Article
Environmental Studies
Michail Sismanis, Rizos-Theodoros Chadoulis, Ioannis Manakos, Anastasios Drosou
Summary: The frequency and severity of large, destructive fires have increased recently, causing extensive impacts on the landscape, human population, and ecosystems. This study proposes an unsupervised approach using Sentinel-2 satellite imagery for mapping burned areas, considering the variability of spectral response. It achieves high classification accuracy and can be used as a complementary tool to existing forest fire management services and decision support systems.
Article
Environmental Sciences
Peng Liu, Yongxue Liu, Xiaoxiao Guo, Wanjing Zhao, Huansha Wu, Wenxuan Xu
Summary: In this study, an automatic burned area (BA) detection algorithm based on Sentinel-2 MultiSpectral Instrument (MSI) and Google Earth Engine was proposed. By optimizing spectral indices, utilizing different temporal scales of images, and integrating multisource active fire (AF) products, the proposed method can accurately and quantitatively identify BAs, providing a reliable foundation for fire monitoring programs and climate change research.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Environmental Sciences
Allan A. Pereira, Renata Libonati, Julia A. Rodrigues, Joana Nogueira, Filippe L. M. Santos, Duarte Oom, Waislan Sanches, Swanni T. Alvarado, Jose M. C. Pereira
Summary: Researchers are working on improving the understanding of fire patterns and changes, and the need for a consistent database about the location and extension of burned areas. They have developed a new algorithm to improve BA mapping accuracy in the Brazilian savannas, which can generate automated products over large areas and long periods.
Article
Chemistry, Multidisciplinary
John Gajardo, Marco Mora, Guillermo Valdes-Nicolao, Marcos Carrasco-Benavides
Summary: This paper proposes evaluating extreme learning machines (ELM) for mapping burned areas and compares them with other widely used machine-learning algorithms. The results show that ELM is the best burned-area classification algorithm, considering precision and training time, demonstrating great potential for mapping burned areas at a global scale.
APPLIED SCIENCES-BASEL
(2022)
Article
Environmental Sciences
Donato Amitrano, Gerardo Di Martino, Antonio Iodice, Daniele Riccio, Giuseppe Ruello
Summary: This paper presents a new technique for mapping urban areas using multitemporal synthetic aperture radar data. The proposed methodology combines innovative RGB composites with self-organizing map (SOM) clustering and object-based image analysis. The technique has been tested in different scenarios in Italy and Germany, showing good agreement with the Urban Atlas of the European Environmental Agency.
Article
Environmental Sciences
Miguel A. Belenguer-Plomer, Mihai A. Tanase, Emilio Chuvieco, Francesca Bovolo
Summary: This study analyzed the use of convolutional neural networks for mapping burned areas by combining radar and optical datasets. The optimal CNN settings and sensor integration were determined based on land cover class and data type. Increasing network complexity did not improve accuracy in burned area mapping.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Geochemistry & Geophysics
Weihao Bo, Jie Liu, Xijian Fan, Tardi Tjahjadi, Qiaolin Ye, Liyong Fu
Summary: This article proposes a novel approach of utilizing salient object detection for burned area segmentation and introduces an efficient network model (BASNet) to improve the accuracy and speed of high-resolution UAV image segmentation. By utilizing two modules, BASNet significantly outperforms existing methods in both quantitative and qualitative evaluations.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Mohamed Hamimeche, Simona Niculescu, Antoine Billey, Riadh Moulai
Summary: The study focuses on identifying and mapping the vegetation of Algerian islands and islets using satellite images and machine learning methods. It successfully produced accurate vegetation maps using high-resolution images, which can be used for management and protection plans. The methodological approach led to satisfactory results with overall accuracy values above 92% and kappa index values exceeding 0.90 for Pleiades images, and overall accuracy values over 83% and kappa index values above 0.80 for SPOT 6/7 images.
ENVIRONMENTAL MONITORING AND ASSESSMENT
(2021)
Article
Computer Science, Information Systems
Lu Liu, Zixuan Xu, Daqing He, Dequan Yang, Hongchen Guo
Summary: This paper systematically studies vanishing attacks against a remote sensing image object detection model and proposes adversarial attack adaptation methods based on interpolation scaling and patch perturbation stacking. It also suggests a hot restart perturbation update strategy and a local pixel attack algorithm based on sensitive pixel location to achieve good attack effects. Experimental results show that the proposed attack method achieves a balance between attack effect and attack cost.
Article
Environmental Sciences
Xikun Hu, Yifang Ban, Andrea Nascetti
Summary: The study compares deep learning (DL) models and machine learning (ML) algorithms for mapping burned areas from satellite imagery in three wildfire sites. DL algorithms outperform ML methods in compact burned areas, while ML methods are more suitable for dispersed burn in boreal forests.
Article
Remote Sensing
Joanne Hall, Fernanda Argueta, Louis Giglio
Summary: The study finds that small fires are often underestimated in agricultural areas within global burned area and fire emission inventories. Current validation methods designed for larger wildfires are not suitable for small fires. An alternative approach using detailed field-level burned area reference maps was used to validate two global burned area products, revealing high omission and commission error rates.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2021)
Article
Environmental Sciences
Yuxian Wang, Yuan Fang, Wenlong Zhong, Rongming Zhuo, Junhuan Peng, Linlin Xu
Summary: This paper presents a novel spatial-temporal deep learning-based approach for sub-pixel mapping (SPM) of different crop types within mixed pixels from MODIS images. The proposed approach outperforms other classical SPM methods and state-of-the-art deep learning methods, especially for fragmented categories. The experiments show the promising spatial-temporal generalization capabilities of the proposed method across different regions and years.
Article
Environmental Sciences
Joshua Lizundia-Loiola, Magi Franquesa, Amin Khairoun, Emilio Chuvieco
Summary: This paper presents a hybrid algorithm based on Copernicus Sentinel-3 and Visible Infrared Imaging Radiometer Suite data for global detection of burned areas. The algorithm enhances burn signals using a multi-temporal separability index and extracts burned patches through spatio-temporal clustering and contextual growing. The new FireCCIS310 product shows significant improvements in omission and commission errors, temporal reporting accuracy, and reduced border effects compared to the previous product.
REMOTE SENSING OF ENVIRONMENT
(2022)
Article
Environmental Sciences
Seyd Teymoor Seydi, Mahdi Hasanlou, Jocelyn Chanussot
Summary: Wildfires, a destructive natural disaster, have significant impacts on the environment and wildlife. Remote sensing satellite imagery plays a key role in accurately detecting burned areas, but accurate mapping remains a challenge due to background complexity and diversity of burned areas. A novel framework based on Deep Siamese Morphological Neural Network (DSMNN-Net) has shown high performance in detecting burned areas in Australian forests using multispectral Sentinel-2 and hyperspectral PRISMA image datasets.
Article
Green & Sustainable Science & Technology
Hiroki Amano, Yoichiro Iwasaki
Summary: Agricultural fields, grasslands, and forests play a crucial role in groundwater recharge, but were damaged in the Kumamoto area of Japan by natural disasters in 2016. By creating a land cover map and estimating groundwater recharge in 2016, it was found that groundwater recharge decreased due to land cover changes induced by the disasters. Efforts should be made to compensate for the reduced amount of groundwater recharge caused by the disasters to ensure sustainable use of groundwater in the future.
Article
Engineering, Aerospace
Samet Aksoy, Aylin Yildirim, Taha Gorji, Nikou Hamzehpour, Aysegul Tanik, Elif Sertel
Summary: The study focuses on the importance of soil salinization detection using remote sensing techniques and machine-learning algorithms in arid and semi-arid regions. Among the three machine-learning algorithms analyzed, random forest algorithm demonstrated the most reliable spatial distribution of soil salinity classes in the selected study area, despite slightly better prediction results from classification and regression trees (CART) in some aspects.
ADVANCES IN SPACE RESEARCH
(2022)
Article
Environmental Sciences
Paria Ettehadi Osgouei, Gareth Roberts, Sinasi Kaya, Muhammad Bilal, Jadunandan Dash, Elif Sertel
Summary: Aerosol loading has significant impacts on radiative forcing, climate, and human health. This study evaluated and compared multiple satellite aerosol products in the Eastern Mediterranean and the Black Sea region, with VIIRS aerosol product showing the best performance over coastal areas.
ATMOSPHERIC ENVIRONMENT
(2022)
Article
Computer Science, Information Systems
Serdar Kizilkaya, Ugur Alganci, Elif Sertel
Summary: This study introduces the VHRShips dataset, which is a unique and rich ship dataset that can improve the scalability of ship detection and mapping applications. A deep learning-based multi-stage approach called HieD is proposed for ship type classification. The results show that HieD outperforms other methods in localization, recognition, and identification stages.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Article
Geosciences, Multidisciplinary
Esma Efe, Ugur Alganci
Summary: Detecting and monitoring change on Earth has always been of great interest, as human activities and their impact on land cover have become increasingly evident. Detecting and monitoring land cover change has become crucial for decision-makers due to industrial activities and settlement expansion. This study used multi-temporal Sentinel 2 satellite images to determine land cover change caused by urbanization and agricultural activity in Kocaeli province. Various data reduction and classification methods were applied and their performances were evaluated. The results showed that the Principal Component Analysis-Regression Tree method achieved the highest accuracy rate of 83.88%.
Article
Engineering, Aerospace
Enes Hisam, Ali Danandeh Mehr, Ugur Alganci, Dursun Zafer Seker
Summary: The study aims to comprehensively and comparatively evaluate grid-based precipitation products over Turkey's Mediterranean region. The evaluation results indicate that PERSIANN CDR, CHIRPS, IMERG v6, GSMaP Gauge, and ERA5 performed well in all evaluation aspects, while PERCIANN CCS, PDIR-Now, and GSMaP MVK performed poorly. Most products underestimated heavy rainfall events, while all products performed better for low to moderate precipitation events. Moreover, the performance of most products degraded at elevations greater than 1000 meters. The evaluation suggests that PERSIANN CDR, CHIRPS, IMERG v6, GSMaP Gauge, and ERA5 can be used as good precipitation data sources in Turkey's Mediterranean region, complementing ground-based meteorological stations.
ADVANCES IN SPACE RESEARCH
(2023)
Article
Environmental Sciences
Ahmet Tarik Torun, Semih Ekercin, Ugur Alganci, Ferruh Yilmazturk
Summary: The production of digital elevation models (DEMs) using the interferometric synthetic aperture radar (InSAR) technique has proven to be more useful than traditional methods. This study produced new DEMs from TerraSAR-X images using external DEMs and analyzed the accuracy. The results showed that the quality of the external DEM has a significant impact on DEM production, with STEREO DEM achieving the highest accuracy of 1.52 meters.
JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING
(2023)
Article
Environmental Sciences
Kubra Bahsi, Beyza Ustaoglu, Samet Aksoy, Elif Sertel
Summary: This research aims to determine the amount of crop-based residue burning (CRB) in the Southeastern Anatolia Region of Turkiye, using Sentinel-2 images and Intergovernmental Panel on Climate Change standards. The analysis showed that CRB practices in 2019 released 14,444.307 Gg of Greenhouse Gases and 117.809 Gg of Particulate Matters. The results can improve national statistics and support agricultural decision-making processes.
GEOCARTO INTERNATIONAL
(2023)
Article
Computer Science, Information Systems
Nooshin Mashhadi, Ugur Alganci
Summary: This study evaluated different vegetation indices (VIs) in forest degradation using Landsat 8 images and the BFASTMonitor approach. The results showed that water-sensitive VIs utilizing shortwave infrared bands were more sensitive in detecting forest disturbances, while chlorophyll-sensitive VIs had lower accuracy. The study suggests that BFASTMonitor can be used as a tool for monitoring forest environments, with slightly better performance in small-scale deforestation patterned regions.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Article
Computer Science, Artificial Intelligence
Peijuan Wang, Elif Sertel
Summary: With the advancement of artificial intelligence techniques and the launch of new satellites with video capturing capability, multi-frame super-resolution of remote sensing images has become a critical research topic. In this study, an attention-based Generative Adversarial Network (GAN) algorithm is proposed for multi-frame remote sensing image super-resolution. Several experiments were conducted, comparing the results of different models and the proposed approach using SpaceNet7 and Jilin-1 datasets.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Environmental Sciences
Emre Gulher, Ugur Alganci
Summary: Satellite-derived bathymetry (SDB) is a process to estimate water depth in shallow coastal and inland waters using satellite imagery. Recent advancements in technology and data processing have improved the accuracy and availability of SDB. This study aims to create an SBD map of Horseshoe Island using optical satellite images and compare the performance of different models and atmospheric correction methods. Machine learning-based models, specifically random forest and XGBoost, provided the highest performance and best fitting ability, followed by deep learning-based models. Landsat 8 performed better for deeper depths, while Sentinel 2 was slightly better for shallower depths. ACOLITE, iCOR, and ATCOR all produced reliable results, with ACOLITE offering the highest level of automation.
Article
Environmental Sciences
Emre Gulher, Ugur Alganci
Summary: This study investigates the capability of Gokturk-1 satellite in satellite-derived bathymetry (SDB) and improves the prediction performance using machine learning methods. The results show that the bathymetric inversion performance of the Gokturk-1 satellite is comparable to Landsat-8 and Sentinel-2, and the addition of brightness value parameter significantly improves the performance.
Article
Engineering, Geological
Bugrahan oezcihan, Levent Dogukan oezlue, Muemin Ilker Karakap, Halime Suermeli, Ugur Alganci, Elif Sertel
Summary: Satellite images are widely used in the production of geospatial information. Geometric correction is essential for image pre-processing to extract accurate locational information. This study performed geometric correction on satellite images obtained from Pleiades 1A (PHR) and SPOT-6 using empirical and physical models. Several experiments were conducted to investigate the effects of various parameters on the performance of the geometric correction procedure. The results showed that the model using RPC from data providers achieved lower RMSE values, providing better locational accuracy.
INTERNATIONAL JOURNAL OF ENGINEERING AND GEOSCIENCES
(2023)
Article
Remote Sensing
Haydar Akcay, Samet Aksoy, Sinasi Kaya, Elif Sertel, Jadu Dash
Summary: This study evaluated the performance of Sentinel-1 and Sentinel-2 data fusion for regional mapping of olive trees. Using the Izmir Province in Turkiye as a case study, the researchers successfully produced a regional-scale olive distribution map. The results showed that this method can be scaled up to the entire country and replicated elsewhere, providing a foundation for other scientific studies and effective management practices.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2023)
Proceedings Paper
Engineering, Aerospace
Ramil Safarov, Elif Sertel
Summary: This study used Remote Sensing and Geographic Information Systems to analyze the coastal changes around the Baku International Sea Trade Port over the past thirty years. The results showed that the most significant shoreline change occurred on the east side of the port, while the smallest change was observed 11.5 kilometers south of the port. Additionally, the study found that the land area had increased by 633 hectares due to coastline filling.
2023 10TH INTERNATIONAL CONFERENCE ON RECENT ADVANCES IN AIR AND SPACE TECHNOLOGIES, RAST
(2023)
