Creating accurate maps today is a painstaking, time-consuming manual process, even with access to satellite imagery and mapping software. Many regions -- particularly in the developing world -- remain largely unmapped. To help close this gap, Facebook AI researchers and engineers have developed a new method that uses deep learning and weakly supervised training to predict road networks from commercially available high-resolution satellite imagery. The resulting model sets a new bar for the state of the art for accuracy, and because it is able to accommodate regional differences in road networks, it can effectively predict roads around the globe. We are now sharing the details of our model and making data available to the global mapping community through Map With AI, a new set of specialized map-editing services and tools. Map With AI includes an editor interface, RapiD, which allows mapping experts to easily review, verify, and adjust the map as needed.

In my earlier post, I wrote about the events leading up to my paper in GIScience & Remote Sensing. In this short post I would like to help you conduct your own machine learning classification of Sentinel-2 data using the open source package R. The process is pretty straightforward if you have experience in remote sensing and image classification. Even if you don't have extensive experience, basic knowledge of remote sensing terminology is sufficient. I've provided detailed information about different machine learning algorithms, including explanations of key concepts in my article linked below.

Despite recent advances of deep Convolutional Neural Networks (CNNs) in various computer vision tasks, their potential for classification of multispectral remote sensing images has not been thoroughly explored. In particular, the applications of deep CNNs using optical remote sensing data have focused on the classification of very high-resolution aerial and satellite data, owing to the similarity of these data to the large datasets in computer vision. Accordingly, this study presents a detailed investigation of state-of-the-art deep learning tools for classification of complex wetland classes using multispectral RapidEye optical imagery. Specifically, we examine the capacity of seven well-known deep convnets, namely DenseNet121, InceptionV3, VGG16, VGG19, Xception, ResNet50, and InceptionResNetV2, for wetland mapping in Canada. In addition, the classification results obtained from deep CNNs are compared with those based on conventional machine learning tools, including Random Forest and Support Vector Machine, to further evaluate the efficiency of the former to classify wetlands. The results illustrate that the full-training of convnets using five spectral bands outperforms the other strategies for all convnets. InceptionResNetV2, ResNet50, and Xception are distinguished as the top three convnets, providing state-of-the-art classification accuracies of 96.17%, 94.81%, and 93.57%, respectively. The classification accuracies obtained using Support Vector Machine (SVM) and Random Forest (RF) are 74.89% and 76.08%, respectively, considerably inferior relative to CNNs. Importantly, InceptionResNetV2 is consistently found to be superior compared to all other convnets, suggesting the integration of Inception and ResNet modules is an efficient architecture for classifying complex remote sensing scenes such as wetlands.

Remote Sensing Images from satellites have been used in various domains for detecting and understanding structures on the ground surface. In this work, satellite images were used for localizing parking spaces and vehicles in parking lots for a given parcel using an RCNN based Neural Network Architectures. Parcel shapefiles and raster images from USGS image archive were used for developing images for both training and testing. Feature Pyramid based Mask RCNN yields average class accuracy of 97.56% for both parking spaces and vehicles

For machine learning perception problems, human-level classification performance is used as an estimate of top algorithm performance. Thus, it is important to understand as precisely as possible the factors that impact human-level performance. Knowing this 1) provides a benchmark for model performance, 2) tells a project manager what type of data to obtain for human labelers in order to get accurate labels, and 3) enables ground-truth analysis--largely conducted by humans--to be carried out smoothly. In this empirical study, we explored the relationship between resolution and human classification performance using the MNIST data set down-sampled to various resolutions. The quantitative heuristic we derived could prove useful for predicting machine model performance, predicting data storage requirements, and saving valuable resources in the deployment of machine learning projects. It also has the potential to be used in a wide variety of fields such as remote sensing, medical imaging, scientific imaging, and astronomy.

These are exciting times for computational sciences with the digital revolution permeating a variety of areas and radically transforming business, science, and our daily lives. The Internet and the World Wide Web, GPS, satellite communications, remote sensing, and smartphones are dramatically accelerating the pace of discovery, engendering globally connected networks of people and devices. The rise of practically relevant artificial intelligence (AI) is also playing an increasing part in this revolution, fostering e-commerce, social networks, personalized medicine, IBM Watson and AlphaGo, self-driving cars, and other groundbreaking transformations. Unfortunately, humanity is also facing tremendous challenges. Nearly a billion people still live below the international poverty line and human activities and climate change are threatening our planet and the livelihood of current and future generations. Moreover, the impact of computing and information technology has been uneven, mainly benefiting profitable sectors, with fewer societal and environmental benefits, further exacerbating inequalities and the destruction of our planet. Our vision is that computer scientists can and should play a key role in helping address societal and environmental challenges in pursuit of a sustainable future, while also advancing computer science as a discipline. For over a decade, we have been deeply engaged in computational research to address societal and environmental challenges, while nurturing the new field of Computational Sustainability.

Road extraction from very high resolution satellite images is one of the most important topics in the field of remote sensing. For the road segmentation problem, spatial properties of the data can usually be captured using Convolutional Neural Networks. However, this approach only considers a few local neighborhoods at a time and has difficulty capturing long-range dependencies. In order to overcome the problem, we propose Non-Local LinkNet with non-local blocks that can grasp relations between global features. It enables each spatial feature point to refer to all other contextual information and results in more accurate road segmentation. In detail, our method achieved 65.00\% mIOU scores on the DeepGlobe 2018 Road Extraction Challenge dataset. Our best model outperformed D-LinkNet, 1st-ranked solution, by a significant gap of mIOU 0.88\% with much less number of parameters. We also present empirical analyses on proper usage of non-local blocks for the baseline model.

In this paper we address the challenge of land cover classification for satellite images via Deep Learning (DL). Land Cover aims to detect the physical characteristics of the territory and estimate the percentage of land occupied by a certain category of entities: vegetation, residential buildings, industrial areas, forest areas, rivers, lakes, etc. DL is a new paradigm for Big Data analytics and in particular for Computer Vision. The application of DL in images classification for land cover purposes has a great potential owing to the high degree of automation and computing performance. In particular, the invention of Convolution Neural Networks (CNNs) was a fundament for the advancements in this field. In [1], the Satellite Task Team of the UN Global Working Group describes the results achieved so far with respect to the use of earth observation for Official Statistics. However, in that study, CNNs have not yet been explored for automatic classification of imagery. This work investigates the usage of CNNs for the estimation of land cover indicators, providing evidence of the first promising results. In particular, the paper proposes a customized model, called Satellite-Net, able to reach an accuracy level up to 98% on test sets.

Accurately forecasting urban development and its environmental and climate impacts critically depends on realistic models of the spatial structure of the built environment, and of its dependence on key factors such as population and economic development. Scenario simulation and sensitivity analysis, i.e., predicting how changes in underlying factors at a given location affect urbanization outcomes at other locations, is currently not achievable at a large scale with traditional urban growth models, which are either too simplistic, or depend on detailed locally-collected socioeconomic data that is not available in most places. Here we develop a framework to estimate, purely from globally-available remote-sensing data and without parametric assumptions, the spatial sensitivity of the (\textit{static}) rate of change of urban sprawl to key macroeconomic development indicators. We formulate this spatial regression problem as an image-to-image translation task using conditional generative adversarial networks (GANs), where the gradients necessary for comparative static analysis are provided by the backpropagation algorithm used to train the model. This framework allows to naturally incorporate physical constraints, e.g., the inability to build over water bodies. To validate the spatial structure of model-generated built environment distributions, we use spatial statistics commonly used in urban form analysis. We apply our method to a novel dataset comprising of layers on the built environment, nightlighs measurements (a proxy for economic development and energy use), and population density for the world's most populous 15,000 cities.

As climate change escalates, the impact of natural disasters is likely to become less predictable. To encourage the use of machine learning for building damage assessment this week, Carnegie Mellon University's Software Engineering Institute and CrowdAI -- the U.S. Department of Defense's Joint AI Center (JAIC) and Defense Innovation Unit -- open-sourced a labeled data set of some of the largest natural disasters in the past decade. Called xBD, it covers the impact of disasters around the globe, like the 2010 earthquake that hit Haiti. "Although large-scale disasters bring catastrophic damage, they are relatively infrequent, so the availability of relevant satellite imagery is low. Furthermore, building design differs depending on where a structure is located in the world. As a result, damage of the same severity can look different from place to place, and data must exist to reflect this phenomenon," reads a research paper detailing the creation of xBD.