Desertification Detection Using an Improved Variational Autoencoder-Based Approach Through ETM-Landsat Satellite Data

Spatial analysis of land use and cover changes: Implications of green legacy initiative on climate action in Upper Awash Basin, Ethiopia

A major problem of wireless devices is the detection of security threats in an efficient manner. Several recent incidents show that malicious applications (apps) can find their ways to online markets (e.g., Google Play Store) and be available for download and installation. Such malicious apps can collect sensitive data from millions of users and send them to a third-party servers. In this paper, we propose a methodology that leverages the power consumption of wireless devices to build a model that makes them more robust to the presence of malicious apps. The method consists of two stages: (i) Feature Extraction where stacked Restricted Boltzmann Machine (RBM) AutoEncoders (AE) and Principal Component Analysis (PCA) are used to extract features vector based on AE’s reconstruction errors. (ii) Classifier where One-Class Support Vector Machine is trained to perform the classification task. The validation of the methodology is performed on a real measurements dataset. The obtained results show a good potential and prove that AEs’ reconstruction error can be used as a good discriminating feature. The obtained detection accuracy surpasses previously reported techniques, where it reaches up to ~ 98% in some scenarios.

<p><strong>Deep generative models have greatly advanced the field of artificial intelligence by learning the distribution of unlabelled datasets. In this thesis, we aim to develop a novel variational autoencoder (VAE)-based deep generative model that learns meaningful representations for effective unsupervised clustering in the latent space of high-dimensional datasets.</strong></p><p>Existing VAE-based deep clustering algorithms assume a mixture distribution either for the variational posterior over the latent variables or for the prior, to approximate the distribution of unlabelled datasets. The proposed mixtures variational autoencoders (MVAE) model assumes a mixture distribution for both the prior and variational posterior over the latent variables within the VAE framework.</p><p>We apply the variational inference to construct the evidence lower bound (ELBO) of the marginal log-likelihood function for our proposed MVAE model and then derive the analytical form for the clustering assignment estimate, also called the posterior probability estimate. This estimate is associated with each component of the VAE framework and enables the optimization of two distinct ELBO functions based on soft and hard assignment approaches. The training procedure for MVAE involves the joint optimization of both clustering assignment probabilities and model parameters. We evaluate the clustering performance on the latent embeddings of a dataset using both the posterior probability estimate and the Gaussian mixture model (GMM) methods.</p><p>We proposed two variants of the expectation-maximization (EM) algorithm to optimize the parameters for the MVAE model. The MVAE (EM) algorithm provides two distinct, numerically stable solutions for the posterior probability estimate: MVAE(EM-V1), where the estimate is associated with only the prior distribution, and MVAE(EM-V2), where the estimate incorporates both the variational posterior and the prior distribution. Among the proposed models, MVAE(EM-V2) requires less computation time for training. Additionally, this model achieves superior clustering performance on most datasets compared to the baseline models.</p><p>We modified the MVAE(EM-V2) algorithm by including a coefficient (β) with the regularizer term. The trained regularized mixtures VAE model with a small regularization coefficient (β < 1) achieves good unsupervised clustering performance on the test datasets. We further propose a variant of the regularized mixtures VAE model in which the regularization coefficient follows an annealing schedule from β > 1 to β < 1. The scheduled regularized model demonstrates superior clustering accuracy across most benchmark datasets compared to state-of-the-art deep clustering algorithms.</p><p>In this thesis, we point out that assuming a mixture distribution for both the prior and variational posterior components over the latent variables within the VAE framework enhances unsupervised clustering in the latent space. Our proposed models outperform state-of-the-art deep clustering algorithms, including VADE and k-DVAE, as well as the standard VAE model, in cluster analysis of latent representations across most benchmark datasets. Additionally, the proposed models demonstrate reasonable reconstruction performance and generate realistic examples from the latent space.</p>

Decoding regulatory structures and features from epigenomics profiles: A Roadmap-ENCODE Variational Auto-Encoder (RE-VAE) model.

Change detection is usually treated as a problem of explicitly detecting land cover transitions in satellite images obtained at different times, and helps with emergency response and government management. This study presents an unsupervised change detection method based on the image fusion of multi-temporal images. The main objective of this study is to improve the accuracy of unsupervised change detection from high-resolution multi-temporal images. Our method effectively reduces change detection errors, since spatial displacement and spectral differences between multi-temporal images are evaluated. To this end, a total of four cross-fused images are generated with multi-temporal images, and the iteratively reweighted multivariate alteration detection (IR-MAD) method—a measure for the spectral distortion of change information—is applied to the fused images. In this experiment, the land cover change maps were extracted using multi-temporal IKONOS-2, WorldView-3, and GF-1 satellite images. The effectiveness of the proposed method compared with other unsupervised change detection methods is demonstrated through experimentation. The proposed method achieved an overall accuracy of 80.51% and 97.87% for cases 1 and 2, respectively. Moreover, the proposed method performed better when differentiating the water area from the vegetation area compared to the existing change detection methods. Although the water area beneath moderate and sparse vegetation canopy was captured, vegetation cover and paved regions of the water body were the main sources of omission error, and commission errors occurred primarily in pixels of mixed land use and along the water body edge. Nevertheless, the proposed method, in conjunction with high-resolution satellite imagery, offers a robust and flexible approach to land cover change mapping that requires no ancillary data for rapid implementation.

Land use planners require up-to-date and spatially accurate time series land resources information and changing pattern for future management. As a result, assessing the status of land cover change due to population growth and arable expansion, land degradation and poor resource management, partial implementation of policy strategies, and poorly planned infrastructural development is essential. Thus, the objective of the study was to quantify the spatiotemporal dynamics of land use land cover change between 1995 and 2014 using 5 multi-temporal cloud-free Landsat Thematic Mapper images. The maximum likelihood (ML)-supervised classification technique was applied to create signature classes for significant land cover categories using means and variances of the training data to estimate the probability that a pixel is a member of a class. The final Bayesian ML classification resulted in 12 major land cover units, and the spatiotemporal change was quantified using post-classification and statistical change detection techniques. For a period of 20 years, there was a continuously increasing demand for arable areas, which can be represented by an exponential growth model. Excepting the year 2009, the built-up area has shown a steady increase due to population growth and its need for infrastructure development. There was nearly a constant trend for water bodies with a change in slope significantly less than +0.01%. The 2014 land cover change statistics revealed that the area was mainly covered by cultivated, wood, bush, shrub, grass, and forest land mapping units accounting nearly 63%, 12%, 8%, 6%, 4%, and 2% of the total, respectively. Land cover change with agro-climatic zones, soil types, and slope classes was common in most part of the area and the conversion of grazing land into plantation trees and closure area development were major changes in the past 20 years.

One-class Classification-Based Machine Learning Model for Estimating the Probability of Wildfire Risk

Recent advances in deep learning and neural networks have led to an increased interest in the application of generative models in statistical and condensed matter physics. In particular, restricted Boltzmann machines (RBMs) and variational autoencoders (VAEs) as specific classes of neural networks have been successfully applied in the context of physical feature extraction and representation learning. Despite these successes, however, there is only limited understanding of their representational properties and limitations. To better understand the representational characteristics of RBMs and VAEs, we study their ability to capture physical features of the Ising model at different temperatures. This approach allows us to quantitatively assess learned representations by comparing sample features with corresponding theoretical predictions. Our results suggest that the considered RBMs and convolutional VAEs are able to capture the temperature dependence of magnetization, energy, and spin-spin correlations. The samples generated by RBMs are more evenly distributed across temperature than those generated by VAEs. We also find that convolutional layers in VAEs are important to model spin correlations whereas RBMs achieve similar or even better performances without convolutional filters.

Recent failures of bridges worldwide highlight the need for robust structural health surveillance systems to provide alerts for early damage and prevent severe loss. Structural health monitoring (SHM) continues to evolve and gain wide adoption among asset managers to mitigate catastrophic failure risks of structural systems. With the prolific integration of SHM with artificial intelligence and internet of things systems becoming prevalent, several data-driven approaches have gained popularity in SHM. However, it is challenging to obtain ground-truth-labelled damage samples for supervised machine learning methods. A class of shallow machine learning methods known as unsupervised methods (e.g. the one-class support vector machine (OCSVM)), which only uses unlabelled data from a healthy state, has been shown to achieve promising results. However, shallow machine learning methods require laborious expert-crafted feature inputs for optimal performance. Inspired by the automatic feature-extraction ability of deep neural networks, unsupervised methods (deep learning models trained without supervisory ground truth labels) such as autoencoder (AE)-based methods were explored to detect structural damage. Results obtained on both real-world data from Sydney Harbour Bridge, one of Australia's iconic structures, and data collected from laboratory specimens demonstrate the effectiveness of the AE-based method over conventional shallow methods such as the OCSVM.

A variational autoencoder (VAE) is a generational deep learning model based on encoding a particular observation into a latent space and then decoding it while incorporating some random noise with the intuition of being able to generate slightly different forms of the input observation. Here, I propose a VAE that is able to generate denovo drug compounds by feeding in a known set of drug compounds against a particular biological target. To demonstrate the ability of the proposed VAE as a generative model, known drug molecules belonging to the class of Neuraminidase (NA) inhibitors were taken from the ZINC database and fed into the VAE model as one-hot encoded SMILES strings. Similarly, active NA inhibitors and decoy molecules together were also fed to compare efficiency. The generated molecules were then screened to remove impractical structures. Next, a drug-likeness (QED) score was computed for each candidate molecule and a cutoff of 0.5 was used to extract viable candidates. To ensure that the generated drug compounds were active NA inhibitors, a series of Artificial Neural Networks (ANNs) classifiers based on three different characterization techniques, namely chemical fingerprinting, molecular descriptions and graph convolutions, were developed to identify active NA inhibitors from decoy molecules. The feature candidate data were then fed into the three designed ANNs to obtain the final set of novel, viable and active NA inhibitors. Seventy-one new NA inhibitors were obtained after three runs of the VAE model under different parameterizations. The proposed VAE can hence be used to generate de-novo drug compounds for a wide variety of biological targets.

The pace of change in land use and cover in Ethiopia depends on three main factors that cause pressure on agriculture land: resettlement programmes, population growth and increasing agricultural investments. Gambella is one of the regions of Ethiopia that attracts large-scale agricultural investments that extensively drive land use and cover changes in the region. The aim of this study is to examine the rate, extent and distribution of various land use and cover changes in Gambella Regional State, Ethiopia, from 1987 to 2017. The analysis is mainly based on Landsat 5 and Sentinel 2A satellite images and fieldwork. Two Landsat Thematic Mapper and a Sentinel 2A image were used for determining the maximum likelihood of land use/cover classification. The results show that farmland decreased by 26 km2 from 1987 to 2000; however, during the last two decades, agricultural land area increased by 599 km2, mainly at the cost of tropical grasslands and forests. We found that areas cultivated by smallholder farmers increased by 9.17% from 1987 to 2000. However, small-scale farm activities decreased by 7% from 2000 to 2017. Areas cultivated by large-scale state farms totalled 202 km2 in 1987; but by 2000, this large-scale state farming had been completely abandoned by the state, and as a result, its land use has decreased to zero. Despite this, in 2017 large-scale farming increased to 746 km2. In addition, Gambella National Park, which is the nation's largest national park and ecosystem, was also largely affected by Land Use and Land Cover changes. The conversion of savannah/tropical grasslands to agricultural farmland has caused varied and extensive environmental degradation to the park. The Land Use and Land Cover changes in the Gambella region are discussed on the basis of underlying socioeconomic factors.

This paper evaluates the effectiveness of advanced Variational Autoencoder (VAE) models in overcoming latent space entanglement and insufficient disentanglement, common issues in traditional VAEs. Traditional VAEs often face challenges in separating distinct features within the latent space, leading to entangled representations that hinder interpretability and compression efficiency. The advanced VAE models examined in this study address these issues by enhancing disentanglement, which results in clearer separation of latent factors and more interpretable representations. However, this improvement in disentanglement may result in a trade-off with reconstruction quality. The article shows that, while these sophisticated models improve disentanglement, they may also have worse reconstruction quality than classic VAEs. The findings highlight the necessity of hyperparameter optimization in successfully navigating this trade-off. Future study should investigate novel model architectures and hyperparameter optimization strategies to optimize the balance of disentanglement and reconstruction quality. Overall, the research emphasizes the ability of advanced VAE models to generate more interpretable representations and the importance of careful tuning to resolve the inherent trade-offs.

Accurate and effective classification of plant diseases is critical for increasing yield and quality in agricultural production, minimizing economic losses through early detection of diseases, and implementing sustainable agriculture approaches. In this study, an approach for the detection and classification of plant leaf diseases is presented. We compare the performance of machine learning and deep learning-based models, and we use GAN-based data synthesis methods on a dataset we created to improve the model performance. For machine learning methods, ResNet-based feature extraction is performed and XGBoost, Random Forest, SVM, and InceptionV3 models are evaluated. In contrast, AlexNet, VGG16, VGG19, DenseNet, and ResNet models are examined within the scope of deep learning. The study was analyzed in three classes Phytophthora Infestans, Potassium Deficiency, and Healthy, and tested on data obtained from 21 different plant species. According to the model performances obtained, the deep learning-based ResNet model showed the highest success in all performance metrics and achieved 99% accuracy, showing superior performance compared to other methods. In the study, a comprehensive evaluation of multiple classification, GAN-based data synthesis, machine learning, and deep learning models was carried out. A valuable contribution was made to the existing studies in the literature.

Analyzing spatiotemporal characteristics of land-cover (LC) change is important for assessing environmental consequences of urban growth and supporting land management and planning. Less attention, however, has been given to the comparison between land-cover change patterns in developing and developed countries. In this study, Xuzhou city and Dortmund city region were selected as study areas. Multitemporal Landsat images were classified by using the integration method of maximum likelihood classifier, subpixel classifier, and multiple normalized difference vegetation index values based on Vegetation-Impervious Surface-Soil model. Urban growth patterns and processes of the two study areas were investigated and compared through land-cover change detection, buffer analysis, and jaggedness degree. The results indicated that the urban area in Xuzhou city increased more than threefold dramatically from 128.5 to 418.3 km 2 , and the increased sprawling development trend was observed during the study period, while Dortmund city region showed a slight increase from 498 to 715.5 km 2 in urban areas with an increasingly compact development trend. The results revealed a notable difference of spatiotemporal land-cover pattern dynamics between the two study areas as well as confirmed the effectiveness of the combined method of remote sensing and spatial analysis that can be used to support land management and policy decisions.

The geomorphological evidences of subsidence in the Nile Delta: Analysis of high resolution topographic DEM and multi-temporal satellite images