Predict Changes in Multi-Dimensional Geo Data Dots Using Quantum Artificial Intelligence

Business, science and administration, but also politics and society are increasingly relying on the analysis of spatial- and datetime-referenced data to reveal hidden patterns in existing information visible, to gain new insights and to stay one step ahead of the competition. Comprehensive knowledge of existing conditions and values is an essential basis for planning, reorientation and utilization processes.
Quantum Computing is the next big thing in information technology. Combined with Geographic Information Systems tools it will enable a wide range of further advances in spatial analysis. Based on the phenomena of quantum mechanics, superposition and entanglement, and the associated high performance of quantum computers, artificial intelligence can be operated more efficiently on quantum hardware than on classical computers.
The technical basis of the GIS used here includes connectors for layers of information from above, at, and below the Earth’s surface. This allows to extract and connect data from various layers into Geo Data Dots and use them to train the QAI system. With the trained system predictions are made. Finally, the results are retransformed and submitted to the GIS.
The system is up and running, and it’s working well. In the next steps the algorithm is to be adjusted to run on other quantum hardware. At the same time the structure of the circuits, the presentation of data for the quantum hardware, and the entire data workflow will be optimized.
Predict Changes in Multi-Dimensional Geo Data Dots Using Quantum Artificial Intelligence

Key Insights & References

Value proposition

Improve the quality of predictions for complex data structures

Bottleneck of SOTA

Predicting changes in massive, multi-dimensional data structures involving complex numbers on classical hardware is not as simple and/or fast as it should be.

Year Published

2026

Application Area

Artificial Intelligence

Quantum Computing

Operational Mode

Real-Time
(indicates that the quantum solution operates or provides results as events occur, suitable for applications where immediate or near-immediate feedback is required.)

Problem Domain

Machine Learning 

Solution type

Quantum algorithm on quantum hardware

Datatype for algorithms

Quantum data 

Hardware

NISQ

Plattform

Superconducting 

Current Status/ Technology Readiness

Demonstrations on realistic data 

Algorithm

Machine Learning

Runtime Scaling

Circuit depth

Number of shots
(for high fidelity)

128

Iterations
(to converge on a solution)

128

Number of qubits needed

Logical Qubits

Physical Qubits

Accuracy

Fidelities

Gate Fidelity

State Preparation Fidelity

Measurement Fidelity

Error Correction Threshold

Problem size and accuracy
the state-of-the-art classical solution
is able to solve

Problem Size

Accuracy

Solution Method

Computational Resources

Quantum Business Network

We Build a Strong Quantum Industry Together!

Login in on QBN Platform

Issues logging in?

or