# MLReal: Bridging the gap between training on synthetic data and real data applications in machine learning

arXiv: https://arxiv.org/abs/2109.05294 · HTML: https://mlsanity.com/paper/2109.05294/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 41 references that are in the map.
- First posted on arXiv 11 Sep 2021.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [An introduction to domain adaptation and transfer learning](https://mlsanity.com/paper/1812.11806/) (2018)
- [Image Inpainting via Generative Multi-column Convolutional Neural Networks](https://mlsanity.com/paper/1810.08771/) (2018)

## Built on by (most cited first, 19 of 19)

- [A prior regularized full waveform inversion using generative diffusion models](https://mlsanity.com/paper/2306.12776/) (2023)
- [Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark](https://mlsanity.com/paper/2310.16981/) (2023)
- [The potential of self-supervised networks for random noise suppression in seismic data](https://mlsanity.com/paper/2109.07344/) (2021)
- [StorSeismic: A new paradigm in deep learning for seismic processing](https://mlsanity.com/paper/2205.00222/) (2022)
- [ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2502.16890/) (2025)
- [Microseismic source imaging using physics-informed neural networks with hard constraints](https://mlsanity.com/paper/2304.04315/) (2023)
- [A hybrid approach to seismic deblending: when physics meets self-supervision](https://mlsanity.com/paper/2205.15395/) (2022)
- [Transfer learning for self-supervised, blind-spot seismic denoising](https://mlsanity.com/paper/2209.12210/) (2022)
- [Home Electricity Data Generator (HEDGE): An open-access tool for the generation of electric vehicle, residential demand, and PV generation profiles](https://mlsanity.com/paper/2310.01661/) (2023)
- [D4D: An RGBD diffusion model to boost monocular depth estimation](https://mlsanity.com/paper/2403.07516/) (2024)
- [Bifurcation Identification for Ultrasound-driven Robotic Cannulation](https://mlsanity.com/paper/2409.06817/) (2024)
- [Deep Preconditioners and their application to seismic wavefield processing](https://mlsanity.com/paper/2207.09938/) (2022)
- [Joint Microseismic Event Detection and Location with a Detection Transformer](https://mlsanity.com/paper/2307.09207/) (2023)
- [DE-CGAN: Boosting rTMS Treatment Prediction with Diversity Enhancing Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2404.16913/) (2024)
- [Comparative analysis of Realistic EMF Exposure Estimation from Low Density Sensor Network by Finite & Infinite Neural Networks](https://mlsanity.com/paper/2504.07990/) (2025)
- [Propagating the prior from far to near offset: A self-supervised diffusion framework for progressively recovering near-offsets of towed-streamer data](https://mlsanity.com/paper/2602.01909/) (2026)
- [Data Enrichment for Symbolic Regression Using Diffusion Models](https://mlsanity.com/paper/2606.00988/) (2026)
- [A Comprehensive Survey of Wireless Foundation Models for AI-Native 6G Networks](https://mlsanity.com/paper/2608.14694/) (2026)
- [Should All Noises Be Treated Equally: Impact of Input Noise Variability on Neural Network Robustness](https://mlsanity.com/paper/2609.14504/) (2026)

## Abstract (arXiv)

Among the biggest challenges we face in utilizing neural networks trained on waveform data (i.e., seismic, electromagnetic, or ultrasound) is its application to real data. The requirement for accurate labels forces us to develop solutions using synthetic data, where labels are readily available. However, synthetic data often do not capture the reality of the field/real experiment, and we end up with poor performance of the trained neural network (NN) at the inference stage. We describe a novel approach to enhance supervised training on synthetic data with real data features (domain adaptation). Specifically, for tasks in which the absolute values of the vertical axis (time or depth) of the input data are not crucial, like classification, or can be corrected afterward, like velocity model building using a well-log, we suggest a series of linear operations on the input so the training and application data have similar distributions. This is accomplished by applying two operations on the input data to the NN model: 1) The crosscorrelation of the input data (i.e., shot gather, seismic image, etc.) with a fixed reference trace from the same dataset. 2) The convolution of the resulting data with the mean (or a random sample) of the autocorrelated data from another domain. In the training stage, the input data are from the synthetic domain and the auto-correlated data are from the real domain, and random samples from real data are drawn at every training epoch. In the inference/application stage, the input data are from the real subset domain and the mean of the autocorrelated sections are from the synthetic data subset domain. Example applications on passive seismic data for microseismic event source location determination and active seismic data for predicting low frequencies are used to demonstrate the power of this approach in improving the applicability of trained models to real data.