3 Spatial Data Science Trends to Watch in 2021


Geography is changing faster than ever before. Read our predictions for the key Spatial Data Science trends & industries to watch in 2021.

This post may describe functionality for an old version of CARTO. Find out about the latest and cloud-native version here.
3 Spatial Data Science Trends to Watch in 2021

Geography is changing faster than ever before. Global warming and COVID-19 are pushing change at an unprecedented speed  modifying our environments  markets  and society. This means that we now have a new set of requirements for spatial analysis with the study of Geography and Spatial Data Science becoming much more real time.

As we've seen in 2020 change can happen abruptly and we need to be ready. As we start a new year  one of renewed optimism and hope  what are these requirements and what trends should we be focusing on to ensure we can meet the challenges ahead?

New Requirements for Spatial Analysis

  • Immediate: The time from action to insight is reducing dramatically
  • Fresh: Primary data needs to be days or months old  not years old
  • Multi-source: Competitive alternative sources for completeness or validation
  • Continuous: Analysis can no longer be a point in time
  • Automated: Possibility to continuously replicate and connect to decision tools

Cloud Native Spatial Analysis

This set of new requirements needs new solutions and the ability to perform analysis in a different way. Cloud native spatial data infrastructures will enable us to work much faster and with even more data. Not only will they help us work more efficiently but in a much more fun way since we will not have to worry about 'the plumbing'.

   {% include icons/icon-quotes.svg %}    It is an appropriate moment to move on from the data-dominated GIS era towards a computational geography
       Stan Openshaw  Founder Center for Computational Geography  

Computational geography is not a new concept (the quote above is from 1994) but only now is it possible thanks to the cloud and more needed than ever. No-code interactive dashboards are enabling data storytelling at a scale never seen before.

Next Gen Data Warehouses

Next generation data warehouses  such as BigQuery  Snowflake  Redshift  and Azure Synapse Analytics  provide processing power that can be leverage through SQL or Python notebooks which have three key characteristics that make the game changers from previous generations:

  1. Computing Storage separation: leveraging cheap cloud storage and making all your data available all of the time  always ready
  2. Scalability: leverage large computing capabilities transparently and cost effectively
  3. Data Multi-tenancy: providing the data right in your database

In recent times major next generation data warehouses have added spatial support to their products - think PostGIS but at scale  which is a major step forward for the industry.

At last year's Spatial Data Science Conference  Dr. Chad W. Jennings  GIS Product Lead at Google Cloud gave more details about the geospatial support within BigQuery.

Data Democratization

   {% include icons/icon-quotes.svg %}    Data democratization means that everybody has access to data and there are no gatekeepers that create a bottleneck at the gateway to the data. It requires that we accompany the access with an easy way for people to understand the data so that they can use it to expedite decision-making and uncover opportunities for an organization.
       Bernard Marr  Author & Strategic Business & Technology Advisor  

One of the main problems in data analytics today is the amount of time Data Scientists spend gathering the right data. We frequently hear that 80% of their total analysis time is dedicated to gathering  cleaning and feature preparation  while only the remaining 20% is actually spent on analysis  modeling  and communication of results.

Time spent by Data Scientists

Data marketplaces allow location data democratization. They provide simple access to thousands of public and premium datasets from vetted sources; simplifying the licensing process and giving the end-user standardized methods to access up-to-date and ready to query high-quality location data.

Homogenizing the metadata for datasets offered in such marketplaces allows for a consistent exploration of all available products and ensures simple but precise data enrichment methods.

Data can be accessed from relevant work environments; via Jupyter Notebooks and Python packages  or via drag and drop mapping tools  in order to extract key insights  and create lightweight  intuitive dashboards to share across organizations.

These Spatial Data Science trends can play a key role in the recovery of many industries suffering from the events of 2020. This year we predict an increasing adoption of such technologies across all industries  in particular in CPG & Retail  Financial Services  and Logistics. Keep your eyes on the blog and our social accounts for an event announcement relating to these industries very soon!

Want to get started?

Sign up for a free account