Abstract--The extraction of geological lineaments from digital satellite data is a fundamental application in remote sensing. The location of geological lineaments such as faults and dykes are of interest for a range of applications, particularly because of their association with hydrothermal mineralization. Although a wide range of applications have utilized computer vision techniques, a standard workflow for application of these techniques to mineral exploration is lacking. We present a framework for extracting geological lineaments using computer vision techniques which is a combination of edge detection and line extraction algorithms for extracting geological lineaments using optical remote sensing data. It features ancillary computer vision techniques for reducing data dimensionality, removing noise and enhancing the expression of lineaments. We test the proposed framework on Landsat 8 data of a mineral-rich portion of the Gascoyne Province in Western Australia using different dimension reduction techniques and convolutional filters. To validate the results, the extracted lineaments are compared to our manual photointerpretation and geologically mapped structures by the Geological Survey of Western Australia (GSWA). The results show that the best correlation between our extracted geological lineaments and the GSWA geological lineament map is achieved by applying a minimum noise fraction transformation and a Laplacian filter. Application of a directional filter instead shows a stronger correlation with the output of our manual photointerpretation and known sites of hydrothermal mineralization. Hence, our framework using either filter can be used for mineral prospectivity mapping in other regions where faults are exposed and observable in optical remote sensing data. IGITAL satellite data with different spatial and spectral resolution are available for almost every locality on the Earth's land surface [1]-[5]. This enables the procurement of detailed information from surficial features and processes at different scales. Linear features are considered as one of the most important surficial features in different fields of study [6]-[8]. R. Scalzo is with the Centre for Translational Data Science, University of Sydney, Sydney, NSW 2006, Australia (email: richard.scalzo@sydney.edu.au). Linear features represent the expression of some degree of linearity of a single or diverse grouping of both natural and cultural features [9], [10].

Deep neural networks have established as a powerful tool for large scale supervised classification tasks. The state-of-the-art performances of deep neural networks are conditioned to the availability of large number of accurately labeled samples. In practice, collecting large scale accurately labeled datasets is a challenging and tedious task in most scenarios of remote sensing image analysis, thus cheap surrogate procedures are employed to label the dataset. Training deep neural networks on such datasets with inaccurate labels easily overfits to the noisy training labels and degrades the performance of the classification tasks drastically. To mitigate this effect, we propose an original solution with entropic optimal transportation. It allows to learn in an end-to-end fashion deep neural networks that are, to some extent, robust to inaccurately labeled samples. We empirically demonstrate on several remote sensing datasets, where both scene and pixel-based hyperspectral images are considered for classification. Our method proves to be highly tolerant to significant amounts of label noise and achieves favorable results against state-of-the-art methods.

The aim of this project is to detect the rooftop of buildings to determine the available area at different locations and to identify the most suitable ones for solar energy application such as solar PV using Neural Networks and satellite imagery. The Inria Aerial Image Labeling addresses a core topic in remote sensing: the automatic pixelwise labeling of aerial imagery. The first approach to organize the data was to make MX files, one per image, each file contain the 100 images with their respective mask. In order to do that a function mxFileCreator was build. The net selected for this project was at Wolfram Neural Net Repository for Semantic Segmentation.

With the popularization of Artificial Intelligence and its gradual emergence as the core technology that is impelling momentous developments in a large number of fields, there has been a spurt in the use of machine learning and deep learning as well. As per multiple surveys and studies, AI and Machine Learning would be among the highest-paid and most lucrative career streams in the years to come. AI and Machine Learning would revolutionize our existing technological frameworks and usher in a new industrial age by reorienting and transforming everything from the simplest of appliances to automobiles. The applications of Machine Learning are not only limited to the terrestrial zone but have reached for the sky too, both literally as well as figuratively. Just like all other domains that are constantly reimagining themselves and girding for the future, the domain of remote sensing is also undergoing profound changes and witnessing increasing use of specified algorithms when Big Data and Cloud have become almost ubiquitous.

Hydrocarbon exploration is an expensive affair; hence it has to be initiated only after costs and benefits are assessed. There are various methods to identify the sources of oil and gas like Well logging, remote sensing, Gravity survey, magnetic survey, seismic survey etc. which involves high costs and efforts. Exploring oil and gas under land or within the seabed using surface methods is based on two main principles. One is to survey geological features of the land to determine sedimentary rock formation, repeated folds, and faults. The other is to identify the hydrocarbon seepage on the earth surface.

As automation, Machine Learning and AI leave their indelible imprint on multiple and diverse fields, including image analytics, workflow management, construction, autonomous vehicles, agriculture and the future of communication systems, it does seem that very soon these technologies will blast us off to the stratosphere. And the metaphor is quite fitting! AI and Machine Learning solutions are being increasingly researched and implemented in the space sector for a space age of the future, whose mainstay would be advanced robotics and which might resemble a robotic inter-galactic adventure. Application of AI is being extensively researched in the domain of satellite operations, especially in supporting the operational mechanism of huge satellite constellations, which usually includes many facets – relative positioning, communication, if cycle management etc. Machine Learning is being used for analyzing and processing high-resolution satellite imagery and for getting exact and precise visual representations.

Machine learning, combined with satellite imagery and Cloud computing, is enabling understanding of the world and making the food supply chain more efficient. There are more than 7 billion people on Earth now, and roughly one in eight people do not have enough to eat. According to the World Bank, the human population will hit an astounding 9 billion by 2050. With rapidly increasing population, the growing need for food is becoming a grave concern. The burden is now on technology to make up for the looming food crises in the coming decades.

This paper presents a useful method to achieve classification in satellite imagery. The approach is based on pixel level study employing various features such as correlation, homogeneity, energy and contrast. In this study gray-scale images are used for training the classification model. For supervised classification, two classification techniques are employed namely the Support Vector Machine (SVM) and the Naive Bayes. With textural features used for gray-scale images, Naive Bayes performs better with an overall accuracy of 76% compared to 68% achieved by SVM. The computational time is evaluated while performing the experiment with two different window sizes i.e., 50x50 and 70x70. The required computational time on a single image is found to be 27 seconds for a window size of 70x70 and 45 seconds for a window size of 50x50.

Semantic labeling for very high resolution (VHR) images in urban areas, is of significant importance in a wide range of remote sensing applications. However, many confusing manmade objects and intricate fine-structured objects make it very difficult to obtain both coherent and accurate labeling results. For this challenging task, we propose a novel deep model with convolutional neural networks (CNNs), i.e., an end-to-end self-cascaded network (ScasNet). Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation. Technically, multi-scale contexts are captured on the output of a CNN encoder, and then they are successively aggregated in a self-cascaded manner. Meanwhile, for fine-structured objects, ScasNet boosts the labeling accuracy with a coarse-to-fine refinement strategy. It progressively refines the target objects using the low-level features learned by CNN's shallow layers. In addition, to correct the latent fitting residual caused by multi-feature fusion inside ScasNet, a dedicated residual correction scheme is proposed. It greatly improves the effectiveness of ScasNet. Extensive experimental results on three public datasets, including two challenging benchmarks, show that ScasNet achieves the state-of-the-art performance.

This project is jointly funded by the Data Lab and MASTS Industrial Doctorate program and by the University of Strathclyde. The successful candidate will be based at the University of Strathclyde in the Physics Department but will work with a range of experts in machine learning (Dr Jinchang Ren, EEE, Strathclyde), remote sensing (Dr Jacqueline Tweddle, University of Aberdeen) and with Scottish Government scientists (Drs Alejandro Gallego, Matthew Gubbins and Eileen Bresnan, Marine Scotland, Aberdeen). The PhD is open to EU nationals and is fully funded for a total of 3.5 years, with preferred start date of 1st Oct 2018. FTE Category A staff submitted: 27.00