# Urban Change Forecasting from Satellite Images

arXiv: https://arxiv.org/abs/2204.12875 · HTML: https://mlsanity.com/paper/2204.12875/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 27 Apr 2022.

## Builds on (most cited first, 11 of 11)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks](https://mlsanity.com/paper/1810.08468/) (2018)
- [Learning to Compare Image Patches via Convolutional Neural Networks](https://mlsanity.com/paper/1504.03641/) (2015)
- [Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model](https://mlsanity.com/paper/1909.07726/) (2019)
- [DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images](https://mlsanity.com/paper/2003.03608/) (2020)
- [The Multi-Temporal Urban Development SpaceNet Dataset](https://mlsanity.com/paper/2102.04420/) (2021)

## Built on by (most cited first, 6 of 6)

- [Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices](https://mlsanity.com/paper/2507.03367/) (2025)
- [Continuous Urban Change Detection from Satellite Image Time Series with Temporal Feature Refinement and Multi-Task Integration](https://mlsanity.com/paper/2406.17458/) (2024)
- [Operational Change Detection for Geographical Information: Overview and Challenges](https://mlsanity.com/paper/2503.14109/) (2025)
- [Geospatial Diffusion for Land Cover Imperviousness Change Forecasting](https://mlsanity.com/paper/2508.10649/) (2025)
- [Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbations](https://mlsanity.com/paper/2602.19881/) (2026)
- [ChangeFlow -- Latent Rectified Flow for Change Detection in Remote Sensing](https://mlsanity.com/paper/2605.15375/) (2026)

## Abstract (arXiv)

Forecasting where and when new buildings will emerge is a rather unexplored topic, but one that is very useful in many disciplines such as urban planning, agriculture, resource management, and even autonomous flying. In the present work, we present a method that accomplishes this task with a deep neural network and a custom pretraining procedure. In Stage 1, a U-Net backbone is pretrained within a Siamese network architecture that aims to solve a (building) change detection task. In Stage 2, the backbone is repurposed to forecast the emergence of new buildings based solely on one image acquired before its construction. Furthermore, we also present a model that forecasts the time range within which the change will occur. We validate our approach using the SpaceNet7 dataset, which covers an area of 960 km^2 at 24 points in time across two years. In our experiments, we found that our proposed pretraining method consistently outperforms the traditional pretraining using the ImageNet dataset. We also show that it is to some degree possible to predict in advance when building changes will occur.