indices based on Sentinel-2 satellite data. Cloud-free composites of normalized difference vegetation index (NDVI) are compared for the nearest period before and after active hostilities in a specific area (dates and locations are obtained from the ACLED source). Pixels whose relative difference exceeds a given threshold are considered damaged. The survey of the country's territories was conducted from February 24 to September 25, 2022, dividing the dates into biweekly periods. According to the results of the research, such damage to agricultural fields as craters from explosions and shelling, traces of machinery, burnt fields, etc., were found. The relative difference between the minimum and average values of vegetation indices in the affected areas averaged 25% versus 15% for the minimum period before and after the lesion. The detected damaged areas were validated using ACLED data. It was determined that more than 50% of the total number of areas identified as damaged were located within a radius of up to 5 km from the zone of combat activities.
Відкритий доступ
Persistent Homology in Machine Learning: Applied Sciences Review
(2023) Yavorskyi, Oleksandr; Asseko-Nkili, Andrii; Kussul, Nataliia
Topological Data Analysis (‘TDA’) has become a vibrant and quickly developing field in recent years, providing topology-enhanced data processing and Machine Learning (‘ML’) applications. Due to the novelty of the field, as well as the dissimilarity between the mathematics behind the classical ML and TDA, it might be complicated for a field newcomer to assess the feasibility of the approaches proposed by TDA and the relevancy of the possible applications. The current paper aims to provide an overview of the recent developments that relate to persistent homology, a part of the mathematical machinery behind the TDA, with a particular focus on applied sciences. We consider multiple areas, such as physics, healthcare, material sciences, and others, examining the recent developments in the field. The resulting summary of this paper could be used by field experts to expand their knowledge on recent persistent homology applications, while field newcomers could assess the applicability of this TDA approach for their research. We also point out some of the current restrictions on the use of persistent homology, as well as potential development trajectories that might be useful to the whole field.
Відкритий доступ
KNN-Based Algorithm of Hard Case Detection in Datasets for Classification
(2023) Okhrimenko, Anton; Kussul, Nataliia
The machine learning models for classification are designed to find the best way to separate two or more classes. In case of class overlapping, there is no possible way to clearly separate such data. Any ML algorithm will fail to correctly classify a certain set of datapoints, which are surrounded by a significant number of another class data points at the feature space. However, being able to find such hardcases in a dataset allows using another set of rules than for normal data samples. In this work, we introduce a KNN-based detection algorithm of data points and subspaces for which the classification decision is ambiguous. The algorithm described in details along with demonstration on artificially generated dataset. Also, the possible usecases are discussed, including dataset quality assessment, custom ensemble strategy and data sampling modifications. The proposed algorithm can be used during full cycle of machine learning model developing, from forming train dataset to real case model inference.

Переглянути

Нові надходження