# Deep Learning-based Signal Strength Prediction Using Geographical Images and Expert Knowledge

arXiv: https://arxiv.org/abs/2008.07747 · HTML: https://mlsanity.com/paper/2008.07747/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2020.

## Built on by (most cited first, 9 of 9)

- [Data-Driven Radio Environment Map Estimation Using Graph Neural Networks](https://mlsanity.com/paper/2407.07713/) (2024)
- [Two-Stage Radio Map Construction with Real Environments and Sparse Measurements](https://mlsanity.com/paper/2410.18092/) (2024)
- [Machine Learning for Modeling Wireless Radio Metrics with Crowdsourced Data and Local Environment Features](https://mlsanity.com/paper/2501.01344/) (2025)
- [AIRMap: AI-Generated Radio Maps for Wireless Digital Twins](https://mlsanity.com/paper/2511.05522/) (2025)
- [Variational Autoencoder Assisted Neural Network Likelihood RSRP Prediction Model](https://mlsanity.com/paper/2207.00166/) (2022)
- [Learning Cellular Coverage from Real Network Configurations using GNNs](https://mlsanity.com/paper/2304.10328/) (2023)
- [RSSI Estimation for Constrained Indoor Wireless Networks using ANN](https://mlsanity.com/paper/2404.15337/) (2024)
- [Context-Aware Mobile Network Performance Prediction Using Network & Remote Sensing Data](https://mlsanity.com/paper/2405.00220/) (2024)
- [Deep learning approaches to indoor wireless channel estimation for low-power communication](https://mlsanity.com/paper/2405.12427/) (2024)

## Abstract (arXiv)

Methods for accurate prediction of radio signal quality parameters are crucial for optimization of mobile networks, and a necessity for future autonomous driving solutions. The power-distance relation of current empirical models struggles with describing the specific local geo-statistics that influence signal quality parameters. The use of empirical models commonly results in an over- or under-estimation of the signal quality parameters and require additional calibration studies. In this paper, we present a novel model-aided deep learning approach for path loss prediction, which implicitly extracts radio propagation characteristics from top-view geographical images of the receiver location. In a comprehensive evaluation campaign, we apply the proposed method on an extensive real-world data set consisting of five different scenarios and more than 125.000 individual measurements. It is found that 1) the novel approach reduces the average prediction error by up to 53% in comparison to ray-tracing techniques, 2) A distance of 250-300 meters spanned by the images offer the necessary level of detail, 3) Predictions with a root-mean-squared error of approximately 6 dB is achieved across inherently different data sources.