Maria Sdraka's research while affiliated with Harokopio University and other places

Over the last decade there has been an increasing frequency and intensity of wildfires across the globe, posing significant threats to human and animal lives, ecosystems, and socio-economic stability. Therefore urgent action is required to mitigate their devastating impact and safeguard Earth's natural resources. Robust Machine Learning methods combined with the abundance of high-resolution satellite imagery can provide accurate and timely mappings of the affected area in order to assess the scale of the event, identify the impacted assets and prioritize and allocate resources effectively for the proper restoration of the damaged region. In this work, we create and introduce a machine-learning ready dataset we name FLOGA. This dataset is unique as it comprises of satellite imagery acquired before and after a wildfire event with variable spatial and spectral resolution, and contains a large number of events where the corresponding burnt area ground truth has been annotated by domain experts. FLOGA covers the wider region of Greece, which is characterized by a Mediterranean landscape and climatic conditions. We use FLOGA to provide a thorough comparison of specialized spectral indices as well as multiple Machine Learning and Deep Learning algorithms for the automatic extraction of burnt areas, approached as a change detection task. Finally, we propose a novel Deep Learning model, namely BAM-CD. Our benchmark results demonstrate the efficacy of the proposed technique in the automatic extraction of burnt areas, outperforming all other methods in terms of accuracy and robustness. Our dataset and code are publicly available at: https://github.com/Orion-AI-Lab/FLOGA</uri

The past few years have seen an accelerating integration of deep learning (DL) techniques into various remote sensing (RS) applications, highlighting their power to adapt and achieving unprecedented advancements. In the present review, we provide an exhaustive exploration of the DL approaches proposed specifically for the spatial downscaling of RS imagery. A key contribution of our work is the presentation of the major architectural components and models, metrics, and data sets available for this task as well as the construction of a compact taxonomy for navigating through the various methods. Furthermore, we analyze the limitations of the current modeling approaches and provide a brief discussion on promising directions for image enhancement, following the paradigm of general computer vision (CV) practitioners and researchers as a source of inspiration and constructive insight.

In this work we introduce Sen4AgriNet, a Sentinel-2 based time series multi country benchmark dataset, tailored for agricultural monitoring applications with Machine and Deep Learning. Sen4AgriNet dataset is annotated from farmer declarations collected via the Land Parcel Identification System (LPIS) for harmonizing country wide labels. These declarations have only recently been made available as open data, allowing for the first time the labeling of satellite imagery from ground truth data. We proceed to propose and standardise a new crop type taxonomy across Europe that address Common Agriculture Policy (CAP) needs, based on the Food and Agriculture Organization (FAO) Indicative Crop Classification scheme. Sen4AgriNet is the only multi-country, multi-year dataset that includes all spectral information. It is constructed to cover the period 2016-2020 for Catalonia and France, while it can be extended to include additional countries. Currently, it contains 42.5 million parcels, which makes it significantly larger than other available archives. We extract two sub-datasets to highlight its value for diverse Deep Learning applications; the Object Aggregated Dataset (OAD) and the Patches Assembled Dataset (PAD). OAD capitalizes zonal statistics of each parcel, thus creating a powerful label-to-features instance for classification algorithms. On the other hand, PAD structure generalizes the classification problem to parcel extraction and semantic segmentation and labeling. The PAD and OAD are examined under three different scenarios to showcase and model the effects of spatial and temporal variability across different years and different countries.

In this work, we introduce Sen4AgriNet, a Sentinel-2-based time series multicountry benchmark dataset, tailored for agricultural monitoring applications with machine and deep learning. Sen4AgriNet dataset is annotated from farmer declarations collected via the land parcel identification system (LPIS) for harmonizing country-wide labels. These declarations have only recently been made available as open data, allowing for the first time the labeling of satellite imagery from ground truth data. We proceed to propose and standardize a new crop type taxonomy across Europe that addresses common agriculture policy (CAP) needs, based on the Food and Agriculture Organization (FAO) indicative crop classification scheme. Sen4AgriNet is the only multicountry, multiyear dataset that includes all spectral information. It is constructed to cover the period 2016–2020 for Catalonia and France, while it can be extended to include additional countries. Currently, it contains 42.5 million parcels, which makes it significantly larger than other available archives. We extract two subdatasets to highlight its value for diverse deep learning applications—the object aggregated dataset (OAD) and the patches assembled dataset (PAD). OAD capitalizes zonal statistics of each parcel, thus creating a powerful label-to-features instance for classification algorithms. On the other hand, PAD structure generalizes the classification problem to parcel extraction and semantic segmentation and labeling. The PAD and OAD are examined under three different scenarios to showcase and model the effects of spatial and temporal variability across different years and different countries. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup

Background A very popular technique for isolating significant genes from cancerous tissues is the application of various clustering algorithms on data obtained by DNA microarray experiments. Aim The objective of the present work is to take into consideration the chromosomal identity of every gene before the clustering, by creating a three-dimensional structure of the form Chromosomes×Genes×Samples. Further on, the k-Means algorithm and a triclustering technique called δ- TRIMAX, are applied independently on the structure. Materials and Methods The present algorithm was developed using the Python programming language (v. 3.5.1). For this work, we used two distinct public datasets containing healthy control samples and tissue samples from bladder cancer patients. Background correction was performed by subtracting the median global background from the median local Background from the signal intensity. The quantile normalization method has been applied for sample normalization. Three known algorithms have been applied for testing the “gene cube”, a classical k-means, a transformed 3D k-means and the δ-TRIMAX. Results Our proposed data structure consists of a 3D matrix of the form Chromosomes×Genes×Samples. Clustering analysis of that structure manifested very good results as we were able to identify gene expression patterns among samples, genes and chromosomes. Discussion: to the best of our knowledge, this is the first time that such a structure is reported and it consists of a useful tool towards gene classification from high-throughput gene expression experiments. Conclusion Such approaches could prove useful towards the understanding of disease mechanics and tumors in particular.

A critical issue for the safe operation of nuclear power plants is to quickly and accurately detect possible anomalies and perturbations in the reactor. Defects in operation are principally identified through changes in the neutron flux, as captured by detectors placed at various points inside and outside of the core. While wavelet-based analysis of the measured signals has been thoroughly used for anomaly detection, it has yet to be coupled with deep learning approaches. To this end, this work presents a novel technique for anomaly detection on nuclear reactor signals through the combined use of wavelet-based analysis and convolutional neural networks. In essence, the wavelet transform is applied to the signals and the corresponding scaleograms are produced, which are subsequently used to train a convolutional neural network that detects possible perturbations in the reactor core. The overall methodology is experimentally validated on a set of simulated nuclear reactor signals generated by a well-established relevant tool. The obtained results indicate that the trained network achieves high levels of accuracy in failure detection, while at the same time being robust to noise.