Spatial interpolation using conditional generative adversarial neural networks

Zhu, Daoyun; Cheng, Ximeng; Zhang, Fan; Yao, Xin; Gao, Yong; Liu, Yu

doi:10.1080/13658816.2019.1599122

Cited by 122 publications

(64 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep convolutional neural networks (DCNNs) [28] are appropriate algorithms to capture hidden hierarchies of geographical patterns. They have shown great ability to detect deep knowledge for land cover classification [29]- [31], image semantic segmentation [32], [33], object localization [34], [35] and spatial interpolation [36]. Traditional DCNNs utilize local connections of features inside a target image.…”

Section: Introductionmentioning

confidence: 99%

Mapping Human Activity Volumes Through Remote Sensing Imagery

Xing

Huang

Cheng

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

The spatial concentration of human activity is a crucial indication of socioeconomic vitality. Accurately mapping activity volumes is fundamental to support regional sustainable development. Current approaches rely on mobile positioning data, which record information about human daily activity but are inaccessible in most cities due to privacy and data sharing concerns. Alternative methods are needed to provide more generalized predictions on extensive areas while maintaining low cost. This study demonstrates how remote sensing imagery can be used through an end-to-end deep learning framework for reliable estimates of human activity volumes. The neighbour effect, representing the inherent nature of spatial autocorrelation in the volumes, is incorporated to improve the network. The proposed model exhibits strong predictive power and demonstrates great explainability of physical environment on variations of activity volumes. Landscape interpretations based on hierarchical features provide both object-based and region-based insights into the co-evolvement of landscape and human activity. Our findings indicate the possibility of extensively predicting activity volumes, especially in areas with limited access to mobile data, and provide support for the promising framework to better comprehend broad aspects of human society from observable physical environments.

show abstract

Section: Introductionmentioning

confidence: 99%

Mapping Human Activity Volumes Through Remote Sensing Imagery

Xing

Huang

Cheng

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, spatial auto-correlation could be leveraged beyond the set of features we have included so far (see S8 Appendix for a discussion of the spatial auto-correlation in our data and model output). The emerging sub-field of spatial machine learning provides new approaches that are more tailored to spatial data than the methods used here [ 58 – 60 ].…”

Section: Discussionmentioning

confidence: 99%

Learning from urban form to predict building heights

et al. 2020

View full text Add to dashboard Cite

Understanding cities as complex systems, sustainable urban planning depends on reliable high-resolution data, for example of the building stock to upscale region-wide retrofit policies. For some cities and regions, these data exist in detailed 3D models based on real-world measurements. However, they are still expensive to build and maintain, a significant challenge, especially for small and medium-sized cities that are home to the majority of the European population. New methods are needed to estimate relevant building stock characteristics reliably and cost-effectively. Here, we present a machine learning based method for predicting building heights, which is based only on open-access geospatial data on urban form, such as building footprints and street networks. The method allows to predict building heights for regions where no dedicated 3D models exist currently. We train our model using building data from four European countries (France, Italy, the Netherlands, and Germany) and find that the morphology of the urban fabric surrounding a given building is highly predictive of the height of the building. A test on the German state of Brandenburg shows that our model predicts building heights with an average error well below the typical floor height (about 2.5 m), without having access to training data from Germany. Furthermore, we show that even a small amount of local height data obtained by citizens substantially improves the prediction accuracy. Our results illustrate the possibility of predicting missing data on urban infrastructure; they also underline the value of open government data and volunteered geographic information for scientific applications, such as contextual but scalable strategies to mitigate climate change.

show abstract

“…Hyperspectral Image Analysis for efficient and accurate object detection using Deep Learning is one of the timely topics of GeoAI. The most recent research examples include detection of soil characteristics [18], detailed ways of capturing densely populated areas [19], extracting information from scanned historical maps [20], semantic point sorting [21], innovative spatial interpolation methods [22] and traffic forecasting [23].…”

Section: Application Of the Mame-zsl In Hyperspectral Image Analysismentioning

confidence: 99%

GeoAI: A Model-Agnostic Meta-Ensemble Zero-Shot Learning Method for Hyperspectral Image Analysis and Classification

Demertzis

Iliadis

2020

Algorithms

View full text Add to dashboard Cite

Deep learning architectures are the most effective methods for analyzing and classifying Ultra-Spectral Images (USI). However, effective training of a Deep Learning (DL) gradient classifier aiming to achieve high classification accuracy, is extremely costly and time-consuming. It requires huge datasets with hundreds or thousands of labeled specimens from expert scientists. This research exploits the MAML++ algorithm in order to introduce the Model-Agnostic Meta-Ensemble Zero-shot Learning (MAME-ZsL) approach. The MAME-ZsL overcomes the above difficulties, and it can be used as a powerful model to perform Hyperspectral Image Analysis (HIA). It is a novel optimization-based Meta-Ensemble Learning architecture, following a Zero-shot Learning (ZsL) prototype. To the best of our knowledge it is introduced to the literature for the first time. It facilitates learning of specialized techniques for the extraction of user-mediated representations, in complex Deep Learning architectures. Moreover, it leverages the use of first and second-order derivatives as pre-training methods. It enhances learning of features which do not cause issues of exploding or diminishing gradients; thus, it avoids potential overfitting. Moreover, it significantly reduces computational cost and training time, and it offers an improved training stability, high generalization performance and remarkable classification accuracy. Algorithms 2020, 13, 61 2 of 25 Algorithms 2020, 13, 61 3 of 25In contrast to the learning process of the traditional neural networks, it is not sufficient for the network to learn good representations of the training classes, as the testing classes are distinct and they are not presented in training. However, it is desirable to learn features which distinguish the existing classes.The evaluation process consists of two distinct stages of the following format [4]:Step 1: Given k examples (value of k-shot), if k = 1, then the process is called one-shot; if k = 5, five-shot, and so on. The parameter k represents the number of labeled samples given to the algorithm by each class. By considering these samples, which comprise the support set, the network is required to classify and eventually adapt to existing classes.Step 2: Unknown examples of the labeled classes are presented randomly, unlike the ones presented in the previous step, which the network is called to correctly classify. The set of examples in this stage is known as the query set.The above procedure (steps) is repeated many times using random classes and examples which are sampled from the testing-evaluation set.As it is immediately apparent from the description of the evaluation process, as the number of classes increases, the task becomes more difficult, because the network has to decide between several alternatives. This means that Zero-shot Learning [5] is clearly more difficult than the one-shot, which is more difficult than the five-shot, and so on. Although humans have the ability to cope with this process, traditional ANN require many more examples to genera...

show abstract

Spatial interpolation using conditional generative adversarial neural networks

Cited by 122 publications

References 30 publications

Mapping Human Activity Volumes Through Remote Sensing Imagery

Mapping Human Activity Volumes Through Remote Sensing Imagery

Learning from urban form to predict building heights

GeoAI: A Model-Agnostic Meta-Ensemble Zero-Shot Learning Method for Hyperspectral Image Analysis and Classification

Contact Info

Product

Resources

About