Understanding the evolution of a process over space and time is fundamental to a variety of disciplines. Such phenomena that exhibit dynamics in both space and time include propagation of diseases, evolution of agro-ecosystems, variations in air pollution, dynamics in fluid flows, and patterns in neural activity. In addition to these fields in which modeling the nonlinear evolution of a process is the focus, there is also an emerging interest in decision-making and controlling of autonomous agents in the spatiotemporal domain. That is, in addition to learning what actions to take, when and where to take actions is becoming crucial for an agent to successfully interact with dynamic environments. Although various modeling techniques and conventions are used in different application domains, the fundamental principles remain unchanged. Automatically capturing the dependencies between spatial and temporal components, making accurate predictions into the future, quantifying the uncertainty associated with predictions, real-time performance, and working in both big data and data scarce regimes are some of the key aspects that deserve our attention. Establishing connections between Machine Learning and Statistics, this workshop aims at:
(1) Raising open questions on challenges of spatiotemporal modeling and decision-making;
(2) Establishing connections among diverse application domains of spatiotemporal modeling and control; and
(3) Encouraging conversation between theoreticians and practitioners to develop robust predictive models.


    Theory: stochastic processes, deep learning/convolutional LSTM, control theory, Bayesian filtering, kernel methods,                time-frequency analysis, chaos theory, reinforcement learning for dynamic environments,

                 dynamic policy learning, biostatistics, epidemiology, geostatistcs, climatology, neuroscience, etc.


            Natural phenomena: disease propagation and outbreaks, environmental monitoring, climate modeling, etc.

       Social sciences and economics: predictive policing, population mapping, poverty mapping, food resources,

                                                               agricultural monitoring and control, etc.

            Engineering/robotics: active data collection, traffic modeling, motion prediction, fluid dynamics,

                                     music representation and generation, analysis of video data, multi-sensor fusion, etc.

 * We have 20 tickets from the reserved tickets pool available for speakers of the workshop.

 Important Dates
   Camera ready deadline: November 30, 2018 11:59 pm AOE
   Workshop: December 07, 2018 8.00-6:30 (Room 513ABC, Palais des Congrès de Montréal, Montréal, Canada)

Camera-ready submission instructions
     1. Replace the original NIPS latex style file with this modified latex style file. The only difference in the new style file is that the details of the workshop has been added to the footnote.
     2. Change \usepackage{nips_2018} to \usepackage[final]{nips_2018} in the tex file. Make sure all author details are added.
     3. Please note that the maximum number of pages for the main content of the paper is four, excluding references and supplementary materials. If the paper accompanies supplementary files (pdfs, videos, etc.), please upload them to your own file hosting service (dropbox, youtube, github, etc.) and clearly provide the links just below the abstract. Alternatively, you might append the paper (after references) with supplementary materials.
     4. Replace the existing pdf file in the OpenReview System with the camera-ready pdf.
Attending NIPS
Visit https://nips.cc/. Note that NIPS tickets to the main conference are already sold out. However, a limited number of tickets from the reserved tickets pool will be offered to the speakers of the workshops.


First call for contributions
We welcome short papers (max 4 pages, excluding references) with theory, direct applications, or attempts to improve efficiency in existing spatiotemporal modeling techniques. Following NIPS formatting guidelines, the papers should be submitted via OpenReview.net/nips18_spatiotemporal in pdf format. As far as the manuscript is not entirely identical, dual submission is allowed. The papers will be peer-reviewed (double-blind). Accepted papers will be will be available online on OpenReview and presented as contributed talks or posters.

Manuscript submission instructions
  1. Use the NIPS style file to format your paper. 
  2. Limit the maximum number of pages to four, excluding references. 
  3. Anonymize the authors in the manuscript (the pdf file that will be uploaded) for the purpose of double-blind reviewing.
  4. If the manuscript accompanies supplementary files (pdfs, videos, etc.), please upload them to your own file hosting service (dropbox, youtube, etc) and clearly provide the links just below the abstract.
  5. Visit [submit] and click "Add: NIPS 2018 Workshop Spatiotemporal Submission" to upload a pdf of the manuscript.
  6. Please use the same author names and email addresses that you intend to use/have used to register in the NIPS.cc website.
  7. If the paper is an application, please pick keywords that reflect both the application domain and the theory used. New keywords can be added in addition to the keywords listed above.
 Important Dates

   Second round:
   Paper submission deadline:  October 19, 2018 11:59 pm AOE [submit]
   Acceptance notification: November 03, 2018 (by email) - updated!

   First round:
   Paper submission deadline:  September 30, 2018 11:59 pm AOE [submit]
   Acceptance notification: October 24, 2018 (by email) - updated!