Use Case Intelligence RSS Search use cases Search
NVIDIA Public Sector Spain

Government of Cantabria

Cantabria's small six-person GIS team needed to produce more environmental and infrastructure mapping output with limited staff, but manual cartography and legacy stereo-mapping workflows were too slow and too expensive for regional-scale geospatial analysis.

Read the original story Explore all use cases
1:5,000-scale mapping completed in just three days
From 12 months to under one week
Over 98 percent reduction in production time
Saved over €1.2 million

Reported impact

Business outcome

Cantabria reduced one mapping project's production time by more than 98 percent, saved over €1.2 million versus legacy stereo mapping, and turned work that once required dozens of professionals and up to a year into workflows a single data scientist can complete in days.

  • Cost Reduction
  • Productivity Improvement
  • Risk Reduction

Solution

The Government of Cantabria modernized geospatial analysis by running Esri ArcGIS Pro with GeoAI on NVIDIA RTX workstations and CUDA-accelerated computer vision workflows. The team uses ArcGIS GeoAI together with open models such as U-Net, MaskRCNN, adversarial networks, and VGG-16 to segment land cover, enhance aerial imagery, detect invasive species, and restore historical surveys. NVIDIA RTX 4000 Ada Generation GPUs provide on-premises acceleration for both fine-tuning and inference, which means the GIS office can iterate rapidly on large raster blocks without relying on cloud or data-center infrastructure. The same stack also supports Esri raster analytics pipelines with perceptual-loss feedback loops so analysts can improve color balance, recover shadowed areas, and preserve pixel-level geospatial fidelity. This turns complex earth-observation tasks into workstation-scale workflows that a small public-sector team can operate directly.

Data flow

Satellite and aerial imagery enters ArcGIS Pro, GeoAI models running on CUDA and RTX GPUs segment land cover and enhance raster blocks, specialized models restore or classify imagery, and the resulting maps are published for government planning, biodiversity monitoring, and wildfire-related analysis.

Solution architecture

7 components · 2 layers
  1. Compute
    • GeoAI Supplies the AI computer-vision capabilities used for segmentation, super-resolution, and land-cover analysis.
    • NVIDIA CUDA Accelerates the AI and raster-analytics workloads that process large geospatial imagery datasets.
    • NVIDIA RTX 4000 Ada Generation GPUs Deliver the on-premises workstation compute used for training and inference without cloud infrastructure.
    • U-Net Supports image-transformation and segmentation tasks in Cantabria's geospatial workflows.
    • MaskRCNN Handles object segmentation across diverse terrain and mapping classes.
    • VGG-16 Evaluates perceptual quality when restoring historical aerial imagery.
  2. Serving
    • Esri ArcGIS Pro Provides the geospatial analysis environment that hosts Cantabria's GPU-accelerated mapping workflows.

Architecture clues

  • Perceptual-loss feedback loops are used to validate large image-block enhancements.
  • The same GeoAI stack is used for land-cover mapping, historical image restoration, invasive-species detection, and crop-field classification.
  • The team runs the full workflow on-premises with workstation GPUs instead of cloud or data-center infrastructure.

Evidence from the source

Reduced production time for one project by over 98 percent, from 12 months to under one week.
Saved over €1.2 million using NVIDIA RTX Workstation™, compared to legacy stereo mapping solutions.
The Government of Cantabria is transforming geospatial analysis by using Esri ArcGIS Pro with GeoAI, powered by NVIDIA RTX Workstation™ GPUs and CUDA®.
The integration of NVIDIA CUDA with Esri ArcGIS GeoAI has empowered Cantabria's geospatial team to generate high-resolution cartographic displays with unprecedented speed and precision.
The team was able to accelerate AI fine-tuning and inference cycles without the need for data center or cloud infrastructure.
Transparency Evidence & methodology 100/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    4 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. NVIDIA

    Government of Cantabria customer story

    First-party
    https://www.nvidia.com/en-us/case-studies/next-gen-geospatial-insights-with-cuda-and-gpu-acceleration/
    Source type
    Vendor-published customer story
    Published
    Jan 23, 2026
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Jan 23, 2026 · NVIDIA · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
NVIDIA Oct 9, 2026 California Department of Transportation (Caltrans) Public Sector United States Caltrans needed to inspect and monitor roughly 1,200 active transportation projects more frequently and safely, but manual site visits were slow, inconsistent, and risky for staff working around traffic, bridges, and… Remote operations up to 100 miles Real-time Analytics Esri ArcGIS · NVIDIA CUDA · NVIDIA Jetson Orin NVIDIA Aug 12, 2026 Internal Revenue Service Public Sector United States IRS investigators needed to search multi-terabyte tax and transaction data to expose fraud and identity-theft rings, but CPU clusters and manual data stitching could not finish graph-heavy jobs quickly enough to support… 3+ terabyte dataset Fraud Detection Cloudera · NVIDIA AI Enterprise · NVIDIA RAPIDS NVIDIA Jul 7, 2026 French Ministry of Economy and Finance Public Sector France French public servants needed to answer citizen requests against more than 100 million documents per year while maintaining legal accuracy, security, confidentiality, and compliance, but manual retrieval and analysis of… 1,000 work hours saved per month for a typical 100-user deployment Document ProcessingFraud Detection DeepBrain · NVIDIA AI Enterprise · NVIDIA DGX platform