Efficient downscaling of satellite oceanographic data with convolutional neural networks

Space-borne satellite radiometers measure Sea Surface Temperature (SST), which is pivotal to studies of air-sea interactions and ocean features. Under clear sky conditions, high resolution measurements are obtainable. But under cloudy conditions, data analysis is constrained to the available low resolution measurements. We assess the efficiency of Deep Learning (DL) architectures, particularly Convolutional Neural Networks (CNN) to downscale oceanographic data from low spatial resolution (SR) to high SR. With a focus on SST Fields of Bay of Bengal, this study proves that Very Deep Super Resolution CNN can successfully reconstruct SST observations from 15 km SR to 5km SR, and 5km SR to 1km SR. This outcome calls attention to the significance of DL models explicitly trained for the reconstruction of high SR SST fields by using low SR data. Inference on DL models can act as a substitute to the existing computationally expensive downscaling technique: Dynamical Downsampling. The complete code is available on this Github Repository.

The 3rd ACM SIGSPATIAL International Workshop on Geospatial Simulation

Space has long been acknowledged by researchers as a fundamental constraint which shapes our world. As technological changes have transformed the very concept of distance, the relative location and connectivity of geospatial phenomena have remained stubbornly significant in how systems function. At the same time, however, technology has advanced the science of geospatial simulation to bear on our understanding of how such systems work. While previous generations of scientists and practitioners were unable to gather spatial data or to incorporate it into models at any meaningful scale, new methodologies and data sources are becoming increasingly available to researchers, developers, users, and practitioners. These developments present new research opportunities for geospatial simulation.

The 13th ACM SIGSPATIAL International Workshop on Computational Transportation Science (IWCTS 2020)

Today's growth in big data, edge computing, high-performance computing, and machine learning has opened tremendous opportunities for advances in mobility. The 13 th International Workshop on Computational Transportation Science (IWCTS 2020) is particularly timely given the prominence of connected automated vehicles technologies in the global auto industry's near-term growth strategies, of big data analytics, unprecedented access to sensing data of mobility, and of integration of this analytics into the optimization of mobility and transport. These developments (as listed below) are deeply computational. • Transportation Planning & Modeling: travel behavioral analysis, modeling and simulation of population movements and freight transportation systems. • Transportation Operations: Connected and Autonomous (CAVs), Computational traffic flow models and control algorithms, role of transportation in community spread of a pandemic (COVID-19). • Infrastructure Sensing: Digital Twin, Data-driven approaches to transportation systems operations • Other Technologies: Urban sensing technologies, Geoinformatics and Regional Science

The 1st ACM SIGSPATIAL International Workshop on Modeling and Understanding the Spread of COVID-19

In response to the COVID-19 pandemic, a number of spatially-explicit models have been developed to better explain the pathways of the disease, to predict the trajectory of the disease, and to test the effect of different health guidelines and policies on the number of cases and deaths. The 1st ACM SIGSPATIAL International Workshop on Modeling and Understanding the Spread of COVID-19 workshop (COVID'2020) featured research efforts that aim to understand the spatial processes and patterns of COVID-19 spread using a variety of spatial modeling, simulation, and mining approaches. The goal of this workshop was to bring together a range of interdisciplinary researchers in the SIGSPATIAL community in the fields of computer science, spatial modeling, social sciences, and epidemiology. Also, this workshop was advertised for anyone interested in infectious disease data and modelling, including but not limited to COVID-19.

The 2nd ACM SIGSPATIAL International Workshop on Spatial Gems

Researchers and practitioners working with spatial data often develop fundamental new techniques they would like to share with their community. These are not necessarily new research results, not yet in any textbook, but they are interesting, self-contained techniques for doing something useful in the domain of spatial data. We call these techniques "spatial gems".

The 2nd ACM SIGSPATIAL International Workshop on Geospatial Data Access and Processing APIs (SpatialAPI 2020)

With the increasing amount of publicly available geospatial data, the demand on spatial data exploration and analysis kept growing. The SIGSPATIAL community is both a provider of new systems with cutting-edge technology on accessing and processing geospatial data, and a user for all these systems. The SpatialAPI workshop is designed to help the SIGSPATIAL community by growing the knowledge of the existing well-established systems that are available for accessing and processing geospatial data. This includes, but is not limited to, web APIs, programming libraries, database systems, and geospatial extensions to existing systems.

Introduction to this special issue

The 28th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2020) was originally planned to take place in Beijing, China. Due to the coronavirus outbreak, the conference was first moved to Seattle, Washington, USA and then transitioned into a fully virtual conference. This newsletter provides event and experience reports of the organizers of the main conference and the ten satellite workshops.

The Fourth ACM SIGSPATIAL Workshop on Location-Based Recommendations, Geosocial Networks and Geoadvertising

The amount of publicly available geo-referenced data has seen a dramatic increase over the last years. Many user activities generate data that are annotated with location and contextual information. Moreover, it has become easier to collect and combine rich and diverse location information. In the context of geoadvertising, the use of geosocial data for targeted marketing is receiving significant attention from a wide spectrum of companies and organizations. With the advent of smartphones and online social networks, a multi-billion dollar industry that utilizes geosocial data for advertising and marketing has emerged. Geotagged social-media posts, GPS traces, data from cellular antennas and WiFi access points are used widely to directly access people for advertising, recommendations, marketing, and group purchases. Exploiting this torrent of geo-referenced data provides a tremendous potential to materially improve existing recommendation services and offer novel ones, with numerous applications in many domains, including social networks, marketing, and tourism.

The 5th ACM SIGSPATIAL International Workshop on Safety and Resilience

Safety is vital for people and emergency management helps keep people safe. Emergency management includes four stages: Planning and Mitigation, Preparedness, Response and Recovery. Geospatial applications (including GIS) have been extensively used in each stage of emergency management. Nowadays, on the technical side, artificial intelligence tools like deep learning could be put to good use. For example, one of the main benefits of deep learning over various machine learning algorithms is its ability to generate new features from limited series of features located in the training dataset. Therefore, deep learning algorithms can create new tasks to solve current ones. Decision-makers can utilize the geospatial information to develop planning and mitigation strategies with such advanced techniques. GIS models and simulation capabilities are used to exercise response and recovery plans during non-disaster times. They help the decision-makers sense the near real-time possibilities during an event. Once disaster occurs, GIS will take effect in real time response and recovery activities.