scholarly journals Domain-Adversarial Training of Self-Attention-Based Networks for Land Cover Classification Using Multi-Temporal Sentinel-2 Satellite Imagery

2021 ◽  
Vol 13 (13) ◽  
pp. 2564
Author(s):  
Mauro Martini ◽  
Vittorio Mazzia ◽  
Aleem Khaliq ◽  
Marcello Chiaberge
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Domain Adaptation ◽  
Learning Approaches ◽  
Atmospheric Conditions ◽  
Practical Applications ◽  
Area Of Interest ◽  
Multi Temporal ◽  
Significant Performance ◽  
Adversarial Training

The increasing availability of large-scale remote sensing labeled data has prompted researchers to develop increasingly precise and accurate data-driven models for land cover and crop classification (LC&CC). Moreover, with the introduction of self-attention and introspection mechanisms, deep learning approaches have shown promising results in processing long temporal sequences in the multi-spectral domain with a contained computational request. Nevertheless, most practical applications cannot rely on labeled data, and in the field, surveys are a time-consuming solution that pose strict limitations to the number of collected samples. Moreover, atmospheric conditions and specific geographical region characteristics constitute a relevant domain gap that does not allow direct applicability of a trained model on the available dataset to the area of interest. In this paper, we investigate adversarial training of deep neural networks to bridge the domain discrepancy between distinct geographical zones. In particular, we perform a thorough analysis of domain adaptation applied to challenging multi-spectral, multi-temporal data, accurately highlighting the advantages of adapting state-of-the-art self-attention-based models for LC&CC to different target zones where labeled data are not available. Extensive experimentation demonstrated significant performance and generalization gain in applying domain-adversarial training to source and target regions with marked dissimilarities between the distribution of extracted features.

Bullying, School Violence, and Climate in Evolving Contexts

2018 ◽  
Author(s):  
Ron Avi Astor ◽  
Rami Benbenisthty
Keyword(s):  
School Violence ◽  
School Safety ◽  
Media Coverage ◽  
Large Scale ◽  
Ecological Model ◽  
Empirical Studies ◽  
Practical Applications ◽  
Teacher Student ◽  
Area Of Interest ◽  
New Research

Since 2005, the bullying, school violence, and school safety literatures have expanded dramatically in content, disciplines, and empirical studies. However, with this massive expansion of research, there is also a surprising lack of theoretical and empirical direction to guide efforts on how to advance our basic science and practical applications of this growing scientific area of interest. Parallel to this surge in interest, cultural norms, media coverage, and policies to address school safety and bullying have evolved at a remarkably quick pace over the past 13 years. For example, behaviors and populations that just a decade ago were not included in the school violence, bullying, and school safety discourse are now accepted areas of inquiry. These include, for instance, cyberbullying, sexting, social media shaming, teacher–student and student–teacher bullying, sexual harassment and assault, homicide, and suicide. Populations in schools not previously explored, such as lesbian, gay, bisexual, transgender, and queer students and educators and military- and veteran-connected students, become the foci of new research, policies, and programs. As a result, all US states and most industrialized countries now have a complex quilt of new school safety and bullying legislation and policies. Large-scale research and intervention funding programs are often linked to these policies. This book suggests an empirically driven unifying model that brings together these previously distinct literatures. This book presents an ecological model of school violence, bullying, and safety in evolving contexts that integrates all we have learned in the 13 years, and suggests ways to move forward.

scholarly journals Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

2019 ◽  
Vol 11 (10) ◽  
pp. 1153 ◽  
Author(s):  
Mesay Belete Bejiga ◽  
Farid Melgani ◽  
Pietro Beraldini
Keyword(s):  
Neural Networks ◽  
Land Cover ◽  
Transfer Learning ◽  
Large Scale ◽  
Domain Adaptation ◽  
Land Cover Classification ◽  
Target Domain ◽  
Training Samples ◽  
Latent Space ◽  
Large Scale Land

Learning classification models require sufficiently labeled training samples, however, collecting labeled samples for every new problem is time-consuming and costly. An alternative approach is to transfer knowledge from one problem to another, which is called transfer learning. Domain adaptation (DA) is a type of transfer learning that aims to find a new latent space where the domain discrepancy between the source and the target domain is negligible. In this work, we propose an unsupervised DA technique called domain adversarial neural networks (DANNs), composed of a feature extractor, a class predictor, and domain classifier blocks, for large-scale land cover classification. Contrary to the traditional methods that perform representation and classifier learning in separate stages, DANNs combine them into a single stage, thereby learning a new representation of the input data that is both domain-invariant and discriminative. Once trained, the classifier of a DANN can be used to predict both source and target domain labels. Additionally, we also modify the domain classifier of a DANN to evaluate its suitability for multi-target domain adaptation problems. Experimental results obtained for both single and multiple target DA problems show that the proposed method provides a performance gain of up to 40%.

scholarly journals A Generic Data-Driven Recommendation System for Large-Scale Regular and Ride-Hailing Taxi Services

Electronics ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 648 ◽  
Author(s):  
Xiangpeng Wan ◽  
Hakim Ghazzai ◽  
Yehia Massoud
Keyword(s):  
Waiting Time ◽  
Large Scale ◽  
Recommendation System ◽  
Performance Metrics ◽  
Routing Algorithm ◽  
Area Of Interest ◽  
The Future ◽  
Taxi Service ◽  
Significant Performance ◽  
Performance Gains

Modern taxi services are usually classified into two major categories: traditional taxicabs and ride-hailing services. For both services, it is required to design highly efficient recommendation systems to satisfy passengers’ quality of experience and drivers’ benefits. Customers desire to minimize their waiting time before rides, while drivers aim to speed up their customer hunting. In this paper, we propose to leverage taxi service efficiency by designing a generic and smart recommendation system that exploits the benefits of Vehicular Social Networks (VSNs). Aiming at optimizing three key performance metrics, number of pick-ups, customer waiting time, and vacant traveled distance for both taxi services, the proposed recommendation system starts by efficiently estimating the future customer demands in different clusters of the area of interest. Then, it proposes an optimal taxi-to-region matching according to the location of each taxi and the future requested demand of each region. Finally, an optimized geo-routing algorithm is developed to minimize the navigation time spent by drivers. Our simulation model is applied to the borough of Manhattan and is validated with realistic data. Selected results show that significant performance gains are achieved thanks to the additional cooperation among taxi drivers enabled by VSN, as compared to traditional cases.

Land Use and Land Cover Change Based on Remote Sensing and GIS in Changping, Beijing, China and Lake Velence Watershed, Hungary

2011 ◽  
Vol 403-408 ◽  
pp. 1543-1547
Author(s):  
Gai Ying Chen ◽  
Da Zhi Guo ◽  
Malgorzata Verőné Wojtaszek ◽  
Béla Márkus
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Information System ◽  
Land Cover ◽  
Land Cover Change ◽  
Large Scale ◽  
Remote Sensing And Gis ◽  
The Past ◽  
Multi Temporal ◽  
Beijing China

Because of the rapid economy development and the enormous society evolution, large scale changes of land use and land cover had occurred in areas of Beijing and Hungary in the past two decades. This paper focused on monitoring on LUCC(land use and land cover change) in Changping，Beijing, China and Lake Velence watershed area in Szekesfehervar, Hungary based on Multi-Temporal, Multi-Spatial and multi-source remotely sensed images and Geographic Information System( GIS).

scholarly journals Flood Detection Using Multi-Modal and Multi-Temporal Images: A Comparative Study

2020 ◽  
Vol 12 (15) ◽  
pp. 2455
Author(s):  
Kazi Aminul Islam ◽  
Mohammad Shahab Uddin ◽  
Chiman Kwan ◽  
Jiang Li
Keyword(s):  
Domain Adaptation ◽  
Human Life ◽  
Ground Truth ◽  
Accurate Estimation ◽  
Support Vector ◽  
Learning Approaches ◽  
Radar Images ◽  
Response Team ◽  
Multi Temporal ◽  
Flood Detection

Natural disasters such as flooding can severely affect human life and property. To provide rescue through an emergency response team, we need an accurate flooding assessment of the affected area after the event. Traditionally, it requires a lot of human resources to obtain an accurate estimation of a flooded area. In this paper, we compared several traditional machine-learning approaches for flood detection including multi-layer perceptron (MLP), support vector machine (SVM), deep convolutional neural network (DCNN) with recent domain adaptation-based approaches, based on a multi-modal and multi-temporal image dataset. Specifically, we used SPOT-5 and RADAR images from the flood event that occurred in November 2000 in Gloucester, UK. Experimental results show that the domain adaptation-based approach, semi-supervised domain adaptation (SSDA) with 20 labeled data samples, achieved slightly better values of the area under the precision-recall (PR) curve (AUC) of 0.9173 and F1 score of 0.8846 than those by traditional machine approaches. However, SSDA required much less labor for ground-truth labeling and should be recommended in practice.

scholarly journals A New Set of Tools for the Generation of InSAR Visibility Maps Over Wide Areas

Geosciences ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 229
Author(s):  
Matteo Del Soldato ◽  
Lorenzo Solari ◽  
Alessandro Novellino ◽  
Oriol Monserrat ◽  
Federico Raspini
Keyword(s):  
Land Cover ◽  
Ground Motion ◽  
Large Scale ◽  
Good Practice ◽  
Technical Note ◽  
Target Area ◽  
Reliable Technique ◽  
Precise Tool ◽  
Challenging Environment ◽  
Multi Temporal

Multi-temporal Interferometric Synthetic Aperture Radar (MTInSAR) is a solid and reliable technique used to measure ground motion in many different environments. Today, the scientific community and a wide variety of users and stakeholders consider MTInSAR a precise tool for ground motion-related applications. The standard product of a MTInSAR analysis is a deformation map containing a high number of point-like measurement points (MP) which carry information on ground motion. The density of MPs is uneven, and they cannot be extracted continuously at large scale due to geometrical distortions and unfavourable landcover. It is a good practice to assess the feasibility of the interferometric analysis ahead of data processing. This technical note proposes a ready-to-use set of tools aimed at updating existing methods for modelling the effects of local topography and land cover on MTInSAR approaches. The goal of the tools is to provide InSAR experts and non-experts with a fast and automatic way to derive visibility maps, useful for pre-processing screening of a target area, and to forecast the expected density of MP over a specified area. Moreover, the visibility maps are a valid support for users to better understand the available standard and advanced interferometric results. Two workflows are proposed: the first generates the so-called Rindex map (Ri_m) to estimate the influence of topography on MP detection, the second is used to derive a land cover-calibrated Ri_m seen as a probabilistic model for MP detection (MPD_m). The proposed set of tools was applied in the context of the Alpine arc, whose climatic, morphological, and land cover characteristics represent a challenging environment for any interferometric approach.

scholarly journals Removing Inter-Experimental Variability from Functional Data in Systems Neuroscience

2021 ◽  
Author(s):  
Dominic Gonschorek ◽  
Larissa Hoefling ◽  
Klaudia P Szatko ◽  
Katrin Franke ◽  
Timm Schubert ◽  
...  
Keyword(s):  
Large Scale ◽  
Complex Analysis ◽  
Domain Adaptation ◽  
Cell Types ◽  
Learning Approaches ◽  
Cell Type ◽  
Systems Neuroscience ◽  
Biological Signal ◽  
Multiple Data ◽  
Experimental Variability

Integrating data from multiple experiments is common practice in systems neuroscience but it requires inter-experimental variability to be negligible compared to the biological signal of interest. This requirement is rarely fulfilled; systematic changes between experiments can drastically affect the outcome of complex analysis pipelines. Modern machine learning approaches designed to adapt models across multiple data domains offer flexible ways of removing inter-experimental variability where classical statistical methods often fail. While applications of these methods have been mostly limited to single-cell genomics, in this work, we develop a theoretical framework for domain adaptation in systems neuroscience. We implement this in an adversarial optimization scheme that removes inter-experimental variability while preserving the biological signal. We compare our method to previous approaches on a large-scale dataset of two-photon imaging recordings of retinal bipolar cell responses to visual stimuli. This dataset provides a unique benchmark as it contains biological signal from well-defined cell types that is obscured by large inter-experimental variability. In a supervised setting, we compare the generalization performance of cell type classifiers across experiments, which we validate with anatomical cell type distributions from electron microscopy data. In an unsupervised setting, we remove inter-experimental variability from data which can then be fed into arbitrary downstream analyses. In both settings, we find that our method achieves the best trade-off between removing inter-experimental variability and preserving biological signal. Thus, we offer a flexible approach to remove inter-experimental variability and integrate datasets across experiments in systems neuroscience.

scholarly journals INTER-COMPARISON OF THE GLOBAL LAND COVER MAPS IN AFRICA SUPPLEMENTED BY SPATIAL ASSOCIATION OF ERRORS

2019 ◽  
Vol XLII-4/W14 ◽  
pp. 11-16
Author(s):  
G. Bratic ◽  
D. Oxoli ◽  
M. A. Brovelli
Keyword(s):  
Land Cover ◽  
Large Scale ◽  
Confusion Matrix ◽  
Spatial Association ◽  
Probability Of Error ◽  
Earth Observations ◽  
Area Of Interest ◽  
Global Land Cover ◽  
Land Cover Maps ◽  
Single Pixel

<p><strong>Abstract.</strong> Recent advances in Earth Observations supported development of high-resolution land cover (LC) maps on a large-scale. This is an important step forward, especially for developing countries, which experienced problems in the past due to absence of reliable LC information. Nevertheless, increasing number of LC products is imposing additional validation workload to confirm their quality. In this paper inter-comparison of two recent LC products (GlobeLand30 and S2 prototype LC 20m map of Africa) for country of Rwanda in Africa was done. It is a way to facilitate validation by identifying the areas with higher probability of error. Specific approach of comparison of single pixel of one map with multiple pixels of another map provided confusion matrix and sub-pixel agreement table. In this work, accuracy indexes based on the confusion matrix were computed as a measure of similarity between the two maps. Furthermore, Moran’s I index was computed for estimation of spatial association of the pixels in disagreement. Also, total disagreement, as well as disagreement of particularly confused classes was visualised to analyse their spatial distribution. The results are showing that similarity of the two maps is about 66%. Disagreements are spatially associated and the most evident in the eastern and north-western part of the area of interest. This coincides also with the distribution of the two most confused classes Wetland and Shrubland. The results delineate areas of inconsistency between the two maps, and therefore areas where careful accuracy analysis are needed.</p>

scholarly journals Accuracy Assessment of the FROM-GLC30 Land Cover Dataset Based on Watershed Sampling Units: A Continental-Scale Study

2020 ◽  
Vol 12 (20) ◽  
pp. 8435
Author(s):  
Zitian Guo ◽  
Chunmei Wang ◽  
Xin Liu ◽  
Guowei Pang ◽  
Mengyang Zhu ◽  
...  
Keyword(s):  
High Resolution ◽  
Land Cover ◽  
Large Scale ◽  
Reference Data ◽  
Accuracy Assessment ◽  
Visual Interpretation ◽  
Land Cover Types ◽  
Practical Applications ◽  
Land Type ◽  
Continental Scale

Land cover information plays an essential role in the study of global surface change. Multiple land cover datasets have been produced to meet various application needs. The FROM-GLC30 (Finer Resolution Observation and Monitoring of Global Land Cover) dataset is one of the latest land cover products with a resolution of 30 m, which is a relatively high resolution among global public datasets, and the accuracy of this dataset is of great concern in many related researches. The objective of this study was to calculate the accuracy of the FROM-GLC30 2017 dataset at the continental scale and to explore the spatial variation differences of each land type accuracy in different regions. In this study, the visual interpretation land cover results at 20,936 small watershed sampling units based on high-resolution remote sensing images were used as the reference data covering 65 countries in Asia, Europe, and Africa. The reference data were verified by field survey in typical watersheds. Based on that, the accuracy assessment of the FROM-GLC30 2017 dataset was carried out. The results showed (1) the area proportion of different land cover types in the FROM-GLC30 2017 dataset was generally consistent with that of the reference data. (2) The overall accuracy of the FROM-GLC30 2017 dataset was 72.78%, and was highest in West Asia–Northeast Africa, and lowest in South Asia. (3) Among all the seven land cover types, the accuracy of bareland and forest was relatively higher than that of others, and the accuracy of shrubland was the lowest. The accuracy for each land cover type differed among regions. The results of this work can provide useful information for land cover accuracy assessment researches at a large scale and promote the further practical applications of the open-source land cover datasets.

Sign in / Sign up

Export Citation Format

Share Document