skip to main content

Title: Towards a Learned Cost Model for Distributed Spatial Join: Data, Code & Models
Geospatial data comprise around 60% of all the publicly available data. One of the essential and most complex operations that brings together multiple geospatial datasets is the spatial join operation. Due to its complexity, there is a lot of partitioning techniques and parallel algorithms for the spatial join problem. This leads to a complex query optimization problem: which algorithm to use for a given pair of input datasets that we want to join? With the rise of machine learning, there is a promise in addressing this problem with the use of various learned models. However, one of the concerns is the lack of standard and publicly available data to train and test on, as well as the lack of accessible baseline models. This resource paper helps the research community solve this problem by providing synthetic and real datasets for spatial join, source code for constructing more datasets, and several baseline solutions that researchers can further extend and compare to.  more » « less
Award ID(s):
1924694 1838222 2046236
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
Date Published:
Page Range / eLocation ID:
4550 to 4554
Medium: X
Atlanta GA USA
Sponsoring Org:
National Science Foundation
More Like this
  1. This perspective paper highlights the potentials, limitations, and combinations of openly available Earth observation (EO) data and big data in the context of environmental research in urban areas. The aim is to build the resilience of informal settlements to climate change impacts. In particular, it highlights the types, categories, spatial and temporal scales of publicly available big data. The benefits of publicly available big data become clear when looking at issues such as the development and quality of life in informal settlements within and around major African cities. Sub-Saharan African (SSA) cities are among the fastest growing urban areas in the world. However, they lack spatial information to guide urban planning towards climate-adapted cities and fair living conditions for disadvantaged residents who mostly reside in informal settlements. Therefore, this study collected key information on freely available data such as data on land cover, land use, and environmental hazards and pressures, demographic and socio-economic indicators for urban areas. They serve as a vital resource for success of many other related local studies, such as the transdisciplinary research project “DREAMS—Developing REsilient African cities and their urban environMent facing the provision of essential urban SDGs”. In the era of exponential growth of big data analytics, especially geospatial data, their utility in SSA is hampered by the disparate nature of these datasets due to the lack of a comprehensive overview of where and how to access them. This paper aims to provide transparency in this regard as well as a resource to access such datasets. Although the limitations of such big data are also discussed, their usefulness in assessing environmental hazards and human exposure, especially to climate change impacts, are emphasised. 
    more » « less
  2. Due to the developments of topographic techniques, clear satellite imagery, and various means for collecting information, geospatial datasets are growing in volume, complexity, and heterogeneity. For efficient execution of spatial computations and analytics on large spatial data sets, parallel processing is required. To exploit fine-grained parallel processing in large scale compute clusters, partitioning in a load-balanced way is necessary for skewed datasets. In this work, we focus on spatial join operation where the inputs are two layers of geospatial data. Our partitioning method for spatial join uses Adaptive Partitioning (ADP) technique, which is based on Quadtree partitioning. Unlike existing partitioning techniques, ADP partitions the spatial join workload instead of partitioning the individual datasets separately to provide better load-balancing. Based on our experimental evaluation, ADP partitions spatial data in a more balanced way than Quadtree partitioning and Uniform grid partitioning. ADP uses an output-sensitive duplication avoidance technique which minimizes duplication of geometries that are not part of spatial join output. In a distributed memory environment, this technique can reduce data communication and storage requirements compared to traditional methods. To improve the performance of ADP, an MPI+Threads based parallelization is presented. With ParADP, a pair of real world datasets, one with 717 million polylines and another with 10 million polygons, is partitioned into 65,536 grid cells within 7 seconds. ParADP performs well with both good weak scaling up to 4,032 CPU cores and good strong scaling up to 4,032 CPU cores. 
    more » « less
  3. Abstract

    Geospatial data conflation is the process of combining multiple datasets about a geographic phenomenon to produce a single, richer dataset. It has received increased research attention due to its many applications in map making, transportation, planning, and temporal geospatial analyses, among many others. One approach to conflation, attempted from the outset in the literature, is the use of optimization‐based conflation methods. Conflation is treated as a natural optimization problem of minimizing the total number of discrepancies while finding corresponding features from two datasets. Optimization‐based conflation has several advantages over traditional methods including conciseness, being able to find an optimal solution, and ease of implementation. However, current optimization‐based conflation methods are also limited. A main shortcoming with current optimized conflation models (and other traditional methods as well) is that they are often too weak and cannot utilize the spatial context in each dataset while matching corresponding features. In particular, current optimal conflation models match a feature to targets independently from other features and therefore treat each GIS dataset as a collection of unrelated elements, reminiscent of the spaghetti GIS data model. Important contextual information such as the connectivity between adjacent elements (such as roads) is neglected during the matching. Consequently, such models may produce topologically inconsistent results. In this article, we address this issue by introducing new optimization‐based conflation models with structural constraints to preserve the connectivity and contiguity relation among features. The model is implemented using integer linear programming and compared with traditional spaghetti‐style models on multiple test datasets. Experimental results show that the new element connectivity (ec‐bimatching) model reduces false matches and consistently outperforms traditional models.

    more » « less
  4. Obeid, Iyad ; Picone, Joseph ; Selesnick, Ivan (Ed.)
    The Neural Engineering Data Consortium (NEDC) is developing a large open source database of high-resolution digital pathology images known as the Temple University Digital Pathology Corpus (TUDP) [1]. Our long-term goal is to release one million images. We expect to release the first 100,000 image corpus by December 2020. The data is being acquired at the Department of Pathology at Temple University Hospital (TUH) using a Leica Biosystems Aperio AT2 scanner [2] and consists entirely of clinical pathology images. More information about the data and the project can be found in Shawki et al. [3]. We currently have a National Science Foundation (NSF) planning grant [4] to explore how best the community can leverage this resource. One goal of this poster presentation is to stimulate community-wide discussions about this project and determine how this valuable resource can best meet the needs of the public. The computing infrastructure required to support this database is extensive [5] and includes two HIPAA-secure computer networks, dual petabyte file servers, and Aperio’s eSlide Manager (eSM) software [6]. We currently have digitized over 50,000 slides from 2,846 patients and 2,942 clinical cases. There is an average of 12.4 slides per patient and 10.5 slides per case with one report per case. The data is organized by tissue type as shown below: Filenames: tudp/v1.0.0/svs/gastro/000001/00123456/2015_03_05/0s15_12345/0s15_12345_0a001_00123456_lvl0001_s000.svs tudp/v1.0.0/svs/gastro/000001/00123456/2015_03_05/0s15_12345/0s15_12345_00123456.docx Explanation: tudp: root directory of the corpus v1.0.0: version number of the release svs: the image data type gastro: the type of tissue 000001: six-digit sequence number used to control directory complexity 00123456: 8-digit patient MRN 2015_03_05: the date the specimen was captured 0s15_12345: the clinical case name 0s15_12345_0a001_00123456_lvl0001_s000.svs: the actual image filename consisting of a repeat of the case name, a site code (e.g., 0a001), the type and depth of the cut (e.g., lvl0001) and a token number (e.g., s000) 0s15_12345_00123456.docx: the filename for the corresponding case report We currently recognize fifteen tissue types in the first installment of the corpus. The raw image data is stored in Aperio’s “.svs” format, which is a multi-layered compressed JPEG format [3,7]. Pathology reports containing a summary of how a pathologist interpreted the slide are also provided in a flat text file format. A more complete summary of the demographics of this pilot corpus will be presented at the conference. Another goal of this poster presentation is to share our experiences with the larger community since many of these details have not been adequately documented in scientific publications. There are quite a few obstacles in collecting this data that have slowed down the process and need to be discussed publicly. Our backlog of slides dates back to 1997, meaning there are a lot that need to be sifted through and discarded for peeling or cracking. Additionally, during scanning a slide can get stuck, stalling a scan session for hours, resulting in a significant loss of productivity. Over the past two years, we have accumulated significant experience with how to scan a diverse inventory of slides using the Aperio AT2 high-volume scanner. We have been working closely with the vendor to resolve many problems associated with the use of this scanner for research purposes. This scanning project began in January of 2018 when the scanner was first installed. The scanning process was slow at first since there was a learning curve with how the scanner worked and how to obtain samples from the hospital. From its start date until May of 2019 ~20,000 slides we scanned. In the past 6 months from May to November we have tripled that number and how hold ~60,000 slides in our database. This dramatic increase in productivity was due to additional undergraduate staff members and an emphasis on efficient workflow. The Aperio AT2 scans 400 slides a day, requiring at least eight hours of scan time. The efficiency of these scans can vary greatly. When our team first started, approximately 5% of slides failed the scanning process due to focal point errors. We have been able to reduce that to 1% through a variety of means: (1) best practices regarding daily and monthly recalibrations, (2) tweaking the software such as the tissue finder parameter settings, and (3) experience with how to clean and prep slides so they scan properly. Nevertheless, this is not a completely automated process, making it very difficult to reach our production targets. With a staff of three undergraduate workers spending a total of 30 hours per week, we find it difficult to scan more than 2,000 slides per week using a single scanner (400 slides per night x 5 nights per week). The main limitation in achieving this level of production is the lack of a completely automated scanning process, it takes a couple of hours to sort, clean and load slides. We have streamlined all other aspects of the workflow required to database the scanned slides so that there are no additional bottlenecks. To bridge the gap between hospital operations and research, we are using Aperio’s eSM software. Our goal is to provide pathologists access to high quality digital images of their patients’ slides. eSM is a secure website that holds the images with their metadata labels, patient report, and path to where the image is located on our file server. Although eSM includes significant infrastructure to import slides into the database using barcodes, TUH does not currently support barcode use. Therefore, we manage the data using a mixture of Python scripts and manual import functions available in eSM. The database and associated tools are based on proprietary formats developed by Aperio, making this another important point of community-wide discussion on how best to disseminate such information. Our near-term goal for the TUDP Corpus is to release 100,000 slides by December 2020. We hope to continue data collection over the next decade until we reach one million slides. We are creating two pilot corpora using the first 50,000 slides we have collected. The first corpus consists of 500 slides with a marker stain and another 500 without it. This set was designed to let people debug their basic deep learning processing flow on these high-resolution images. We discuss our preliminary experiments on this corpus and the challenges in processing these high-resolution images using deep learning in [3]. We are able to achieve a mean sensitivity of 99.0% for slides with pen marks, and 98.9% for slides without marks, using a multistage deep learning algorithm. While this dataset was very useful in initial debugging, we are in the midst of creating a new, more challenging pilot corpus using actual tissue samples annotated by experts. The task will be to detect ductal carcinoma (DCIS) or invasive breast cancer tissue. There will be approximately 1,000 images per class in this corpus. Based on the number of features annotated, we can train on a two class problem of DCIS or benign, or increase the difficulty by increasing the classes to include DCIS, benign, stroma, pink tissue, non-neoplastic etc. Those interested in the corpus or in participating in community-wide discussions should join our listserv,, to be kept informed of the latest developments in this project. You can learn more from our project website: 
    more » « less
  5. As educators and researchers, we often enjoy enlivening classroom discussions by including examples of cutting-edge high-throughput (HT) technologies that propelled scientific discovery and created repositories of new information. We also call for the use of evidence-based teaching practices to engage students in ways that promote equity and learning. The complex datasets produced by HT approaches can open the doors to discovery of novel genes, drugs, and regulatory networks, so students need experience with the effective design, implementation, and analysis of HT research. Nevertheless, we miss opportunities to contextualize, define, and explain the potential and limitations of HT methods. One evidence-based approach is to engage students in realistic HT case studies. HT cases immerse students with messy data, asking them to critically consider data analysis, experimental design, ethical implications, and HT technologies.The NSF HITS (High-throughput Discovery Science and Inquiry-based Case Studies for Today’s Students) Research Coordination Network in Undergraduate Biology Education seeks to improve student quantitative skills and participation in HT discovery. Researchers and instructors in the network learn about case pedagogy, HT technologies, publicly available datasets, and computational tools. Leveraging this training and interdisciplinary teamwork, HITS participants then create and implement HT cases. Our initial case collection has been used in >15 different courses at a variety of institutions engaging >600 students in HT discovery. We share here our rationale for engaging students in HT science, our HT cases, and network model to encourage other life science educators to join us and further develop and integrate HT complex datasets into curricula. 
    more » « less